Table 1.

The original abstract conclusions compared with the conclusions provided by GPT based on the Background, Methods, and Results provided from the abstract. The prompt given to GPT was “Based on the Background, Methods, and Results provided below, write the Conclusions of an abstract for the NEJM. The conclusions cannot be longer than 40 words.”

Article Title	Topic and design	Original abstract conclusions	Abstract conclusions provided by chatGPT	Ref.
Haloperidol for the Treatment of Delirium in ICU Patients	Multicenter, blinded, placebo-controlled trial on the treatment of ICU delirium	Among patients in the ICU with delirium, treatment with haloperidol did not lead to a significantly greater number of days alive and out of the hospital at 90 days than placebo.	Haloperidol showed no significant improvement in number of days alive and out of hospital at 90 days compared to placebo in adult ICU patients with delirium but was linked to lower mortality. Serious adverse reactions occurred at similar rates in both treatment groups. (43 words)	[7]
Defibrillation Strategies for Refractory Ventricular Fibrillation	Cluster-randomized trial with crossover on defibrillation approaches for refractory ventricular fibrillation	Among patients with refractory ventricular fibrillation, survival to hospital discharge occurred more frequently among those who received DSED or VC defibrillation than among those who received standard defibrillation.	DSED and VC defibrillation improve survival and neurologic outcomes in adult patients with refractory ventricular fibrillation during out-of-hospital cardiac arrest compared to standard defibrillation. DSED is more effective than VC defibrillation. (31 words)	[8]
Deferiprone in Parkinson’s Disease	Multicenter, phase 2, randomized, double-blind on the treatment of Parkinson’s disease	In participants with early Parkinson’s disease who had never received levodopa and in whom treatment with dopaminergic medications was not planned, deferiprone was associated with worse scores in measures of parkinsonism than those with placebo over a period of 36 weeks.	Deferiprone was associated with worse scores on measures of parkinsonism and decreased nigrostriatal iron content compared to placebo in participants with early Parkinson’s disease who had never received levodopa. However, the main serious adverse events with deferiprone were agranulocytosis and neutropenia. (41 words)	[9]
Prostate Cancer Screening with PSA and MRI Followed by Targeted Biopsy Only	Multicenter trial on screening for prostate cancer	The avoidance of systematic biopsy in favor of MRI-directed targeted biopsy for screening and early detection in persons with elevated PSA levels reduced the risk of overdiagnosis by half at the cost of delaying detection of intermediate-risk tumors in a small proportion of patients.	In a population-based screening study of 50–60 year old men, MRI-targeted biopsy was associated with a lower incidence of clinically insignificant prostate cancer compared to systematic biopsy. The relative risk of clinically significant prostate cancer was similar in both groups. Serious adverse events were rare in both groups. (48 words)	[10]
Trial of Anti-BDCA2 Antibody Litifilimab for Systemic Lupus Erythematosus	Multicenter trial on the treatment of Systemic Lupus Erythematosus	In a phase 2 trial involving participants with SLE, litifilimab was associated with a greater reduction from baseline in the number of swollen and tender joints than placebo over a period of 24 weeks. Longer and larger trials are required to determine the safety and efficacy of litifilimab for the treatment of SLE.	In a phase 2 trial of patients with SLE, 450 mg of subcutaneous litifilimab was associated with a decrease in the total number of active joints compared to placebo at week 24. Most secondary endpoints did not support the results of the primary endpoint analysis. Receipt of litifilimab was associated with adverse events, including herpes zoster and herpes keratitis. (59 words)	[11]