Machine learning based analysis of stroke lesions on mouse tissue sections

Investigating the Influence of Heavy Metals and Environmental Factors on Metabolic Syndrome Risk Based on Nutrient Intake: Machine Learning Analysis of Data from the Eighth Korea National Health and Nutrition Examination Survey (KNHANES)

This study delves into the complex interrelations among nutrient intake, environmental exposures (particularly to heavy metals), and metabolic syndrome. Utilizing data from the Korea National Health and Nutrition Examination Survey (KNHANES), machine learning techniques were applied to analyze associations in a cohort of 5719 participants, categorized into four distinct nutrient intake phenotypes. Our findings reveal that different nutrient intake patterns are associated with varying levels of heavy metal exposure and metabolic health outcomes. Key findings include significant variations in metal levels (Pb, Hg, Cd, Ni) across the clusters, with certain clusters showing heightened levels of specific metals. These variations were associated with distinct metabolic health profiles, including differences in obesity, diabetes prevalence, hypertension, and cholesterol levels. Notably, Cluster 3, characterized by high-energy and nutrient-rich diets, showed the highest levels of Pb and Hg exposure and had the most concerning metabolic health indicators. Moreover, the study highlights the significant impact of lifestyle habits, such as smoking and eating out, on nutrient intake phenotypes and associated health risks. Physical activity emerged as a critical factor, with its absence linked to imbalanced nutrient intake in certain clusters. In conclusion, our research underscores the intricate connections among diet, environmental factors, and metabolic health. The findings emphasize the need for tailored health interventions and policies that consider these complex interplays, potentially informing future strategies to combat metabolic syndrome and related health issues.

Prediction of in-hospital hypokalemia using machine learning and first hospitalization day records in patients with traumatic brain injury

AIMS

Hypokalemia is a common complication following traumatic brain injury, which may complicate treatment and lead to unfavorable outcomes. Identifying patients at risk of hypokalemia on the first day of admission helps to implement prophylactic treatment, reduce complications, and improve prognosis.

METHODS

This multicenter retrospective study was performed between January 2017 and December 2020 using the electronic medical records of patients admitted due to traumatic brain injury. A propensity score matching approach was adopted with a ratio of 1:1 to overcome overfitting and data imbalance during subgroup analyses. Five machine learning algorithms were applied to generate a best-performed prediction model for in-hospital hypokalemia. The internal fivefold cross-validation and external validation were performed to demonstrate the interpretability and generalizability.

RESULTS

A total of 4445 TBI patients were recruited for analysis and model generation. Hypokalemia occurred in 46.55% of recruited patients and the incidences of mild, moderate, and severe hypokalemia were 32.06%, 12.69%, and 1.80%, respectively. Hypokalemia was associated with increased mortality, while severe hypokalemia cast greater impacts. The logistic regression algorithm had the best performance in predicting decreased serum potassium and moderate-to-severe hypokalemia, with an AUC of 0.73 ± 0.011 and 0.74 ± 0.019, respectively. The prediction model was further verified using two external datasets, including our previous published data and the open-assessed Medical Information Mart for Intensive Care database. Linearized calibration curves showed no statistical difference (p > 0.05) with perfect predictions.

CONCLUSIONS

The occurrence of hypokalemia following traumatic brain injury can be predicted by first hospitalization day records and machine learning algorithms. The logistic regression algorithm showed an optimal predicting performance verified by both internal and external validation.