Background: ChatGPT may act as a research assistant to help organize the direction of thinking and summarize research findings. However, few studies have examined the quality, similarity (abstracts being similar to the original one), and accuracy of the abstracts generated by ChatGPT when researchers provide full-text basic research papers. Objective: We aimed to assess the applicability of an artificial intelligence (AI) model in generating abstracts for basic preclinical research. Methods: We selected 30 basic research papers from Nature, Genome Biology, and Biological Psychiatry. Excluding abstracts, we inputted the full text into ChatPDF, an application of a language model based on ChatGPT, and we prompted it to generate abstracts with the same style as used in the original papers. A total of 8 experts were invited to evaluate the quality of these abstracts (based on a Likert scale of 0-10) and identify which abstracts were generated by ChatPDF, using a blind approach. These abstracts were also evaluated for their similarity to the original abstracts and the accuracy of the AI content. Results: The quality of ChatGPT-generated abstracts was lower than that of the actual abstracts (10-point Likert scale: mean 4.72, SD 2.09 vs mean 8.09, SD 1.03; P<.001). The difference in quality was significant in the unstructured format (mean difference –4.33; 95% CI –4.79 to –3.86; P<.001) but minimal in the 4-subheading structured format (mean difference –2.33; 95% CI –2.79 to –1.86). Among the 30 ChatGPT-generated abstracts, 3 showed wrong conclusions, and 10 were identified as AI content. The mean percentage of similarity between the original and the generated abstracts was not high (2.10%-4.40%). The blinded reviewers achieved a 93% (224/240) accuracy rate in guessing which abstracts were written using ChatGPT. Conclusions: Using ChatGPT to generate a scientific abstract may not lead to issues of similarity when using real full texts written by humans. However, the quality of the ChatGPT-generated abstracts was suboptimal, and their accuracy was not 100%.

PURPOSE: Evidence suggests an increased long-term risk of major psychiatric disorders (MPDs) in childhood and adolescent cancer survivors (CACSs). However, definitive conclusions regarding such associations and whether such associations vary for different types of cancers remain unclear. METHODS: Using a nationwide data set from 2001 to 2011, we enrolled CACSs and likewise randomly selected individuals without cancer from the general population (1:10 ratio) who were matched to the CACSs with regard to demographic data. We investigated eight organ system–related cancers. The primary outcomes were the risks of seven MPD diagnoses: autism spectrum disorder (ASD), attention-deficit/hyperactivity disorder (ADHD), schizophrenia, bipolar disorder (BD), major depressive disorder (MDD), obsessive-compulsive disorder (OCD), and post-traumatic stress disorder. RESULTS: CACSs (n = 5,121; mean age = 9.08 years) showed increased risks of six MPD diagnoses than controls (n = 51,210), with results as follows (in descending order): ASD (hazard ratio [HR], 10.42; associated 95% CI, 4.58 to 23.69), ADHD (HR, 6.59; 95% CI, 4.91 to 8.86), BD (HR, 2.93; 95% CI, 1.26 to 6.80), MDD (HR, 1.88; 95% CI, 1.26 to 2.79), OCD (HR, 3.37; 95% CI, 1.33 to 8.52), and post-traumatic stress disorder (HR, 6.10; 95% CI, 1.46 to 25.54). CACSs also showed earlier ages at diagnoses of ADHD, schizophrenia, MDD, and OCD than controls. The risks of MPD diagnoses vary according to specific cancer types/categories. Brain cancer and lymphatic/hematopoietic tissue cancer were associated with the greatest number of MPD diagnoses (ie, each was associated with six diagnoses). In addition, ASD and ADHD were associated with most organ system–related cancers (ie, each was associated with five categories). CONCLUSION: We found that CACSs were at higher risks of MPD diagnoses than controls. Follow-up care should include psychosocial interventions focusing on early signs of mental health problems and early interventions in this high-risk group.

Limited evidence exists about suicide risk in persons with polycystic ovary syndrome (PCOS). To assess suicide risk in persons with PCOS, accounting for psychiatric comorbid conditions and age group. Cohort study. Data from the Taiwanese nationwide database from 1997 to 2012. A cohort of 18 960 patients diagnosed with PCOS, each matched with control participants in a 1:10 ratio on the basis of age, psychiatric comorbid conditions, urbanization level, and income. Suicide attempts were evaluated using Cox regression models. Suicide risk with hazard ratios (HRs). Participants with PCOS had a notable 8.47-fold increase in risk for suicide attempt compared with the control group (HR, 8.47 [95% CI, 7.54 to 9.51]), after adjustment for demographic characteristics, psychiatric comorbid conditions, Charlson Comorbidity Index scores, and frequency of all-cause clinical visits. The elevated risk was evident across the adolescent (HR, 5.38 [CI, 3.93 to 7.37]), young adult (<40 years; HR, 9.15 [CI, 8.03 to 10.42]), and older adult (HR, 3.75 [CI, 2.23 to 6.28]) groups. Sensitivity analyses involving the exclusion of data from the first year or the first 3 years of observation yielded consistent results. Potential underestimation of PCOS and mental disorder prevalence due to use of administrative claims data; lack of clinical data, such as body mass index and depressive symptoms; and no assessment of a confounding effect of valproic acid exposure. This study underscores the heightened risk for suicide attempt that persons with PCOS face, even after adjustment for demographics, psychiatric comorbid conditions, physical conditions, and all-cause clinical visits. This suggests the importance of routine monitoring of mental health and suicide risk in persons diagnosed with PCOS. Taipei Veterans General Hospital, Yen Tjing Ling Medical Foundation, and Ministry of Science and Technology of Taiwan.