{"id":1015281,"date":"2026-10-29T12:54:12","date_gmt":"2026-10-29T16:54:12","guid":{"rendered":"https:\/\/www.marketnewsdesk.com\/index.php\/doximity-launches-dosecheck-to-catch-dangerous-ai-drug-dosing-errors-before-they-reach-doctors\/"},"modified":"2026-10-29T12:54:12","modified_gmt":"2026-10-29T16:54:12","slug":"doximity-launches-dosecheck-to-catch-dangerous-ai-drug-dosing-errors-before-they-reach-doctors","status":"publish","type":"post","link":"https:\/\/www.marketnewsdesk.com\/index.php\/doximity-launches-dosecheck-to-catch-dangerous-ai-drug-dosing-errors-before-they-reach-doctors\/","title":{"rendered":"Doximity Launches DoseCheck to Catch Dangerous AI Drug Dosing Errors Before They Reach Doctors"},"content":{"rendered":"

<\/p>\n

Doximity Launches DoseCheck to Catch Dangerous AI Drug Dosing Errors Before They Reach Doctors<\/b><\/p>\n

AI models make mistakes in more than 1 in 50 drug dosing recommendations.<\/i><\/p>\n

DoseCheck AI hardening reduces the error rate to near zero<\/i><\/p>\n

SAN FRANCISCO–(BUSINESS WIRE<\/a>)–Doximity<\/a>, Inc. (NYSE: DOCS), the leading digital platform for U.S. medical professionals, has launched DoseCheck, a free additional safety layer in Doximity Ask<\/a> that instantly checks every AI-generated medication dosing claim against a structured drug database to reduce treatment errors and increase patient safety.<\/p>\n

This press release features multimedia. View the full release here: https:\/\/www.businesswire.com\/news\/home\/20261029499969\/en\/<\/a><\/p>\n

\"Doximity<\/p>\n

Doximity DoseCheck reduces AI drug dosing errors by more than 99%.<\/p>\n<\/div>\n

\nThe probabilistic nature of AI means that it predicts the most likely answer based on the data it\u2019s been trained on. This can lead to different but equally confident answers to the same prompt. When it comes to drug dosing, doctors need to know that the dosing recommendations AI generates are consistently accurate.<\/p>\n

\nBuilding on Doximity\u2019s existing work around AI safety, DoseCheck adds a deterministic, rule-based verification step to all dosing recommendations in Doximity Ask, Doximity\u2019s clinical decision making support tool. By checking against FDA labeling and professional guidelines, DoseCheck increases accuracy to more than 99%.<\/p>\n

Addressing an industry-wide challenge<\/b><\/p>\n

\nDrug dosing accuracy is a challenge for any platform using AI to make recommendations to doctors. Doximity tested nine widely used AI models with more than 8,000 dosing questionsbased on real physician queries. At least 2.3% of dosing claims made by these models were wrong, and 43.8% of detected errors were serious or potentially lethal.<\/p>\n

\n\u201cAI is probabilistic. Drug dosing can\u2019t be,\u201d said Dr. Louis-Antoine Mullie, Chief AI Researcher at Doximity. \u201cDoseCheck doesn\u2019t ask a language model to grade its own homework. It checks dosing claims against a structured, authoritative database, so physicians get the same verified dosing answer every time.\u201d<\/p>\n

\nCommon sources of errors identified in the analysis included:<\/p>\n