ChatGPT has been a popular natural language processing tool driven by AI that has been used in recent months by the public for a variety of different tasks, including generating images, text and even writing code.
Recently, one mother decided to use ChatGPT to figure out answers to her child’s health issues, having unsuccessfully visited 17 doctors. The mother’s four-year-old child had been struggling with a persistent toothache and stunted growth. The three-year-long medical mystery finally reached a turning point when ChatGPT aided in diagnosing the medical ailment.
The mystery for the child, Alex, and his mother, Courtney, began during the height of the COVID-19 pandemic when Alex had discomfort when chewing. His mother sought medical help, but despite numerous hospital visits and an emergency room visit, the mystery of the ailment remained. In addition to the toothache, Alex’s growth rate had slowed.
Doctors thought that it was perhaps a lingering effect of COVID-19, but the situation remained unresolved. After 17 doctors' visits and no final diagnosis, Courtney turned to ChatGPT, sharing Alex’s symptoms with the AI tool in hope of attaining a diagnosis. What ChatGPT suggested was a rare neurological condition known as tethered cord syndrome.
Courtney then joined a Facebook group for parents whose children struggled with the rare condition and examined Alex’s MRI notes to cross reference them with ChatGPT’s guidance. After one detail caught her attention that indicated a structural issue – Courtney arranged an appointment with a neurosurgeon who eventually confirmed Alex’s diagnosis.
ChatGPT as a diagnostic tool
While ChatGPT making a rare diagnosis may seem like a rare happenstance, it is more of an indication of the possibilities that AI tools can provide in healthcare.
A recently published research paper in the Annals of Emergency Medicine journal found that an AI chatbot diagnosed patients and also trained doctors. The researchers at Jeroen Bosch Hospital in The Netherlands entered physicians’ notes and anonymized information for about 30 patients, including examination results, symptoms and lab results into two versions of ChatGPT.
“We found that ChatGPT performed well in generating a list of likely diagnoses and suggesting the most likely option,” said study author Dr Hidde ten Berg, from the emergency medicine department at Jeroen Bosch Hospital, in a statement.
It’s important to note that the research is viewed as a proof of concept by the researchers and was not used to impact patients. It was instead used to test the feasibility of using generative AI for diagnosis.
HCLTech’s healthcare solutions
HCLTech has focused on three main areas for its life sciences and healthcare practices: enhancing consumer experience, improving care delivery and generating value across the enterprise with cutting-edge technologies like AI, data and analytics and IoT.
HCLTech has helped clients develop GenAI-based tools using large language models to understand patient queries and used AI to help streamline the premedical questionnaire process for a client. HCLTech understands the importance and benefits AI can provide in the health IT field, creating new opportunities for caregivers, hospitals, medical device providers, doctors and more.