Source link <\/a><\/p>\n","protected":false},"excerpt":{"rendered":"October 14, 2026 2 min read
Add topic to email alerts
Receive an email when new articles are posted on
Please provide your email address to receive an email when new articles are posted on . “
data-action=”subscribe”>
Subscribe
We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com. Back to Healio Key takeaways: AI responses to patient-facing gastroenterology questions were less accurate in non-English languages. Non-English responses also failed to recommend immediate medical intervention during emergency situations. NASHVILLE, Tenn. \u2014 AI tools were less likely to flag emergencies and deliver accurate, comprehensive gastroenterology advice in the six most common U.S. languages after English, according to a presenter at ACG Annual Scientific Meeting. \u201cAI is already part of everyday life, and people are turning to it with health questions, often before speaking with a physician,\u201d Harika Dadigiri, MD, resident physician at New York Medical College at Saint Mary\u2019s and Saint Clare\u2019s Hospital in New Jersey, told Healio regarding her presentation. \u201cFor patients who struggle to find reliable medical information in their preferred language, being able to ask a question and receive an immediate answer can be especially appealing.\u201d
As many as 68 million individuals in the U.S. speak a language other than English at home, according to study background. \u201cBut just because AI can give an answer does not mean that answer is accurate or safe,\u201d Dadigiri said. \u201cThat concern inspired our study: Would patients describing the same GI symptoms receive equally reliable guidance in different languages, especially when they needed emergency care?\u201d Dadigiri and colleagues input 50 patient-facing gastroenterology questions on topics with clear guidance from ACG, AGA and CDC, among other health organizations into four large language models (LLMs). The models \u2014 OpenAI\u2019s GPT-5 Mini, Google\u2019s Gemini 3 Flash, Anthropic\u2019s Claude Haiku 4.5 and Meta\u2019s Llama 3.3 70B Instruct \u2014 output three answers to each question. The researchers translated their questions into Spanish, Chinese, Tagalog, Vietnamese, Arabic and French using Nvidia\/Riva-Translate-4B. They used the same modality to back-translate the large language model (LLM) responses into English. Dadigiri and colleagues rated responses with rubrics that considered guideline adherence, comprehensiveness and ability to assign triage stage. Based on the researchers\u2019 rubric, guidelines concordance reached 91.3% in English. However, concordance ranged from 63.8% to 87.5% in non-English languages. The LLM output was least accurate in Chinese (OR = 0.18; 95% CI, 0.12-0.28) and Vietnamese (OR = 0.15; 95% CI, 0.1-0.23). \u201cThat variation is a reason to evaluate each language individually,\u201d Dadigiri said. \u201cA single overall performance score can obscure differences that matter to the patients using the tool.\u201d Answers were most comprehensive (92.7%) in English, but comprehensiveness fell as low as 48.7% in Vietnamese. \u201cClinicians should pay attention to what an answer omits as well as what it says,\u201d Dadigiri said. The LLMs failed to advise patients to seek immediate treatment for medical emergency in 15% of responses in English, 37.5% of responses in Chinese (RR = 2.46) and 40.8% of responses in Vietnamese (RR = 2.68). \u201cLanguage equity is part of patient safety,\u201d Dadigiri said. \u201cThe findings reported in our abstract support making language-specific evaluation part of how GI practices select and implement AI tools,\u201d she added. \u201cWe should ask how a tool performs in the languages [our] patients actually use, including whether it recognizes red-flag symptoms and gives clear instructions about seeking care.\u201d Dadigiri and colleagues acknowledged study limitations, including reliance on expert rubric to evaluate responses, rather than physician adjudication. Though the study did not evaluate clinical outcomes, Dadigiri noted that it does \u201cidentify performance concerns under the tested conditions and help define priorities for clinical validation.\u201d She added, \u201cFor patient education, I would prioritize clinician-reviewed content, plain language and review by qualified language professionals. For symptom-related questions, there should be clear escalation pathways to a clinician or emergency services.\u201d For more information: Harika Dadigiri, MD, can be reached at gastroenterology@healio.com. Published by: Sources\/Disclosures Source: Dadigiri H, et al. Does AI speak gastroenterology equitably? A multilingual safety and accuracy benchmark of large language models across the seven most common U.S. languages. Presented at: ACG Annual Scientific Meeting; Oct 12-14: Nashville, Tenn. (hybrid meeting).
Disclosures:
The authors report no relevant financial disclosures.
Ask a clinical question and tap into Healio AI’s knowledge base.
PubMed, enrolling\/recruiting trials, guidelines
Clinical Guidance, Healio CME, FDA news
Healio’s exclusive daily news coverage of clinical data
Learn more
Add topic to email alerts
Receive an email when new articles are posted on
Please provide your email address to receive an email when new articles are posted on . “
data-action=”subscribe”>
Subscribe
We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com. Back to Healio Source link<\/p>\n","protected":false},"author":1,"featured_media":4023,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-4022","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=\/wp\/v2\/posts\/4022","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4022"}],"version-history":[{"count":0,"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=\/wp\/v2\/posts\/4022\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=\/wp\/v2\/media\/4023"}],"wp:attachment":[{"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4022"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=4022"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/drsoniafawad.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=4022"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"Healio](\"https:\/\/www.healio.com\/~\/media\/h5\/feature\/news\/publogos\/hgld\/healio_gastro.svg?la=en&h=40&w=152&hash=2C654A538F2E250F5183D42A89FE0EC0\")
\n <\/div>\n<\/p><\/div>\n<\/p><\/div>\n