Winsorization greatly reduces false positives by popular differential expression methods when analyzing human population samples

Motor learning-based clinical pilates training for the Parkinson's disease rehabilitation @Parkinsonpilates: A parallel group, randomised controlled trial with 3-month follow-up

OBJECTIVES

To examine the effect of integrated motor learning clinical pilates protocol we developed for patients with Parkinson's Disease (pwPD) on providing enduring motor skills in walking, balance, reaction time, cadence, and functional mobility at 3-months follow-up.

DESIGN

A parallel-group, randomized controlled trial (RCT).

SETTING

XXX Medical Center, XXX, and XXX Physiotherapy and Rehabilitation Center, Nicosia.

PARTICIPANTS

32 pwPD with Hoehn&Yahr stages 2-3 were randomly assigned to the Parkinsonpilates Group (PP) and the Conventional Physiotherapy (CP) Group.

INTERVENTIONS

Both groups received 60 min of training, twice a week, and a home physiotherapy program 4 times a week, for 12 weeks. The intervention group received PP, while the CP group received general physiotherapy training for PD.

MAIN OUTCOME MEASURES

The primary outcomes were untimed Gait and Balance Scale, Cadence, and Nelson Foot Reaction Test scores. The secondary outcomes were The Unified Parkinson's Disease Rating Scale-III subscales, Timed Up and Go Test, Functional Reach Test, and Berg Balance Scale. Outcomes were convened 4 times: pre-test, 6. weeks, post-treatment, and after 3-month follow-up.

RESULTS

At post-test, gait and balance, reaction time, functional mobility, static and dynamic balance showed a significant improvement in PP compared to CP, and the motor examination was similar(p > .05). In addition to these results at follow-up, functional mobility was similar(p > .05) and cadence(p < .05) showed a significant improvement in PP. In addition, according to pairwise comparisons, the PP showed a significant improvement in cadence and reaction time in all 4 measures compared to CP.

CONCLUSIONS

More studies are needed to clarify the effects of the program we developed for PD. It should not be ignored that our protocol can be improved again according to the suggestions of future studies.

Machine Learning for the Prediction of Acute Kidney Injury in Critically Ill Patients with Coronary Heart Disease: Algorithm Development and Validation

BACKGROUND

Acute kidney injury (AKI) frequently occurs in critically ill patients with coronary heart disease (CHD), and its development markedly elevates mortality rates and prolongs hospitalization duration. Early AKI prediction is crucial for timely intervention and amelioration of patient outcomes.

OBJECTIVE

This study aims to develop and verify a clinical prediction model for the occurrence of AKI upon admission in the critically ill CHD population through machine learning (ML).

METHODS

Data from the MIMIC-IV (version 2.2) database were gathered and included information on critically ill CHD individuals in the intensive care unit (ICU). The dataset was randomized into a training set (70%) and a test set (30%). LASSO regression was employed for feature variable selection. ML models, including logistic regression (LR), decision tree (DT), naive bayes (NB), random forest (RF), extreme gradient boosting (XGBoost), and support vector machine (SVM), were constructed using the training set. The six models were compared in the test set to identify the best-performing model. Subsequently, the model was assessed by calibration curve and decision curve analysis(DCA). External validation was conducted using data from the Second Affiliated Hospital of Zhengzhou University. Ultimately, the predictive model was interpreted via SHapley Additive Explanations (SHAP) values.

RESULTS

2,711 ICU-admitted CHD patients were selected, with 1,809 (66.7%) having AKI. Thirteen variables were selected to construct the six ML models. XGBoost exhibited the best performance regarding discrimination (AUC =0.765, 95% CI 0.731-0.800), accuracy (0.725), and sensitivity (0.759). External validation using a cohort of 226 patients confirmed the strong generalizability of the XGBoost model (AUC = 0.835, 95% CI 0.782-0.887). Feature importance analyses derived from SHAP values, DT, RF, and XGBoost consistently identified five key predictors associated with the development of AKI: mechanical ventilation, use of antiplatelet agents, age, N-terminal pro B-type natriuretic peptide (NT-proBNP) levels, and acute physiology score III (APSIII).

CONCLUSIONS

ML models can serve as reliable tools for forecasting AKI in the critically ill CHD cohort. The XGBoost model is highly accurate and may aid doctors in identifying high-risk individuals for early intervention to lower mortality.

CLINICALTRIAL

Response to "Neglecting normalization impact in semi-synthetic RNA-seq data simulation generates artificial false positives" and "Winsorization greatly reduces false positives by popular differential expression methods when analyzing human population samples"

Two correspondences raised concerns or comments about our analyses regarding exaggerated false positives found by differential expression (DE) methods. Here, we discuss the points they raise and explain why we agree or disagree with these points. We add new analysis to confirm that the Wilcoxon rank-sum test remains the most robust method compared to the other five DE methods (DESeq2, edgeR, limma-voom, dearseq, and NOISeq) in two-condition DE analyses after considering normalization and winsorization, the data preprocessing steps discussed in the two correspondences.