Machine Learning-Based Risk Model for Predicting Early Mortality After Surgery for Infective Endocarditis.

Background The early mortality after surgery for infective endocarditis is high. Although risk models help identify patients at high risk, most current scoring systems are inaccurate or inconvenient. The objective of this study was to construct an accurate and easy-to-use prediction model to identify patients at high risk of early mortality after surgery for infective endocarditis. Methods and Results A total of 476 consecutive patients with infective endocarditis who underwent surgery at 2 centers were included. The development cohort consisted of 276 patients. Eight variables were selected from 89 potential predictors as input of the XGBoost model to train the prediction model, including platelet count, serum albumin, current heart failure, urine occult blood ≥(++), diastolic dysfunction, multiple valve involvement, tricuspid valve involvement, and vegetation >10 mm. The completed prediction model was tested in 2 separate cohorts for internal and external validation. The internal test cohort consisted of 125 patients independent of the development cohort, and the external test cohort consisted of 75 patients from another center. In the internal test cohort, the area under the curve was 0.813 (95% CI, 0.670-0.933) and in the external test cohort the area under the curve was 0.812 (95% CI, 0.606-0.956). The area under the curve was significantly higher than that of other ensemble learning models, logistic regression model, and European System for Cardiac Operative Risk Evaluation II (all, P<0.01). This model was used to develop an online, open-access calculator (http://42.240.140.58:1808/). Conclusions We constructed and validated an accurate and robust machine learning-based risk model to predict early mortality after surgery for infective endocarditis, which may help clinical decision-making and improve outcomes.

Belumosudil, ROCK2-specific inhibitor, alleviates cardiac fibrosis by inhibiting cardiac fibroblasts activation.

Cardiac fibrosis is thought to be the hallmark of pathological hypertrophic remodeling, of which the myofibroblast transdifferentiation is the key cell biological event. However, there is still no specific and effective therapeutic agent approved for cardiac fibrosis. To investigate the effects of belumosudil, the first ρ-associated kinase-2 (ROCK2)-specific inhibitor, on cardiac hypertrophy, fibrosis, and dysfunction induced by pressure overload, the transverse aortic constriction (TAC) or sham operation was carried out on wild-type C57BL/6 mice (male, 6-8 wk old) under pentobarbital anesthesia. After that, mice were randomly divided into three groups: sham operation + vehicle, TAC + vehicle, TAC + 50 mg·kg-1·day-1 belumosudil. We found that belumosudil effectively ameliorated cardiac hypertrophy, fibrosis, and dysfunction in TAC mice. To elucidate the underlying mechanism, we inhibited the expression of ROCK2 in vitro by either belumosudil or siRNA. We showed that the inhibition of ROCK2 by either belumosudil or knockdown suppressed cardiac fibroblasts activation and proliferation significantly induced by transforming growth factor-ß1 (TGF-ß1). Furthermore, our study confirmed ROCK2 mediates cardiac fibrosis by interacting with TGF-ß1/mothers against decapentaplegic homolog 2 (Smad2) pathway. Taken together, we demonstrated that belumosudil ameliorates cardiac hypertrophy and fibrosis induced by TAC via inhibiting cardiac fibroblasts activation. In conclusion, belumosudil may be a promising therapeutic drug for cardiac hypertrophy and fibrosis induced by myocardial pressure overload.NEW & NOTEWORTHY Although ρ-associated kinase-2 (ROCK2) is the main isoform of ρ-associated kinases (ROCKs) in the heart and more important in cardiac hypertrophy and fibrosis than ρ-associated kinase-1 (ROCK1), there has not been any pharmacological approach to inhibit ROCK2 selectively. Our study demonstrates for the first time that belumosudil, the first ROCK2-specific inhibitor, effectively ameliorates cardiac hypertrophy, fibrosis, and dysfunction induced by TAC via inhibiting cardiac fibroblasts activation.