Existing question answering (QA) datasets derived from electronic health records (EHR) are artificially generated and consequently fail to capture realistic physician information needs. We present Discharge Summary Clinical Questions (DiSCQ), a newly curated question dataset composed of 2,000+ questions paired with the snippets of text (triggers) that prompted each question. The questions are generated by medical experts from 100+ MIMIC-III discharge summaries. We analyze this dataset to characterize the types of information sought by medical experts. We also train baseline models for trigger detection and question generation (QG), paired with unsupervised answer retrieval over EHRs. Our baseline model is able to generate high quality questions in over 62% of cases when prompted with human selected triggers. We release this dataset (and all code to reproduce baseline model results) to facilitate further research into realistic clinical QA and QG. 1

Patients with acromegaly carry a high risk of developing cardiovascular diseases (CVD). In fact, CVD is the leading cause of mortality among this group of patients. The most frequent cardiovascular complications are heart failure (HF), valvular disease, hypertension, arrhythmias, and coronary artery disease (CAD). The pathophysiology centers on the family of growth hormone (GH). These hormones are involved in normal cardiac development and function; however, excess of insulin-like growth factor-1 (IGF-1), the principally active hormone, can also cause negative effects on the cardiovascular system. HF in acromegaly usually presents with biventricular enlargement and diastolic dysfunction and is strongly associated with the duration of GH excess rather than the degree of hormone elevation. There is a high prevalence of valvular disease affecting aortic and mitral valves among patients with longer disease duration. The development of hypertension in acromegaly may be attributed to the effects of chronic GH/IGF-1 excess on different organ systems, which act via several mechanisms. The aspect of arrhythmia and CAD complicating acromegaly are currently not fully understood.

Background: Randomized controlled trials (RCTs) of sodium-glucose transporter-2 inhibitors (SGLT-2is) have proven to be effective in decreasing major adverse cardiovascular events (MACE) in patients with heart failure. A recently published meta-analysis showed that the use of SGLT-2i among women with diabetes resulted in less reduction in MACE vs. men. This study aims to determine sex differences in MACE in patients with chronic heart failure. Methods: We systematically searched the medical database until April 30, 2022, and retrieved all the RCTs using SGLT-2is with specified CV outcomes. We used PRISMA, Preferred Reporting Items for a Review and Meta-analysis. We pooled the hazard ratio (HR) of MACE in both sexes, did a meta-analysis, and analyzed the odds ratio (OR) of MACE based on sex. Statistical analysis was completed with the use of Cochrane Review Manager (RevMan) version 5.4. Results of the pooled hazard ratio (HR) and the 95% confidence interval (CI) were made based on intention-to-treat analysis. Results: Figure 1 shows the results of the meta-analysis of 4 RCTs conducted with SGLT-2is (n=20725) vs. placebo. MACE was significantly lower in males and females taking SGLT-2is (men - HR 0.76; 95% CI 0.69 to 0.83; p=0.00001; women - HR 0.72; 95% CI 0.63 to 0.83; p=0.00001). Pooled data from three of the RCTs (n=7233) revealed a greater reduction in MACE in females vs. males (OR 1.32; 95% CI 1.14 to 1.53; p=0.0002). Conclusion: SGLT-2is reduce the risk of MACE in patients with heart failure, regardless of sex. However, the benefits were more pronounced in females, contrary to the meta-analysis of SGLT-2is in patients with diabetes. This finding may reflect an actual sex difference due to physiologic or behavioral factors or can be due to inadequate statistical power. More sex-based RCTs may help establish these sex differences in cardiovascular outcomes.