EHR exercise tool trims falls in primary care trial; family physicians rank high in OpenEvidence AI use; survey weighs AI portal replies

• Technology Oct 16, 2026
  EHR decision support for exercise lowers fall rate to 19.3 from 21.2 per 100 patient-years in eSTEPS primary care trial
  The matched-pair cluster randomized trial, published in JAMA Network Open, enrolled 11,945 adults 65 and older with a positive fall-risk screen at 22 primary care practices in a U.S. integrated health system. The eSTEPS tool, embedded in the electronic health record, offered tailored exercise recommendations, optional physical therapy referral and patient handouts, a website and an app. The rate of patients with one or more recorded falls was 19.3 versus 21.2 per 100 patient-years (rate ratio 0.91, 95% CI 0.88 to 0.95; P < .001). Exercise prescriptions went to 22.1% of intervention patients, and mortality did not differ.
  Sources: JAMA Network Open, JAMA Network Open (article page)
• AI Oct 15, 2026
  Family medicine use ratio of OpenEvidence AI platform is 1.80 in JAMA study of 271 million clinician queries
  Researchers analyzed 271 million queries that 952,008 U.S. clinicians, including 556,200 physicians, submitted to the OpenEvidence AI-enabled clinical information platform from January 2024 to June 2026, according to the JAMA cross-sectional study. Family medicine's use ratio of 1.80 placed it among the specialties with a higher-than-average share of queries relative to the national workforce. Treatment and management made up 33.1% of physician queries and diagnosis 13.9%. Three authors were OpenEvidence employees during the study, and the company provided data and contributed to the analysis, according to the disclosures.
  Sources: JAMA, JAMA (article page), Becker's Hospital Review
• AI Oct 14, 2026
  Survey of 1,185 adults finds 63.1% would wait up to 48 hours for clinician-reviewed answers to medical portal messages
  The cross-sectional survey, published in JAMA Network Open, asked U.S. adults in June and July 2024 to choose between a fast AI answer within 5 minutes and waiting up to 48 hours for an answer reviewed and edited by a doctor or nurse. For logistical messages such as appointment scheduling and prescription refills, 57.4% preferred the faster AI response. For medical messages, 63.1% preferred to wait for a health professional's review.
  Sources: JAMA Network Open, JAMA Network Open (article page)

The weekly innovation roundup for family medicine, published every Sunday for the week before; every item links to its sources. Latest family medicine news · All specialties