artificial intelligence (AI)
Jump to navigation
Jump to search
Principle
- each problem requires some degree of understanding of the problem
- big data are too large & heterogeneous, & change too quickly, to be stored, analyzed, & used
- interactions between physicians & data scientists are needed to enable clinically meaningful automated & predictive data analysis
- computer program able to classify skin lesions as benign or malignant, & whether they would need biopsy as well as board-certified dermatologists[3]
Notes
- AI can free clinicians to perform higher-level tasks[4]
- AI likely to improve clinician decision-making processes
- AI likely to improve cost-effectiveness of care delivery
- AI unlikely to diminish need for physicians[4]
- an artificial intelligence (AI) company owned by Google developed a program that predicts 3-dimensional protein structure from their amino acid sequence[8]
- on July 22, 2021, the company published its prediction of the structures of nearly all ~20,000 human proteins[8]
- AI can predict 10 year risk of major cardiac events from a chest x-ray, presumably by recognizing coronary artery calcium[13]
- AsymMirai is an AI system that compares differences between right & left breasts to predict risk of breast cancer 5 years in advance[14]
More specific terms
References
- ↑ Krittanawong C. The rise of artificial intelligence and the uncertain future for physicians. Eur J Intern Med. 2017 Jun 23. pii: S0953-6205(17)30261-3. PMID: https://www.ncbi.nlm.nih.gov/pubmed/28651747
- ↑ Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T. Artificial Intelligence in Precision Cardiovascular Medicine. J Am Coll Cardiol. 2017 May 30;69(21):2657-2664. Review. PMID: https://www.ncbi.nlm.nih.gov/pubmed/28545640
- ↑ 3.0 3.1 Hilton L The Artificial Brain as Doctor. AI equals dermatologists in identifying lesions. MedPage Today. Dermatology Times. January 15, 2018 https://www.medpagetoday.com/dermatology/generaldermatology/70513
Esteva A et al Dermatologist-level classification of skin cancer with deep neural networks. Nature 2017; 542: 115-118 PMID: https://www.ncbi.nlm.nih.gov/pubmed/28117445 - ↑ 4.0 4.1 4.2 Davenport TH, Glover WJ. Artificial Intelligence and the Augmentation of Health Care Decision-Making. NEJM Catalyst. June 19, 2018 https://catalyst.nejm.org/ai-technologies-augmentation-healthcare-decisions/
- ↑ Liu X, Faes L, Kale AU et al A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. The Lancet Digital Health. Sept 25, 2019 Not indexed in PubMed https://www.thelancet.com/journals/landig/article/PIIS2589-7500(19)30123-2/fulltext
Cook TS Human versus machine in medicine: can scientific literature answer the question?. The Lancet Digital Health. Sept 25, 2019 Not indexed in PubMed https://www.sciencedirect.com/science/article/pii/S2589750019301244 - ↑ Stokes JM et al. A deep learning approach to antibiotic discovery. Cell 2020 Feb 20; 180:688 PMID: https://www.ncbi.nlm.nih.gov/pubmed/32084340
- ↑ Vaishampayan U Using Artificial Intelligence to Personalize Therapy and Individual Level of Outcome Prediction. Investigations like these will improve the accuracy of our predictions and strengthen optimal therapeutic decisions. MedPage Today. ASCO Reading Room. June 10, 2021 https://www.medpagetoday.com/reading-room/asco/immunotherapy/93023
- ↑ 8.0 8.1 8.2 Tunyasuvunakool K, Adler J, Wu Z et al. Highly accurate protein structure prediction for the human proteome. Nature 2021 Jul 22; [e-pub]. PMID: https://www.ncbi.nlm.nih.gov/pubmed/34293799 https://www.nature.com/articles/s41586-021-03828-1
Jumper J, Evans R, Pritzel A et al. Highly accurate protein structure prediction with AlphaFold. Nature 2021 Jul 15; [e-pub]. PMID: https://www.ncbi.nlm.nih.gov/pubmed/34265844 https://www.nature.com/articles/s41586-021-03819-2
Callaway E. Deepmind's AI predicts structures for a vast trove of proteins. Nature 2021 Jul 29; 595:635. PMID: https://www.ncbi.nlm.nih.gov/pubmed/34294928 https://www.nature.com/articles/d41586-021-02025-4
The Editors. Artificial intelligence in structural biology is here to stay. Nature 2021 Jul 29; 595:625. PMID: https://www.ncbi.nlm.nih.gov/pubmed/34316055 https://www.nature.com/articles/d41586-021-02037-0 - ↑ Cao L et al. Design of protein-binding proteins from the target structure alone. Nature 2022 May; 605:551. PMID: https://www.ncbi.nlm.nih.gov/pubmed/35332283 PMCID: PMC9117152 Free PMC article https://www.nature.com/articles/s41586-022-04654-9
Service RF. Software-designed miniproteins could create new class of drugs. Science 2022 Apr; 376:17. PMID: https://www.ncbi.nlm.nih.gov/pubmed/35357932 https://www.science.org/content/article/software-designed-miniproteins-could-create-new-class-drugs - ↑ Cutler DM What Artificial Intelligence Means for Health Care. JAMA Health Forum. 2023;4(7):e232652 PMID: https://www.ncbi.nlm.nih.gov/pubmed/37410474 Free article https://jamanetwork.com/journals/jama-health-forum/fullarticle/2807176
- ↑ Voelker R. The Promise and Pitfalls of AI in the Complex World of Diagnosis, Treatment, and Disease Management. JAMA. Published online September 27, 2023 PMID: https://www.ncbi.nlm.nih.gov/pubmed/37755919 https://jamanetwork.com/journals/jama/fullarticle/2810236
- ↑ Voelker R, Hswen Y Medical News & Perspectives | AI in Medicine Clinical AI Tools Must Be Fed the Right Data, Stanford Health Care's Chief Data Scientist Says. JAMA. Published online November 15, 2023 PMID: https://www.ncbi.nlm.nih.gov/pubmed/37966811 https://jamanetwork.com/journals/jama/fullarticle/2812191
- ↑ 13.0 13.1 Weiss J, et al. Deep learning to estimate cardiovascular risk from chest radiographs: A risk prediction study. Ann Intern Med 2024 Mar 26; [e-pub] PMID: https://www.ncbi.nlm.nih.gov/pubmed/38527287 https://www.acpjournals.org/doi/10.7326/M23-1898
- ↑ 14.0 14.1 Marshall L New Transparent AI Predicts Breast Cancer 5 Years Out. Medscape. March 21, 2024 https://www.medscape.com/viewarticle/new-transparent-ai-predicts-breast-cancer-5-years-out-2024a100059l
Donnelly J, Moffett L, Barnett AJ et al AsymMirai: Interpretable Mammography-based Deep Learning Model for 1-5-year Breast Cancer Risk Prediction. Radiology 2024 Mar;310(3):e232780 PMID: https://www.ncbi.nlm.nih.gov/pubmed/38501952 https://pubs.rsna.org/doi/10.1148/radiol.232780