Background: Privacy restrictions limit access to protected patient-derived health information for research purposes. Consequently, data anonymization is required to allow researchers data access for initial analysis before granting institutional review board approval. A system installed and activated at our institution enables synthetic data generation that mimics data from real electronic medical records, wherein only fictitious patients are listed. Objective: This paper aimed to validate the results obtained when analyzing synthetic structured data for medical research. A comprehensive validation process concerning meaningful clinical questions and various types of data was conducted to assess the accuracy and precision of statistical estimates derived from synthetic patient data. Methods: A cross-hospital project was conducted to validate results obtained from synthetic data produced for five contemporary studies on various topics. For each study, results derived from synthetic data were compared with those based on real data. In addition, repeatedly generated synthetic datasets were used to estimate the bias and stability of results obtained from synthetic data. Results: This study demonstrated that results derived from synthetic data were predictive of results from real data. When the number of patients was large relative to the number of variables used, highly accurate and strongly consistent results were observed between synthetic and real data. For studies based on smaller populations that accounted for confounders and modifiers by multivariate models, predictions were of moderate accuracy, yet clear trends were correctly observed. Conclusions: The use of synthetic structured data provides a close estimate to real data results and is thus a powerful tool in shaping research hypotheses and accessing estimated analyses, without risking patient privacy. Synthetic data enable broad access to data (eg, for out-of-organization researchers), and rapid, safe, and repeatable analysis of data in hospitals or other health organizations where patient privacy is a primary value.

Objective Anti-drug antibodies (ADA) to anti-tumour necrosis factor (anti-TNF) therapy drive treatment loss of response. An association between intestinal microbial composition and response to anti-TNF therapy was noted. We therefore aimed to assess the implications of antibiotic treatments on ADA formation in patients with inflammatory bowel disease (IBD). Design We analysed data from the epi-IIRN (epidemiology group of the Israeli IBD research nucleus), a nationwide registry of all patients with IBD in Israel. We included all patients treated with anti-TNF who had available ADA levels. Survival analysis with drug use as time varying covariates were used to assess the association between antibiotic use and ADA development. Next, specific pathogen and germ-free C57BL mice were treated with respective antibiotics and challenged with infliximab. ADA were assessed after 14 days. Results Among 1946 eligible patients, with a median follow-up of 651 days from initiation of therapy, 363 had positive ADA. Cox proportional hazard model demonstrated an increased risk of ADA development in patients who used cephalosporins (HR=1.97, 95% CI 1.58 to 2.44), or penicillins with β-lactamase inhibitors (penicillin-BLI, HR=1.4, 95% CI 1.13 to 1.74), whereas a reduced risk was noted in patients treated with macrolides (HR=0.38, 95% CI 0.16 to 0.86) or fluoroquinolones (HR=0.20, 95% CI 0.12 to 0.35). In mice exposed to infliximab, significantly increased ADA production was observed in cephalosporin as compared with macrolide pretreated mice. Germ-free mice produced no ADA. Conclusion ADA production is associated with the microbial composition. The risk of ADA development during anti-TNF therapy can possibly be reduced by avoidance of cephalosporins and penicillin-BLIs, or by treatment with fluoroquinolones or macrolides.

Background and study aims Rising prevalence of pancreatic cysts and inconsistent management guidelines necessitate innovative approaches. New features of large language models (LLMs), namely custom GPT creation, provided by ChatGPT can be utilized to integrate multiple guidelines and settle inconsistencies. Methods A custom GPT was developed to provide guideline-based management advice for pancreatic cysts. Sixty clinical scenarios were evaluated by both the custom GPT and gastroenterology experts. A consensus was reached between experts and review of guidelines and the accuracy of recommendations provided by the custom GPT was evaluated and compared with experts. Results The custom GPT aligned with expert recommendations in 87% of scenarios. Initial expert recommendations were correct in 97% and 87% of cases, respectively. No significant difference was observed between the accuracy of custom GPT and the experts. Agreement analysis using Cohen's and Fleiss' Kappa coefficients indicated consistency among experts and the custom GPT. Conclusions This proof-of-concept study shows the custom GPT's potential to provide accurate, guideline-based recommendations for pancreatic cyst management, comparable to expert opinions. The study highlights the role of advanced features of LLMs in enhancing clinical decision-making in fields with significant practice variability.

Background: Hyperglycemia is associated with adverse outcomes in hospitalized patients. We aimed to assess the impact of glucose levels upon admission on the subsequent deterioration or improvement of kidney function in inpatients with a focus on diabetes or reduced baseline kidney function as possible modifiers of this effect. Methods: Running a retrospective cohort analysis, we compared patients with normal vs. high glucose levels upon admission. We applied multivariable logistic regression models to study the association between baseline glucose levels with subsequent renal and clinical outcomes. Interaction terms were used to study a possible modifier effect of diabetes. Results: Among 95,556 inpatients (52% males, mean age 61 years), 15,675 (16.5%) had plasma glucose higher than 180 mg/dL, and 72% of them were diabetics. Patients with higher glucose at presentation were older, with a higher proportion of co-morbid conditions. Rates of acute kidney injury (AKI), acute kidney functional recovery (AKR), and mortality were proportional to reduced renal function. AKI, AKR, and mortality were almost doubled in patients with high baseline glucose upon admission. Multivariable analysis with interaction terms demonstrated an increasing adjusted probability of all events as glucose increased, yet this association was observed principally in non-diabetic patients. Conclusions: Hyperglycemia is associated with AKI, AKR, and mortality in non-diabetic inpatients in proportion to the severity of their acute illness. This association diminishes in diabetic patients, suggesting a possible impact of treatable and easily reversible renal derangement in this population.