Using machine learning to predict the bleeding risk for patients with cardiac valve replacement treated with warfarin in hospitalized.

BACKGROUND: Distinguishing warfarin-related bleeding risk at the bedside remains challenging. Studies indicate that warfarin therapy should be suspended when international normalized ratio (INR) ≥ 4.5, or it may sharply increase the risk of bleeding. We aim to develop and validate a model to predict the high bleeding risk in valve replacement patients during hospitalization. METHOD: Cardiac valve replacement patients from January 2016 to December 2021 across Nanjing First Hospital were collected. Five different machine-learning (ML) models were used to establish the prediction model. High bleeding risk was an INR ≥4.5. The area under the receiver operating characteristic curve (AUC) was used for evaluating the prediction performance of different models. The SHapley Additive exPlanations (SHAP) was used for interpreting the model. We also compared ML with ATRIA score and ORBIT score. RESULTS: A total of 2376 patients were finally enrolled in this model, 131 (5.5%) of whom experienced the high bleeding risk after anticoagulation therapy of warfarin during hospitalization. The extreme gradient boosting (XGBoost) exhibited the best overall prediction performance (AUC: 0.882, confidence interval [CI] 0.817-0.946, Brier score, 0.158) compared to other prediction models. It also shows superior performance compared with ATRIA score and ORBIT score. The top 5 most influential features in XGBoost model were platelet, thyroid stimulation hormone, body surface area, serum creatinine and white blood cell. CONCLUSION: A model for predicting high bleeding risk in valve replacement patients who treated with warfarin during hospitalization was successfully developed by using machine learning, which may well assist clinicians to identify patients at high risk of bleeding and allow timely adjust therapeutic strategies in evaluating individual patient.

Evaluation of the impact of rifampicin on the plasma concentration of linezolid in tuberculosis co-infected patients.

Linezolid combined with rifampicin has shown excellent clinical outcomes against infection by multi-resistant Gram-positive bacteria. However, several studies have indicated that rifampicin reduces the plasma concentration of linezolid in patients with severe infection. Linezolid has been recommended for the treatment of patients with multidrug-resistant or extensively drug-resistant tuberculosis. However, studies on the interaction between linezolid and rifampicin in patients suffering from tuberculosis with infection are lacking. We evaluated the interaction between linezolid and rifampicin based on therapeutic drug monitoring (TDM). A retrospective analysis was undertaken for patients with tuberculosis and infection who were treated with linezolid and undergoing TDM. Patients were divided into the linezolid group and linezolid + rifampicin group. Data on demographic characteristics, disease, duration of linezolid therapy, and the plasma concentration of linezolid were used for statistical analyses. Eighty-eight patients with tuberculosis and infection were assessed. Values for the peak (Cmax) and trough (Cmin) concentrations of linezolid in plasma were available for 42 and 46 cases, respectively. Patients in the linezolid group had a significantly higher Cmax [15.76 (8.07-26.06) vs. 13.18 (7.48-23.64) mg/L, p = 0.048] and Cmin [8.38 (3.06-16.53) vs. 4.27 (0.45-10.47), p = 0.005] than those in the linezolid + rifampicin group. The plasma concentration of linezolid increased obviously in two patients after rifampicin discontinuation. However, the total efficiency and prevalence of hematologic adverse reactions were not significantly different in the linezolid group and linezolid + rifampin group. The plasma concentration of linezolid decreased upon combination with rifampicin, suggesting that TDM may aid avoidance of subtherapeutic levels of linezolid upon co-treatment with rifampicin.

Interpretable Machine Learning Model Predicting Early Neurological Deterioration in Ischemic Stroke Patients Treated with Mechanical Thrombectomy: A Retrospective Study.

Early neurologic deterioration (END) is a common and feared complication for acute ischemic stroke (AIS) patients treated with mechanical thrombectomy (MT). This study aimed to develop an interpretable machine learning (ML) model for individualized prediction to predict END in AIS patients treated with MT. The retrospective cohort of AIS patients who underwent MT was from two hospitals. ML methods applied include logistic regression (LR), random forest (RF), support vector machine (SVM), and extreme gradient boosting (XGBoost). The area under the receiver operating characteristic curve (AUC) was the main evaluation metric used. We also used Shapley Additive Explanation (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) to interpret the result of the prediction model. A total of 985 patients were enrolled in this study, and the development of END was noted in 157 patients (15.9%). Among the used models, XGBoost had the highest prediction power (AUC = 0.826, 95% CI 0.781-0.871). The Delong test and calibration curve indicated that XGBoost significantly surpassed those of the other models in prediction. In addition, the AUC in the validating set was 0.846, which showed a good performance of the XGBoost. The SHAP method revealed that blood glucose was the most important predictor variable. The constructed interpretable ML model can be used to predict the risk probability of END after MT in AIS patients. It may help clinical decision making in the perioperative period of AIS patients treated with MT.

Dynamic Prediction of Mechanical Thrombectomy Outcome for Acute Ischemic Stroke Patients Using Machine Learning.

The unfavorable outcome of acute ischemic stroke (AIS) with large vessel occlusion (LVO) is related to clinical factors at multiple time points. However, predictive models used for dynamically predicting unfavorable outcomes using clinically relevant preoperative and postoperative time point variables have not been developed. Our goal was to develop a machine learning (ML) model for the dynamic prediction of unfavorable outcomes. We retrospectively reviewed patients with AIS who underwent a consecutive mechanical thrombectomy (MT) from three centers in China between January 2014 and December 2018. Based on the eXtreme gradient boosting (XGBoost) algorithm, we used clinical characteristics on admission ("Admission" Model) and additional variables regarding intraoperative management and the postoperative National Institute of Health stroke scale (NIHSS) score ("24-Hour" Model, "3-Day" Model and "Discharge" Model). The outcome was an unfavorable outcome at the three-month mark (modified Rankin scale, mRS 3-6: unfavorable). The area under the receiver operating characteristic curve and Brier scores were the main evaluating indexes. The unfavorable outcome at the three-month mark was observed in 156 (62.0%) of 238 patients. These four models had a high accuracy in the range of 75.0% to 87.5% and had a good discrimination with AUC in the range of 0.824 to 0.945 on the testing set. The Brier scores of the four models ranged from 0.122 to 0.083 and showed a good predictive ability on the testing set. This is the first dynamic, preoperative and postoperative predictive model constructed for AIS patients who underwent MT, which is more accurate than the previous prediction model. The preoperative model could be used to predict the clinical outcome before MT and support the decision to perform MT, and the postoperative models would further improve the predictive accuracy of the clinical outcome after MT and timely adjust therapeutic strategies.

Stalled developmental programs at the root of pediatric brain tumors.

Childhood brain tumors have suspected prenatal origins. To identify vulnerable developmental states, we generated a single-cell transcriptome atlas of >65,000 cells from embryonal pons and forebrain, two major tumor locations. We derived signatures for 191 distinct cell populations and defined the regional cellular diversity and differentiation dynamics. Projection of bulk tumor transcriptomes onto this dataset shows that WNT medulloblastomas match the rhombic lip-derived mossy fiber neuronal lineage and embryonal tumors with multilayered rosettes fully recapitulate a neuronal lineage, while group 2a/b atypical teratoid/rhabdoid tumors may originate outside the neuroectoderm. Importantly, single-cell tumor profiles reveal highly defined cell hierarchies that mirror transcriptional programs of the corresponding normal lineages. Our findings identify impaired differentiation of specific neural progenitors as a common mechanism underlying these pediatric cancers and provide a rational framework for future modeling and therapeutic interventions.

[The correlation of age with the risk of multiple organ dysfunction syndrome in the elderly patients with congestive heart failure and hypertension].

OBJECTIVE: To study the prediction value of age and congestive heart failure (CHF) for occurrence of multiple organ dysfunction syndrome elderly(MODSE) in old patients with hypertension. METHODS: Medical history of 19,996 cases (aged over 60 year) admitted to PLA General Hospital because of hypertension or developing hypertension during hospital stay from Jan 1993 to Dec 2008 were analyzed retrospectively. According to age the patients were divided into four groups: 60-69 year group; 70-79 year group; 80-89 year group; > or = 90 year older group. The incidence of CHF and the morbidity of MODSE induced by CHF at different ages and different boundary ages were investigated. RESULTS: 1. The incidence of MODSE in CHF cases was higher than that in the non-CHF cases (7.43% versus 3.05%, Chi(2) 195.15, P < 0.01), showing CHF were the important factor in happening of MODSE. 2. The incidence of CHF and the morbidity of MODSE were 10.60% versus 18.88% versus 30.11% versus 60.57%, P <0.05, P < 0.05 and 1.6 versus 7.0 versus 17.08 versus 25.47% , in 60-69 year group; 70-79 year group; 80-89 year group; > or =90 year older group, P < 0.05. Occurrence of CHF and that of MODSE were positively correlated with age (r = 0.696 - 0.987, P < 0.01). High risk population of MODSE induced by CHF were old patients with hypertension above 69 year old. CONCLUSION: The age is valuable for early prediction of MODSE induced by CHF in old patients with hypertension. The distinctly boundary age for the incidence of MODSE induced by CHF in old patients with hypertension is 69.