ChatGPT Uses Human-Like Medical Diagnosis Abilities for Patients
LAHORE MIRROR — Dutch researchers have discovered that an artificial intelligence chatbot called ChatGPT can diagnose emergency patients at least as effectively as doctors, and in some instances, it even surpasses their diagnostic abilities.
This breakthrough suggests that AI has the potential to bring about a significant transformation in the field of medicine.
However, it’s important to note that the report published on Wednesday emphasizes that emergency room (ER) doctors should not hang up their scrubs just yet. While the chatbot can expedite the diagnostic process, it cannot replace the critical elements of human medical judgment and experience.
In a study conducted in the Netherlands in 2022, scientists examined 30 cases treated in an emergency service. They input anonymized patient histories, laboratory test results, and the observations made by doctors into ChatGPT. Subsequently, they asked the chatbot to provide five possible diagnoses.
This research showcases the potential of AI to enhance the efficiency of medical diagnosis in emergency situations. However, it underscores the indispensable role of human medical professionals in providing comprehensive care and making crucial decisions in the medical field.
They then compared the chatbot’s shortlist to the same five diagnoses suggested by ER doctors with access to the same information, then cross-checked with the correct diagnosis in each case.
Doctors had the correct diagnosis in the top five in 87 per cent of cases, compared to 97pc for ChatGPT version 3.5 and 87pc for version 4.0.
“Simply put, this indicates that ChatGPT was able to suggest medical diagnoses much like a human doctor would,” said Hidde ten Berg, from the emergency medicine department at the Netherlands’ Jeroen Bosch Hospital.
Co-author Steef Kurstjens said the survey did not indicate that computers could one day be running the ER, but that AI can play a vital role in assisting under-pressure medics.
Source: AFP