Search Articles

View query in Help articles search

Search Results (1 to 5 of 5 Results)

Download search results: CSV END BibTex RIS


Reference Hallucination Score for Medical Artificial Intelligence Chatbots: Development and Usability Study

Reference Hallucination Score for Medical Artificial Intelligence Chatbots: Development and Usability Study

Perplexity, Bing, and Chat GPT had no significant difference regarding their hallucination results for DOI, authors’ names, reference web links, and reference titles. Perplexity and Bing hallucinated significantly lesser than Chat GPT regarding the journal name. Perplexity hallucinated slightly lesser than Chat GPT regarding reference title. Bing had significantly fewer hallucination results for references’ irrelevancy to the prompt medical topic than Chat GPT (P=.045).

Fadi Aljamaan, Mohamad-Hani Temsah, Ibraheem Altamimi, Ayman Al-Eyadhy, Amr Jamal, Khalid Alhasan, Tamer A Mesallam, Mohamed Farahat, Khalid H Malki

JMIR Med Inform 2024;12:e54345

Search Engines and Generative Artificial Intelligence Integration: Public Health Risks and Recommendations to Safeguard Consumers Online

Search Engines and Generative Artificial Intelligence Integration: Public Health Risks and Recommendations to Safeguard Consumers Online

Specifically, 13.23% (18/136) of Google SGE’s responses and 19.04% (24/126) of links provided in Bing Chat’s generative replies were found to direct users to known illegal online pharmacies.

Amir Reza Ashraf, Tim Ken Mackey, András Fittler

JMIR Public Health Surveill 2024;10:e53086

Beyond the Hype—The Actual Role and Risks of AI in Today’s Medical Practice: Comparative-Approach Study

Beyond the Hype—The Actual Role and Risks of AI in Today’s Medical Practice: Comparative-Approach Study

The Microsoft Bing AI chatbot [7] is an intelligent conversational agent developed by Microsoft Corporation, designed to assist users in navigating the Microsoft Bing search engine and answering various queries. Leveraging AI, natural language processing, and machine learning, the Microsoft Bing AI chatbot understands user inputs and provides relevant information or search results accordingly.

Steffan Hansen, Carl Joakim Brandt, Jens Søndergaard

JMIR AI 2024;3:e49082

Identifying Sleep Disorders From Search Engine Activity: Combining User-Generated Data With a Clinically Validated Questionnaire

Identifying Sleep Disorders From Search Engine Activity: Combining User-Generated Data With a Clinically Validated Questionnaire

We advertised on Microsoft Advertising to US-based users of Bing who queried for one of a range of sleep disorder–related terms (see Multimedia Appendix 1); those people were shown 1 of 12 advertisements, which are listed in Multimedia Appendix 2. People who clicked on the advertisements were referred to a dedicated landing page. The web page described the experiment to potential participants.

Mairav Cohen Zion, Iddo Gescheit, Nir Levy, Elad Yom-Tov

J Med Internet Res 2022;24(11):e41288

The Role of Information Boxes in Search Engine Results for Symptom Searches: Analysis of Archival Data

The Role of Information Boxes in Search Engine Results for Symptom Searches: Analysis of Archival Data

Health information boxes (info boxes), also known as health knowledge graph boxes, information cards, or task panes, were created at major search engines about 10 years ago—at Bing in 2010 and at Google in 2012 [6]. They were developed to address health information gaps and misinformation for commonly searched symptoms that might arise from search results alone [4].

Lorien C Abroms, Elad Yom-Tov

JMIR Infodemiology 2022;2(2):e37286