Search

Background: Diabetic ketoacidosis (DKA) is a frequent acute complication of diabetes mellitus (DM). It develops quickly, produces severe symptoms, and greatly affects the lives and health of individuals with DM.This article utilizes machine learning methods to examine the baseline characteristics that significantly contribute to the development of DKA. Its goal is to identify and prevent DKA in a targeted and early manner., Methods: This study selected 2382 eligible diabetic patients from the MIMIC-IV dataset, including 1193 DM patients with ketoacidosis and 1186 DM patients without ketoacidosis. A total of 42 baseline characteristics were included in this research. The research process was as follows: Firstly, important features were selected through Pearson correlation analysis and random forest to identify the relevant physiological indicators associated with DKA. Next, logistic regression was used to individually predict DKA based on the 42 baseline characteristics, analyzing the impact of different physiological indicators on the experimental results. Finally, the prediction of ketoacidosis was performed by combining feature selection with machine learning models include logistic regression, XGBoost, decision tree, random forest, support vector machine, and k-nearest neighbors classifier., Results: Based on the importance analysis conducted using different feature selection methods, the top five features in terms of importance were identified as mean hematocrit (haematocrit_mean), mean hemoglobin (haemoglobin_mean), mean anion gap (aniongap_mean), age, and Charlson comorbidity index (charlson_comorbidity_index). These features were found to have significant relevance in predicting DKA. In the individual prediction using logistic regression, these five features have been proven to be effective, with F1 scores of 1.000 for hematocrit mean, 0.978 for haemoglobin_mean, 0.747 for age, 0.692 for aniongap_mean and 0.666 for charlson_comorbidity_index. These F1 scores indicate the effectiveness of each feature in predicting DKA, with the highest score achieved by mean hematocrit. In the prediction of DKA using machine learning models, including logistic regression, XGBoost, decision tree, and random forest demonstrated excellent results, achieving an F1 score of 1.000. Additionally, by applying feature selection techniques, noticeable improvements were observed in the experimental performance of the support vector machine and k-nearest neighbors classifier., Conclusion: The study found that hematocrit, hemoglobin, anion gap, age, and Charlson comorbidity index are closely associated with ketoacidosis. In clinical practice, these five baseline characteristics should be given with the special attention to achieve early detection and treatment, thus reducing the incidence of the disease., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Liu, Mo, Wang, Shao, Zeng and Bi.)

Introduction: Hyperuricemia (HUA) is a metabolic disorder caused by purine metabolism dysfunction in which the increasing purine levels can be partially attributed to seafood consumption. Perillae Folium (PF), a widely used plant in functional food, has been historically used to mitigate seafood-induced diseases. However, its efficacy against HUA and the underlying mechanism remain unclear., Methods: A network pharmacology analysis was performed to identify candidate targets and potential mechanisms involved in PF treating HUA. The candidate targets were determined based on TCMSP, SwissTargetPrediction, Open Targets Platform, GeneCards, Comparative Toxicogenomics Database, and DrugBank. The potential mechanisms were predicted via Gene Ontology (GO) and Kyoto Gene and Genome Encyclopedia (KEGG) analyses. Molecular docking in AutoDock Vina and PyRx were performed to predict the binding affinity and pose between herbal compounds and HUA-related targets. A chemical structure analysis of PF compounds was performed using OSIRIS DataWarrior and ClassyFire. We then conducted virtual pharmacokinetic and toxicity screening to filter potential inhibitors. We further performed verifications of these inhibitors' roles in HUA through molecular dynamics (MD) simulations, text-mining, and untargeted metabolomics analysis., Results: We obtained 8200 predicted binding results between 328 herbal compounds and 25 potential targets, and xanthine dehydrogenase (XDH) exhibited the highest average binding affinity. We screened out five promising ligands (scutellarein, benzyl alpha-D-mannopyranoside, elemol, diisobutyl phthalate, and (3R)-hydroxy-beta-ionone) and performed MD simulations up to 50 ns for XDH complexed to them. The scutellarein-XDH complex exhibited the most satisfactory stability. Furthermore, the text-mining study provided laboratory evidence of scutellarein's function. The metabolomics approach identified 543 compounds and confirmed the presence of scutellarein. Extending MD simulations to 200 ns further indicated the sustained impact of scutellarein on XDH structure., Conclusion: Our study provides a computational and biomedical basis for PF treating HUA and fully elucidates scutellarein's great potential as an XDH inhibitor at the molecular level, holding promise for future drug design and development., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2024 Wu, Wong, Chen, Yang, Chen, Sun, Zhou, Liu, Yang, Bi, Hung, Li and Zhao.)