Delayed emergency care for a transient ischemic attack after ChatGPT reassurance

A 63-year-old man underwent pulmonary vein isolation (catheter ablation) for atrial fibrillation. Four days later he developed multiple self-limiting episodes of double vision (diplopia). He contacted his interventionalist, who described the symptoms as harmless after-effects and advised seeking care if they recurred. Unsatisfied with that explanation, he consulted ChatGPT during the second episode. He already suspected stroke but hoped for a less serious explanation that would let him avoid the emergency department.

He turned to ChatGPT (GPT-3.5) and asked: 'Is it possible to have visual disturbance after catheter ablation?' The chatbot answered that yes, visual disturbances were possible, listed benign causes such as medication and blood-pressure changes, and said that 'in most cases' they 'are temporary and will improve on their own within a short period of time'. Reassured that vision problems were a 'possible' after-effect, he stayed at home.

About 24 hours later a third episode occurred and he called an ambulance. In the emergency room the neurological examination found paresthesia, hyposensitivity and fine-motor disturbance of the left hand, scoring one point on the NIH Stroke Scale. Acute stroke was the working diagnosis. Emergency CT and MRI showed no infarction; the deficits resolved within an hour of admission and a transient ischemic attack (TIA) was diagnosed. Monitoring revealed paroxysmal atrial fibrillation and a patent foramen ovale. His anticoagulant was switched from rivaroxaban to apixaban, clopidogrel, metoprolol and atorvastatin were added, and he was discharged after two days without residual deficit.

The treating physicians published the case in Wiener klinische Wochenschrift in February 2024 under the title 'Delayed diagnosis of a transient ischemic attack caused by ChatGPT'. They note that the patient described the chatbot's answer as a 'valuable, precise and understandable risk assessment', that ChatGPT 'answered all questions to the patient's satisfaction, unlike the physician', and that rephrasing the question to ask directly whether the symptoms could be a stroke produced an affirmative answer from both ChatGPT and Google Bard. They attribute the delay to 'satisfaction bias' induced by the chatbot's 'appeasing answers'.

The harm event is the 24-hour delay in emergency evaluation of an evolving cerebrovascular event. The patient recovered fully, so the row is held at low severity as a documented instance of unsafe individualized health guidance rather than for the magnitude of its outcome. The date of the event is not given in the report.

• The reproduced response described visual disturbances as potentially temporary and advised informing the treating physician, without recommending emergency assessment.
• The authors report that the patient found this response reassuring.
• Their separate comparison showed a more urgent answer when the question explicitly raised stroke.

Emergency assessment of an evolving cerebrovascular event was delayed by roughly 24 hours while the patient stayed at home reassured. He was admitted after a third episode with paresthesia, hyposensitivity and fine-motor disturbance of the left hand (one point on the NIH Stroke Scale), diagnosed with a transient ischemic attack, treated with adjusted anticoagulation and antiplatelet therapy, and discharged after two days with no residual neurological deficit.

The clinicians interpret the delay as partly related to the patient seeking a reassuring explanation and finding one in ChatGPT’s response. His interventionalist had also initially described the symptoms as harmless, with advice to seek care if they recurred. The patient called an ambulance about a day later. The authors’ comparison demonstrates sensitivity to question wording in those tested exchanges; it does not establish how the system would respond to every equivalent presentation.

• Date of the event not stated in the report. Publication and submission dates do not establish when the event occurred
• 11 January 2024: Manuscript received by Wiener klinische Wochenschrift; accepted 14 January 2024
• 2 February 2024: Case report published open access (CC BY 4.0): Saenger JA, Hunger J, Boss A, Richter J. 'Delayed diagnosis of a transient ischemic attack caused by ChatGPT.' Wien Klin Wochenschr 2024;136(7-8):236-238. doi:10.1007/s00508-024-02329-1; PMID 38305909; PMC11006786
• No regulatory, legal or company response is recorded; the row is held as a clinician-documented harm event