←
Doximity5,779 posts
Doximity avatar

Doximity

@doximity

The leading clinical AI company for medical professionals. Download the app today!

◷ Joined June 2010▧ 1,310 Photos and videos
Doximity avatar
Doximity@doximity·15h

A 12-month-old girl presents for her well child check with her family. They are new to the practice, and she has no pertinent past medical problems when you are talking with the family. Physical examination is normal, but there is a small red hemangioma located on her abdomen. Family said that is has been there since birth, and no further investigation or work up had been performed. They think it has been about the same size, or maybe has grown slightly since they first noticed it. Image of the abdomen is included.

Post attachment
NYSE 🏛 avatar
⟳ Doximity retweeted
NYSE 🏛@NYSE·Nov 11

Digital health platform @Doximity wants doctors looking at patients, not screens. CEO @JeffTangney joins @ICEHousePodcast to talk about the impact of the AI wave, building trust with physicians, and what comes next for healthcare. Full episode linked below.

0:28
Alexis R. Narvaez-Rojas, M.D. (DrN) avatar
⟳ Doximity retweeted
Alexis R. Narvaez-Rojas, M.D. (DrN)@AlexisNarvaezMD·Nov 13

Who should shape the future of AI in medicine? Physicians want a leading role. According to Doximity's 2026 Doctor-Driven AI Report, 82% of surveyed physicians believe physicians should help set the rules for AI in medicine, while 64% believe medical societies should be involved. Meanwhile, only 32% selected federal regulatory agencies and just 10% selected AI developers and companies. As AI becomes increasingly integrated into clinical practice, these findings highlight the importance of physician perspectives in shaping responsible AI adoption. #Doximity #DoximityAIF @Doximity #DoximityAIF doximity.com/reports/doctor-…

ANTON avatar
⟳ Doximity retweeted
ANTON@antonmaximus·Nov 12

In @doximity’s 2026 survey of 3,379 U.S. physicians, 85% said they use AI at least weekly, and 82% said physicians should help set the rules for AI in medicine. doximity.com/reports/doctor-… #DoximityAIF

Jon Hershon avatar
⟳ Doximity retweeted
Jon Hershon@jonathanhershon·Nov 12

We just released @Doximity's 2026 survey of 3,379 US physicians 85% now use AI at work every week, and more than half use it every day 81% say it's taught them something clinically new, and 82% say physicians should make the rules for AI in medicine. I agree

0:44
Doximity avatar
Doximity@doximity·Nov 12

A year ago, half of physicians used AI at work weekly. Today it's 85%, and more than half use it every day. Our 2026 Doctor-Driven AI Report surveyed 3,379 U.S. physicians across 20 specialties. The headline isn't adoption. It's what physicians are doing with it, and what they're asking for next. 🔹 81% say AI has taught them something clinically they didn't already know 🔹 46% say AI has already cut their after-hours admin work 🔹 3 in 4 have caught a factual error in AI output. 🔹 3 in 4 say patients are bringing more AI-generated self-diagnoses into the exam room 🔹 Only 28% say their organization has clear AI policies and approvals And when asked who should set the rules for AI in medicine, the answer was clear: 82% said physicians. Physicians aren't waiting on the sidelines of this shift. They're using AI, checking it, and ready to shape it.

0:44
UpToDate avatar
⟳ Doximity retweeted
UpToDate@UpToDate·Nov 5

UpToDate is now available inside Doximity Ask—giving clinicians access to trusted, cited answers within a workflow they already use at the point of care. Learn more: ow.ly/8pzL5104eCQ

Post attachment
Navin Balaji, MD avatar
⟳ Doximity retweeted
Navin Balaji, MD@navinbalaji_MD·Nov 3

Great to see @doximity introduce DoseCheck™ in Doximity Ask, which gives physicians a built-in check on dosing, with access to supporting sources. No language model is involved, so there is no hallucination. This is the kind of AI tool that can lead to safer care. #DoximityAIF

Sawyer Bawek, DO avatar
⟳ Doximity retweeted
Sawyer Bawek, DO@sawyer_bawek·Nov 2

💡 @doximity launches DoseCheck™ in Ask ✅ Free deterministic check of every AI dosing claim vs FDA-label database ✅ Green badge + source link when verified 👉 Patient safety first in clinical AI. #ClinicalAI #PatientSafety @doximity #DoximityAIF 🔗 businesswire.com/news/home/2…

Roupen Odabashian avatar
⟳ Doximity retweeted
Roupen Odabashian@RoupenMD·Oct 31

@Doximity tested nine widely used AI models on more than 8,000 dosing questions drawn from real physician queries. At least 2.3% of the dosing claims were wrong. Of the errors they detected, 43.8% were serious or potentially lethal. That sounds like a small error rate until you remember what a dosing question is. I work in oncology, where renal function, weight, and a decimal point decide whether a dose is right. A tool that is right 97.7% of the time is still wrong about once in every 40 or so answers. The failure modes @Doximity listed are the ones I would worry about too. Newly approved drugs are weak spots because models have had less time to learn them. Doses are not adjusted for the patient in front of you. Units get mixed up, and drug names that look alike get confused. Their fix is interesting. Instead of asking a model to check its own work, they run each dosing claim against a structured database built from FDA labeling and guidelines. The pattern seems right to me. Let the language model draft, and let something deterministic verify. Where else in medicine should the answer be checked against a fixed source before a clinician ever sees it? rutlandherald.com/news/busin…

Maduka Gunasinghe avatar
⟳ Doximity retweeted
Maduka Gunasinghe@MadukaOnCall·Oct 31

No more opening three tabs to double-check a dose. DoseCheck™ in Doximity Ask checks supported dosing statements with explicit rules, not a language model, so the same claim always gets the same result. Tap the seal for the source. @doximity #DoximityAIF blog.doximity.com/articles/o…

Matt avatar
⟳ Doximity retweeted
Matt@respirdoc·Oct 31

Chatbots still get drug doses wrong often enough that one of the biggest physician platforms now checks every AI dose against plain rules before a doctor sees it. Doximity added a deterministic check to its clinical AI tool. Each dosing claim the model makes is compared with FDA labeling and professional guidelines, instead of trusting the model's best guess. In the company's own testing of nine widely used models on thousands of real physician-style dosing questions, at least 2.3% of dosing claims were wrong, and nearly half of those errors were serious or potentially lethal. The misses were the ones we'd expect: newer drugs, adjustments for kidney function and weight, units and decimal points, and look-alike drug names. At the bedside, that's the ICU med list: renally cleared antibiotics, weight-based drips, a drug approved last year. A rule-based check is the right design. It still doesn't know your patient's creatinine trend. Verify the dose. The physician still decides. The limit: this is a press release, not a peer-reviewed study. The accuracy figures are the company's own and haven't been independently tested. Source: Doximity press release via Business Wire, Oct 29, 2026. Vendor-reported internal testing, not peer reviewed. businesswire.com/news/home/2…

Joseph Heaton avatar
⟳ Doximity retweeted
Joseph Heaton@josephnheaton·Oct 31

@doximity 𝗹𝗮𝘂𝗻𝗰𝗵𝗲𝗱 𝗗𝗼𝘀𝗲𝗖𝗵𝗲𝗰𝗸™ 𝗶𝗻 𝗗𝗼𝘅𝗶𝗺𝗶𝘁𝘆 𝗔𝘀𝗸. 𝗗𝗼𝘀𝗲𝗖𝗵𝗲𝗰𝗸𝗧𝗠 parses each dosing claim into drug, dose, route, and frequency, then compares it against our drug database using explicit rules

ANTON avatar
⟳ Doximity retweeted
ANTON@antonmaximus·Nov 1

💊 Medication dosing accuracy matters! Doximity Ask now features DoseCheck™ — automatically verifies supported medication dosing statements against trusted drug references, including FDA labeling. Another step toward safer, more transparent clinical AI! @doximity #DoximityAIF

Post attachment