All Artificial Intelligence is not the same. AI has been in healthcare for over 50 years, though not at the scale we’ve seen over the last decade with advancements in neural networks and transformer architecture. It began with expert knowledge getting encoded into electronic clinical pathways to being able to identify skin conditions and make predictions from electronic health record data. Currently, most AI in medical settings is used for:
This new wave of AI algorithms and other applications powered by AI will likely usher in new ways to support clinicians and other health professionals.
Howell MD, Corrado GS, DeSalvo KB. Three Epochs of Artificial Intelligence in Health Care. JAMA. 2024 Jan 16;331(3):242-244. doi: 10.1001/jama.2023.25057. PMID: 38227029.
Source: https://www.fda.gov/medical-devices/medical-device-regulatory-science-research-programs-conducted-osel/artificial-intelligence-program-research-aiml-based-medical-devices
When conducting your literature searches, ensure reliability and credibility by using accurate sources. Keep these in mind when using AI-based platforms for your literature searching:
Ayers JW, Poliak A, Dredze M, et al. Comparing Physician and Artificial Intelligence Chatbot Responses to Patient Questions Posted to a Public Social Media Forum. JAMA Intern Med. 2023;183(6):589–596. doi:10.1001/jamainternmed.2023.1838
Jin, Q., Chen, F., Zhou, Y. et al. Hidden flaws behind expert-level accuracy of multimodal GPT-4 vision in medicine. npj Digit. Med. 7, 190 (2024). https://doi.org/10.1038/s41746-024-01185-7
From the L.I. Catalog
Healthcare and artificial intelligence by 
Artificial Intelligence for the Internet of Health Things by From the Arkansas Catalog
Co-Intelligence by 
Artificial Intelligence for Improved Patient Outcomes by 
AI Doctor by 
Artificial intelligence and machine learning in health care and medical sciences : best practices and pitfalls by In keeping with the pace of emerging generative AI technologies, publishers are establishing guidelines and policies surrounding the use of AI in scholarly publishing. These guidelines may change and as such, be sure to check or contact the library to confirm whether your research is in accordance with the publisher's policies. The following links are the latest guidelines as of 09/03/2024.
The FDA's Medical Product Centers are collaborating to advance the responsible use of AI for medical products. They are collaborating to build regulations that can be applied across various medical products and used within the health care delivery system. To learn more, read the FDA's paper titled Artificial Intelligence and Medical Products: How CBER, CDER, CDRH, and OCP are Working Together.
The FDA has seen a rapid growth in the number of submissions that reference AI. Clinical trials are an integral part of new product discovery and development and are required by the Food and Drug Administration before a new product can be brought to the market.
The following RSS feed includes the new and existing studies added or modified (last update posted) in the last 14 days on ClinicalTrials.gov that use AI in some capacity. If you want to complete a similar search, these were the search terms used under “Other Terms”:
algorithm OR “artificial intelligence” OR “convolutional network” OR “computer reasoning” OR “vision system” OR “deep learning” OR “Hierarchical Learning” OR “machine intelligence” OR “machine learning” OR “neural network” OR radiomics OR “in-context learning”
If you want to look at AI within a field, just go to ClinicalTrials.gov, type in the provided terms, along with whichever conditions and/or interventions you want to research further.
Across NIH’s 27 institutes and centers, AI/ML technologies are being developed. Follow the link for some specific examples: Institute and Center Funded Initiatives
None of the following resources are meant to provide medical advice, diagnosis, or treatment. Users must assess the information they obtain from any source:
OpenEvidence is an artificial intelligence system to aggregate, synthesize, and visualize clinically relevant evidence in understandable, accessible formats that can be used to make more evidenced-based decisions and improve patient outcomes.
Coalition for Health AI (CHAI) is an initiative to develop and promote responsible AI standards in healthcare to ensure high-quality, trustworthy, and equitable AI applications. They aim to do this by creating a federated network of labs, tools, and a robust framework that can be used by all healthcare providers.
BioMedical Engineering and Imaging Institute focuses on the use of multimodality imaging for brain, heart, and cancer research, along with research in nanomedicine for precision imaging and drug delivery.
Listen to The Role of Artificial Intelligence in Clinical Trial Design and Research with Dr. ElZarrad where the FDA's Division of Drug Information discusses the role of AI in clinical trial design. Listening is worth 0.5 CE credit.
In addition to credit given for various images, parts of this Medical Education & Healthcare page were adapted from work/guides by:
Emory Libraries, New York University, Westport Library, University of North Dakota, Mount Sinai Levy Library
Used with permission or in accordance with Creative Commons Licensing.