Hospitals & Care
99 gains87 Traces101 problems
Every measured gain and problem on the record for this topic, newest first. Updated .
AI in hospitals and care
One square per record, darker for stronger evidence:Evidence: 5 high176 moderate106 emerging
Most of the evidence is chatbots tested on written questions and small single-site studies; a few randomized trials and reviews carry more weight. TRV-2026-0355TRV-2026-1613TRV-2026-2032 Chatbots often match or beat doctors on structured written cases, while a 7294-patient trial of an AI alert in live care found no drop in delirium. TRV-2026-1797TRV-2026-1664
A randomized preclinical trial of 77 surgeons watching laparoscopic video shows AI assistance cut the time to find a bleeding site from 3.23 to 2.53 seconds on average. TRV-2026-2032 In a randomized crossover study, clinical trial staff using AI spent 2.71 fewer minutes per item reviewing charts for immunotherapy side effects, though severity grading was much weaker than event detection. TRV-2026-2318 Three randomized trials with over 90,000 US patients show that messages on personal high flu risk raised vaccination 1.7-3.5 percentage points over no message. TRV-2026-1852 A randomized trial of 130 final-year nursing students found AI-adaptive simulation raised leadership scores more than standard training, under controlled simulation conditions. TRV-2026-1262
In a test of 960 responses to clinician-written cases, ChatGPT Health undertriaged 52% of true emergencies, sending diabetic ketoacidosis and impending respiratory failure to 24-48 hour evaluation. TRV-2026-0181 A randomized trial of 7294 patients at Mount Sinai found an AI-triggered alert did not reduce delirium (35.1% vs 32.7%), though only 17.2% had a documented delirium assessment. TRV-2026-1664 In 16,254 responses to 29 standardized vignettes, all 21 chatbots failed differential diagnosis at rates above 0.80 even though final-diagnosis accuracy was high, a benchmark study found. TRV-2026-0145 A test of eight speech-to-text systems found at least one clinically significant error in 30% to 68% of 800 transcripts, and 39.6% of 53 errors with potential for severe harm involved medication type or dose. TRV-2026-1687
A review of 314 FDA-cleared surgical AI devices found only 5.1% had higher-quality prospective evidence. TRV-2026-1693 A scoping review of 1181 reports on AI decision tools found 62.7% stopped at clinical validation and 14.4% evaluated implementation or impact. TRV-2026-1613 A scoping review found only seven eligible studies of agentic AI in healthcare, with just one trial involving patients. TRV-2026-0166 A review of 310 publications found no study that measured AI's effect on critical thinking or clinical reasoning in medical education. TRV-2026-0458
Studies point in different directions on whether AI scribes ease clinician burnout. TRV-2026-0478TRV-2026-0330 An observational study of 263 clinicians in six US health systems reports that self-reported burnout fell from 51.9% to 38.8% after 30 days with an AI scribe. TRV-2026-0478 A systematic review of 6 real-world studies found clinicians reported less documentation time, but burnout on standardized scales was unaffected. TRV-2026-0330 At one cancer center, 190 of 958 clinicians used the AI scribe; after-hours time fell only from 86.9 to 81.4 minutes a week. TRV-2026-1819
Most tests find chatbot answers to patient questions accurate on average, yet poor readability and occasional unsafe answers recur. TRV-2026-1856TRV-2026-2452TRV-2026-1746TRV-2026-1715
See these 79 recordsChatbots beat doctors on structured written cases, but results on triage and differential diagnosis are mixed. TRV-2026-1797TRV-2026-0181TRV-2026-0145TRV-2026-1421
See these 26 recordsAI scribes cut documentation time for many clinicians, though evidence on burnout and adoption is mixed. TRV-2026-1897TRV-2026-0478TRV-2026-0330
A Trace is one record with both a gain and a problem, so it counts on both sides: 186 records show a gain and 188 show a problem. 128 context records are in the record list but not counted, because they report no measured gain or problem.
| Evidence | Gain side | Problem side |
|---|---|---|
| HighStrong study design, backed by at least two independent sources | 3 | 3 |
| ModerateA measured study or an official source | 113 | 107 |
| EmergingEarly, small, unreviewed or reported second-hand | 70 | 78 |
By type of evidence: 95 benchmark or lab tests; 43 observational studies; 42 controlled comparisons; 33 commentaries or narrative reviews; 29 surveys; 15 interview studies; 9 systematic reviews or meta-analyses; 9 randomized trials; 4 case reports; 3 investigations by reporters; 2 news reports; 2 regulatory or legal actions. How evidence is scored
In an online French study of 204 GPs and 942 patient histories, AI recorded histories more effectively than doctors, most clearly for older patients and for allergy and family cancer history.
In an observational study of 12,468 chronic disease patients in three Chinese provinces, AI-enabled care was linked to hypertension control targets met rising from 68% to 82%, with health data accuracy above 95%.
Clinicians using AI note-taking scribes in 6 real-world studies reported spending less time on documentation, though the evidence is sparse and based on self-reports.
A literature review linked AI decision support to vulnerabilities in doctors' physical examination, differential diagnosis, clinical judgment and patient communication skills, though magnitude and reversibility remain uncertain.
In 16,254 responses to 29 standardized clinical vignettes, all 21 AI chatbots tested failed differential diagnosis at rates above 0.80, even though final-diagnosis accuracy was high.
One review in this topic printed a pooled result: one figure calculated across many studies. They are the reviews’ own numbers, checked word for word against their abstracts. They often measure different things, so they are listed side by side, not added up.
AI predicts gallbladder surgery difficulty well, but 16 of 18 studies were at high risk of bias · TRV-2026-0787
AUC 0.818 (95% CI 0.797 to 0.840)
18 studies · search to March 2, 2026
For 32 validation models, the pooled AUC was 0.818 (95% CI, 0.797-0.840).
AUC 0.848 (95% CI 0.829 to 0.868)
18 studies · search to March 2, 2026
The pooled AUC for 27 training models was 0.848 (95% CI, 0.829-0.868).
AI virtual patients and simulation helped trainees in several small studies, while reviews and interviews raise skill erosion as a risk. TRV-2026-1262TRV-2026-1044TRV-2026-0490TRV-2026-0147
See these 39 recordsSurveys find patients and clinicians wary of AI, and regulation and the NHS Palantir contract draw scrutiny. TRV-2026-1843TRV-2026-2394TRV-2026-2335TRV-2026-0359
See these 32 recordsSurgical, imaging and prediction tools mostly rest on small retrospective or preclinical tests with little prospective evidence. TRV-2026-2032TRV-2026-1623TRV-2026-0787TRV-2026-1693
See these 53 recordsEach record sits in one thread at most. A record with both a gain and a problem counts on both sides. 44 records fit none of these threads.
In a 7294-patient trial at Mount Sinai, an AI-triggered health-record alert did not reduce delirium (35.1% vs 32.7%, P = .37) or change adherence to best practices, though only 17.2% had a documented delirium assessment.
415 records · page 3 of 28
Freedom of information requests, obtained by the charity Medact and shared with the Guardian, show that 29 hospital trusts NHS England lists as realising benefits from Palantir's federated data platform say they are not using it or any of its applications.
The Guardian
Researchers gave images of Dupuytren's contracture, a hand condition, to three AI chatbots: ChatGPT, Gemini and Claude.
Researchers followed 88 patients on peritoneal dialysis through a 3-month program and a 2-month follow-up. Twenty of them voluntarily sent screenshots of their ChatGPT questions to nurses over LINE and got feedback, and…
The parents of Bowen Wan, a 31-year-old software engineer in Seattle, have sued OpenAI. They allege that after she lost her job at Amazon, ChatGPT, communicating in Chinese, urged her to taper off her epilepsy medication…
Researchers built a loop that pairs a locally run DeepSeek-R1 language model with an automatic planning algorithm for seed implant brachytherapy.
Researchers built an agentic large language model system that reads clinical notes and pulls out whether an immune-related adverse event is present, when it happened, how severe it was, what caused it…
A cross-sectional online survey of 136 members of the German-speaking One Minute Wonder Network, mostly nurses, asked how they use AI to build short workplace-based learning resources.
Researchers asked four AI chatbots, DeepSeek-V3.2, GPT-5.5, Gemini 3.1 Pro and Claude Sonnet 4.6, 16 questions about type 2 diabetes remission, using six prompting styles. That produced 384 responses.
Researchers posed standardized questions drawn from American Academy of Orthopaedic Surgeons carpal tunnel guidelines to four chatbots: ChatGPT-4, Gemini, Claude-3 and Mistral-7B.
Researchers gave 55 multiple-choice adult reconstruction questions from the AAOS ResStudy bank to seven chatbots, including several ChatGPT versions, Gemini, Claude and Co-Pilot.
Researchers built a ten-domain rubric called OMNI for health professionals, administrators and researchers to judge generative AI outputs.
Researchers tested six chatbots, ChatGPT, Gemini, Claude, DeepSeek, Copilot and Manus, on 25 applied surgical anatomy scenarios written by an anatomy professor and two plastic surgeons.
Researchers gave 225 multiple-choice questions from the refractive surgery section of the American Academy of Ophthalmology's Basic and Clinical Science Course to OpenEvidence and to six…
A commonwealth ombudsman report published on Monday examined the Integrated Assessment Tool used to decide home support funding for older Australians.
An article in the Australian Health Review examines who should be held legally responsible when clinician-facing AI tools cause physical or psychological harm to patients.
ace