[{"data":1,"prerenderedAt":386},["ShallowReactive",2],{"slug-the-promise-of-crispr-gpt-specialized-chatgpts-could-transform-medicine":3},{"post":4,"relatedPosts":181,"relatedBooks":298},{"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":35,"project_category":43,"contact_email_category":47,"yst_prominent_words":48,"class_list":54,"better_featured_image":75,"acf":108,"yoast_meta":125,"_links":128},56163,"2024-05-23T09:30:00","2024-05-23T07:30:00",{"rendered":9},"https:\u002F\u002Fmedicalfuturist.com\u002F?post_id=56163&_wpnonce=d85dc5f64a&status=auto-draft&type=post","2024-05-23T08:08:27","2024-05-23T06:08:27","the-promise-of-crispr-gpt-specialized-chatgpts-could-transform-medicine","publish","post","https:\u002F\u002Fmedicalfuturist.com\u002Fthe-promise-of-crispr-gpt-specialized-chatgpts-could-transform-medicine",{"rendered":17},"The Promise Of CRISPR GPT: Specialised ChatGPTs Could Transform Medicine",{"rendered":19,"protected":20},"\n\u003Cp>We’ve recently \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fwww.nature.com\u002Farticles\u002Fd41586-024-01243-w\" target=\"_blank\">come across\u003C\u002Fa> some \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fpdf\u002F2404.18021\">fascinating\u003C\u002Fa> developments in the field of gene editing: CRISPR GPT, a large language model agent designed to automate the design of gene-editing experiments. This got us thinking: what other ‘\u003Cem>specialty GPTs\u003C\u002Fem>‘ could we think of? What highly specific applications might there be for large language models (LLMs)?\u003C\u002Fp>\n\n\n\n\u003Cp>CRISPR GPT is a large language model similar to ChatGPT, but it’s been trained on a very specialised dataset focused on gene editing and CRISPR technology. This makes it exceptionally effective in that specific area, understanding the nuances of gene editing, identifying potential errors or risks, and suggesting optimal experimental designs. However, unlike ChatGPT, which is designed to handle a broad range of general questions, CRISPR GPT may not perform well on general queries outside its gene-editing domain. \u003C\u002Fp>\n\n\n\n\u003Cp>The genius of this idea is using a large language model’s ability to handle vast amounts of data in gene editing. Researchers must sift through massive databases to identify suitable gene sequences, understand potential side effects, and optimise the CRISPR system. An LLM like GPT can analyse this data, identify patterns, and make suggestions, significantly accelerating and enhancing the research process.\u003C\u002Fp>\n\n\n\n\u003Cp>So, what other fields could benefit from this technology? Where else in medicine do professionals need to interact with, analyse, and interpret enormous amounts of complex data?\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">At pharmaceutical companies\u003C\u002Fh2>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for drug discovery\u003C\u002Fh3>\n\n\n\n\u003Cp>Drug-GPTs could quickly go through massive datasets of molecular structures, chemical properties, and biological activity to predict how different molecules might interact with potential drug targets. This could significantly speed up identifying promising drug candidates and optimising their structures, accelerating the development of new medications.\u003C\u002Fp>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for protein engineering\u003C\u002Fh3>\n\n\n\n\u003Cp>Protein engineering is another field ripe for innovation with GPT. These models can assist in developing new proteins with specific functions, which are crucial in biotechnology and therapeutic applications. By simulating protein folding and interactions, GPT can help design proteins that perform desired tasks, potentially leading to breakthroughs in medical treatments and industrial processes.\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\u002F11\u002Ftmf_article_299-01-768x432.png\" alt=\"drug, drug design, pharma\" class=\"wp-image-36791\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F11\u002Ftmf_article_299-01-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F11\u002Ftmf_article_299-01-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F11\u002Ftmf_article_299-01-1536x864.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F11\u002Ftmf_article_299-01.png 1920w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for antibody design\u003C\u002Fh3>\n\n\n\n\u003Cp>Antibody-GPTs could generate novel antibody sequences for therapeutic use, enhancing the immune response or targeting specific pathogens with high precision. This capability could lead to the rapid development of new treatments for various infectious and autoimmune diseases.\u003C\u002Fp>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for clinical trial design\u003C\u002Fh3>\n\n\n\n\u003Cp>Trial-GPT can streamline the design of clinical trials by analysing biomedical literature and patient data to identify optimal trial designs, patient cohorts, and potential biomarkers. Which means faster development of new treatments and improved efficiency of clinical research.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">In medical practices and hospitals\u003C\u002Fh2>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for personalised medicine\u003C\u002Fh3>\n\n\n\n\u003Cp>Doctor-GPTs digest patient data in seconds, including genetic information, medical history, lifestyle factors, and environmental exposures. This can help identify individual risk factors, predict disease susceptibility, and tailor treatment plans to each patient’s unique genetic makeup. With such a personalised approach, patients could receive the most effective therapies based on their genetic and health profiles. Thinking a bit ahead, such LLMs could help us move medicine towards prevention, instead of treatments.\u003C\u002Fp>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for 3D printing in medicine\u003C\u002Fh3>\n\n\n\n\u003Cp>Special 3D-printing LLMs could help design intricate scaffolds for tissue engineering, optimize printing parameters for different materials, and even predict how printed structures will interact with biological tissues. This could lead to more precise and personalised medical devices and potentially even accelerate the development of bioprinted organs for transplantation.\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\u002F03\u002Ftmf_article_249-01-768x432.png\" alt=\"3D printing\" class=\"wp-image-33403\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Ftmf_article_249-01-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Ftmf_article_249-01-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Ftmf_article_249-01-1536x864.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2021\u002F03\u002Ftmf_article_249-01.png 1920w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for cancer genomics\u003C\u002Fh3>\n\n\n\n\u003Cp>A Cancer-GPT could analyse large-scale genomic data from cancer patients to identify the specific mutations driving tumor growth and predict how tumors will respond to different treatments. This could lead to more targeted therapies and improve the chances of successful treatment for cancer patients.\u003C\u002Fp>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for surgical planning\u003C\u002Fh3>\n\n\n\n\u003Cp>Surgeon-GPTs could assist surgical planning for complex procedures. They could analyse patient data and medical imaging, simulate different surgical approaches, determine the best strategies, minimize risks, and improve patient outcomes.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">For everyone\u003C\u002Fh2>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for neural network simulations\u003C\u002Fh3>\n\n\n\n\u003Cp>LLMs could be used to create detailed simulations of neural circuits, helping researchers understand how neurons communicate, how neural networks process information, and how different brain regions interact. These simulations could also help identify how disruptions in neural circuits lead to neurological disorders like Alzheimer’s, Parkinson’s, and epilepsy. Ultimately, this could lead to new treatments for these debilitating conditions.\u003C\u002Fp>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for nutritional science\u003C\u002Fh3>\n\n\n\n\u003Cp>A Nutrition-GPT could assist in nutritional science by analysing dietary data, medical history, and genetic information to create personalised nutrition plans. This can help individuals achieve better health outcomes through tailored dietary recommendations based on their specific needs and conditions. What \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fwhy-is-nutrigenomics-the-biggest-flop-in-digital-health\u002F\">nutrigenomics\u003C\u002Fa> currently lacks to deliver on its promises could maybe come from large language models. \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\u002F12\u002Ftmf_article_345-01-768x432.png\" alt=\"nutrigenomics\" class=\"wp-image-48473\" srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F12\u002Ftmf_article_345-01-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F12\u002Ftmf_article_345-01-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F12\u002Ftmf_article_345-01-1536x864.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F12\u002Ftmf_article_345-01-2048x1152.png 2048w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F12\u002Ftmf_article_345-01.png 1920w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003C\u002Ffigure>\n\n\n\n\u003Ch3 class=\"wp-block-heading\">GPT for epidemiology\u003C\u002Fh3>\n\n\n\n\u003Cp>The Covid-pandemic was \u003Ca href=\"https:\u002F\u002Fdeptmedicine.utoronto.ca\u002Fnews\u002Ftracking-coronavirus-pandemic-ai-bluedot-featured-60-minutes\">first spotted by Bluedot\u003C\u002Fa>, an AI company in Toronto. As the AI arena just got more advanced in the past few years, the field of epidemiology can handsomely benefit from its development. Pandemic-GPT could analyse data from various sources to predict disease outbreaks, track the spread of infectious diseases, and evaluate the effectiveness of public health interventions. This can help public health officials make informed decisions and implement timely measures to control epidemics.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">Specialised GPTs are easier to image than to create\u003C\u002Fh2>\n\n\n\n\u003Cp>These are just a few examples of the many ways in which large language models could help medicine. Of course, imagining these specialised GPTs is far easier than creating them and ensuring they work reliably enough for use in healthcare. Rigorous testing, validation, and regulatory approval will be essential before these models can be deployed in real-world medical settings.\u003C\u002Fp>\n\n\n\n\u003Cp>However, thinking about potential use cases is never a waste of time. Such thought experiments highlight that there will hardly be a stone left unturned in healthcare by these changes. The new potential brought by specialised GPTs will improve the care patients can receive, enhance the work doctors can do, advance medical research, and streamline the logistics behind healthcare.\u003C\u002Fp>\n",false,{"rendered":22,"protected":20},"\u003Cp>Specifically trained GPTs, like CRISPR GPT, won’t be good in general chat but will excel in analyzing DNA, designing personalized nutrition. or helping surgical planning.\u003C\u002Fp>\n",6,47667,"closed",true,"","standard",{"_acf_changed":20,"footnotes":27},[31,32,33,34],7079,504,488,489,[36,37,38,39,40,41,42],7671,570,7673,7741,7807,7943,7945,[44,45,46],948,950,953,[],[49,50,51,52,53],5499,1693,1807,3357,4507,[55,14,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74],"post-56163","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tmf","category-artificial-intelligence","category-genomics","category-personalized-medicine","tag-ai-in-healthcare","tag-crispr","tag-ai-in-medicine","tag-large-language-models","tag-gpt-in-healthcare","tag-specialzed-gpts","tag-crispr-gpt","project_category-developers","project_category-medical-professionals","project_category-researchers",{"id":24,"alt_text":76,"caption":27,"description":27,"media_type":77,"media_details":78,"post":106,"source_url":107},"tmf dna sequence","image",{"width":79,"height":80,"file":81,"sizes":82,"image_meta":104},1800,1012,"2022\u002F10\u002Ftmf_DNA-sequence.png",{"medium":83,"large":89,"thumbnail":94,"medium_large":98,"1536x1536":99},{"file":84,"width":85,"height":86,"mime-type":87,"source_url":88},"tmf_DNA-sequence-370x208.png","370","208","image\u002Fpng","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F10\u002Ftmf_DNA-sequence-370x208.png",{"file":90,"width":91,"height":92,"mime-type":87,"source_url":93},"tmf_DNA-sequence-768x432.png","768","432","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F10\u002Ftmf_DNA-sequence-768x432.png",{"file":95,"width":96,"height":96,"mime-type":87,"source_url":97},"tmf_DNA-sequence-150x150.png","150","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F10\u002Ftmf_DNA-sequence-150x150.png",{"file":90,"width":91,"height":92,"mime-type":87,"source_url":93},{"file":100,"width":101,"height":102,"mime-type":87,"source_url":103},"tmf_DNA-sequence-1536x864.png","1536","864","https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F10\u002Ftmf_DNA-sequence-1536x864.png",{"aperture":105,"credit":27,"camera":27,"caption":27,"created_timestamp":105,"copyright":27,"focal_length":105,"iso":105,"shutter_speed":105,"title":27,"orientation":105},"0",15142,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2022\u002F10\u002Ftmf_DNA-sequence.png",{"cta_type":109,"cta_color":27,"related_posts_footer":110,"related_posts":20,"related_books":114,"subtitle":27,"key_takeaways":118},"subscribe",[111,112,113],55791,17898,55481,[115,116,117],52203,37033,24761,[119,121,123],{"title":120},"\u003Cp>Large language models could be surprisingly efficient in various medical areas – not just for problems including human conversations, but data and network analyses too.\u003C\u002Fp>\n",{"title":122},"\u003Cp>Pharma companies like Roche have already started deploying their own ChatGPT-like tools in practice, there are untapped potentials in specific research areas.\u003C\u002Fp>\n",{"title":124},"\u003Cp>As CRISPR GPT paved the way, here are a few examples that might as well become reality in the coming years.\u003C\u002Fp>\n",{"yoast_wpseo_title":126,"yoast_wpseo_metadesc":127,"yoast_wpseo_canonical":15},"The Promise Of CRISPR GPT: Specialized ChatGPTs In Medicine","Specifically trained GPTs, like CRISPR GPT, won't be good in general chat but will excel in analyzing DNA or designing personalized nutrition.",{"self":129,"collection":135,"about":138,"author":141,"replies":144,"version-history":147,"predecessor-version":151,"wp:featuredmedia":155,"wp:attachment":158,"wp:term":161,"curies":177},[130],{"href":131,"targetHints":132},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F56163",{"allow":133},[134],"GET",[136],{"href":137},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts",[139],{"href":140},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Ftypes\u002Fpost",[142],{"embeddable":26,"href":143},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fusers\u002F6",[145],{"embeddable":26,"href":146},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcomments?post=56163",[148],{"count":149,"href":150},7,"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F56163\u002Frevisions",[152],{"id":153,"href":154},56221,"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F56163\u002Frevisions\u002F56221",[156],{"embeddable":26,"href":157},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia\u002F47667",[159],{"href":160},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia?parent=56163",[162,165,168,171,174],{"taxonomy":163,"embeddable":26,"href":164},"category","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcategories?post=56163",{"taxonomy":166,"embeddable":26,"href":167},"post_tag","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Ftags?post=56163",{"taxonomy":169,"embeddable":26,"href":170},"project_category","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fproject_category?post=56163",{"taxonomy":172,"embeddable":26,"href":173},"contact_email_category","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcontact_email_category?post=56163",{"taxonomy":175,"embeddable":26,"href":176},"yst_prominent_words","https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fyst_prominent_words?post=56163",[178],{"name":179,"href":180,"templated":26},"wp","https:\u002F\u002Fapi.w.org\u002F{rel}",[182],{"id":113,"date":183,"date_gmt":184,"guid":185,"modified":187,"modified_gmt":188,"slug":189,"status":13,"type":14,"link":190,"title":191,"content":193,"excerpt":195,"author":23,"featured_media":197,"comment_status":25,"ping_status":25,"sticky":26,"template":27,"format":28,"meta":198,"categories":199,"tags":200,"project_category":201,"contact_email_category":202,"yst_prominent_words":203,"class_list":208,"better_featured_image":210,"acf":245,"yoast_meta":253,"_links":256},"2024-04-11T09:30:02","2024-04-11T07:30:02",{"rendered":186},"https:\u002F\u002Fmedicalfuturist.com\u002F?post_id=55481&_wpnonce=9fe6e72c97&status=auto-draft&type=post","2024-04-11T08:45:08","2024-04-11T06:45:08","new-e-book-100-questions-and-answers-about-generative-ai-in-healthcare","https:\u002F\u002Fmedicalfuturist.com\u002Fnew-e-book-100-questions-and-answers-about-generative-ai-in-healthcare",{"rendered":192},"New E-Book: 100 Questions And Answers About Generative AI In Healthcare",{"rendered":194,"protected":20},"\n\u003Cp>We are happy and proud to introduce you to the new book we’ve been working on in the past few months: \u003Ca href=\"https:\u002F\u002Fleanpub.com\u002F100-questions-about-ai-in-healthcare\" target=\"_blank\" rel=\"noreferrer noopener\">100 Questions And Answers About Generative AI In Healthcare\u003C\u002Fa>. This is a brand new format for us, and we hope you will like it. \u003C\u002Fp>\n\n\n\n\u003Cfigure class=\"wp-block-image size-large\">\u003Ca class=\"img\" href=\"https:\u002F\u002Fleanpub.com\u002F100-questions-about-ai-in-healthcare\" target=\"_blank\" rel=\"noreferrer noopener\">\u003Cimg loading=\"lazy\" decoding=\"async\" width=\"768\" height=\"432\" src=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-02-768x432.png\" alt=\"\" class=\"wp-image-55487\"\u002F\u003C\u002Fa srcset=\"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-02-768x432.png 768w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-02-370x208.png 370w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-02-1536x864.png 1536w, https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-02.png 1600w\" sizes=\"auto, (max-width: 768px) 100vw, 768px\" \u002F>\u003C\u002Fa>\u003C\u002Ffigure>\n\n\n\n\u003Cp>Artificial intelligence has become the buzzword of the past year. Although \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fmedicalfuturist.com\u002F7-things-you-can-expect-from-a-i-in-healthcare\u002F\" target=\"_blank\">we have\u003C\u002Fa> been \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fno-precision-medicine-without-artificial-intelligence\u002F\" target=\"_blank\">predicting\u003C\u002Fa> for \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fartificial-intelligence-will-redesign-healthcare\u002F\" target=\"_blank\">years\u003C\u002Fa> how it will \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fguide-to-artificial-intelligence-in-healthcare\u002F\" target=\"_blank\">revolutionise\u003C\u002Fa> healthcare, it suddenly became very relatable as tools like ChatGPT or MidJourney became \u003Ca rel=\"noreferrer noopener\" href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fa-year-in-ai-the-most-important-milestones-for-medicine\u002F\" target=\"_blank\">available to all of us\u003C\u002Fa>. \u003C\u002Fp>\n\n\n\n\u003Cp>It is an undeniable – and \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002F10-things-you-can-definitely-expect-from-the-future-of-healthcare-ai\u002F\" target=\"_blank\" rel=\"noreferrer noopener\">unstoppable\u003C\u002Fa> – force in healthcare, but this rapid evolution can leave us feeling overwhelmed. With the power to transform diagnostics, drug discovery, and even patient care, this is a vast field, and it can be sometimes challenging to find the focus. \u003Cbr>\u003Cbr>In this new book, we listed 100 questions in 10 chapters, all related to artificial intelligence in healthcare, moving from the basics to the specifics. We did our best to keep the answers short and easy to follow, and the structure of the book light and airy. What kind of topics will be discussed here? \u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">Here’s a sample of 5 questions, let’s explore some of the answers!\u003C\u002Fh2>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">What are large language models?\u003C\u002Fh2>\n\n\n\n\u003Cp>Large language models (LLMs) are a type of artificial intelligence that can “understand” and generate human-like texts. They are trained on massive amounts of data, from which they learn the patterns and relationships within language, allowing them to generate text, translate between languages, write different kinds of creative content, and answer your questions in an informative way. We can think of them as brilliant autocomplete machines that have mastered the nuances of language.\u003C\u002Fp>\n\n\n\n\u003Cp>Most LLMs work using a neural network architecture called a transformer. This architecture helps them focus on the most relevant parts of the input, making them adept at understanding context and generating responses that are both coherent and relevant. Examples of LLMs include models like GPT-3, GPT-3.5, and GPT-4 (used in \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fthe-chatgpt-revolution-heres-our-new-book-on-generative-ai-in-healthcare\u002F\" target=\"_blank\" rel=\"noreferrer noopener\">ChatGPT\u003C\u002Fa>), Google’s LaMDA, Bard or PaLM, and models like Llama or Claude.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">What are the tasks automation could impact the most in healthcare?\u003C\u002Fh2>\n\n\n\n\u003Cp>As a rule of thumb, the best candidates for automation are processes that are both data-based and repetitive. In a hospital, it will first include tasks like \u003C\u002Fp>\n\n\n\n\u003Cul class=\"wp-block-list\">\n\u003Cli>Scheduling and appointment management: you don’t need humans to fill regular 30-minute spots with patients, it is a task that can be easily managed by an automated system and by the patients themselves.\u003C\u002Fli>\n\n\n\n\u003Cli>Billing and claims processing: automating this monotone, often error-prone process reduces paperwork, speeds up reimbursement, and frees up staff for patient-focused tasks.\u003C\u002Fli>\n\n\n\n\u003Cli>Image processing: well-trained algorithms are many orders of magnitude faster than even the best human specialists. Like Arterys’s \u003Ca href=\"https:\u002F\u002Fwww.forbes.com\u002Fsites\u002Fbernardmarr\u002F2017\u002F01\u002F20\u002Ffirst-fda-approval-for-clinical-cloud-based-deep-learning-in-healthcare\u002F\">cloud-based deep learning model\u003C\u002Fa> that analyses heart images in 15 seconds, which would take a doctor 30-60 minutes.\u003C\u002Fli>\n\u003C\u002Ful>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">Will AI increase or decrease the cost of healthcare?\u003C\u002Fh2>\n\n\n\n\u003Cp>As AI finds its way into everyday clinical settings, a critical question emerges: who will pay for the deployment (and use and maintenance) of such systems? And this is not a sci-fi question, but something we face today. We discussed this issue in depth \u003Ca href=\"https:\u002F\u002Fmedicalfuturist.com\u002Fwill-patients-have-to-pay-for-using-ai-in-their-healthcare\u002F\">in this article\u003C\u002Fa>.\u003C\u002Fp>\n\n\n\n\u003Cp>The financial implications of AI in healthcare are still evolving, and it’s unclear how these will reshape overall costs. In countries with private insurance-based healthcare systems, the key factor is insurance coverage: will plans adapt to cover AI-enhanced services, and how will this affect premiums and out-of-pocket expenses? In countries with socialized medicine, the question is whether there are sufficient funds to deploy AI technologies in the first place.\u003C\u002Fp>\n\n\n\n\u003Cp>This article discussed how the author was asked \u003Ca href=\"https:\u002F\u002Fedition.cnn.com\u002F2024\u002F01\u002F26\u002Fhealth\u002Fai-mammograms-kff-health-news\u002Findex.html\">if she wanted to pay $40 extra\u003C\u002Fa> for additional AI analysis in mammography. In her case, a Manhattan radiology clinic offered an AI analysis of their mammogram for an additional $40, not covered by insurance. This scenario was echoed at a clinic in suburban Baltimore, where patients were similarly offered AI-assisted mammography for a $40 fee. These instances mark the initial real-world applications of AI in patient care but also introduce new factors to the healthcare equation.\u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">How do I interact with AI? \u003C\u002Fh2>\n\n\n\n\u003Cp>The AI models we use most often these days – like ChatGPT, Gemini or Midjourney – work by receiving text-based instructions from the users. These instructions are called prompts, and the “art” of crafting good prompts that make machines create the desired result is called ‘prompt engineering’. \u003C\u002Fp>\n\n\n\n\u003Cp>This might sound fancy or complicated, but the point is this: prompts are our inputs, and the better we get at giving great prompts, the better the output will be. Like any skill, mastery of prompt engineering comes with practice and a good amount of trial and error. The best way to become good at it is by doing it. Just type in anything, a request for an exciting cocktail recipe using limes, a question about the meaning of life or try and make the algorithm sound like an angry elementary school teacher. \u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">What can we expect from healthcare AI in the next 3 years?\u003C\u002Fh2>\n\n\n\n\u003Cp>In the coming years, AI will play a greater role in patient-facing applications, like skin-checking apps, refining their accuracy and expanding the range of detectable conditions. AI-powered tools supporting doctors and nurses in administrative tasks will become commonplace, freeing up time for meaningful patient interactions. Chatbots are likely to evolve, assisting with initial symptom assessment and offering support for common healthcare questions to bridge gaps in access.\u003C\u002Fp>\n\n\n\n\u003Cp>We may see early adopters of generative AI tools like ChatGPT for tasks such as personalised health summaries or patient communication materials tailored to a specific individual’s understanding level. While widespread clinical use of these tools is still some time away, we expect initial pilots and experimentation. And we can also expect the arrival of multimodal large language models – systems capable of dealing with all kinds of input (including text, sound, images, videos, and even gestures) that may serve as a “central hub”, as the ultimate interface between physicians and specialised AI applications. \u003C\u002Fp>\n\n\n\n\u003Ch2 class=\"wp-block-heading\">Another 95 questions await you\u003C\u002Fh2>\n\n\n\n\u003Cp>The intersection of AI and healthcare is ripe with both challenges and unprecedented opportunities. The examples provided here are just the tip of the iceberg, illustrating how each question opens a door to further inquiry, and, hopefully, a better understanding of how AI can serve both practitioners and patients in meaningful ways.\u003C\u002Fp>\n\n\n\n\u003Cp>With “\u003Ca href=\"https:\u002F\u002Fleanpub.com\u002F100-questions-about-ai-in-healthcare\" target=\"_blank\" rel=\"noreferrer noopener\">100 Questions And Answers About Generative AI In Healthcare\u003C\u002Fa>,” you’re invited to dive deeper into this fascinating topic. Another 95 questions await to equip you with the knowledge and insight needed to navigate the healthcare AI field. Whether you’re a healthcare professional looking to incorporate AI into your practice, a student eager to understand the future of medicine, or simply a curious mind, we hope this book helps your discovery and understanding.\u003C\u002Fp>\n",{"rendered":196,"protected":20},"\u003Cp>In this new book, we listed 100 questions in 10 chapters, all related to artificial intelligence in healthcare, moving from the basics to the specifics.\u003C\u002Fp>\n",55381,{"_acf_changed":20,"footnotes":27},[31,32],[],[],[],[204,205,206,207],1683,1715,1833,1835,[209,14,56,57,58,59,60,61,62],"post-55481",{"id":197,"alt_text":27,"caption":27,"description":27,"media_type":77,"media_details":211,"post":243,"source_url":244},{"width":212,"height":213,"file":214,"filesize":215,"sizes":216,"image_meta":241},1820,1024,"2024\u002F04\u002F100-q-header-03.png",1911958,{"medium":217,"large":223,"thumbnail":229,"medium_large":234,"1536x1536":235},{"file":218,"width":219,"height":220,"mime-type":87,"filesize":221,"source_url":222},"100-q-header-03-370x208.png",370,208,70858,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-03-370x208.png",{"file":224,"width":225,"height":226,"mime-type":87,"filesize":227,"source_url":228},"100-q-header-03-768x432.png",768,432,261955,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-03-768x432.png",{"file":230,"width":231,"height":231,"mime-type":87,"filesize":232,"source_url":233},"100-q-header-03-150x150.png",150,29979,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-03-150x150.png",{"file":224,"width":225,"height":226,"mime-type":87,"filesize":227,"source_url":228},{"file":236,"width":237,"height":238,"mime-type":87,"filesize":239,"source_url":240},"100-q-header-03-1536x864.png",1536,864,917313,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-03-1536x864.png",{"aperture":105,"credit":27,"camera":27,"caption":27,"created_timestamp":105,"copyright":27,"focal_length":105,"iso":105,"shutter_speed":105,"title":27,"orientation":105,"keywords":242},[],55379,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2024\u002F04\u002F100-q-header-03.png",{"cta_type":109,"cta_color":27,"related_books":246,"related_posts_footer":249,"related_posts":20,"subtitle":27,"key_takeaways":20},[115,247,248],24759,34151,[250,251,252],55033,55367,54887,{"yoast_wpseo_title":254,"yoast_wpseo_metadesc":255,"yoast_wpseo_canonical":190},"E-Book: 100 Questions And Answers About Generative AI In Healthcare","In this new book, we listed 100 questions in 10 chapters, all related to artificial intelligence in healthcare, moving from the basics to the specifics.",{"self":257,"collection":262,"about":264,"author":266,"replies":268,"version-history":271,"predecessor-version":275,"wp:featuredmedia":279,"wp:attachment":282,"wp:term":285,"curies":296},[258],{"href":259,"targetHints":260},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F55481",{"allow":261},[134],[263],{"href":137},[265],{"href":140},[267],{"embeddable":26,"href":143},[269],{"embeddable":26,"href":270},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcomments?post=55481",[272],{"count":273,"href":274},10,"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F55481\u002Frevisions",[276],{"id":277,"href":278},55549,"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fposts\u002F55481\u002Frevisions\u002F55549",[280],{"embeddable":26,"href":281},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia\u002F55381",[283],{"href":284},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia?parent=55481",[286,288,290,292,294],{"taxonomy":163,"embeddable":26,"href":287},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcategories?post=55481",{"taxonomy":166,"embeddable":26,"href":289},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Ftags?post=55481",{"taxonomy":169,"embeddable":26,"href":291},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fproject_category?post=55481",{"taxonomy":172,"embeddable":26,"href":293},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcontact_email_category?post=55481",{"taxonomy":175,"embeddable":26,"href":295},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fyst_prominent_words?post=55481",[297],{"name":179,"href":180,"templated":26},[299],{"id":117,"date":300,"date_gmt":301,"guid":302,"modified":304,"modified_gmt":305,"slug":306,"status":13,"type":307,"link":308,"title":309,"content":311,"excerpt":313,"author":273,"featured_media":315,"comment_status":25,"ping_status":25,"template":27,"yst_prominent_words":316,"class_list":318,"better_featured_image":321,"acf":339,"yoast_meta":355,"_links":357},"2023-11-01T15:46:07","2023-11-01T14:46:07",{"rendered":303},"https:\u002F\u002Fapi.medicalfuturist.com\u002F?post_type=book&p=24761","2023-11-01T15:46:17","2023-11-01T14:46:17","tech-giants-in-healthcare","book","https:\u002F\u002Fapi.medicalfuturist.com\u002Fbooks\u002Ftech-giants-in-healthcare\u002F",{"rendered":310},"Tech Giants in Healthcare – Updated Edition",{"rendered":312,"protected":20},"\n\u003Cp>This comprehensive guide, Tech Giants in Healthcare, clarifies how and why big tech companies step into healthcare, and breaks it down from one market player to the other in what direction they are going, what tools they are using and what horizons they have in front of them.\u003C\u002Fp>\n",{"rendered":314,"protected":20},"\u003Cp>This comprehensive guide, Tech Giants in Healthcare, clarifies how and why big tech companies step into healthcare, and breaks it down from one market player […]\u003C\u002Fp>\n",53261,[204,317],1595,[319,307,320,57,59,60],"post-24761","type-book",{"id":315,"alt_text":27,"caption":27,"description":27,"media_type":77,"media_details":322,"post":117,"source_url":338},{"width":323,"height":324,"file":325,"filesize":326,"sizes":327,"image_meta":336},700,906,"2020\u002F05\u002F1031_techgiants_2023-5-1-1.png",1092124,{"medium":328,"thumbnail":332},{"file":329,"width":219,"height":220,"mime-type":87,"filesize":330,"source_url":331},"1031_techgiants_2023-5-1-1-370x208.png",112044,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-1-370x208.png",{"file":333,"width":231,"height":231,"mime-type":87,"filesize":334,"source_url":335},"1031_techgiants_2023-5-1-1-150x150.png",42366,"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-1-150x150.png",{"aperture":105,"credit":27,"camera":27,"caption":27,"created_timestamp":105,"copyright":27,"focal_length":105,"iso":105,"shutter_speed":105,"title":27,"orientation":105,"keywords":337},[],"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-1.png",{"leanpub_url":340,"buy_button_text":341,"preview":342},"https:\u002F\u002Fleanpub.com\u002Ftech-giants-in-healthcare","Get it on Leanpub",[343,345,347,349,351,353],{"image":344},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-10-01.png",{"image":346},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-10-02.png",{"image":348},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-10-03.png",{"image":350},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-10-04.png",{"image":352},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-10-05.png",{"image":354},"https:\u002F\u002Fcdn.medicalfuturist.com\u002Fwp-content\u002Fuploads\u002F2020\u002F05\u002F1031_techgiants_2023-5-1-10-06.png",{"yoast_wpseo_title":356,"yoast_wpseo_metadesc":27,"yoast_wpseo_canonical":308},"Tech Giants in Healthcare - Updated Edition - The Medical Futurist",{"self":358,"collection":363,"about":366,"author":369,"replies":372,"wp:featuredmedia":375,"wp:attachment":378,"wp:term":381,"curies":384},[359],{"href":360,"targetHints":361},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fbook\u002F24761",{"allow":362},[134],[364],{"href":365},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fbook",[367],{"href":368},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Ftypes\u002Fbook",[370],{"embeddable":26,"href":371},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fusers\u002F10",[373],{"embeddable":26,"href":374},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fcomments?post=24761",[376],{"embeddable":26,"href":377},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia\u002F53261",[379],{"href":380},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fmedia?parent=24761",[382],{"taxonomy":175,"embeddable":26,"href":383},"https:\u002F\u002Fapi.medicalfuturist.com\u002Fwp-json\u002Fwp\u002Fv2\u002Fyst_prominent_words?post=24761",[385],{"name":179,"href":180,"templated":26},1786620425689]