Effect of Whey Protein Supplementation in Postmenopausal Women: A Systematic Review and Meta-Analysis.

(1) Background: Whey protein (WP) in combination with resistance training (RT) is beneficial in improving sarcopenic obesity and its damaging effects in older adults, while the difference between men and women should be considered while interpreting results. This review aims to investigate WP's efficacy on postmenopausal women with or without RT; (2) Material and Methods: We searched electronic databases including PubMed, EMBASE, and the Cochrane Library from inception to August 2021 for randomized controlled trials that included comparison groups to evaluate WP's efficacy in women aged 55 years and above. The outcomes included body composition, muscular strength, functional capacity, and dietary intake. Standardized mean differences (SMDs) with 95% confidence intervals (CIs) were used to estimate the effect of WP. We also performed subgroup analysis with or without RT; (3) Results: We included 14 studies in the systematic review and 10 studies in the meta-analysis. Subgroup analyses showed RT was a major confounder for muscle strength, lean mass, and dietary protein intake (PI). In the RT subgroup, WP supplementation had a significant positive effect on biceps curl strength (BC) (SMD: 0.6805, 95% CI: 0.176, 1.185, I2: 0%), and lower limb lean-mass (LLLM) (SMD: 1.103, 95% CI: 0.632, 1.574, I2: 14%). In the subgroup without RT, a significant negative effect on PI (SMD: -0.4225, 95% CI: -0.774, -0.071, I2: 47%) was observed, while no significant effect on muscle strength or lean mass was revealed. WP supplementation did not show a significantly different effect on fat mass or body weight loss in both the subgroups; (4) Conclusions: In postmenopausal women, WP supplementation only in combination with RT enhances BC and LLLM compared to placebo controls. Without RT, WP has no significant benefit on muscle strength or lean mass.

Applying artificial neural network for early detection of sepsis with intentionally preserved highly missing real-world data for simulating clinical situation.

PURPOSE: Some predictive systems using machine learning models have been developed to predict sepsis; however, they were mostly built with a low percent of missing values, which does not correspond with the actual clinical situation. In this study, we developed a machine learning model with a high rate of missing and erroneous data to enable prediction under missing, noisy, and erroneous inputs, as in the actual clinical situation. MATERIALS AND METHODS: The proposed artificial neural network model was implemented using the MATLAB ANN toolbox, based on stochastic gradient descent. The dataset was collected over the past decade with approval from the appropriate institutional review boards, and the sepsis status was identified and labeled using Sepsis-3 clinical criteria. The imputation method was built by last observation carried forward and mean value, aimed to simulate clinical situation. RESULTS: The mean area under the receiver operating characteristic (ROC) curve (AUC) of classifying sepsis and nonsepsis patients was 0.82 and 0.786 at 0 h and 40 h prior to onset, respectively. The highest model performance was found for one-hourly data, demonstrating that our ANN model can perform adequately with limited hourly data provided. CONCLUSIONS: Our model has the moderate ability to predict sepsis up to 40 h in advance under simulated clinical situation with real-world data.