An interpretable machine learning approach for predicting 30-day readmission after stroke.

BACKGROUND: Stroke is the second leading cause of death worldwide and has a significantly high recurrence rate. We aimed to identify risk factors for stroke recurrence and develop an interpretable machine learning model to predict 30-day readmissions after stroke. METHODS: Stroke patients deposited in electronic health records (EHRs) in Xuzhou Medical University Hospital between February 1, 2021, and November 30, 2021, were included in the study, and deceased patients were excluded. We extracted 74 features from EHRs, and the top 20 features (chi-2 value) were used to build machine learning models. 80% of the patients were used for pre-training. Subsequently, a 20% holdout dataset was used for verification. The Shapley Additive exPlanations (SHAP) method was used to explore the interpretability of the model. RESULTS: The cohort included 6,558 patients, of whom the mean (SD) age was 65 (11) years, 3,926 were males (59.86 %), and 132 (2.01 %) were readmitted within 30 days. The area under the receiver operating characteristic curve (AUROC) for the optimized model was 0.80 (95 % CI 0.68-0.80). We used the SHAP method to identify the top 10 risk factors (i.e., severe carotid artery stenosis, weak, homocysteine, glycosylated hemoglobin, sex, lymphocyte percentage, neutrophilic granulocyte percentage, urine glucose, fresh cerebral infarction, and red blood cell count). The AUROC of a model with the 10 features was 0.80 (95 % CI 0.69-0.80) and was not significantly different from that of the model with 20 risk factors. CONCLUSIONS: Our methods not only showed good performance in predicting 30-day readmissions after stroke but also revealed risk factors that provided valuable insights for treatments.

Methyl Jasmonate Promotes Phospholipid Remodeling and Jasmonic Acid Signaling To Alleviate Chilling Injury in Peach Fruit.

Chilling injury (CI) is a physiological disorder induced by cold, which heavily limit crop production and postharvest preservation worldwide. Methyl jasmonate (MeJA) can alleviate CI in various fruit species, including peach; however, the underlying molecular mechanism is poorly understood. Here, changes in contents of phenolics, lipids, and jasmonic acid (JA) and gene expressions are compared between MeJA and control fruit. Exogenous MeJA inhibited expressions of PpPAL1, PpPPO1, and PpPOD1/2 but did not affect the phenolic content. Furthermore, MeJA fruit showed lower relative electrolyte leakage, indicating less membrane damage. Meanwhile, the enrichment of linoleic acid in the potential lipid biomarkers, especially phosphatidylcholine, phosphatidylethanolamine, and phosphatidylglycerol, coincided with lower expressions of PpFAD8.1 but higher PpLOX3.1 and JA content. In the JA signaling pathway, MeJA significantly upregulated expressions of PpMYC2.2 and PpCBF3 but downregulated PpMYC2.1. In conclusion, adjustments of fatty acids in phospholipids contribute to MeJA-induced alleviation of CI in peach fruit via induction of the JA-mediated C-repeat-binding factor pathway.