The coronavirus disease 2019 (COVID-19) has a significant impact on the global population, particularly on individuals with chronic kidney disease (CKD). COVID-19 patients with CKD will face a considerably higher risk of mortality than the general population. This study developed a predictive model for assessing mortality in COVID-19-affected CKD patients, providing personalized risk prediction to optimize clinical management and reduce mortality rates. We developed machine learning algorithms to analyze 219 patients’ clinical laboratory test data retrospectively. The performance of each model was assessed using a calibration curve, decision curve analysis, and receiver operating characteristic (ROC) curve. It was found that the LightGBM model showed the most satisfied performance, with an area under the ROC curve of 0.833, sensitivity of 0.952, and specificity of 0.714. Prealbumin, neutrophil percent, respiratory index in arterial blood, half-saturated pressure of oxygen, carbon dioxide in serum, glucose, neutrophil count, and uric acid were the top 8 significant variables in the prediction model. Validation by 46 patients demonstrated acceptable accuracy. This model can serve as a powerful tool for screening CKD patients at high risk of COVID-19-related mortality and providing decision support for clinical staff, enabling efficient allocation of resources, and facilitating timely and targeted management for those who need the relevant interference urgently.

Therapy‑related acute myeloid leukemia (t‑AML) following chemotherapy in patients with small cell lung cancer (SCLC) is rare, and its clinical and genetic characteristics remain poorly elucidated. In the present study, a 53‑year‑old male patient with SCLC is reported. After diagnosis in June 2023, the patient received 9 cycles of etopside and cisplatin (EP) chemotherapy, 7 cycles of EP plus durvalumab and 1 cycle of etoposide plus durvalumab sequentially. Hematological abnormalities developed 23 months after the initial chemotherapy. Bone marrow aspiration revealed 28% blasts, and flow cytometry identified 36.4% abnormal myeloid blasts. Chromosomal karyotype analysis displayed 46,XY,t(11;20)(p15; q11) [7]/46,idem,add(6)(p25)[13], consistent with a diagnosis of t‑AML (M2). The present case represents t‑AML with a rare karyotype and extreme latency following treatment for SCLC. The present case report enriches the available genetic spectrum of t‑AML associated with SCLC, suggesting the necessity for long‑term hematological monitoring in patients with SCLC and provides a reference for the clinical management of dual malignancies.

Background: Older adults are the high-risk group for COVID-19-related death. This study aimed to develop an accurate, efficient, clinically interpretable machine learning (ML) model for predicting mortality risk in this population, using only routine hematological indicators at admission to avoid extra medical costs and radiation exposure. Methods: 2393 COVID-19 patients were enrolled in this retrospective study. Missing values were imputed via Random Forest. RandomOverSampler was utilized during model training to alleviate moderate class imbalance. Feature selection was conducted following the maximum relevance-minimum redundancy principle. Five ML algorithms—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), XGBoost (XGB), Light Gradient Boosting Machine (LGBM) were optimized via bayesian optimization (BO). We performed 10 rounds of random stratified data splitting; models were fitted on the training set, with intermediate screening and hyperparameter optimization implemented on the validation set. The independent held-out test set was strictly reserved for final performance evaluation. Model performances were assessed using the ROC curve, accuracy, precision, recall, F1-score and brier score. Calibration curve evaluated concordance between predicted probabilities and actual outcomes, and decision curve analysis (DCA) quantified net clinical benefit in clinical practice. Shapley additive exPlanations (SHAP) values and partial dependence plots (PDPs) interpreted feature importance and their associations with mortality risk. A simplified model was further developed using the top 10 key features identified by SHAP analysis and a corresponding risk prediction system was constructed to facilitate clinical application by physicians. Results: The LGBM model achieved the best comprehensive performance: AUC of 0.973, recall of 0.924, accuracy of 0.918, F1-score of 0.918, NPV of 0.923, and Brier score of 0.064. It outperformed other algorithms in computational efficiency and cross-dataset stability. Top 10 key features identified included basophil percentage (BA%), C-reactive protein (CRP), procalcitonin (PCT), D-dimer (D-dimer), AST/ALT ratio, cardiac troponin I (cTnI), standard bicarbonate (SB), age, aspartate transaminase (AST), and oxygen saturation (SaO ₂ ) for predicting mortality risk in older adults. Non-linear associations and threshold effects were observed (e.g., risk surged when CRP > 100 mg/L or D-dimer > 5–10 μg/mL). The simplified model reduced training time by 58.31% without compromising performance, comparable accuracy and interpretability. Conclusion: This study developed a TPE-LGBM model based on routine hematological indicators to predict mortality risk in older adults with COVID-19. The model demonstrated favorable accuracy, efficiency, and interpretability, suggesting the potential value of applying explainable machine learning to address unmet medical needs.