Aso S. Muhialdeen, Shorsh A. Mohammed, Nahida Hama Ameen Ahmed, Shaho F. Ahmed, Wriya N. Hassan, Hoshmand R. Asaad, Dana T. Gharib, Huda M. Muhammad and 13 more
Introduction The introduction of Artificial Intelligence (AI) tools like ChatGPT and Google Bard promises transformative advances in clinical diagnostics. The aim of this study is to examine the ability of these two AI tools to diagnose various medical scenarios. Methods Experts from varied medical domains curated 20…
Artificial Intelligence in Medicine: A Comparative Study of ChatGPT and Google Bard in Clinical Diagnostics
Aso S. Muhialdeen, Shorsh A. Mohammed, Nahida Hama Ameen Ahmed, Shaho F. Ahmed, Wriya N. Hassan, Hoshmand R. Asaad, Dana T. Gharib, Huda M. Muhammad and 13 more
IntroductionThe introduction of Artificial Intelligence (AI) tools like ChatGPT and Google Bard promises transformative advances in clinical diagnostics. The aim of this study is to examine the ability of these two AI tools to diagnose various medical scenarios.
MethodsExperts from varied medical domains curated 20 case scenarios, each paired with its ideal diagnostic answer. Both AI systems, ChatGPT (updated in September 2021) and Google Bard (updated in January 2023), were tasked with diagnosing these cases. Their outcomes were recorded and subsequently assessed by human medical professionals.
ResultsIn the diagnostic evaluations, ChatGPT achieved an accuracy of 90%, correctly diagnosing 18 out of 20 cases, while Google Bard displayed an 80% accuracy rate, correctly answering 16 questions. Notably, both AIs faltered in specific complex scenarios. For instance, both systems misdiagnosed a labor situation, and while ChatGPT incorrectly identified a case of hypertrophic pyloric stenosis, Google Bard suggested a less suitable diagnostic procedure (pelvic ultrasound) for a 56-year-old patient.
ConclusionThis study showcases the promising capabilities of ChatGPT and Google Bard in the realm of clinical diagnostics, with both AI tools achieving commendable accuracy rates.
Ameer M. Salih, Nashaddin A. Mohammed, Yousif M. Mahmood, Sabah J. Hassan, Hiwa S. Namiq, Abdullah K. Ghafour, Saywan K. Asaad, Suhaib H. Kakamad and 7 more
Introduction There are several controversies regarding thoracic outlet syndrome. This manuscript evaluates the utility of ChatGPT in providing insights into the controversies surrounding neurogenic thoracic outlet syndrome (nTOS). Methods The following questions were chatted with ChatGPT based on OpenAI's GPT-4…
ChatGPT Insight and Opinion Regarding the Controversies in Neurogenic Thoracic Outlet Syndrome: A Case-Based Study
Ameer M. Salih, Nashaddin A. Mohammed, Yousif M. Mahmood, Sabah J. Hassan, Hiwa S. Namiq, Abdullah K. Ghafour, Saywan K. Asaad, Suhaib H. Kakamad and 7 more
IntroductionThere are several controversies regarding thoracic outlet syndrome. This manuscript evaluates the utility of ChatGPT in providing insights into the controversies surrounding neurogenic thoracic outlet syndrome (nTOS).
MethodsThe following questions were chatted with ChatGPT based on OpenAI's GPT-4 architecture, which was last updated in September 2021. What is your opinion regarding the psychological abnormalities in patients with nTOS? What is your opinion about the role of duplex ultrasound in the diagnosis of nTOS? In your opinion, which one is preferred? First rib resection or only scalenectomy for the surgical management of nTOS?
ResultsChatGPT was accurate in addressing the psychiatric disorders associated with nTOS and the outcome of different types of surgical intervention while it failed to highlight the role of duplex scanning in this disease apart from ruling out another differential diagnosis.
ConclusionWhile ChatGPT offers valuable insights, it should be noted that its last update was in September 2021. Hence, some newer developments in the field may not be addressed. Nonetheless, a comprehensive approach to understanding and managing nTOS, combining both clinical expertise and technological advancements, is vital for the well-being of patients.
