{"id":16002,"date":"2023-12-29T18:09:04","date_gmt":"2023-12-29T12:39:04","guid":{"rendered":"https:\/\/www.fitterfly.com\/blog\/?p=16002"},"modified":"2024-01-25T14:45:45","modified_gmt":"2024-01-25T09:15:45","slug":"ai-in-diabetes-care-past-present-future","status":"publish","type":"post","link":"https:\/\/www.fitterfly.com\/blog\/ai-in-diabetes-care-past-present-future\/","title":{"rendered":"AI in Diabetes Care: Past, Present &#038; Future"},"content":{"rendered":"<h2><b>Abstract<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">This blog delves into the future of AI in diabetes care, certifying its current implementations and tracing its historical evolution. It sheds light on the promising trajectory of AI in diabetes care, highlighting innovations such as Case-Based Reasoning (CBR), Clinical Decision Support Systems (DSS), health guidance by ChatGPT, and the integration of Machine Learning (ML) and deep learning in diabetes management. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Presently, AI has become integral to diabetes management, featuring FDA-approved devices like Continuous Glucose Monitoring (CGM) and closed-loop insulin pumps. As we embrace this evolving landscape, AI developers will continue to shape a future where technology optimally serves the complex needs of diabetes patients globally.<\/span><\/p>\n<h2><b>Transformative Role of Artificial Intelligence in Diabetes Care<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">In the ever-evolving diabetes care ecosystem, artificial intelligence emerges as a transformative force, offering precision, personalisation, and efficiency in treatment strategies. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">The convergence of machine learning algorithms, wearable devices, and real-time data analytics has ushered in a new era in patient-centric diabetes management. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">This blog embarks on an exploration anticipating the promising future of <\/span>AI in Diabetes Care <span style=\"font-weight: 400;\">while tracing its footsteps through the past and unravelling its current impact.<\/span><\/p>\n<h2><b>Latest Innovations and Upcoming Prospects in AI in Diabetes Care<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">The future of<\/span> artificial intelligence in diabetes care<span style=\"font-weight: 400;\"> is poised to revolutionize the management and treatment of this chronic condition, ushering in an era of personalised and proactive healthcare. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Here are some arenas where AI in diabetes management is likely to provide a significant impact in the future.<\/span><\/p>\n<h3><b>1. Case-Based Reasoning (CBR)<\/b><\/h3>\n<p><a href=\"https:\/\/link.springer.com\/referenceworkentry\/10.1007\/978-1-4899-7687-1_34\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">Case-based reasoning<\/span><\/a><span style=\"font-weight: 400;\"> in diabetes care is an experience-based approach to resolving new problems. This method builds computational memories through analogical reasoning to find solutions to similar issues. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">CBR helps control blood sugar, suggesting prior-experience-based approaches to solve the latest problems, and remembering the effective and ineffective solutions for individual patients.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Roger Schank and his students at Yale University pioneered CBR implementation in the early 1980s. The four main steps of CBR include:<\/span> <a href=\"https:\/\/www.iiia.csic.es\/~mantaras\/RRRR.pdf\" target=\"_blank\" rel=\"noopener\"><b>retrieve, reuse, revise, and retain.<\/b><\/a><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Retrieve: Retrieve relevant cases from a library through keyword searches or other forms of data mining.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Reuse: Reuse old cases to solve the current problem.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Revise: Revise the old solution to better fit the target problem.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Retain: Retain the newly developed solution for future use.<\/span><\/li>\n<\/ul>\n<p><img decoding=\"async\" class=\"alignnone wp-image-16004 size-full lazyload\" data-src=\"https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01.webp\" alt=\"The 4 steps of CBR by Joaquim Mel\u00e9ndez \" width=\"1200\" height=\"628\" data-srcset=\"https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01.webp 1200w, https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01-300x157.webp 300w, https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01-1024x536.webp 1024w, https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01-768x402.webp 768w\" data-sizes=\"(max-width: 1200px) 100vw, 1200px\" src=\"data:image\/gif;base64,R0lGODlhAQABAAAAACH5BAEKAAEALAAAAAABAAEAAAICTAEAOw==\" style=\"--smush-placeholder-width: 1200px; --smush-placeholder-aspect-ratio: 1200\/628;\" \/><noscript><img decoding=\"async\" class=\"alignnone wp-image-16004 size-full\" src=\"https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01.webp\" alt=\"The 4 steps of CBR by Joaquim Mel\u00e9ndez \" width=\"1200\" height=\"628\" srcset=\"https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01.webp 1200w, https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01-300x157.webp 300w, https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01-1024x536.webp 1024w, https:\/\/www.fitterfly.com\/blog\/wp-content\/uploads\/2023\/12\/AI-in-Diabetes-Care-Past-Present-Future-banner-1-01-768x402.webp 768w\" sizes=\"(max-width: 1200px) 100vw, 1200px\" \/><\/noscript><\/p>\n<p style=\"text-align: center;\"><i><span style=\"font-weight: 400;\">Fig 1: The 4 steps of CBR by Joaquim Mel\u00e9ndez<\/span><\/i><\/p>\n<h3><b>2. Machine Learning and Deep Learning in Diabetes Care<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Machine learning and deep learning techniques are widely used to build digital support in diabetes care. <\/span><a href=\"https:\/\/dmsjournal.biomedcentral.com\/articles\/10.1186\/s13098-021-00767-9\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">Deep Neural Networks (DNN), Support Vector Machines (SVM), k-Nearest Neighbors (KNN), Decision Trees (DT), and Random Forests (RF<\/span><\/a><span style=\"font-weight: 400;\">) are prominent deep learning models for diabetes management. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">In these models, each layer corresponds to a level of learned knowledge, ranging from low-level details to higher abstract concepts.<\/span><\/p>\n<h3><b>3. Decision Support System (DSS)<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Clinical DSS implements computer programs to analyse large datasets for the timely delivery of information. This AI tool aims to improve care quality and clinical outcomes by transforming data into knowledge or meaningful advice through a digital interface. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">DSS has immensely contributed to individual patient management and comprehensive screening for diabetes.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">A 2018 review of <\/span><a href=\"https:\/\/academic.oup.com\/jamia\/article\/25\/5\/593\/4209526?login=false\"><span style=\"font-weight: 400;\">70 inpatient studies by <\/span><i><span style=\"font-weight: 400;\">Julian Varghese et al <\/span><\/i><span style=\"font-weight: 400;\">demonstrated positive patient outcomes via clinical DSS.<\/span><\/a><span style=\"font-weight: 400;\"> Among these 70 studies, 14 were related to blood glucose management, and 70% of them demonstrated positive outcomes. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Another <\/span><a href=\"https:\/\/www.amjmed.com\/article\/S0002-9343(20)30339-9\/fulltext\"><span style=\"font-weight: 400;\">2020 review of diabetes-related DSS<\/span><\/a><span style=\"font-weight: 400;\"> revealed that technology interventions reduced fasting, postprandial glucose, and HbA1c levels in diabetes patients.<\/span><\/p>\n<h3><b>4. Diabetes-related health guidance via ChatGPT<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">ChatGPT by OpenAI can augment diabetes care by offering on-demand answers to patients\u2019 queries based on large language models (LLMs). Currently, ChatGPT has also passed the U.S. Medical Licensing Examination reinforcing its diabetes self-management and education (DSME) portfolio.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Recently, <\/span><a href=\"https:\/\/www.medrxiv.org\/content\/10.1101\/2023.09.27.23296144v1.full-text\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">Zhen Ying et al conducted a retrospective dataset evaluation on ChatGPT <\/span><\/a><span style=\"font-weight: 400;\">to explore its feasibility in diabetes education. The researchers asked 85 questions to ChatGPT covering seven aspects of diabetes education and ChatGPT scored high on correctness, relevance, helpfulness, and safety parameters.<\/span><\/p>\n<h2><b>Present Implementation of AI in Diabetes Management<\/b><\/h2>\n<p>AI and Diabetes Management<span style=\"font-weight: 400;\"> witnessed a transformative revolution following the AI boom in 2021. Currently, multiple FDA-approved AI-based medical devices are implementing AI\/machine learning technology. Listed below are some practical implementations of artificial intelligence in diabetes treatment.<\/span><\/p>\n<h3><b>1. Continuous Glucose Monitoring (CGM)<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">CGM devices monitor blood sugar at regular intervals painlessly. Currently, doctors recognize three types of CGM gadgets: intermittently viewed CGM (iCGM) and real-time CGM (rtCGM) gadgets. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">While iCGm provides glycaemic information on demand retrospectively, rtCGM offers real-time data for diabetes management. Moreover, rtCGM-integrated insulin pumps enable timely insulin infusion based on real-time glycaemic values.<\/span><\/p>\n<h3><b>2. Insulin Pumps and Closed Loop Delivery Systems<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">Insulin pumps are a sought-after therapeutic option, especially for managing T1DM. The latest continuous subcutaneous insulin infusion (CSII) pumps come with a bolus calculator and automatic basal rate suspension to reduce hypoglycaemia. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Scientists are working towards subcutaneous closed-loop system development. STG-55 (Nikkiso, Tokyo, Japan) and its predecessor, the STG-22 are the only commercially available fully closed-loop insulin pumps in today&#8217;s market. Automated insulin delivery (AID) will improve the time in the target glucose range with either no increase or a reduction in hypoglycemia.<\/span><\/p>\n<h3><b>3. Diabetes screening via analysing ECG, Radiographs &amp; Voice Samples<\/b><\/h3>\n<p><span style=\"font-weight: 400;\">\u00a0It is now possible to predict T2DM by studying<\/span><a href=\"https:\/\/innovations.bmj.com\/content\/9\/1\/32\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\"> electrocardiographs (ECG), <\/span><\/a><a href=\"https:\/\/www.nature.com\/articles\/s41467-023-39631-x\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">frontal chest radiographs, <\/span><\/a><span style=\"font-weight: 400;\">and even voice analysis via smartphone apps. <\/span><\/p>\n<p><i><span style=\"font-weight: 400;\">Anoop R Kulkarni et al<\/span><\/i> <a href=\"https:\/\/innovations.bmj.com\/content\/9\/1\/32\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">detected diabetes and pre-diabetes from ECGs with 97% accuracy<\/span><\/a><span style=\"font-weight: 400;\">. <\/span><i><span style=\"font-weight: 400;\">Ayis Pyrros et al <\/span><\/i><span style=\"font-weight: 400;\">in a 2022 study analyzed <\/span><a href=\"https:\/\/www.nature.com\/articles\/s41467-023-39631-x\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">271,065 chest radiographs (CXRs) from 160,244 patients for opportunistic screening of T2DM.<\/span><\/a><span style=\"font-weight: 400;\">\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Another study involving <\/span><a href=\"https:\/\/www.sciencedirect.com\/science\/article\/pii\/S2949761223000731\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">267 participants and 18,465 recordings <\/span><\/a><span style=\"font-weight: 400;\">stressed significant differences in voice samples of people with and without diabetes. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Scientists could predict diabetes with\u00a0 75% accuracy among women and 70% among men via 5-fold cross-validation in the age-matched and BMI-matched recordings.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Similarly, it is possible to <\/span><a href=\"https:\/\/www.nature.com\/articles\/s41467-023-42404-1\" target=\"_blank\" rel=\"noopener\"><span style=\"font-weight: 400;\">predict the onset of T2DM by metabolic fingerprinting<\/span><\/a><span style=\"font-weight: 400;\"> on retinal pigment epithelium thickness. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Researchers established that a reduction in vivo measurements of retinal pigment epithelium thickness (RPET) is a crucial risk factor for T2DM. They even identified 64 RPET metabolic fingerprints that are independently associated with reduced RPET.<\/span><\/p>\n<h2><b>The advent of AI in Healthcare\u00a0<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">The term \u201cartificial intelligence\u201d first came into consideration during the Dartmouth College conference proposal in 1955. However, AI applications were introduced in healthcare in the 1970s, when an AI program, MYCIN,\u00a0 aided blood infection treatments. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Finally, in 1979,\u00a0 the American Association for Artificial Intelligence came into existence, currently known as the Association for the Advancement of Artificial Intelligence (AAAI).\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">In conclusion, the trajectory of artificial intelligence (AI) in diabetes care is nothing short of transformative. Looking forward, the potential uses and future prospects of <\/span>artificial intelligence in diabetes treatment<span style=\"font-weight: 400;\"> are vast and promising. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Roger Schank\u2019s CBR offers an experience-based approach to diabetes management, DSS harnesses the power of AI to analyze large datasets, while CGM devices and insulin pumps showcase the tangible impact of AI in real-world healthcare scenarios. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">Today, AI stands at the forefront of diabetes care, promising a future marked by unprecedented advancements in treatment strategies and patient outcomes.<\/span><\/p>\n<h2><b>Key Takeaways<\/b><\/h2>\n<p><span style=\"font-weight: 400;\">The abstract encapsulates the collaborative efforts shaping the landscape of AI in healthcare, emphasizing the potential for unprecedented advancements in diabetes treatment strategies and patient outcomes on the horizon. <\/span><\/p>\n<p><span style=\"font-weight: 400;\">The key takeaways include:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">The integration of artificial intelligence (AI) in diabetes care heralds a patient-centric paradigm, ensuring precision, personalization, and enhanced efficiency in treatment strategies.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Case-Based Reasoning (CBR) emerges as an innovative approach to problem-solving in diabetes care.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Machine learning and deep learning techniques, including Deep Neural Networks and Decision Support Systems, are transforming diabetes care by analysing large datasets.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">ChatGPT by OpenAI can augment diabetes care by offering on-demand answers to patients\u2019 queries based on large language models (LLMs).<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">AI extends its reach beyond traditional glucose monitoring, utilising diverse data sources such as ECGs, radiographs, and voice samples for diabetes screening and prediction.<\/span><\/li>\n<\/ul>\n<p><b>About Us<\/b><\/p>\n<p><a href=\"https:\/\/www.fitterfly.com\/\" target=\"_blank\" rel=\"noopener\">Fitterfly<\/a>\u00a0is on a mission to fuel the global metabolic health revolution through the power of Digital Therapeutics (DTx). We partner with physicians to deliver advanced customised digital therapeutics solutions aimed at enhancing the health outcomes of their patients.<\/p>\n<p>By partnering with\u00a0<a href=\"https:\/\/www.fitterfly.com\/\">Fitterfly<\/a>, you can save time in your clinics, ensure continuity of care for your patients, get research publications, and also enhance your revenue. To know more, please fill out the form below or call us at 080-47093933.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Abstract This blog delves into the future of AI in diabetes care, certifying its current implementations and tracing its historical evolution. It sheds light on the promising trajectory of AI [&hellip;]<\/p>\n","protected":false},"author":40,"featured_media":16006,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"wds_primary_category":413,"footnotes":""},"categories":[418,413],"tags":[],"acf":{"reviewed_by":false,"references":null,"author":"","table_content":null,"medically_reviewed":9607,"show_updated_date_in_post":"No","faq_list":null,"custom_schema":"","media_url":"","reviewer":null},"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/posts\/16002"}],"collection":[{"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/users\/40"}],"replies":[{"embeddable":true,"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/comments?post=16002"}],"version-history":[{"count":0,"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/posts\/16002\/revisions"}],"acf:post":[{"embeddable":true,"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/reviewers\/9607"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/media\/16006"}],"wp:attachment":[{"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/media?parent=16002"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/categories?post=16002"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.fitterfly.com\/blog\/wp-json\/wp\/v2\/tags?post=16002"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}