Habib, Robert

Background This study evaluated the role of supplementing Society of Thoracic Surgeons (STS) risk models for surgical aortic valve replacement with machine learning (ML). Methods and Results Adults undergoing isolated surgical aortic valve replacement in the STS National Database between 2007 and 2017 were included. ML models for operative mortality and major morbidity were previously developed using extreme gradient boosting. Concordance and discordance in predicted risk between ML and STS models were defined using equal‐size tertile‐based thresholds of risk. Calibration metrics and discriminatory capability were compared between concordant and discordant patients. A total of 243 142 patients were included. Nearly all calibration metrics were improved in cases of concordance. Similarly, concordance indices improved substantially in cases of concordance for all models with the exception of deep sternal wound infection. The greatest improvements in concordant versus discordant cases were in renal failure: ML model (concordance index, 0.660 [95% CI, 0.632–0.687] discordant versus 0.808 [95% CI, 0.794–0.822] concordant) and STS model (concordance index, 0.573 [95% CI, 0.549–0.576] discordant versus 0.797 [95% CI, 0.782–0.811] concordant) (each P <0.001). Excluding deep sternal wound infection, the concordance indices ranged from 0.549 to 0.660 for discordant cases and 0.674 to 0.808 for concordant cases. Conclusions Supplementing ML models with existing STS models for surgical aortic valve replacement may have an important role in risk prediction and should be explored further. In particular, for the roughly 25% to 50% of patients demonstrating discordance in estimated risk between ML and STS, there appears to be a substantial decline in predictive performance suggesting vulnerability of the existing models in these patient subsets.

Abstract Context Guidelines for the dosage of vitamin D supplementation vary widely globally. Objective To investigate the impact of 2 vitamin D doses, bracketed between the IOM recommended dietary allowance (RDA) and the upper tolerable limit, on vitamin D nutritional status in elderly individuals. Methods This post hoc analysis of data collected from a 12-month, double-blind, randomized control trial included 221 ambulatory participants (≥ 65 years) with a mean BMI of 30.2 kg/m2 and a mean baseline serum 25-hydroxyvitamin D [25(OH)D] level of 20.4 ± 7.4 ng/mL, who were recruited from 3 outpatient centers in Lebanon. All participants received 1000 mg of elemental calcium daily from calcium citrate plus the daily equivalent of either 600 IU or 3750 IU of vitamin D3. Results Mean 25(OH)D level at 12 months was 26.0 ng/mL with low dose and 36.0 ng/mL with high dose vitamin D3. The proportion of participants reaching a value ≥ 20 ng/mL was 86% in the low dose, and 99% in the high dose arms, with no gender differences. The increment of 25(OH)D per 100 IU/day was 1 ng/mL with the low dose, and 0.41 ng/mL with the high dose. Serum 25(OH)D levels at 1 year were highly variable in both treatment arms. Baseline 25(OH)D level and vitamin D dose—but not age, BMI, gender, or season—were significant predictors of serum 25(OH)D level post-intervention. Conclusion The IOM Recommended Dietary Allowance (RDA) of 600 IU/day does not bring 97.5% of ambulatory elderly individuals above the desirable threshold of 20 ng/mL. Country-specific RDAs are best derived taking into account the observed variability and predictors of achieved 25(OH)D levels.