Objective:To construct the risk prediction model of unplanned readmission for elderly patients in emergency department within 30 days based on different machine learning algorithms, so as to help clinical staff identify high-risk patients early and formulate preventive interventions.Methods:A total of 1 207 elderly patients admitted to the emergency department of the First Affiliated Hospital of Naval Medical University from May 2022 to December 2023 were retrospectively selected as the study objects and were divided into the training set ( n = 842) and the test set ( n = 365) in a ratio of approximately 7∶3. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to screen the factors affecting the unplanned readmission of elderly patients within 30 days. Six prediction models, including extreme Gradient Boost (XGBoost), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost) Logistic regression, K-nearest neighbor (KNN) and Gauss Naive Bayes classification (GNB) were constructed respectively. The models were summarized, evaluated and validated, and the importance of key variables was analyzed using Shapley Additive Interpretation (SHAP). Results:Among 1 207 elderly patients, there were 842 in the training set, 430 males with a median age of 77 years, and 365 in the test set, 176 males with a median age of 78 years. Eight variable features were selected by LASSO regression. The GNB model performed the best among the 6 prediction models constructed based on XGBoost, LightGBM, AdaBoost, Logistic regression, KNN, GNB. The AUC of the test set was 0.818, and the sensitivity was 0.890, while the specificity was 0.660, and the train set and the verification set had strong fitting ability and high stability. The eight characteristics affecting the unplanned readmitted of elderly patients in the emergency department within 30 days were ranked in importance by age, chronic obstructive pulmonary disease, length of stay, Charson comorbidity index≥3, hypoproteinemia, abnormal vital signs≥2, stroke, anemia.Conclusions:The GNB model based on machine learning algorithms for unplanned readmission of elderly emergency patients within 30 days has good predictive performance, which helps medical staff to identify high-risk patients as early as possible before discharge, formulate targeted preventive measures, thereby reducing the short-term unplanned readmission rate of patients and improving their quality of life.

OBJECTIVES: To investigate the risk factors of recurrence of acute ischemic stroke (AIS) within 1 year and establish a nomogram model for predicting the recurrence risk. METHODS: This study was conducted in two cohorts of AIS patients (≤7 days) hospitalized in Dongzhimen Hospital (modeling set) and Fangshan Hospital (validation set) from March, 2021 to March, 2022. Lasso regression analysis was used to identify the important predictive factors for AIS recurrence within 1 year, and multivariate Logistic regression analysis was performed to analyze the independent factors affecting AIS recurrence. The recurrence risk prediction nomogram model was constructed using R studio, and its discriminating power and calibration were assessed using ROC curve analysis and Hosmer-Lemeshow goodness-of-fit test. RESULTS: The modeling and validation sets contained 28 cases (15.22%) and 21 cases (15.00%) of AIS recurrence, respectively. In the modeling set, compared with the non-relapse group, the recurrence group had higher proportions of patients with age >65 years, diabetes, arrhythmia, constipation after stroke, and FBG >7.5 and significantly higher levels of NLR, UREA, Cr, HbA1c, FIB and TT (P<0.05). Multivariate Logistic regression analysis showed that an age >65 years, arrhythmia, constipation after stroke, FBG >7.5, NLR and Cr were all independent risk factors of AIS recurrence (P<0.05). Hosmer-Lemeshow goodness-of-fit test and calibration curve analysis showed that the risk prediction model had good fitting between the modeling set and the verification set. The ROC curve showed that for predicting AIS recurrence within 1 year, the AUC of the predictive model was 0.857 (95%CI: 0.782-0.932) in the modeling set and 0.679 (95%CI: 0.563-0.794) in the validation set. CONCLUSIONS The nomogram model established based on age >65 years, arrhythmia, constipation after stroke, FBG >7.5, NLR and Cr has a good predictive value for AIS recurrence within 1 year.
Humans ; Nomograms ; Risk Factors ; Recurrence ; Ischemic Stroke/etiology* ; Female ; Male ; Logistic Models ; Aged ; ROC Curve ; Middle Aged ; Stroke/etiology*

OBJECTIVE: To perform gene mutation analysis in a patient with atypical clinical manifestations of tuberous sclerosis (TSC) for definite diagnosis. METHODS: Peripheral blood DNA was obtained from a patient with clinically suspected TSC and her parents, and all exons and their flanking sequences of RESULTS: A heterozygous nonsense mutation c.1096G>T (p.E366*) was identified in the exon 11 of the CONCLUSIONS The somatic mosaic mutation c.1096G>T (p.e366*) may be responsible for the phenotype of TSC in this patient. And the drop digital PCR is expected to be a diagnostic method for somatic cells mosaicism.
Female ; Humans ; Male ; Mosaicism ; Mutation ; Tuberous Sclerosis/genetics* ; Tuberous Sclerosis Complex 2 Protein/genetics* ; Whole Exome Sequencing