[{"data":1,"prerenderedAt":438},["ShallowReactive",2],{"slug-a-i-bias-in-healthcare":3},{"post":4,"relatedPosts":200,"relatedBooks":321},{"id":5,"date":6,"date_gmt":7,"guid":8,"modified":10,"modified_gmt":11,"slug":12,"status":13,"type":14,"link":15,"title":16,"content":18,"excerpt":21,"author":23,"featured_media":24,"comment_status":25,"ping_status":25,"sticky":26,"template":27,"format":28,"meta":29,"categories":30,"tags":33,"project_category":55,"contact_email_category":56,"yst_prominent_words":57,"class_list":66,"better_featured_image":96,"acf":133,"yoast_meta":144,"_links":147},24878,"2019-09-19T16:59:30","2019-09-19T14:59:30",{"rendered":9},"https:\u002F\u002Fmedicalfuturist.com\u002F?post_id=24878&_wpnonce=63e7ccbf7c&status=auto-draft&type=post","2023-03-22T18:35:38","2023-03-22T17:35:38","a-i-bias-in-healthcare","publish","post","https:\u002F\u002Fmedicalfuturist.com\u002Fa-i-bias-in-healthcare",{"rendered":17},"A.I. Bias In Healthcare",{"rendered":19,"protected":20},"\n\u003Ctable style=\"width: 100%; border-collapse: collapse; background-color: #eee; border-top: 4px solid #444;\" cellpadding=\"5px\">\n\u003Ctbody>\n\u003Ctr>\n\u003Ctd style=\"width: 100%;\">\n\u003Cp style=\"color: #555;font-size: 12px;line-height: 14px\">THIS ARTICLE HAS NOT BEEN UPDATED SINCE 2019. THE INFORMATION SHARED IN THE ARTICLE WAS ACCURATE AT THE TIME OF ITS PUBLICATION, BUT IT MAY BE OUT OF DATE NOW. \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fmagazine\">BROWSE OUR LATEST ARTICLES HERE\u003C\u002Fa>\u003C\u002Fp>\n\u003C\u002Ftd> \u003C\u002Ftr>\u003C\u002Ftbody>\u003C\u002Ftable>\n\n\n\n\u003Cp>Logical, reasoned, and rational masterpieces of human intelligence that are assumed to make objective, logical, reasoned decisions and choices. Instead, what the scientific community had to follow lately was how praised smart algorithms proved to be just as biased and judgmental as their human masters, sometimes even leading to scientifically questionable or discriminatory outcomes. Where does A.I. bias come from, how does it appear in healthcare, and what can we do about it? \u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">\u003Cstrong>Are you\nA.I.’s favorite?\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Cp>Two years ago, Google came under fire when \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.buzzfeed.com\u002Ffionarutherford\u002Fheres-why-some-people-think-googles-results-are-racist\" target=\"_blank\">research\u003C\u002Fa> had shown that \u003Ca href=\"https:\u002F\u002Ftechcrunch.com\u002F2019\u002F07\u002F25\u002Fbias-in-ai-a-problem-recognized-but-still-unresolved\u002F\">when a user searched online for “hands,” the image results were almost all white\u003C\u002Fa>; but when searching for “black hands,” the pictures were far more derogatory depictions, including a white hand reaching out to offer help to a black one, or black hands working in the earth. Not much changed – if you search for “hands” or “black hands”, you still come up with similar results, although the supportive white hand disappeared. \u003C\u002Fp>\n\n\n\n\u003Cp>Similar racial bias follows through the story of A.I. \u003Cstrong>We could hear from a lot of news outlets how facial recognition software favors white faces, but a \u003Ca href=\"http:\u002F\u002Fgendershades.org\u002F\">study\u003C\u002Fa> out of the MIT Media Lab published in February 2018 actually found that facial-recognition systems from companies like IBM and Microsoft were 11-19 percent more accurate on lighter-skinned individuals\u003C\u002Fstrong>. They were particularly bad at identifying women of color. The smart algorithms were 34 percent less accurate at recognizing darker-skinned females compared to lighter-skinned males. \u003Ca href=\"https:\u002F\u002Fqz.com\u002F1367177\u002Fif-ai-is-going-to-be-the-worlds-doctor-it-needs-better-textbooks\u002F\">In another example\u003C\u002Fa>, when A.I. was implemented in the U.S. criminal justice system to predict recidivism, it was found to disproportionately suggest that black people were \u003Ca href=\"https:\u002F\u002Fwww.propublica.org\u002Farticle\u002Fmachine-bias-risk-assessments-in-criminal-sentencing\">more likely to commit future crimes\u003C\u002Fa>, regardless of how minor their initial offense. \u003C\u002Fp>\n\n\n\n\u003Cp>\u003Cstrong>It’s not only racial prejudice, but A.I. algorithms also often discriminate against women, minorities, other cultures, or ideologies\u003C\u002Fstrong>. For example, \u003Ca href=\"https:\u002F\u002Fwww.reuters.com\u002Farticle\u002Fus-amazon-com-jobs-automation-insight\u002Famazon-scraps-secret-ai-recruiting-tool-that-showed-bias-against-women-idUSKCN1MK08G?zd_source=hrt&zd_campaign=4174&zd_term=arranstewart\">Amazon’s HR department had to stop using their A.I.-based machine learning tool\u003C\u002Fa>, which the company developed for sorting out the best job applicants, as it turned out that the smart algorithm favored men. As the tech scene is mainly dominated by men, and the data that the software was fed contained resumés from the past 10 years, the program taught itself that women were less preferable candidates. While programmers tried to tweak the A.I., it still didn’t bring the expected results, so in the end, they decided to scrap the program entirely. But what happened here? What went wrong with the algorithm? What’s the difficulty with teaching A.I.?\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"341\" src=\"https:\u002F\u002F1712507217.rsc.cdn77.org\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FBiased-Algorithms-512x341.jpeg\" alt=\"A.I. Bias\" class=\"wp-image-24880\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FBiased-Algorithms-512x341.jpeg 512w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FBiased-Algorithms-768x512.jpeg 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FBiased-Algorithms-1536x1024.jpeg 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FBiased-Algorithms.jpeg 2000w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \u002F>\u003Cfigcaption class=\"wp-element-caption\">Source: www.entrepreneur.com\u003C\u002Ffigcaption>\u003C\u002Ffigure>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">\u003Cstrong>A quest for\nunbiased cat pictures\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Cp>In order to discern why an A.I. algorithm could be biased, let’s take everyone’s favorite machine learning example: an algorithm recognizing cats in images. You will need millions of photos about all kinds of cats labeled as cats, and feed them to the algorithm, which will eventually learn to categorize the animal – without actually instructing it that cats are furry animals with four legs and two eyes. Such description would anyways exclude sphynx cats or our three-legged buddies. But what if those hairless creatures got ignored for other reasons, too? \u003C\u002Fp>\n\n\n\n\u003Cp>Here are the three main reasons for biased algorithms:\u003C\u002Fp>\n\n\n\n\u003Cp>1.\u003Cstrong>Judgmental data sets\u003C\u002Fstrong>\u003C\u002Fp>\n\n\n\n\u003Cp>\u003Cstrong>Algorithms are trained on datasets, thus the quality of the data is crucial in the process. If the dataset is incomplete, not diverse enough, stems mainly from one area of study, the A.I. software could work flawlessly in the test environment, but come up with its inherent bias in the ‘real world’.\u003C\u002Fstrong> For example, if our cat-spotting algorithm never gets to see any sphynx cat, it will fairly believe that cats are furry – and when eventually encounters a hairless animal, it won’t recognize it. That’s what often happens with facial recognition software\u003C\u002Fp>\n\n\n\n\u003Cp>2. \u003Cstrong>Deeply ingrained social injustices\u003C\u002Fstrong>\u003C\u002Fp>\n\n\n\n\u003Cp>\u003Cstrong>Another, more complex issue is when the dataset is representative and diverse enough, but the algorithm still arrives at discriminative conclusions. The reason for that could be a social practice ingrained so deeply in society that will automatically be transferred into the judgment process of the A.I. \u003C\u002Fstrong>For example, as cats have not worn sweaters for centuries, a smart algorithm might miss out a modern-day cat in a pullover. In a nutshell, that’s the reason for Amazon’s gender-biased HR algorithm: the program was fed with applications from the previous ten years, whose majority came from male candidates. As a consequence, the A.I. started to believe that the correlation between gender and qualifications in this area also meant causation – and a point of reference for selection.\u003C\u002Fp>\n\n\n\n\u003Cp>3. \u003Cstrong>Unconscious or conscious individual choices \u003C\u002Fstrong>\u003C\u002Fp>\n\n\n\n\u003Cp>And what if the programmer must choose or leave out some parameters to help the program learn? \u003Cstrong>By describing the cat in a certain way – hairiness, color, legs, eyes, etc. -, they already include their hidden and frequently unconscious bias.\u003C\u002Fstrong> When a shelter wants to decide which cat to offer for adoption, how will the parameters look? And turning to people, when banks screen through loan applications with the help of algorithms, who decides who can get the loan? The programmer, the bank, or a human being? In such cases, the software developer can unconsciously include their own values and beliefs about the world into the code, and in an even more sensitive situation, perhaps with even riskier outcomes, the programmer could set some variables selecting specific characteristics for individuals or groups – which might have a biased outcome. Either way, individual choices can greatly influence how smart algorithms ‘behave’.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"160\" src=\"https:\u002F\u002F1712507217.rsc.cdn77.org\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F10-21-2018-Digitalist_Q1_AI-Bias_F-512x160.jpg\" alt=\"A.I. Bias\" class=\"wp-image-24879\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F10-21-2018-Digitalist_Q1_AI-Bias_F-512x160.jpg 512w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F10-21-2018-Digitalist_Q1_AI-Bias_F-768x240.jpg 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F10-21-2018-Digitalist_Q1_AI-Bias_F-1536x480.jpg 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F10-21-2018-Digitalist_Q1_AI-Bias_F.jpg 1920w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \u002F>\u003Cfigcaption class=\"wp-element-caption\">Source: www.geneticliteracyproject.org\u003C\u002Ffigcaption>\u003C\u002Ffigure>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">\u003Cstrong>Health data\nis mostly white and male\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Cp>Thus, \u003Cstrong>the source, the quality, and the diversity of the data, the historical social practices ingrained into the data – meaning the bias of the deeper social structure, as well as the individual, conscious or unconscious preferences of individual programmers, determine whether and to what extent an A.I. will become biased.\u003C\u002Fstrong> Now, let’s look at some examples from healthcare where many could believe that as smart algorithms look at medical images, ECG strips or electronic medical records, the “bias factor” must be less prevalent.\u003C\u002Fp>\n\n\n\n\u003Cp>Well, we shall bring some disillusionment. Even \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=TATSAHJKRd8\">comedian John Oliver said\u003C\u002Fa> that bias in medicine, in general, is a serious issue with consequences for American society. \u003Ca href=\"https:\u002F\u002Fqz.com\u002F1367177\u002Fif-ai-is-going-to-be-the-worlds-doctor-it-needs-better-textbooks\u002F\">Healthcare data is extremely male and extremely white\u003C\u002Fa>, and that has real-world impacts. A 2014 study that \u003Ca href=\"https:\u002F\u002Fonlinelibrary.wiley.com\u002Fdoi\u002Ffull\u002F10.1002\u002Fcncr.28617\">tracked cancer mortality over 20 years\u003C\u002Fa> pointed to a lack of diverse research subjects as a key reason why black Americans are significantly more likely to die from cancer than white Americans. \u003C\u002Fp>\n\n\n\n\u003Cp>In another area of research, \u003Ca href=\"https:\u002F\u002Fwww.nature.com\u002Fnews\u002Fgenomics-is-failing-on-diversity-1.20759\">meta-analysis\u003C\u002Fa> looking at 2,511 studies from around the world found\nthat 81 percent of participants in genome-mapping studies were of European\ndescent. This has severe real-world impacts: researchers who download\npublicly-available data to study disease are far more likely to use the genomic\ndata of people of European descent than those of African, Asian, Hispanic, or\nMiddle Eastern descent. And these distorted datasets would be the starting\npoints for A.I. development. \u003C\u002Fp>\n\n\n\n\u003Cp>Sometimes, ignorance of inherent bias in data could even jeopardize the applicability of an algorithm. \u003Ca href=\"https:\u002F\u002Fwinterlightlabs.com\u002F\">Winterlight Labs\u003C\u002Fa>, a Toronto-based startup, which is building auditory tests for neurological diseases, \u003Ca href=\"https:\u002F\u002Fqz.com\u002F1367177\u002Fif-ai-is-going-to-be-the-worlds-doctor-it-needs-better-textbooks\u002F\">realized after a while that their technology only worked for English speakers of a particular Canadian dialect\u003C\u002Fa>. That might be a serious problem for other companies, too, which are working with \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fvoice-to-text-technologies-shape-the-future\u002F\">voice-to-text technologies\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fvocal-biomarkers-new-opportunities-prevention\u002F\">vocal biomarkers\u003C\u002Fa>, or digital assistants such as Siri or Alexa for healthcare.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"512\" height=\"341\" src=\"https:\u002F\u002F1712507217.rsc.cdn77.org\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FAlgorithmically-biased-512x341.jpg\" alt=\"A.I. Bias\" class=\"wp-image-24883\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FAlgorithmically-biased-512x341.jpg 512w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FAlgorithmically-biased-768x511.jpg 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FAlgorithmically-biased.jpg 1500w\" sizes=\"auto, (max-width: 512px) 100vw, 512px\" \u002F>\u003Cfigcaption class=\"wp-element-caption\">Source: www.npr.org\u003C\u002Ffigcaption>\u003C\u002Ffigure>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">\u003Cstrong>Getting out of the cognitive cage\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Cp>So, what should we do to eliminate these prejudices\nfrom programming smart algorithms? It is actually a very difficult task as\nhuman beings have their own bias in their thinking – and that has been a useful\ntrait for thousands of years as it shortens the time needed for making snap\ndecisions. It’s also likely that human bias is here to stay, and technologies\nthat are fed by information that is created in the real world \u003Ca href=\"https:\u002F\u002Fwww.zdnet.com\u002Farticle\u002Fwhat-is-bias-in-ai-really-and-why-cant-ai-neutralize-it\u002F\">could fundamentally have the same outcome\u003C\u002Fa>. \u003Cstrong>So now the question is, how do you think about\nthat when you’re actually shifting a cognitive task completely into a machine,\nwhere you don’t have the same kind of qualitative reaction that human beings\nwill have? \u003C\u002Fstrong>\u003C\u002Fp>\n\n\n\n\u003Cp>The response might be twofold and still evolving. \u003C\u002Fp>\n\n\n\n\u003Col class=\"wp-block-list\">\n\u003Cli>\u003Cstrong>We\nhave to raise awareness of inherent bias in algorithms\u003C\u002Fstrong>. It’s a great step that is already applied in some\nplaces. Recently, \u003Ca href=\"https:\u002F\u002Fwww.bbc.com\u002Fnews\u002Ftechnology-49717378\">police officers have raised concerns about using\n“biased” artificial-intelligence tools\u003C\u002Fa>, a report commissioned by one of the UK government’s\nadvisory bodies revealed. The report said policemen were worried about both\ndata bias and becoming more reliant on automation. Another similar example was banning \u003Ca href=\"https:\u002F\u002Fwww.hrtechnologist.com\u002Farticles\u002Fdiversity\u002Fwhy-is-artificial-intelligence-biased-against-women\u002F\">facial recognition software from the streets of San\nFrancisco\u003C\u002Fa>. Activists and\npoliticians, who pushed for the ordinance, cited studies that showed A.I.-based\nfacial recognition technology is less accurate when distinguishing between\nindividual women and people of color.\u003C\u002Fli>\n\n\n\n\u003Cli>\u003Cstrong>We\nmight have to re-create these functions, such as facial recognition technology,\nto represent a more balanced attitude through minimizing bias\u003C\u002Fstrong>. That’s a tricky and a difficult process, especially\nbecause most A.I. algorithms are trained on biased datasets and researchers are\njust starting to bring them to the real-world. \u003C\u002Fli>\n\u003C\u002Fol>\n\n\n\n\u003Cp>Also, in many cases, it must be difficult to admit how biased we, human beings, are, and it’s kind of embarrassing that machines are pointing that out for us. But well, at least, we hope we are learning something about ourselves and how to make the world a less biased place. That would just be fantastic.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image\">\u003Cimg decoding=\"async\" src=\"https:\u002F\u002F1712507217.rsc.cdn77.org\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FAlgorithmic-bias-1-512x288.jpg\" alt=\"A.I. Bias\" class=\"wp-image-24882\"\u002F>\u003Cfigcaption class=\"wp-element-caption\">Source: www.towardsdatascience.com\u003C\u002Ffigcaption>\u003C\u002Ffigure>\n\n\n\n\u003Ctable style=\"width: 100%; border-collapse: collapse; background-color: #eee; border-top: 4px solid #444;\" cellpadding=\"10px\">\n\u003Ctbody>\n\u003Ctr>\n\u003Ctd style=\"width: 100%;\">\n\u003Cp>\u003Cstrong>At The Medical Futurist, we are building a community for making a bold vision about the future of healthcare reality today.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Ciframe loading=\"lazy\" width=\"560\" height=\"315\" src=\"https:\u002F\u002Fwww.youtube.com\u002Fembed\u002FFIbMejImnxs\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen=\"\">\u003C\u002Fiframe>\n\u003Cp>If you’d like to support this mission, we invite you to \u003Ca href=\"https:\u002F\u002Fwww.patreon.com\u002Fthemedicalfuturist\">join The Medical Futurist Patreon Community\u003C\u002Fa>. A community of empowered patients, future-oriented healthcare professionals, concerned health policymakers, sensible health tech developers, and enthusiastic medical students. If there were ever a time to join us, it is now. Every contribution, however big or small, powers our research and sustains our future.\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.patreon.com\u002Fthemedicalfuturist\">\u003Cstrong style=\"background-color: #e71d3299; color: #000;\">Click here to support The Medical Futurist from as little as $3\u003C\u002Fstrong>\u003C\u002Fa> – it only takes a minute. Thank you.\u003C\u002Fp>\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\n\u003C\u002Ftable>\n\u003Cp> \u003C\u002Fp>\n",false,{"rendered":22,"protected":20},"\u003Cp>Logical, reasoned, and rational masterpieces of human intelligence that are assumed to make objective, logical, reasoned decisions and choices. Instead, what the scientific community had to follow lately was how praised smart algorithms proved to be just as biased and judgmental as their human masters, sometimes even leading to scientifically questionable or discriminatory outcomes. Where does A.I. bias come from, how does it appear in healthcare, and what can we do about it? \u003C\u002Fp>\n",6,24884,"closed",true,"","standard",{"_acf_changed":20,"footnotes":27},[31,32],504,521,[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54],271,1228,275,1245,425,1474,1475,1476,636,1477,134,671,1478,137,926,144,1104,229,1168,246,1203,[],[],[58,59,60,61,62,63,64,65],2689,2705,2739,3657,1661,1693,1819,1883,[67,14,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"post-24878","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-artificial-intelligence","category-future-medicine","tag-health","tag-artificial","tag-healthcare","tag-gender","tag-technology-2","tag-bias","tag-prejudice","tag-judgement","tag-deep-learning","tag-racial","tag-ai","tag-machine-learning","tag-ethnic","tag-algorithm","tag-society","tag-artificial-intelligence","tag-genetic","tag-ethics","tag-smart-algorithm","tag-future","tag-smart",{"id":24,"alt_text":97,"caption":27,"description":27,"media_type":98,"media_details":99,"post":5,"source_url":132},"A.I. Bias","image",{"width":100,"height":101,"file":102,"sizes":103,"image_meta":130},1920,1080,"2019\u002F09\u002F108_Biased-AI.png",{"medium":104,"large":110,"thumbnail":115,"medium_large":119,"1536x1536":120,"2048x2048":125},{"file":105,"width":106,"height":107,"mime-type":108,"source_url":109},"108_Biased-AI-370x208.png","370","208","image\u002Fpng","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F108_Biased-AI-370x208.png",{"file":111,"width":112,"height":113,"mime-type":108,"source_url":114},"108_Biased-AI-768x432.png","768","432","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F108_Biased-AI-768x432.png",{"file":116,"width":117,"height":117,"mime-type":108,"source_url":118},"108_Biased-AI-150x150.png","150","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F108_Biased-AI-150x150.png",{"file":111,"width":112,"height":113,"mime-type":108,"source_url":114},{"file":121,"width":122,"height":123,"mime-type":108,"source_url":124},"108_Biased-AI-1536x864.png","1536","864","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F108_Biased-AI-1536x864.png",{"file":126,"width":127,"height":128,"mime-type":108,"source_url":129},"108_Biased-AI-2048x1152.png","2048","1152","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F108_Biased-AI-2048x1152.png",{"aperture":131,"credit":27,"camera":27,"caption":27,"created_timestamp":131,"copyright":27,"focal_length":131,"iso":131,"shutter_speed":131,"title":27,"orientation":131},"0","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002F108_Biased-AI-scaled.png",{"related_posts_footer":134,"related_posts":20,"cta_type":139,"cta_color":140,"subtitle":141,"related_books":142},[135,136,137,138],16375,21023,16292,22987,"keynote","red","Human Pride, Machine Prejudice",[143],24762,{"yoast_wpseo_title":145,"yoast_wpseo_metadesc":146,"yoast_wpseo_canonical":15},"A.I. Bias In Healthcare - The Medical Futurist","The Medical Futurist writes about where A.I. bias comes from, how it appears in healthcare, and how we can make smart algorithms less judgemental.",{"self":148,"collection":154,"about":157,"author":160,"replies":163,"version-history":166,"predecessor-version":170,"wp:featuredmedia":174,"wp:attachment":177,"wp:term":180,"curies":196},[149],{"href":150,"targetHints":151},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F24878",{"allow":152},[153],"GET",[155],{"href":156},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts",[158],{"href":159},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Ftypes\u002Fpost",[161],{"embeddable":26,"href":162},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fusers\u002F6",[164],{"embeddable":26,"href":165},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcomments?post=24878",[167],{"count":168,"href":169},11,"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F24878\u002Frevisions",[171],{"id":172,"href":173},50147,"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F24878\u002Frevisions\u002F50147",[175],{"embeddable":26,"href":176},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia\u002F24884",[178],{"href":179},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia?parent=24878",[181,184,187,190,193],{"taxonomy":182,"embeddable":26,"href":183},"category","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcategories?post=24878",{"taxonomy":185,"embeddable":26,"href":186},"post_tag","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Ftags?post=24878",{"taxonomy":188,"embeddable":26,"href":189},"project_category","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fproject_category?post=24878",{"taxonomy":191,"embeddable":26,"href":192},"contact_email_category","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcontact_email_category?post=24878",{"taxonomy":194,"embeddable":26,"href":195},"yst_prominent_words","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fyst_prominent_words?post=24878",[197],{"name":198,"href":199,"templated":26},"wp","https:\u002F\u002Fapi.w.org\u002F{rel}",[201],{"id":138,"date":202,"date_gmt":203,"guid":204,"modified":202,"modified_gmt":203,"slug":206,"status":13,"type":14,"link":207,"title":208,"content":210,"excerpt":212,"author":23,"featured_media":214,"comment_status":25,"ping_status":25,"sticky":26,"template":27,"format":28,"meta":215,"categories":216,"tags":217,"project_category":223,"contact_email_category":225,"yst_prominent_words":226,"class_list":234,"better_featured_image":242,"acf":262,"yoast_meta":276,"_links":279},"2025-11-27T13:33:46","2025-11-27T12:33:46",{"rendered":205},"https:\u002F\u002Fmedicalfuturist.com\u002F?post_id=22987&_wpnonce=faf4ca9c84&status=auto-draft&type=post","top-ai-algorithms-healthcare","https:\u002F\u002Fmedicalfuturist.com\u002Ftop-ai-algorithms-healthcare",{"rendered":209},"Top Smart Algorithms In Healthcare",{"rendered":211,"protected":20},"\n\u003Cp>As artificial intelligence (AI) tools have been invading more or less every area of healthcare, we made a list to keep track of the top AI algorithms aiming for better diagnostics, more sophisticated patient care or further sighted predictions of diseases.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">\u003Cstrong>Does AI beat doctors?\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Cp>Only if you have lived under a rock for the last couple of years could you not have heard about artificial intelligence and the \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fartificial-intelligence-will-redesign-healthcare\" target=\"_blank\">potential of AI in healthcare\u003C\u002Fa>. \u003Cstrong>Not only smart algorithms themselves but also the \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fwhat-does-gpt-4-mean-for-healthcare\" target=\"_blank\" rel=\"noreferrer noopener\">hype around AI\u003C\u002Fa> has grown immensely, thus every time a new study about deep learning or machine learning in diagnostics, medical imaging or any other medical field gets published, newsreaders can be sure that some titles will say that “\u003Cem>\u003Ca href=\"https:\u002F\u002Fcardiovascularbusiness.com\u002Ftopics\u002Fcardiac-imaging\u002Fechocardiography\u002Fcardiologists-find-ai-be-more-accurate-sonographers-interpreting-echocardiograms\" target=\"_blank\" rel=\"noreferrer noopener\">AI\u003C\u002Fa> has \u003Ca href=\"https:\u002F\u002Fwww.medpagetoday.com\u002Fspecial-reports\u002Fexclusives\u002F103522\" target=\"_blank\" rel=\"noreferrer noopener\">again \u003C\u002Fa>beaten \u003Ca href=\"https:\u002F\u002Fwww.bbc.com\u002Fnews\u002Fhealth-50857759\" target=\"_blank\" rel=\"noreferrer noopener\">doctors\u003C\u002Fa> in \u003Ca href=\"https:\u002F\u002Fwww.insideprecisionmedicine.com\u002Ftopics\u002Fpatient-care\u002Fear-disorders\u002Fai-better-than-doctors-at-diagnosing-pediatric-ear-infections\u002F\" target=\"_blank\" rel=\"noreferrer noopener\">field X\u003C\u002Fa>\u003C\u002Fem>”\u003C\u002Fstrong>. \u003C\u002Fp>\n\n\n\n\u003Cp>The narrative is so distorted towards extreme visions that artificial intelligence is either presented as the ultimate evil destroying mankind – both \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=B-Osn1gMNtw\" target=\"_blank\">Elon Musk\u003C\u002Fa> and \u003Ca rel=\"noreferrer noopener\" href=\"http:\u002F\u002Fwww.bbc.com\u002Fnews\u002Ftechnology-30290540\" target=\"_blank\">Stephen Hawking\u003C\u002Fa> warned about that years ago – or the only source of the future prosperity of humanity. \u003C\u002Fp>\n\n\n\n\u003Cp>Just think of the \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Ftechcrunch.com\u002F2023\u002F03\u002F28\u002F1100-notable-signatories-just-signed-an-open-letter-asking-all-ai-labs-to-immediately-pause-for-at-least-6-months\u002F?guccounter=1&guce_referrer=aHR0cHM6Ly93d3cuZ29vZ2xlLmNvbS8&guce_referrer_sig=AQAAAKmu7s0KQrRwyPz-pZWYbtBvxSfTZel6Bhu79sE47N0ZiTHa8J8dgD0cpbPzxWkUDxqHzo4b8Kmm_vdp9C8AksGAcAa1tGtZTulyeb_ErIP9rg_WbwQYPX1diD78X2bwWJ6Q9jYS_j0UWxGpe-Ryaz9gaJfohEA_9UcTtCvGpK3n\" target=\"_blank\">open letter conundrum\u003C\u002Fa> of \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs42256-023-00649-x\" target=\"_blank\">recent weeks\u003C\u002Fa>, and how fears of the general population were fueled despite the \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fventurebeat.com\u002Fai\u002Ftitans-of-ai-industry-andrew-ng-and-yann-lecun-oppose-call-for-pause-on-powerful-ai-systems\u002F\" target=\"_blank\">opposing opinions\u003C\u002Fa> of the \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.reuters.com\u002Ftechnology\u002Fbill-gates-says-calls-pause-ai-wont-solve-challenges-2023-04-04\u002F\" target=\"_blank\">largest minds\u003C\u002Fa> calling for a more nuanced approach. \u003C\u002Fp>\n\n\n\n\u003Cp>\u003Cstrong>By enumerating the top AI tools that we discovered in healthcare so far, we also aim to add what we believe is already useful for the work of medical professionals.\u003C\u002Fstrong> \u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image size-full is-resized\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"1920\" height=\"1080\" src=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F04\u002Ftmf_article_357.png\" alt=\"TMF, medical student, AI, doctor, data, computer\" class=\"wp-image-50547\" style=\"width:960px;height:540px\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F04\u002Ftmf_article_357.png 1920w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F04\u002Ftmf_article_357-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F04\u002Ftmf_article_357-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F04\u002Ftmf_article_357-1536x864.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F04\u002Ftmf_article_357-2048x1152.png 2048w\" sizes=\"auto, (max-width: 1920px) 100vw, 1920px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">\u003Cstrong>Life is no training data set\u003C\u002Fstrong>\u003C\u002Fh2>\n\n\n\n\u003Cp>Artificial intelligence \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.fastcompany.com\u002F90863983\u002Fchatgpt-medical-diagnosis-emergency-room?utm_source=The+Medical+Futurist+Newsletter&utm_campaign=872032dc60-EMAIL_CAMPAIGN_2022_02_01_COPY_01&utm_medium=email&utm_term=0_efd6a3cd08-872032dc60-420889096&mc_cid=872032dc60&mc_eid=b5d5d75ed3\" target=\"_blank\">has numerous limitations\u003C\u002Fa> just as yet, so before we present our list, it’s worth going through them one by one. Already the term is misleading as AI implies a far more developed technology where it is standing at the moment. At best, current science – meaning \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fmedpalm-new-ai-medical-chatbots-will-soon-be-better-than-waiting-for-a-doctor\" target=\"_blank\" rel=\"noreferrer noopener\">large language models\u003C\u002Fa> and various \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fgenerative-adversarial-networks-how-can-ai-learn-so-much-while-its-iq-remains-zero\" target=\"_blank\" rel=\"noreferrer noopener\">machine learning methods\u003C\u002Fa> – is able to reach artificial narrow intelligence (ANI) in multiple fields, the first level of intelligence created by humans. \u003C\u002Fp>\n\n\n\n\u003Cp>\u003Cstrong>Yet, we have \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.deeplearning.ai\u002Fthe-batch\u002Fartificial-general-intelligence-progress-report\u002F\" target=\"_blank\">not arrived at artificial general intelligence\u003C\u002Fa> (AGI)\u003C\u002Fstrong>, the second level of intelligence when a machine is capable of abstracting concepts from limited experience and transferring knowledge between domains. The third and most fearful domain, superintelligence, when AI evolves into a stand-alone consciousness, is nowhere close.\u003C\u002Fp>\n\n\n\n\u003Cp>Yet, ANI and its two main streams, natural language processing, and computer vision, are developing at an incredible speed. The latter is crucial for diagnostics in healthcare as it is based on pattern recognition. Countless algorithms are currently trained to categorize various patterns seen in medical images and thus help doctors diagnose conditions. \u003C\u002Fp>\n\n\n\n\u003Cp>The limitations of such studies are present in at least three areas. At first, used medical evidence tends to originate from highly developed regions containing their specificity or the framework for conceptualizing the algorithm itself incorporates the subjective assumptions of the working team. Secondly, the forecasting and predictive abilities of smart algorithms are anchored in previous cases – however, they might be useless in new cases of drug side effects or treatment resistance.\u003C\u002Fp>\n\n\n\n\u003Cp>Finally, the majority of the already conducted AI research has been done on training data sets collected from various medical facilities and after the algorithm analyses the images, doctors are provided with the same dataset – usually without reproducing the clinical conditions. \u003C\u002Fp>\n\n\n\n\u003Cp>That does not decrease the theoretical value of the study – but its practical implementation. Life is no training data set. Thousands of patients come and go to a hospital with thousands of symptoms and describe similar or the same conditions very differently. Thus, the results of AI studies conducted on training data sets might not be representative of what would happen in real-life situations. Common interpretations often leave out these limitations focusing on presenting these studies as ultimate revelations.\u003C\u002Fp>\n\n\n\n\u003Cp>Keeping all these constraints in mind, here are the top AI algorithms that we recently found in healthcare.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">1) The algorithm spotting DNA mutations in tumors\u003C\u002Fh2>\n\n\n\n\u003Cp>One of the reasons why it’s so incredibly difficult to treat cancer is that malignant tumors tend to mutate, grow, evolve and change. In the last years, scientists discovered that not only cancer itself transforms but so does its DNA. As sequencing costs significantly dropped, the genetic analysis of tumors became possible, and recently, \u003Ca href=\"https:\u002F\u002Fspectrum.ieee.org\u002Fthe-human-os\u002Fbiomedical\u002Fdiagnostics\u002Fmachine-learning-tool-can-spot-mutations-in-tumors\" target=\"_blank\" rel=\"noreferrer noopener\">human experts with the support of computational tools started to analyze the data\u003C\u002Fa> to figure out what kinds of genetic changes, or mutations, occur.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image size-full is-resized\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"3200\" height=\"1800\" src=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002FFuture-of-pathology.png\" alt=\"creativity in healthcare, TMF\" class=\"wp-image-22989\" style=\"width:800px;height:450px\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002FFuture-of-pathology.png 3200w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002FFuture-of-pathology-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002FFuture-of-pathology-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002FFuture-of-pathology-1536x864.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002FFuture-of-pathology-2048x1152.png 2048w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002FFuture-of-pathology-512x288.png 512w\" sizes=\"auto, (max-width: 3200px) 100vw, 3200px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Cp>For making such existing tools more precise, Personal Genome Diagnostics in Baltimore developed a new method involving machine learning that automates the tumor DNA diagnostic process and improves the accuracy of identifying mutations in cancerous tissues. Bearing that result in mind, the doctor can choose the specific targeted treatment for the patient.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">2) Can AI score better in classifying heart images than humans?\u003C\u002Fh2>\n\n\n\n\u003Cp>Echocardiograms produce sound waves to paint the heart’s picture – from which cardiologists can identify whether the patient has any heart disease. It’s a standard test to check for problems with valves or chambers of our central organ, for congenital heart defect or whether shortness of breath or chest pain is in connection with the heart. \u003C\u002Fp>\n\n\n\n\u003Cp>A fascinating development in this field \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fs41586-023-05947-3\" target=\"_blank\">came from the researchers of Cedars Sinai’s Smidt Heart Institute\u003C\u002Fa> and Division of Artificial Intelligence in Medicine. They reported that artificial intelligence (AI) proved more successful in assessing and diagnosing cardiac function when compared to echocardiogram assessments made by sonographers. In this first randomized, blinded trial cardiologists evaluated 3,495 transthoracic echocardiogram studies, comparing initial assessment by artificial intelligence or by a sonographer. One of the major findings was that cardiologists more frequently agreed with the AI initial assessment, such that they corrected only 16.8% of the initial assessments made by AI and simultaneously corrected 27.2% of the initial assessments made by the sonographers.\u003C\u002Fp>\n\n\n\n\u003Cp>Of course, this was not the first initiative to use AI in cardiology. Earlier Rima Arnaut, an assistant professor and practising cardiologist at UC San Francisco and her colleagues used \u003Ca href=\"https:\u002F\u002Fspectrum.ieee.org\u002Fthe-human-os\u002Fbiomedical\u002Fdiagnostics\u002Fai-cardiologist-aces-its-first-medical-exam\">deep learning to train an AI system that can classify echocardiograms\u003C\u002Fa> according to the type of view shown. When both the AI and expert cardiologists were asked to sort the images, the algorithm achieved an accuracy of 92 percent. The humans got only 79 percent correct. \u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">3) Heart attack predicting algorithms\u003C\u002Fh2>\n\n\n\n\u003Cp>Smart algorithms do not only outperform doctors when it comes to classifying but also in predicting outcomes based on various factors. \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fspectrum.ieee.org\u002Fthe-human-os\u002Fbiomedical\u002Fdiagnostics\u002Fai-predicts-heart-attacks-more-accurately-than-standard-doctor-method\" target=\"_blank\">Researchers at the University of Nottingham in the UK created a system\u003C\u002Fa> that scanned patients’ routine medical data and predicted which of them would have heart attacks or strokes within 10 years. When compared to the standard method of prediction based on well-established risk factors such as high blood pressure, cholesterol, age, smoking, and diabetes, the AI system correctly predicted the fates of 355 more patients.\u003C\u002Fp>\n\n\n\n\u003Cp>There are many promising initiatives in this field, some aim \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.news-medical.net\u002Fnews\u002F20220517\u002FUsing-AI-to-predict-heart-attacks.aspx\" target=\"_blank\">to predict heart attacks\u003C\u002Fa> years \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fedition.cnn.com\u002F2022\u002F11\u002F29\u002Fhealth\u002Fheart-attack-stroke-x-ray\u002Findex.html\" target=\"_blank\">before they actually occurred\u003C\u002Fa>, another distinguishes \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.cedars-sinai.org\u002Fnewsroom\u002Fpredicting-sudden-cardiac-arrest\u002F\" target=\"_blank\">between treatable and untreatable\u003C\u002Fa> sudden cardiac arrests, while this algorithm helps to \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.bhf.org.uk\u002Fwhat-we-do\u002Fnews-from-the-bhf\u002Fnews-archive\u002F2022\u002Faugust\u002Fartificial-intelligence-could-help-narrow-heart-attack-gender-gap\" target=\"_blank\">more accurately detect heart attacks in women\u003C\u002Fa>, whose condition often remains undetected under standard circumstances. \u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">4) More precise skin cancer diagnoses with AI\u003C\u002Fh2>\n\n\n\n\u003Cp>According to \u003Ca href=\"https:\u002F\u002Fwww.iarc.who.int\u002Fcancer-type\u002Fskin-cancer\u002F\" target=\"_blank\" rel=\"noreferrer noopener\">statistics from the WHO\u003C\u002Fa>, currently, around 1.5 million non-melanoma skin cancers and 325,000 melanoma skin cancers occur each year globally. Digital health technologies, such as\u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fthe-2023-skin-checking-apps-landscape-infographic\" target=\"_blank\" rel=\"noreferrer noopener\"> smartphone apps\u003C\u002Fa> like \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fmedicalfuturist.com\u002Faspiring-dermatology-app-under-the-microscope-the-skinvision-review\" target=\"_blank\">SkinVision\u003C\u002Fa>, telemedical services as well as AI are at the frontlines of fighting the widely prevalent disease.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image size-large\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"432\" src=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F06\u002Ftmf_article_274-01-768x432.png\" alt=\"Emerging Trend Alert – Skin Checking Algorithms\" class=\"wp-image-34783\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F06\u002Ftmf_article_274-01-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F06\u002Ftmf_article_274-01-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F06\u002Ftmf_article_274-01-1536x864.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F06\u002Ftmf_article_274-01.png 1920w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003Cfigcaption class=\"wp-element-caption\">Skin Checking Algorithms\u003C\u002Ffigcaption>\u003C\u002Ffigure>\n\n\n\n\u003Cp>Although several research groups developed smart algorithms for diagnosing skin cancer already, the \u003Ca href=\"https:\u002F\u002Fspectrum.ieee.org\u002Fthe-human-os\u002Fbiomedical\u002Fdiagnostics\u002Fcomputer-diagnoses-skin-cancers\" target=\"_blank\" rel=\"noreferrer noopener\">one created at Stanford University is likely the most robust system\u003C\u002Fa> so far. It was trained on more than 1.28 million images and fine-tuned with a set of nearly 130,000 scans of skin lesions from more than 2000 diseases. That’s the most extensive dataset used for automated skin cancer classification as of yet. \u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">5) AI systems for the ICU\u003C\u002Fh2>\n\n\n\n\u003Cp>Intensive care units are battlegrounds for human lives. As every moment counts, patients are monitored 24\u002F7 with an army of devices. Constantly beeping bedside monitors show blood pressure, heart rate or any other vital signs of the patient, a machine takes care of the function of the lungs as best as possible, and another goes for the heart. However, these instruments are usually not connected, they are isolated units in the concert of ICU care.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">6) AI detecting breast cancer\u003C\u002Fh2>\n\n\n\n\u003Cp>Breast cancer is the most commonly occurring cancer in women and the second most common cancer overall. In spite of global awareness-raising and prevention efforts, there were \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.wcrf.org\u002Fdietandcancer\u002Fcancer-trends\u002Fbreast-cancer-statistics\" target=\"_blank\">over 2 million new cases in 2020\u003C\u002Fa>. The statistics also show that almost 700,000 women died from breast cancer in 2020.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image size-large\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"433\" src=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002F070_womens_health-scaled-768x433.png\" alt=\"Women and digital health\" class=\"wp-image-23124\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002F070_womens_health-scaled-768x433.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002F070_womens_health-scaled-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002F070_womens_health-scaled-1536x866.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002F070_womens_health-scaled.png 1915w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Cp>As in the case of many other cancer types, early detection could be a lifesaver. However, women with dense breasts have a higher risk of undergoing mammogram screenings that miss signs of breast cancer. Researchers at the University of California, San Francisco found that commercial software for automatically classifying breast density and thus detecting breast cancer is just as accurate as human radiologists. Shortly, the algorithm could support doctors with cases when breast density would not allow clear diagnosis.\u003C\u002Fp>\n\n\n\n\u003Cp>Algorithms could not only assist radiologists but also pathologists in their fight against breast cancer. The \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F1606.05718\" target=\"_blank\" rel=\"noreferrer noopener\">International Symposium on Biomedical Imaging (ISBI) held a grand challenge to evaluate computational systems\u003C\u002Fa> for the automated detection of metastatic breast cancer. The winning study showed that combining the efforts of the human pathologist and the deep learning system’s predictions, the human error rate decreased by 85 percent when identifying metastatic breast cancer.\u003C\u002Fp>\n\n\n\n\u003Cp>That’s an impressive result, especially bearing in mind that early diagnosis means saving lives when it comes to the lethal disease. Beyond the achievement, it is worth noting that the joint efforts of AI and human doctors indicated a significant improvement in diagnosing, their single results were not even close.\u003C\u002Fp>\n\n\n\n\u003Cp>AI is \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.nytimes.com\u002F2023\u002F03\u002F05\u002Ftechnology\u002Fartificial-intelligence-breast-cancer-detection.html\" target=\"_blank\">already used in Hungary\u003C\u002Fa>, where at five hospitals and clinics that perform more than 35,000 screenings a year, AI systems were rolled out starting in 2021 and now help to check for signs of cancer that a radiologist may have overlooked.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">7) Smart algorithm predicting suicide risk\u003C\u002Fh2>\n\n\n\n\u003Cp>In the future, you might go to the hospital with a broken arm and leave the facility with a cast and a note with a compulsory psychiatry session due to flagged suicide risk. That’s what some scientists aim for with their AI system developed to catch depressive behaviour early on and help reduce the emergence of severe mental illnesses.\u003C\u002Fp>\n\n\n\n\u003Cp>The \u003Ca href=\"http:\u002F\u002Fjournals.sagepub.com\u002Fdoi\u002Fabs\u002F10.1177\u002F2167702617691560?journalCode=cpxa\" target=\"_blank\" rel=\"noreferrer noopener\">machine-learning algorithm\u003C\u002Fa> created at Vanderbilt University Medical Center in Nashville, uses hospital admissions data, including age, gender, zip code, medication, and diagnostic history, to predict the likelihood of any given individual taking their own life. In trials using data \u003Ca href=\"https:\u002F\u002Fqz.com\u002F1367197\u002Fmachines-know-when-someones-about-to-attempt-suicide-how-should-we-use-that-information\u002F\" target=\"_blank\" rel=\"noreferrer noopener\">gathered from more than 5,000 patients who had been admitted to the hospital for either self-harm or suicide attempts\u003C\u002Fa>, the algorithm was 84% accurate at predicting whether someone would attempt suicide the following week, and 80% accurate at predicting whether someone would attempt suicide within the following two years.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">8) AI predicting death risk among inpatients\u003C\u002Fh2>\n\n\n\n\u003Cp>Researchers at Stanford University trained an AI system to increase the number of inpatients who receive end-of-life care exactly when needed – meaning the smart algorithm is able to predict when very seriously ill patients are nearing the end of their lives.\u003C\u002Fp>\n\n\n\n\u003Cp>The \u003Ca href=\"https:\u002F\u002Fwww.fastcompany.com\u002F90157967\u002Fthis-ai-predicts-death-could-it-improve-end-of-life-care\" target=\"_blank\" rel=\"noreferrer noopener\">algorithm was trained to analyze diagnoses, prescriptions, demographics, and other factors within electronic health records during that 3 to 12 month period before a patient passed away\u003C\u002Fa>. Once trained, the algorithm was able to flag still-living patients in a hospital’s system that might be appropriate candidates for palliative care. When Stanford Hospital’s palliative care team assessed 50 randomly chosen patients that the algorithm had flagged as being at very high risk, the team found that all of them were appropriate to be referred. Beyond being able to accurately predict, the program also left decision-making in the hands of the doctor entirely. That could be a future model for algorithms and physicians working together as a team.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image size-large\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"432\" src=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F11\u002Ftmf_article_339-01-768x432.png\" alt=\"robot android artificial intelligence AI algorithm human people man woman\" class=\"wp-image-47983\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F11\u002Ftmf_article_339-01-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F11\u002Ftmf_article_339-01-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F11\u002Ftmf_article_339-01-1536x864.png 1536w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">9) MedPaLM, the medical large language model\u003C\u002Fh2>\n\n\n\n\u003Cp>Large language models undoubtedly have changed this field forever, they are capable of such high-quality assistance that was never seen earlier. Only a few short weeks after the release of ChatGPT, Google\u002FDeepMind announced \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fpharmaphorum.com\u002Fnews\u002Fgoogle-and-deepmind-share-work-on-medical-chatbot-med-palm\u002F\" target=\"_blank\">the release of MedPaLM\u003C\u002Fa>, a large language model \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fmedpalm-new-ai-medical-chatbots-will-soon-be-better-than-waiting-for-a-doctor\u002F\" target=\"_blank\" rel=\"noreferrer noopener\">specifically designed to answer healthcare-related questions\u003C\u002Fa>, based on their 540-billion parameter PaLM model.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"351\" src=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F01\u002FMedpalm2-768x351.jpg\" alt=\"Medpalm google deepmind large languae model\" class=\"wp-image-48673\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F01\u002FMedpalm2-768x351.jpg 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2023\u002F01\u002FMedpalm2.jpg 988w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Cp>This model was trained on six existing medical Q&A datasets (NedQA, MedMCQA, PubMedQA, LiveQA, MedicationQA, and MMLU), and the developer teams also created their own HealthSearchQA, using questions about medical conditions and the associated symptoms. At the moment MedPaLM can’t be tested by the general public, but you can read the \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Farxiv.org\u002Fpdf\u002F2212.13138.pdf\" target=\"_blank\">researcher’s paper here\u003C\u002Fa>. \u003C\u002Fp>\n\n\n\n\u003Cp>Very recently \u003Ca href=\"https:\u002F\u002Fcloud.google.com\u002Fblog\u002Ftopics\u002Fhealthcare-life-sciences\u002Fsharing-google-med-palm-2-medical-large-language-model\" target=\"_blank\" rel=\"noreferrer noopener\">the latest iteration was also launched\u003C\u002Fa> and Google provided access to a select group of users, but we haven’t seen any studies related to the 2.0 version yet. \u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">10) The sepsis-watching algorithms\u003C\u002Fh2>\n\n\n\n\u003Cp>Duke University researchers developed a Sepsis Watch deep learning algorithm that helps assess a patient’s risk for developing sepsis. It automatically alerts the hospital’s rapid response team in case of a high-risk patient and guides them through the first 3 hours of care administration. This is critical in preventing complications. The university has been working on this algorithm for years and implemented the model in clinical work in 2018. \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.advisory.com\u002Fdaily-briefing\u002F2022\u002F04\u002F12\u002Fai-hospitals\" target=\"_blank\">According to Mark Sendak\u003C\u002Fa>, a physician and clinical data scientist at Duke who co-led the project, Duke is conducting a final analysis, but he noted that mortality seems to be down.\u003C\u002Fp>\n\n\n\n\u003Cp>Hospital chain HCA Healthcare also developed a predictive algorithm called Sepsis Prediction and Optimisation of Therapy. It continuously monitors patient data to identify potentially impending sepsis cases. The algorithm is able to detect sepsis six hours earlier—and more accurately—than clinicians, enabling the health care system to cut sepsis mortality rates across 160 hospitals by nearly 30% – \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.wsj.com\u002Farticles\u002Fhow-hospitals-are-using-ai-to-save-lives-11649610000\" target=\"_blank\">The Wall Street Journal reported\u003C\u002Fa>.\u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image size-large\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"432\" src=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F02\u002Ftmf_article_246-01-768x432.png\" alt=\"\" class=\"wp-image-32755\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F02\u002Ftmf_article_246-01-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F02\u002Ftmf_article_246-01-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F02\u002Ftmf_article_246-01-1536x864.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F02\u002Ftmf_article_246-01.png 1920w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">We better look at AI as our new colleague\u003C\u002Fh2>\n\n\n\n\u003Cp>There are many more excellent examples of smart algorithms in healthcare, and a lot more will come in the future. But the last one showed the essence of digital health: the best results are achieved by the cooperative work of artificial intelligence and human doctors. \u003C\u002Fp>\n\n\n\n\u003Cp>As artificial intelligence (AI) is set to revolutionise medical practice, it is vital for medical students, young and practising doctors to be well-prepared for the changing landscape. The rapid advancements in AI have brought about a major paradigm shift.\u003C\u002Fp>\n\n\n\n\u003Cp>I have already said many times before, AI will not replace doctors, but doctors using AI will replace those who are not keeping up with this revolution. \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fmedicalfuturist.thinkific.com\u002Fcourses\u002Fintroduction-to-artificial-intelligence-in-medicine-and-healthcare\" target=\"_blank\">Embracing and integrating AI technologies into medical practice\u003C\u002Fa> will not only benefit patients but also enhance the careers of those who are well-equipped for this new era of medicine.\u003C\u002Fp>\n\n\n\n\u003Ctable style=\"width: 100%; border-collapse: collapse; background-color: #eee; border-top: 4px solid #444;\" cellpadding=\"10px\">\n\u003Ctbody>\n\u003Ctr>\n\u003Ctd style=\"width: 100%;\">\n\u003Cp>\u003Cstrong>At The Medical Futurist, we are building a community for making a bold vision about the future of healthcare reality today.\u003C\u002Fstrong>\u003C\u002Fp>\n\u003Ciframe loading=\"lazy\" width=\"560\" height=\"315\" src=\"https:\u002F\u002Fwww.youtube.com\u002Fembed\u002FFIbMejImnxs\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen=\"\">\u003C\u002Fiframe>\n\u003Cp>If you’d like to support this mission, we invite you to \u003Ca href=\"https:\u002F\u002Fwww.patreon.com\u002Fthemedicalfuturist\">join The Medical Futurist Patreon Community\u003C\u002Fa>. A community of empowered patients, future-oriented healthcare professionals, concerned health policymakers, sensible health tech developers, and enthusiastic medical students. If there were ever a time to join us, it is now. Every contribution, however big or small, powers our research and sustains our future.\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.patreon.com\u002Fthemedicalfuturist\">\u003Cstrong style=\"background-color: #e71d3299; color: #000;\">Click here to support The Medical Futurist from as little as $3\u003C\u002Fstrong>\u003C\u002Fa> – it only takes a minute. Thank you.\u003C\u002Fp>\n\u003C\u002Ftd>\n\u003C\u002Ftr>\n\u003C\u002Ftbody>\n\u003C\u002Ftable>\n\u003Cp> \u003C\u002Fp>\n",{"rendered":213,"protected":20},"\u003Cp>As artificial intelligence tools have been invading more or less every area of healthcare, we made a list to keep track of the top smart algorithms aiming for better diagnostics, more sophisticated patient care or further sighted predictions of diseases. \u003C\u002Fp>\n",22998,{"_acf_changed":20,"footnotes":27},[31],[35,218,53,34,36,219,220,221,38,44,49,222],198,346,361,372,163,[224],950,[],[227,228,229,230,231,64,232,233,58,59,60],2967,1715,1723,1789,1805,1833,2485,[235,14,68,69,70,71,72,73,76,236,94,75,77,237,238,239,79,85,90,240,241],"post-22987","tag-death","tag-pathology","tag-prediction","tag-radiology","tag-cancer-2","project_category-medical-professionals",{"id":214,"alt_text":243,"caption":27,"description":27,"media_type":98,"media_details":244,"post":138,"source_url":261},"top AI algorithms",{"width":100,"height":101,"file":245,"sizes":246,"image_meta":260},"2019\u002F02\u002Fradiologist_001-scaled.png",{"medium":247,"large":250,"thumbnail":253,"medium_large":256,"1536x1536":257},{"file":248,"width":106,"height":107,"mime-type":108,"source_url":249},"radiologist_001-scaled-370x208.png","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002Fradiologist_001-scaled-370x208.png",{"file":251,"width":112,"height":113,"mime-type":108,"source_url":252},"radiologist_001-scaled-768x432.png","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002Fradiologist_001-scaled-768x432.png",{"file":254,"width":117,"height":117,"mime-type":108,"source_url":255},"radiologist_001-scaled-150x150.png","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002Fradiologist_001-scaled-150x150.png",{"file":251,"width":112,"height":113,"mime-type":108,"source_url":252},{"file":258,"width":122,"height":123,"mime-type":108,"source_url":259},"radiologist_001-scaled-1536x864.png","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002Fradiologist_001-scaled-1536x864.png",{"aperture":131,"credit":27,"camera":27,"caption":27,"created_timestamp":131,"copyright":27,"focal_length":131,"iso":131,"shutter_speed":131,"title":27,"orientation":131},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F02\u002Fradiologist_001-scaled.png",{"related_posts":263,"related_posts_footer":267,"cta_type":27,"cta_color":27,"subtitle":27,"related_books":20,"key_takeaways":271},[264,265,266],13650,14848,10983,[268,269,270],10785,16745,16479,[272,274],{"title":273},"\u003Cp>As AI tools have been invading more or less every area of healthcare, we made a list to keep track of the top AI algorithms aiming for better diagnostics, more sophisticated patient care or further sighted predictions of diseases.\u003C\u002Fp>\n\u003Cp> \u003C\u002Fp>\n",{"title":275},"\u003Cp>By enumerating the top AI tools that we discovered in healthcare so far, we also aim to add what we believe is already useful for the work of medical professionals.\u003C\u002Fp>\n",{"yoast_wpseo_title":277,"yoast_wpseo_metadesc":278,"yoast_wpseo_canonical":207},"Top AI Algorithms In Healthcare - The Medical Futurist","The Medical Futurist made a list to keep track of the top AI algorithms aiming for better diagnostics or further sighted predictions in healthcare.",{"self":280,"collection":285,"about":287,"author":289,"replies":291,"version-history":294,"predecessor-version":298,"wp:featuredmedia":302,"wp:attachment":305,"wp:term":308,"curies":319},[281],{"href":282,"targetHints":283},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F22987",{"allow":284},[153],[286],{"href":156},[288],{"href":159},[290],{"embeddable":26,"href":162},[292],{"embeddable":26,"href":293},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcomments?post=22987",[295],{"count":296,"href":297},17,"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F22987\u002Frevisions",[299],{"id":300,"href":301},59573,"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F22987\u002Frevisions\u002F59573",[303],{"embeddable":26,"href":304},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia\u002F22998",[306],{"href":307},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia?parent=22987",[309,311,313,315,317],{"taxonomy":182,"embeddable":26,"href":310},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcategories?post=22987",{"taxonomy":185,"embeddable":26,"href":312},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Ftags?post=22987",{"taxonomy":188,"embeddable":26,"href":314},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fproject_category?post=22987",{"taxonomy":191,"embeddable":26,"href":316},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcontact_email_category?post=22987",{"taxonomy":194,"embeddable":26,"href":318},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fyst_prominent_words?post=22987",[320],{"name":198,"href":199,"templated":26},[322],{"id":143,"date":323,"date_gmt":324,"guid":325,"modified":327,"modified_gmt":328,"slug":329,"status":13,"type":330,"link":331,"title":332,"content":334,"excerpt":336,"author":338,"featured_media":339,"comment_status":25,"ping_status":25,"template":27,"yst_prominent_words":340,"class_list":342,"better_featured_image":345,"acf":385,"yoast_meta":406,"_links":409},"2021-03-03T21:58:00","2021-03-03T20:58:00",{"rendered":326},"https:\u002F\u002Fapi.medicalfuturist.com\u002F?post_type=book&p=24762","2024-05-29T23:37:45","2024-05-29T21:37:45","a-guide-to-artificial-intelligence-in-healthcare","book","https:\u002F\u002Fapi.medicalfuturist.com\u002Fbooks\u002Fa-guide-to-artificial-intelligence-in-healthcare\u002F",{"rendered":333},"A Guide to Artificial Intelligence in Healthcare",{"rendered":335,"protected":20},"\n\u003Cp>Can we stay human in the\nage of A.I.? To go even further, can we grow in humanity, can we shape a\nmore humane, more equitable and sustainable healthcare?\u003C\u002Fp>\n\n\n\n\u003Cp>Our e-book aims to prepare\nhealthcare and medical professionals for the era of human-machine collaboration.\nRead The Medical Futurist’s guide to understanding, anticipating and\ncontrolling artificial intelligence.\u003C\u002Fp>\n",{"rendered":337,"protected":20},"\u003Cp>Can we stay human in the age of A.I.? To go even further, can we grow in humanity, can we shape a more humane, more equitable […]\u003C\u002Fp>\n",10,56335,[341,229],1683,[343,330,344,69,71,72],"post-24762","type-book",{"id":339,"alt_text":27,"caption":27,"description":27,"media_type":98,"media_details":346,"post":143,"source_url":384},{"width":347,"height":348,"file":349,"filesize":350,"sizes":351,"image_meta":382},1700,2200,"2021\u002F03\u002Fai-in-healthcare_2024-v6-1-1.png",785627,{"medium":352,"large":358,"thumbnail":364,"medium_large":369,"1536x1536":370,"2048x2048":376},{"file":353,"width":354,"height":355,"mime-type":108,"filesize":356,"source_url":357},"ai-in-healthcare_2024-v6-1-1-370x208.png",370,208,49495,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Fai-in-healthcare_2024-v6-1-1-370x208.png",{"file":359,"width":360,"height":361,"mime-type":108,"filesize":362,"source_url":363},"ai-in-healthcare_2024-v6-1-1-768x994.png",768,994,349457,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Fai-in-healthcare_2024-v6-1-1-768x994.png",{"file":365,"width":366,"height":366,"mime-type":108,"filesize":367,"source_url":368},"ai-in-healthcare_2024-v6-1-1-150x150.png",150,23049,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Fai-in-healthcare_2024-v6-1-1-150x150.png",{"file":359,"width":360,"height":361,"mime-type":108,"filesize":362,"source_url":363},{"file":371,"width":372,"height":373,"mime-type":108,"filesize":374,"source_url":375},"ai-in-healthcare_2024-v6-1-1-1187x1536.png",1187,1536,849543,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Fai-in-healthcare_2024-v6-1-1-1187x1536.png",{"file":377,"width":378,"height":379,"mime-type":108,"filesize":380,"source_url":381},"ai-in-healthcare_2024-v6-1-1-1583x2048.png",1583,2048,1578683,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Fai-in-healthcare_2024-v6-1-1-1583x2048.png",{"aperture":131,"credit":27,"camera":27,"caption":27,"created_timestamp":131,"copyright":27,"focal_length":131,"iso":131,"shutter_speed":131,"title":27,"orientation":131,"keywords":383},[],"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Fai-in-healthcare_2024-v6-1-1.png",{"leanpub_url":386,"preview":387,"buy_button_text":405},"https:\u002F\u002Fleanpub.com\u002FArtificialIntelligenceinHealthcare",[388,389,391,393,395,397,399,401,403],{"image":384},{"image":390},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FArtificialIntelligenceinHealthcare-3-1.png",{"image":392},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FArtificialIntelligenceinHealthcare-4-1.png",{"image":394},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FArtificialIntelligenceinHealthcare-5-1.png",{"image":396},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FArtificialIntelligenceinHealthcare-6-1.png",{"image":398},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FArtificialIntelligenceinHealthcare-7-1.png",{"image":400},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FArtificialIntelligenceinHealthcare-8-1.png",{"image":402},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FArtificialIntelligenceinHealthcare-9-1.png",{"image":404},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2019\u002F09\u002FArtificialIntelligenceinHealthcare-10-1.png","Get it on Leanpub",{"yoast_wpseo_title":407,"yoast_wpseo_metadesc":408,"yoast_wpseo_canonical":331},"A Guide to Artificial Intelligence in Healthcare - The Medical Futurist","The Guide To Artificial Intelligence In Healthcare aims to prepare healthcare and medical professionals for the era of human-machine collaboration.",{"self":410,"collection":415,"about":418,"author":421,"replies":424,"wp:featuredmedia":427,"wp:attachment":430,"wp:term":433,"curies":436},[411],{"href":412,"targetHints":413},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fbook\u002F24762",{"allow":414},[153],[416],{"href":417},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fbook",[419],{"href":420},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Ftypes\u002Fbook",[422],{"embeddable":26,"href":423},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fusers\u002F10",[425],{"embeddable":26,"href":426},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcomments?post=24762",[428],{"embeddable":26,"href":429},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia\u002F56335",[431],{"href":432},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia?parent=24762",[434],{"taxonomy":194,"embeddable":26,"href":435},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fyst_prominent_words?post=24762",[437],{"name":198,"href":199,"templated":26},1790254579763]