AI in Medicine

The relational nature of large language models and other forms of generative artificial intelligence raises additional ethical questions for medicine, beyond the daunting ethics surrounding predictive AI.

In this article in the series on artificial intelligence in medicine, the authors explore how human values influence the outputs of large language models and other artificial intelligence models.

The authors address the issues that must be confronted if we are to integrate the use of wearable digital health technologies into clinical care in a way that provides an enduring benefit to patients.

One third of people with epilepsy have seizures despite medical treatment. The authors examine wearable digital health devices that can detect seizures and how these devices can affect epilepsy care.

This article reviews the use of digital wearable technologies for monitoring of three common cardiovascular conditions: hypertension, heart failure, and atrial fibrillation.

Sleep patterns and physical activity can be monitored by wearable technology. The authors describe the state of the art for using data from wearable devices in diagnosing and managing depression.

The authors review challenges arising in malpractice litigation related to software errors to inform health care organizations and physicians about liability risk from AI adoption and about strategies to mitigate risk.

Monitors to measure glucose levels have been paired with software controlling insulin delivery. The authors examine the state of the art in digital technology to manage diabetes (types 1 and 2).

There are various possible futures for regulation of artificial intelligence in the United States. The history of rules governing the treatment of human subjects could hold important insights.

Wearable DHT has reached an inflection point between fanciful descriptions and practical applications. The editors announce a series of articles focusing on the clinical applications of wearable DHT.

Challenges at the interface of medical statistics and AI are population inference vs. prediction, generalizability, reproducibility and interpretation of evidence, and stability and statistical guarantees.

Medical AI tools that are trained on skewed data may exhibit bias. The authors discuss how thinking of clinical data as artifacts can identify values, practices, and patterns of inequity in health care.

The authors, both employed by a company providing consulting services for public and private health care organizations, examine the use of AI in reimbursement, clinical operations, and quality and safety.