Evidence

114 items from the daily briefing

What the studies and the professional societies say, and what nobody has shown yet. Each item links to the day it ran and to its original source.

FYIEvidence Nov 7, 2026
Stopping statins in adults 70 and older without heart disease met noninferiority in a 1,880-patient trial, though events rose to 12.7% from 9.2%
Primary careCardiology
From the Nov 9, 2026 post · Sources: New England Journal of Medicine, Crossref record, HCPLive
FYIEvidence Nov 7, 2026
AI plaque analysis on coronary CT beat stress-test-guided care at 180 days in a 530-patient trial, the company reports
Cardiology Radiology
From the Nov 9, 2026 post · Source: Cleerly (Business Wire)
FYIEvidence Nov 8, 2026
Single-pill combinations delivered through team-based care cut systolic pressure 10.1 mm Hg more than usual care in a 1,706-patient trial
Primary careInternal medicine
From the Nov 9, 2026 post · Sources: JAMA, PubMed
FYIEvidence Nov 7, 2026
Routine stents or bypass for stable coronary disease add no survival over medicines alone at 11 years in 5,179-patient ISCHEMIA follow-up
Internal medicine Cardiology
From the Nov 8, 2026 post · Sources: JAMA, PubMed record
FYIEvidence Nov 7, 2026
Two heart drugs fail in full results: pelacarsen cut lipoprotein(a) 78% and ziltivekimab cut CRP, but neither prevented heart attacks or strokes
Cardiology
From the Nov 8, 2026 post · Sources: American Heart Association, TCTMD, NEJM Evidence (extended analyses), PubMed record, NEJM (ZEUS), HCPLive
FYIEvidence Nov 7, 2026
An AI-flagged ECG raised detection of atrial fibrillation or its precursors by a fragile margin in a 14,665-adult randomized trial
Cardiology
From the Nov 8, 2026 post · Sources: Circulation, PubMed record
FYIEvidence Nov 7, 2026
A language model reading clinic notes found lipid therapy was not intensified at 89% of visits where LDL sat above goal
Primary careCardiology
From the Nov 8, 2026 post · Sources: JAMA Cardiology, PubMed record
FYIEvidence Nov 7, 2026
Starting statin plus ezetimibe up front did not cut cardiovascular events at 3 years versus a statin alone in a 3,048-patient trial
Primary careCardiology
From the Nov 8, 2026 post · Sources: Circulation, PubMed record
FYIEvidence Nov 6, 2026
An AI flag on positive ANA tests cut time to autoimmune diagnosis from 138 to 43 days in a Vanderbilt randomized trial
Internal medicinePrimary care
From the Nov 7, 2026 post · Sources: NEJM AI, PubMed record
FYIEvidence Nov 2, 2026
Starting overactive bladder patients on beta-3 agonists instead of anticholinergics did not lower dementia risk in an 830,393-patient cohort
Primary careUrology
From the Nov 7, 2026 post · Sources: JAMA Network Open, PubMed record
FYIEvidence Nov 5, 2026
Google's smartwatch AI catches 65.8% of hypertension cases in a week, beating an initial office cuff reading at 55.3%
Primary careCardiology
From the Nov 6, 2026 post · Sources: Nature, PubMed record
FYIEvidence Nov 5, 2026
Newborns who skip the vitamin K shot have more than twice the risk of intracranial bleeding, a 5.2 million-infant study finds
Pediatrics Family medicine
From the Nov 6, 2026 post · Sources: JAMA, PubMed record
FYIEvidence Nov 2, 2026
A generative AI chatbot for pregnant and postpartum patients fails to improve anxiety or depression in a 400-person trial
Obstetrics and gynecology Psychiatry
From the Nov 6, 2026 post · Sources: JAMA Network Open, PubMed record
FYIEvidence Nov 5, 2026
Electronic record alerts fail to cut routine testing before cataract surgery in a UCLA randomized trial
Internal medicine Ophthalmology
From the Nov 6, 2026 post · Sources: JAMA Ophthalmology, PubMed record
FYIEvidence Nov 3, 2026
Thoracic society strongly recommends steroid-containing rescue inhalers over short-acting beta-agonists alone for mild asthma
Primary carePulmonary and critical care
From the Nov 4, 2026 post · Sources: American Journal of Respiratory and Critical Care Medicine, PubMed record
FYIEvidence Nov 3, 2026
Half of adults with long COVID at 1 year improve meaningfully by 3 years, but only about a quarter fully recover, RECOVER finds
Primary careInternal medicine
From the Nov 4, 2026 post · Sources: Annals of Internal Medicine, PubMed record
FYIEvidence Oct 30, 2026
Columbia clinicians answered portal messages 8.6% slower after Epic's AI draft replies arrived, a 983,154-message study finds
PracticesPrimary care
From the Nov 4, 2026 post · Sources: JAMA Network Open, PubMed record
FYIEvidence Nov 3, 2026
A quarter of Kaiser emergency patients with six common conditions were treated at home, in clinics or in observation instead of a bed
Emergency medicine Hospital medicine
From the Nov 4, 2026 post · Sources: JAMA Network Open, PubMed record
FYIEvidence Nov 3, 2026
Stents and bypass surgery show matching 10-year survival for left main disease in a 5,379-patient registry
Cardiology
From the Nov 4, 2026 post · Sources: The Lancet, PubMed record, TCTMD (TCT 2026 program)
ActEvidence Nov 2, 2026
A child in Lewis County dies in New York's measles outbreak, the state's first measles-associated death in more than 30 years
The state health department advises an early MMR dose from age 6 months where measles is spreading and 21-day quarantine for nonimmune contacts.
Pediatrics Family medicineNew York
From the Nov 3, 2026 post · Source: New York State Department of Health
FYIEvidence Oct 15, 2026
AI listening through a digital stethoscope flags ejection fractions of 40% or less, beating cardiologists 82% to 62% in a 100-patient test
CardiologyPrimary care
From the Nov 3, 2026 post · Sources: NEJM AI, PubMed record
FYIEvidence Oct 15, 2026
AI plain-language summaries sent before visits cut neurosurgery consultations from 33 to 25 minutes in a 300-patient randomized trial
NeurosurgeryPractices
From the Nov 3, 2026 post · Sources: NEJM AI, PubMed record
FYIEvidence Nov 2, 2026
Early valve replacement for moderate aortic stenosis cuts death or heart failure events at 2 years, 744-patient PROGRESS trial finds
Cardiology
From the Nov 3, 2026 post · Sources: New England Journal of Medicine, PubMed record
FYIEvidence Nov 2, 2026
Bicarbonate for metabolic acidosis in the ICU shows no clear survival gain but likely fewer dialysis starts, 1,544-patient meta-analysis finds
Hospital medicine Pulmonary and critical care
From the Nov 3, 2026 post · Sources: Intensive Care Medicine, PubMed record
WatchEvidence Oct 30, 2026
Flu admissions rise 27% in a week to 6,100, the highest late-October hospitalization rate since 2010, almost all H1N1
CDC forecasts 4,800 to 23,200 weekly flu admissions for the week ending Nov. 14, Becker's reported.
All physicians
From the Nov 2, 2026 post · Sources: CDC FluView, week 42, CDC FluView, week 41, Becker's Hospital Review
FYIEvidence Nov 1, 2026
Coronary CT angiography matches intravascular ultrasound for guiding stents and cuts procedure time 17 minutes, 1,105-patient trial finds
Cardiology Radiology
From the Nov 2, 2026 post · Source: TCTMD
FYIEvidence Oct 29, 2026
General-purpose AI models gave seriously wrong drug doses in about 2 of every 100 answers, Doximity analysis reports
All physicians
From the Nov 1, 2026 post · Source: Healthcare Dive
FYIEvidence Oct 30, 2026
AI reading 25,000 primary care notes a week found about 7 times as many missed specialist referrals at Singapore clinics
Primary care
From the Nov 1, 2026 post · Source: npj Digital Medicine
FYIEvidence Oct 30, 2026
Penn Medicine AI trained on 400,000 CT images screens for hundreds of conditions a scan was not ordered to find
Radiology
From the Nov 1, 2026 post · Source: Becker's Hospital Review
FYIEvidence Oct 15, 2026
AI chatbots recommend care costing 3.2 times what physicians ordered, mostly by adding tests at visits where doctors ordered none
Primary careEmergency medicine
From the Oct 31, 2026 post · Sources: NEJM AI, PubMed (NEJM AI study), Annals of Internal Medicine, PubMed (Annals study), TechTarget, The Jerusalem Post
FYIEvidence Oct 30, 2026
U.S. measles cases reach 4,852 in 2026 as Pennsylvania tells clinicians to treat every newborn of an infected mother as exposed
Primary careObstetrics and gynecology
From the Oct 31, 2026 post · Sources: CDC measles cases and outbreaks, Pennsylvania Department of Health advisory, Medical Daily
FYIEvidence Oct 29, 2026
60% of Americans would be uncomfortable with their doctor using AI to diagnose and treat them, and only 3% would let AI diagnose alone
All physicians
From the Oct 30, 2026 post · Sources: Pew Research Center, Becker's Hospital Review
FYIEvidence Oct 29, 2026
Faster 0/1-hour troponin pathways do not shorten emergency stays or raise discharges vs. 0/3-hour, Lancet meta-analysis of 110,933 visits finds
Emergency medicine Hospital medicine
From the Oct 30, 2026 post · Sources: The Lancet, PubMed
FYIEvidence Oct 27, 2026
AI scribes cut emergency physicians' active note time 2.4 minutes across 20 departments without raising 72-hour returns
Emergency medicine
From the Oct 29, 2026 post · Sources: Annals of Emergency Medicine, PubMed
FYIEvidence Oct 28, 2026
Lilly's retatrutide beats Ozempic head to head in type 2 diabetes, with about 21% weight loss vs. 9% at 80 weeks
Primary careEndocrinology
From the Oct 29, 2026 post · Sources: Eli Lilly, BioPharma Dive
FYIEvidence Oct 28, 2026
Voice-guided AI makes endoscopic ultrasound exams more complete in a randomized trial but adds about 2 minutes
Gastroenterology
From the Oct 29, 2026 post · Sources: Clinical Gastroenterology and Hepatology, PubMed
FYIEvidence Oct 28, 2026
Caring text messages beat support calls for suicidal adolescents at 12 months, while adults did better with calls, trial finds
Psychiatry Emergency medicine
From the Oct 29, 2026 post · Sources: American Journal of Psychiatry, PubMed
FYIEvidence Oct 27, 2026
CDC's 2026 superbug report names four urgent threats and drops C. diff to serious
Infectious diseaseHospitals
From the Oct 28, 2026 post · Source: CDC
FYIEvidence Oct 27, 2026
E-cigarettes nearly double 6-month quit rates even without counseling, and phone support doubles them again, NEJM Evidence trial finds
Primary carePulmonary and critical care
From the Oct 28, 2026 post · Sources: NEJM Evidence, PubMed
FYIEvidence Oct 20, 2026
Round-the-clock tele-ICU coverage cut hospital stays by 1.7 days at four safety-net hospitals without in-house intensivists
Pulmonary and critical careHospitals
From the Oct 28, 2026 post · Source: Healio
FYIEvidence Oct 27, 2026
Software reading bone density off lung cancer screening CT flags smokers with a 5.9% two-year fracture risk
RadiologyPrimary care
From the Oct 28, 2026 post · Sources: Radiology, PubMed
FYIEvidence Oct 23, 2026
Obstetricians' college advises stopping GLP-1 drugs 1 to 2 months before conception and opens the door to use while breastfeeding
Obstetrics and gynecologyPrimary care
From the Oct 28, 2026 post · Source: Healio
WatchEvidence Oct 26, 2026
Use of services in Medicare's AI-assisted prior authorization pilot falls 15% to 20% in its first six months, JAMA study finds
The six-year pilot began in January 2026 in six states; the authors said it is not yet known whether forgone care was needed.
PracticesHospitalsArizonaNew JerseyOhioOklahomaTexasWashington
From the Oct 27, 2026 post · Sources: JAMA, University of Minnesota School of Public Health, PubMed
FYIEvidence Oct 27, 2026
Heidi AI scribe enrollment cuts note time 1.2 minutes per encounter at Beth Israel Lahey Health but does not change after-hours closure or wRVUs
Practices
From the Oct 27, 2026 post · Sources: Annals of Internal Medicine, PubMed
FYIEvidence Oct 23, 2026
Thrombectomy improves 90-day function in mild large-vessel stroke and at 24 to 72 hours, two NEJM trials from China find
Neurology Emergency medicine
From the Oct 27, 2026 post · Sources: NEJM (LATE-MT), PubMed (LATE-MT), NEJM (MILD-MT), PubMed (MILD-MT)
FYIEvidence Oct 23, 2026
Radiologists and other physicians both follow wrong AI advice and ignore correct advice on head CT, Lancet Digital Health experiment finds
Radiology
From the Oct 25, 2026 post · Sources: The Lancet Digital Health, PubMed
FYIEvidence Oct 21, 2026
Adding brain imaging, genetics and microbiome data does not improve machine learning prediction of depression relapse, JAMA Psychiatry study finds
Psychiatry
From the Oct 25, 2026 post · Sources: JAMA Psychiatry, PubMed
FYIEvidence Oct 23, 2026
Clinicians' odds of a correct decision are 10 times higher with correct automated advice than with wrong advice, meta-analysis of 46 reports finds
All physicians
From the Oct 24, 2026 post · Source: npj Digital Medicine
FYIEvidence Oct 22, 2026
Beth Israel Lahey Health opens a center to test clinical AI from the clinic to the operating room, led by a hospitalist and a trauma surgeon
HospitalsGeneral surgery
From the Oct 24, 2026 post · Sources: Beth Israel Lahey Health, Becker's Hospital Review
FYIEvidence Oct 21, 2026
Phantom Neuro implants first patients in Australia with a sensor that reads forearm muscle signals to control a prosthetic hand
Orthopedic surgery Occupational therapy
From the Oct 24, 2026 post · Source: MobiHealthNews
FYIEvidence Oct 22, 2026
Microsoft's AI diagnostic panel solves 83.2% of hard NEJM cases vs. 36.1% for generalist physicians, Science paper reports
Internal medicinePrimary care
From the Oct 23, 2026 post · Sources: Microsoft AI, Science (paper record, Crossref), TechCrunch, Microsoft Research (2025 preprint)
FYIEvidence Oct 21, 2026
Google Research's personal health agent ranks first for 46.7% of 45 end users vs 24.4% for a single-agent baseline in a rating study
Primary care
From the Oct 23, 2026 post · Sources: Nature, Nature (PDF)
FYIEvidence Oct 19, 2026
AI model trained on 40 million face photos sorts cancer patients by survival risk, Lancet Digital Health study finds
Oncology
From the Oct 21, 2026 post · Sources: The Lancet Digital Health, PubMed record, Mass General Brigham, Becker's Hospital Review
FYIEvidence Oct 20, 2026
Radical Numerics says phages designed by its AI model were given to a patient with an antibiotic-resistant infection
Infectious disease
From the Oct 21, 2026 post · Source: Radical Numerics
FYIEvidence Oct 20, 2026
Home and virtual supportive oncology program tied to 10.4% fewer admissions among 5,432 Rhode Island cancer patients
Oncology
From the Oct 21, 2026 post · Source: Healthcare IT News
FYIEvidence Oct 15, 2026
Model pairing clinical risk factors with 20 minutes of computerized fetal heart tracing sorts labor risk across 147,350 births, Lancet Digital Health study finds
Obstetrics and gynecology
From the Oct 20, 2026 post · Sources: The Lancet Digital Health, PubMed record
FYIEvidence Oct 13, 2026
Trials of large language model tools often omit model versions, code and harms reporting, BMJ review of 461 trial records finds
All physicians
From the Oct 20, 2026 post · Sources: BMJ, PubMed record
FYIEvidence Oct 16, 2026
Digital GLP-1 program in UK reports 15.5% average weight loss and 91.4% retention among 8,127 women at six months, Nature Medicine study finds
Primary care
From the Oct 19, 2026 post · Sources: Nature Medicine, PubMed record, DOI
FYIEvidence Oct 15, 2026
JAMA Network will launch JAMA AI in early 2027, pairing human peer review with AI-driven assessment of every research paper
All physicians
From the Oct 17, 2026 post · Sources: JAMA, Fierce Healthcare, JAMA Network (2024)
FYIEvidence Oct 15, 2026
More than 950,000 clinicians sent OpenEvidence 271 million queries in 2.5 years, many outside their own specialty, JAMA study finds
All physicians
From the Oct 16, 2026 post · Sources: JAMA, PubMed record, NBC Miami
WatchEvidence Oct 14, 2026
Continuous glucose monitors cut A1C 0.9 point more than routine care in type 2 diabetes without insulin, Dexcom-funded NEJM trial finds
A Leerink Partners analyst expects a CMS decision on wider Medicare CGM coverage before year-end, MedTech Dive reported; timing is unconfirmed.
Primary careEndocrinology
From the Oct 16, 2026 post · Sources: New England Journal of Medicine, PubMed record, MedTech Dive
FYIEvidence Oct 13, 2026
Prostate MRI AI matches radiology readings for significant cancer in 1,974 external patients across 12 countries, SCARLET-1 study reports
Radiology Urology
From the Oct 16, 2026 post · Sources: Radiology, PubMed record
FYIEvidence Oct 13, 2026
Penn team links EEG to a language-model chat app that tells epilepsy patients about seizure risk and learns from their replies
Neurology
From the Oct 16, 2026 post · Sources: Nature Medicine, PubMed record
FYIEvidence Sept 24, 2026
AI reading of dual-stain slides finds 88.3% of cervical precancers vs. 78.1% for manual reading, at lower specificity
Pathology Obstetrics and gynecology
From the Oct 15, 2026 post · Source: NEJM AI
FYIEvidence Sept 17, 2026
Authors from Duke, Mayo Clinic, Northwestern and Michigan propose five evidence phases for clinical AI
Hospitals
From the Oct 15, 2026 post · Source: NEJM AI
FYIEvidence Oct 14, 2026
All 35 EHR developers won certification despite inconsistent, often incomplete AI risk disclosures, npj Digital Medicine study finds
Hospitals
From the Oct 14, 2026 post · Source: npj Digital Medicine
FYIEvidence Oct 5, 2026
Epic's pediatric sepsis alert flags 36% of sepsis cases in 166,943 visits to eight New York emergency departments, JAMA Pediatrics study finds
Pediatrics Emergency medicine
From the Oct 13, 2026 post · Sources: JAMA Pediatrics, PubMed record, TechTarget
FYIEvidence Oct 9, 2026
GPT-5 configurations misread images and stumble with web search on 161 real-world diagnostic cases, npj Digital Medicine study finds
All physicians
From the Oct 12, 2026 post · Source: npj Digital Medicine
FYIEvidence Oct 8, 2026
Short safety reminder cuts harmful clinical choices from 16.6% to 10.1% across 20 AI models and 10 million responses, Mount Sinai reports
All physicians
From the Oct 11, 2026 post · Sources: Communications Medicine, Mount Sinai, Becker's Hospital Review
FYIEvidence Oct 10, 2026
Mayo Clinic system grades radiation side effects from recorded visits with 82.6% exact agreement, near the range of expert raters
Oncology
From the Oct 11, 2026 post · Source: npj Digital Medicine
FYIEvidence Oct 9, 2026
Chest X-ray model identifies osteoporosis with AUROCs of 0.88 to 0.93 in three Korean validation cohorts of more than 150,000 exams
Radiology Endocrinology
From the Oct 10, 2026 post · Source: npj Digital Medicine
FYIEvidence Oct 9, 2026
Robotic console data separate attending surgeons from trainees in inguinal hernia repair with an outside-cohort AUC of 0.84
General surgery
From the Oct 10, 2026 post · Source: npj Digital Medicine
FYIEvidence Oct 8, 2026
Google's patient-facing diagnostic AI needs no safety stops in 98 supervised pre-visit chats at Beth Israel, Lancet study reports
Primary care
From the Oct 9, 2026 post · Sources: The Lancet, PubMed record, Google Research
FYIEvidence Oct 7, 2026
Vanderbilt records show 28 patients whose chatbot use worsened psychosis, 61% of them in a first psychotic episode
Psychiatry
From the Oct 9, 2026 post · Sources: JAMA Psychiatry, PubMed record, Full text (PubMed Central)
FYIEvidence Oct 9, 2026
Review finds only one of 18 radiation oncology AI deployments in lower-income countries reached cross-stage workflow use
Oncology
From the Oct 9, 2026 post · Source: npj Digital Medicine
Evidence Oct 8, 2026
Language model reading clinical notes flags epilepsy with AUCs up to 0.98; neurologists using it beat unaided experts by up to 14%
From the Oct 8, 2026 post · Source: npj Digital Medicine
Evidence Oct 6, 2026
Meta-analysis of 15 studies finds kidney biopsy AI accurate for three glomerular diseases but too little evidence to rank it above pathologists
From the Oct 8, 2026 post · Sources: Renal Failure, PubMed record
Evidence Oct 7, 2026
Longer AI-assisted telerehabilitation does not improve motor scores in early Parkinson's disease in 120-patient Chinese trial
From the Oct 7, 2026 post · Source: npj Digital Medicine
Evidence Oct 5, 2026
No public performance data found for 47 of 77 authorized pathology and hematology AI products, Helsinki review finds
From the Oct 6, 2026 post · Source: npj Digital Medicine
Evidence Oct 5, 2026
Language model agent takes fuller eye-clinic histories than ophthalmology residents in 172-patient randomized trial
From the Oct 6, 2026 post · Source: npj Digital Medicine
Evidence Oct 5, 2026
Review of 98 studies finds rural surgical and anesthesia telemedicine centers on specialist access, preoperative triage and less travel
From the Oct 5, 2026 post · Source: npj Digital Medicine
Evidence Oct 5, 2026
Shanghai eye-care language model raises referral adherence in 170-person community study
From the Oct 5, 2026 post · Source: npj Digital Medicine
Evidence Oct 2, 2026
Clinicians prefer AI-drafted discharge summaries in 95% of 60 hospital stays of seven to 21 days in Stony Brook study
From the Oct 4, 2026 post · Source: npj Digital Medicine
Evidence Oct 3, 2026
Breast ultrasound AI reaches 0.952 AUROC for biopsy triage on outside cohort; four radiologists miss fewer cancers with it
From the Oct 4, 2026 post · Source: npj Digital Medicine
Evidence Oct 1, 2026
Nearly 12 million people in 41 states live in broadband deserts; 650,000 rural residents also lack nearby ambulance and health facilities
From the Oct 4, 2026 post · Source: Healthcare IT News
Evidence Oct 1, 2026
Ten AI tools across 20 Swiss imaging centers cut trauma X-ray turnaround 26% and knee MRI 18%, JACR study reports
From the Oct 3, 2026 post · Sources: Journal of the American College of Radiology, Radiology Business
Evidence Oct 1, 2026
Duke deterioration model beats an unnamed vendor model in a company comparison; OHSU vital signs reach the chart 12 to 25 minutes late
From the Oct 3, 2026 post · Sources: Vega Health, npj Health Systems (OHSU), Healthcare IT News
Evidence Sept 30, 2026
Autonomous AI discharges 25% to 31% of urgent skin cancer referrals at two NHS hospitals, freeing about 8,500 appointments; six cancers missed
From the Oct 1, 2026 post · Sources: EADV Congress release (Mirage News), Dermatology Republic
Evidence Oct 1, 2026
Family doctors who disclose AI use are rated less warm and less competent in 1,030-person vignette study, most among adults under 45
From the Oct 1, 2026 post · Source: npj Digital Medicine
Evidence Sept 29, 2026
No AI evidence-search tool tested found 12% of a gold-standard evidence set; single queries often returned none of it
From the Sept 30, 2026 post · Source: npj Digital Medicine
Evidence Sept 29, 2026
Five-variable model predicts intractable hypoxemia during one-lung ventilation in repeat lung surgery with validation AUROCs of 0.75 to 0.78
From the Sept 30, 2026 post · Source: npj Digital Medicine
Evidence Sept 26, 2026
Oxford's 11-variable AI heart failure score predicts one-year death with C-index of 0.801 in 373,389 patients, above an adapted MAGGIC score
From the Sept 29, 2026 post · Source: npj Digital Medicine
Evidence Sept 29, 2026
Penn radiology team trains CT vision-language model on more than 400,000 scan-report pairs and tests it on 20,000 held-out people
From the Sept 29, 2026 post · Source: npj Digital Medicine
Evidence Sept 29, 2026
Robot motion data separate expert from less experienced surgeons in 98 robotic prostatectomies with an AUC of 0.892
From the Sept 29, 2026 post · Source: npj Digital Medicine
Evidence Sept 26, 2026
Remote blood pressure monitoring reached 5.2% of eligible patients at a Deep South health system; a few doctors made most referrals
From the Sept 29, 2026 post · Source: npj Digital Medicine
Evidence Sept 24, 2026
Wolters Kluwer survey: 26% of patients who researched health questions with AI sought care sooner; 89% want human expert validation
From the Sept 28, 2026 post · Source: Wolters Kluwer Health release
Evidence Sept 26, 2026
Model answers before prostatectomy counseling lower anxiety and cut physician talk time to 11.3 minutes from 19.9 in 268-patient randomized trial
From the Sept 27, 2026 post · Source: npj Digital Medicine
Evidence Sept 25, 2026
Yale-led team releases open ophthalmology language models that beat GPT-4o by 3.32% and seven baselines overall
From the Sept 27, 2026 post · Source: npj Digital Medicine
Evidence Sept 25, 2026
Artera presents five ASTRO abstracts on its prostate cancer AI biomarker, including a 20,000-patient commercial analysis
From the Sept 27, 2026 post · Source: Artera (Business Wire)
Evidence Sept 24, 2026
CT deep learning model predicts organ failure in acute pancreatitis a median 3.5 hours early in 2,746-patient retrospective study
From the Sept 26, 2026 post · Sources: Journal of Pancreatology, Radiology Business
Evidence Sept 24, 2026
Junior clinicians identify 15.8% of GPT-4o hallucinations in multicenter simulation; 13.1% catch none
From the Sept 25, 2026 post · Source: npj Digital Medicine
Evidence Sept 22, 2026
Autonomous robotic thyroid ultrasound avoids 75% of on-site exams and misses 19% of biopsy recommendations in 262-patient, three-center trial
From the Sept 23, 2026 post · Source: npj Digital Medicine
Evidence Sept 22, 2026
EAGLE finds esophageal cancer on noncontrast CT with 90% sensitivity and 98.5% specificity and holds a 42% positive predictive value prospectively
From the Sept 22, 2026 post · Source: Nature Medicine
Evidence Sept 16, 2026
Across 13 countries, 49% say an AI-skilled layperson could do at least one physician task as well as a physician; 59% of adults under 35 agree
From the Sept 22, 2026 post · Sources: Edelman Trust Barometer special analysis with Yale School of Public Health (PDF), Edelman (Trust and Health special report), Becker's Hospital Review, Medical Daily
Evidence Sept 18, 2026
Alibaba's DAMO RADAR reads contrast abdominal CT for 146 findings, outperforms 23 of 26 radiologists in Science; weights free for research
From the Sept 21, 2026 post · Sources: DAMO Academy (GitHub, links the Science paper), South China Morning Post, TechTimes, Federal Register (radiology CADe/CADx/CADt final order)
Evidence Sept 19, 2026
Stigmatizing language about frequent ED use leads three open models to rank deteriorating patients below stable ones in 221,556 comparisons
From the Sept 21, 2026 post · Source: npj Digital Medicine
Evidence Sept 21, 2026
Papers with a physician co-author follow reporting checklist better, discuss fairness more in review of 41 chest X-ray foundation models
From the Sept 21, 2026 post · Source: npj Digital Medicine
Evidence Sept 17, 2026
Year of edits by more than 1,000 UC San Diego physicians shows AI portal drafts that need clinical judgment take 60% to 70% longer to finish
From the Sept 20, 2026 post · Sources: NEJM AI, Becker's Physician Leadership, Healthcare Innovation
Evidence Sept 11, 2026
Epic's End-of-Life Care Index ranks patients well but overstates how many will die in test of 287,106 encounters at 39 hospitals
From the Sept 18, 2026 post · Sources: JAMA Network Open, STAT (Deardorff)
Evidence Sept 16, 2026
Model trained on 140,000 emergency triage decisions scores identical presentations as less severe when the patient is female
From the Sept 18, 2026 post · Source: npj Digital Medicine
Evidence Sept 17, 2026
Review finds developers involved in 73% of 229 digital health trials, with higher odds of a positive result
From the Sept 17, 2026 post · Source: npj Digital Medicine
Evidence Sept 15, 2026
Open-weight diagnostic agent run inside the hospital is 98.9% accurate on the 49.4% of cases it keeps, selected by agreement across five runs
From the Sept 16, 2026 post · Source: Nature Medicine
Evidence Jun 17, 2026
In Nature trial, Google's AMIE management plans rated appropriate 95% to 98% of the time versus 72% to 81% for physicians
From the Sept 16, 2026 post · Sources: Nature, Science, JAMA Network Open, npj Digital Medicine
Evidence Sept 11, 2026
Seven health system leaders tell Becker's autonomous AI needs narrow use cases, named accountability, escalation paths and developer liability
From the Sept 15, 2026 post · Source: Becker's Hospital Review

Latest news

See all the latest news