Check out our latest in @JAMA_current characterizing the use of @OpenEvidence among nearly 1 million clinician users
ja.ma/4Ba9ej2
2
8
26
1,965
Insightful editorial by @rohan_khera and team, with an important call to investigate how this technology affects clinical decisions, patients, and medical education - more to come!
ja.ma/481xKW1
1
146
Thanks to a very talented co-first author @IAmSamFin, and guidance from @AnupamBJena and @TravisZack2
@OpenEvidence @LiuMichaelMD @jbrafel @MGBResearchNews @harvardmed
3
104
Vishal Patel retweeted
US pilots and flight attendants had the highest and second-highest percentages of deaths from radiation-related #Cancer across 503 occupations, while deaths from other cancers were not similarly elevated. ja.ma/4wDT520
1
6
17
3,827
Vishal Patel retweeted
Huge congratulations to @vrpatel97 on being named a 2026 @statnews Wunderkind!
Nobody is better at spotting the natural experiments hiding in everyday life, and turning them into rigorous science. Nobody more deserving!
statnews.com/wunderkinds/vis…
3
10
559
Thanks @nytimes for covering our article!
nytimes.com/2026/07/15/well/…
1
251
Check out our latest in @JAMAPsych showing that traffic fatalities transiently rise after mass shootings.
jamanetwork.com/journals/jam…
1
4
4
750
On the day immediately following the 10 largest mass shooting events over a 15 year study period, traffic fatalities rose by an average of 14.3% compared to the preceding days, corresponding to 19.9 additional deaths across the country.
1
123
The toll of mass shootings reaches well beyond the immediate victims. Grief, distraction, and acute stress may impair driving in the days that follow... a form of collateral harm that rarely enters public accounting.
Team: @AnupamBJena @LiuMichaelMD @ChrisWorsham
1
76
Vishal Patel retweeted
New: a large, blinded evaluation study by a consortium from Stanford, Harvard, UCSF, University of Washington, and the lead statistical editor at JAMA, on the accuracy of OpenEvidence vs foundation models for real point-of-care clinical queries.
- Gold-standard expert subspecialist evaluation: Rather than relying on models rating other models, 149 clinicians from >30 specialties subspecialty-matched to each question evaluated accuracy, blinded.
- OE outperformed foundation models on accuracy, utility, source quality, and verifiability; this holds whether raters had used OpenEvidence before or not.
- After OE, Gemini and Claude perform statistically similarly to each other, and each of Claude and Gemini significantly outperforms GPT5.5.
Paper: arxiv.org/pdf/2606.28960
All code and data including raw queries and answers were publicly released by the authors.
For the past two weeks, our independent team of statisticians, AI evaluation experts, clinical AI researchers, and clinicians was given a unique opportunity to test one question: “How well do different AI tools answer user questions on the OpenEvidence (OE) platform?”
13
42
226
73,340
Vishal Patel retweeted
Today we are sharing the results on arXiv and the benchmark dataset on HuggingFace. Following our prespecified statistical analysis, OE scored highest on all five dimensions of accuracy, clinical utility, source quality, verifiability, and completeness.
1
2
3
755
Check out our latest paper in @JAMA_current, showing that suicide mortality was lower than expected following the launch of the "988" Suicide and Crisis Lifeline.
1
8
57
14,696
Vishal Patel retweeted
Led by @vrpatel97 and @AnupamBJena in @JAMA_current, we find that suicide deaths among young adults declined 📉 by 11% in the US after the launch of the 988 Suicide and Crisis Lifeline📲 - supporting efforts to preserve and expand crisis services.
Link: jamanetwork.com/journals/jam…
1
7
32
8,410
Check out this @Freakonomics episode on our working working paper, which shows that traffic fatalities increase on the days of major music album releases
freakonomics.com/podcast/do-…
nber.org/papers/w34866
1
1
2
188
And the @nytimes cover below!
nytimes.com/2026/04/10/well/…
109
Vishal Patel retweeted
Led by @vrpatel97 in @AnnalsofIM, we show that physicians are more likely to die at home or hospice than others. However, modest gaps suggest that even medical knowledge and familiarity with serious illness are not the principal drivers of end-of-life care
acpjournals.org/doi/10.7326/…
6
13
2,385
Vishal Patel retweeted
NYTimes write up about our work challenging the "epidemic" of cancer in young people in the US. with @vrpatel97
nytimes.com/2025/12/08/healt…
4
1
17
3,236