Key research papers in medical AI - read these first
Last updated: 14th October 2019
This is an extremely active research field, with new papers published regularly. Here we mention some of the landmark papers, with the intention of providing somewhat of an ‘initial reading list’ for those wanting to understand the area better.
(Note: we have only included peer-reviewed papers, and not those solely published on arxiv.)
For several of these papers, we have written short summaries to outline the key findings and implications of the paper.
General perspectives
“High-performance medicine: the convergence of human and artificial intelligence” - Topol (Nature Medicine, Jan 2019)
“Machine Learning in Medicine” – Rajkomar et al. (NEJM, April 2019)
A selection of important papers (in chronological order)
“Dermatologist-level classification of skin cancer with deep neural networks” – Esteva et al. (Nature, Feb 2017) - see our summary here
“Passive Detection of Atrial Fibrillation Using a Commercially Available Smartwatch” - Tison et al. (JAMA Cardiology, May 2018)
“Clinically applicable deep learning for diagnosis and referral in retinal disease” - De Fauw et al. (Nature Medicine, Aug 2018) - see our summary here
“Development and validation of a deep-learning algorithm for the detection of polyps during colonoscopy” - Wang et al. (Nature Biomedical Engineering, Oct 2018)
“The Artificial Intelligence Clinician learns optimal treatment strategies for sepsis in intensive care.” – Komorowski et al. (Nature Medicine, Nov 2018) - see our summary here
“Deep learning for chest radiograph diagnosis: A retrospective comparison of the CheXNeXt algorithm to practicing radiologists” - Rajpurkar et al. (PloS Medicine, Nov 2018)
“End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.” - Ardila et al. (Nature Medicine, June 2019)