Welcome to the forefront of conversational AI as we explore the fascinating world of AI chatbots in our dedicated blog series. Discover the latest advancements, applications, and strategies that propel the evolution of chatbot technology. From enhancing customer interactions to streamlining business processes, these articles delve into the innovative ways artificial intelligence is shaping the landscape of automated conversational agents. Whether you’re a business owner, developer, or simply intrigued by the future of interactive technology, join us on this journey to unravel the transformative power and endless possibilities of AI chatbots.
by
Gloria Leung
AI chatbots' differential diagnostic failure rate reaches 80 percent due to incomplete data, including in ChatGPT, DeepSeek, Gemini, and Claude, according to Harvard Medical School research.
A study evaluated over 20 state-of-the-art AI large language models and found that errors occurred in differential diagnoses based solely on the patient’s initial symptoms and signs.
The research further showed that when patients provided additional test results, the final diagnosis failure rate fell to around 40 percent.
Researchers noted that AI chatbots require sufficiently detailed patient information to deliver more accurate diagnoses; therefore, when patients cannot provide thorough health data, the results generated by AI are deemed to be unreliable.
They also emphasized that using AI to make diagnostic decisions without medical professionals’ intervention is premature.
Download The Standard app to stay informed with news, updates, and significant events:
https://www.thestandard.com.hk/appdownload
