Explore the vast range of titles available.

This first article in a series describes the history of artificial intelligence in medicine; the use of AI in image analysis, identification of disease outbreaks, and diagnosis; and the use of chatbots.

The editors announce both a series of articles focusing on AI and machine learning in health care and the 2024 launch of a new journal, NEJM AI , a forum for evidence, resource sharing, and discussion of the possibilities and limitations of medical AI.

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.

Key Clinical PointsNavigating and Communicating about Serious Illness and End of LifePartnering with patients as they navigate serious illness requires effectively communicating prognostic information while responding to the emotions generated by the conversation.Clinicians should expect, and have the skill, to engage in a continuum of conversations that allow patients to integrate prognostic information cognitively and emotionally.Patients oscillate between expressions of intense hopefulness and more realistic aspirations; this a normal and expected part of the process.Facilitating patient exploration of their hopes and worries allows them to grieve, understand their priorities, and build coping skills for living with a serious illness.As patients integrate prognostic information, clinicians should discuss what is most important to the patient given the likely illness trajectory and incorporate these goals and values into a recommendation about medical care, including care at the end of life.

Key PointsMedical Artificial Intelligence and Human ValuesAs large language models and other artificial intelligence models are used more in medicine, ethical dilemmas can arise depending on how the model was trained. A user must understand how human decisions and values can shape model outputs. Medical decision analysis offers lessons on measuring human values.A large language model will respond differently depending on the exact way a query is worded and how the model was directed by its makers and users. Caution is advised when considering the use of model output in decision making.

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.

Advances in AI for Infectious-Disease SurveillanceThis article in the AI in Medicine series addresses the use of AI and machine-learning tools to identify and track disease outbreaks and monitor mitigation strategies.

Artificial Intelligence in Molecular MedicineMachine-learning methods for analyzing genomic, transcriptomic, epigenomic, proteomic, and metabolomic data sets have yielded clinically directive information, mostly for rare genetic diseases.

Burnout and Depression among PhysiciansDiminished well-being among physicians is of growing concern. The authors review measures of burnout and depression, causal factors, and interventions to improve well-being.

Adverse events during hospitalization are a major cause of patient harm, as documented in the 1991 Harvard Medical Practice Study. Patient safety has changed substantially in the decades since that study was conducted, and a more current assessment of harm during hospitalization is warranted. We conducted a retrospective cohort study to assess the frequency, preventability, and severity of patient harm in a random sample of admissions from 11 Massachusetts hospitals during the 2018 calendar year. The occurrence of adverse events was assessed with the use of a trigger method (identification of information in a medical record that was previously shown to be associated with adverse events) and from review of medical records. Trained nurses reviewed records and identified admissions with possible adverse events that were then adjudicated by physicians, who confirmed the presence and characteristics of the adverse events. In a random sample of 2809 admissions, we identified at least one adverse event in 23.6%. Among 978 adverse events, 222 (22.7%) were judged to be preventable and 316 (32.3%) had a severity level of serious (i.e., caused harm that resulted in substantial intervention or prolonged recovery) or higher. A preventable adverse event occurred in 191 (6.8%) of all admissions, and a preventable adverse event with a severity level of serious or higher occurred in 29 (1.0%). There were seven deaths, one of which was deemed to be preventable. Adverse drug events were the most common adverse events (accounting for 39.0% of all events), followed by surgical or other procedural events (30.4%), patient-care events (which were defined as events associated with nursing care, including falls and pressure ulcers) (15.0%), and health care-associated infections (11.9%). Adverse events were identified in nearly one in four admissions, and approximately one fourth of the events were preventable. These findings underscore the importance of patient safety and the need for continuing improvement. (Funded by the Controlled Risk Insurance Company and the Risk Management Foundation of the Harvard Medical Institutions.).