Quality and accountability of Large Language Models (LLMs) in healthcare in low- and middle-income countries (LMIC) : a simulated patient study using ChatGPT

Using simulated patients to mimic nine established non-communicable and infectious diseases over 27 trials, we assess ChatGPT's effectiveness and reliability in diagnosing and treating common diseases in low- and middle-income countries. We find ChatGPT's performance varied within a single disease, despite a high level of accuracy in both correct diagnosis (74.1%) and medication prescription (84.5%). Additionally, ChatGPT recommended a concerning level of unnecessary or harmful medications (85.2%) even with correct diagnoses. Finally, ChatGPT performed better in managing non-communicable diseases compared to infectious ones. These results highlight the need for cautious AI integration in healthcare systems to ensure quality and safety.