Survey and Evaluation of Hypertension Machine Learning Research.

Background Machine learning (ML) is pervasive in all fields of research, from automating tasks to complex decision-making. However, applications in different specialities are variable and generally limited. Like other conditions, the number of studies employing ML in hypertension research is growing rapidly. In this study, we aimed to survey hypertension research using ML, evaluate the reporting quality, and identify barriers to ML's potential to transform hypertension care. Methods and Results The Harmonious Understanding of Machine Learning Analytics Network survey questionnaire was applied to 63 hypertension-related ML research articles published between January 2019 and September 2021. The most common research topics were blood pressure prediction (38%), hypertension (22%), cardiovascular outcomes (6%), blood pressure variability (5%), treatment response (5%), and real-time blood pressure estimation (5%). The reporting quality of the articles was variable. Only 46% of articles described the study population or derivation cohort. Most articles (81%) reported at least 1 performance measure, but only 40% presented any measures of calibration. Compliance with ethics, patient privacy, and data security regulations were mentioned in 30 (48%) of the articles. Only 14% used geographically or temporally distinct validation data sets. Algorithmic bias was not addressed in any of the articles, with only 6 of them acknowledging risk of bias. Conclusions Recent ML research on hypertension is limited to exploratory research and has significant shortcomings in reporting quality, model validation, and algorithmic bias. Our analysis identifies areas for improvement that will help pave the way for the realization of the potential of ML in hypertension and facilitate its adoption.

Factors associated with length of stay following trans-catheter aortic valve replacement - a multicenter study.

BACKGROUND: Most patients undergoing Transcatheter aortic valve implantation (TAVR) are elderly with significant co-morbidities and there is limited information available regarding factors that influence length of stay (LOS) post-procedure. The aim of this study was to identify the patient, and procedural factors that affect post-TAVR LOS using a contemporary multinational registry. METHODS: We conducted a retrospective cohort study, with patients recruited from three high volume tertiary institutions. The primary outcome was the LOS post-TAVR procedure. We examined patient and procedural factors in a cause-specific Cox multivariable regression model to elucidate their effect on LOS, accounting for the competing risk of post-procedural death. Hazard ratios (HR) greater than 1 indicate a shorter LOS, while HRs less than 1 indicate a longer LOS. RESULTS: The cohort consisted of 809 patients. Patient factors associated with longer LOS were older age, prior atrial fibrillation, and greater patient urgency. Patient factors associated with shorter LOS were lower NYHA class, higher ejection fraction and higher mean aortic valve gradients. Procedural characteristics associated with shorter LOS were conscious sedation (HR = 1.19, 95% CI 1.06-1.35, p = 0.004). Transapical access was associated with prolonged LOS (HR = 0.49, 95% CI 0.41-0.58, p < 0.001). CONCLUSION: This multicenter study identified potentially modifiable patient and procedural factors associated with a prolonged LOS. Future research is needed to determine if interventions focused on these factors will translate to a shorter LOS.