Category: Clinical care & management

High-performance medicine: the convergence of human and Artificial Intelligence

Topol, E.J.

Nat Med 25, 44-56. 2019. DOI: 10.1038/s41591-018-0300-7.

Process of AI in medicine
Share on facebook
Share on twitter
Share on linkedin

The use of deep learning in medicine is beginning to have an impact upon clinicians, healthcare systems and patients. The journey has just begun.

  1. In the near future, almost every type of clinician, ranging from specialty doctor to paramedic, will be using AI technology, and in particular deep learning.
  2. Using electronic health record data, machine- and deep-learning algorithms are already predicting many important clinical parameters.
  3. The goal for patients is to develop deep-learning algorithms to support them to take their health care into their own hands.

A deep learning algorithm to detect chronic kidney disease from retinal photographs in community-based populations

Sabanayagam C, Xu D, (…), Wong TY.

Lancet Digit Health. 2020 DOI: 10.1016/S2589-7500(20)30063-7.

Kidney disease retinal photographs
Share on facebook
Share on twitter
Share on linkedin

An Artificial Intelligence deep learning algorithm (DLA) to detect chronic kidney disease from retinal images.

  1. A retinal image DLA shows good performance in detecting chronic kidney disease.
  2. Combining DLAs with known risk factors for chronic kidney disease showed better accuracy than both used separately.
  3. This study linking the retina and the kidney underlies the feasibility of applying AI to retinal photography as a screening tool for chronic kidney disease in community populations.

Human-machine partnership with Artificial Intelligence for chest radiograph diagnosis

Patel BN, Rosenberg L, (...) Lungren M.

NPJ Digit Med. 2019. DOI: 10.1038/s41746-019-0189-7.

Chest radiograph diagnosis
Share on facebook
Share on twitter
Share on linkedin

An investigation of a new AI technology designed to amplify the diagnostic accuracy of networked human groups by forming real-time systems modeled on biological swarms applied to chest radiographs for the diagnosis of pneumonia.

  1. Both the swarm-based technology and deep-learning technology achieved superior diagnostic accuracy of pneumonia than the human experts alone.
  2. When used in combination, the swarm-based technology and deep-learning technology outperformed either method alone.
  3. These findings have broad implications for the growth in clinical AI deployment and implementation strategies in future practice.