Healthcare AI Safety Gap · Don't break patients
    Peer-reviewed / official11 Nov 2026·Germany / China

    A third of chatbot answers on asthma in pregnancy raised a safety concern

    Frontiers in Digital Health: clinicians found at least one safety concern in 37 of 114 answers (32.5%) from six consumer AI models to common questions about asthma in pregnancy, and judged 4 (3.5%) to be high-risk unsafe advice.

    32.5%
    of chatbot answers on asthma in pregnancy with at least one safety concern

    What the research found

    Researchers narrowed 40 patient questions about asthma in pregnancy to 19 and put each once to six consumer AI models, including GPT-5.5, Claude Sonnet 5, Gemini 3.5 Flash, DeepSeek-V3, Qwen and Doubao, with clinicians rating the 114 answers for quality, readability and safety. After adjudication, 37 answers (32.5%) had at least one safety concern and 4 (3.5%) were rated high-risk unsafe advice; quality varied significantly between models, and none wrote at a median reading level of grade 8 or below. The authors say the results do not establish safety for unsupervised patient use.

    Why it matters for providers

    Pregnant patients with asthma are a group where a confident but wrong answer about medication carries risk for two people, so chatbot advice needs a clinician's check.

    Original source
    Frontiers in Digital Health (Charité – Universitätsmedizin Berlin / Zhejiang Hospital)
    Read the full report ↗
    Peer-reviewed or official source, the most reliable tier.