1.Predicting intraoperative blood transfusion risk in hip fracture patients using explainable machine learning models
Fengting LU ; Xiaoming LI ; Dekui LI ; Xianyuan XIE ; Jiazhong WANG ; Qing YU ; Gan HUANG ; Jun SHEN
Chinese Journal of Blood Transfusion 2026;39(2):196-202
Objective: To investigate the factors influencing intraoperative blood transfusion in patients with hip fractures and to develop a machine learning (ML) model for predicting this risk. Methods: A total of 424 patients with hip fractures who underwent surgical treatment between November 2022 and March 2025 in our hospital were selected. Key feature variables of intraoperative blood transfusion risk were identified using the Boruta algorithm. Four different ML algorithms—support vector machine (SVM), linear discriminant analysis (LDA), mixed discriminant analysis (MDA), and extreme gradient boosting (XGBoost)—were used to develop predictive models for intraoperative blood transfusion risk. The predictive performance of the four ML models were evaluated using accuracy, precision, receiver operating characteristic (ROC) curves, precision-recall curves (PRC), precision-recall gain curves (PRGC), and F1 scores. Shapley additive interpretation (SHAP) was used to interpret the final model. Results: Among the 424 patients, 77(18.2%) received intraoperative blood transfusion. The Boruta algorithm identified albumin (ALB), activated partial thromboplastin time (APTT), types of anesthesia, types of fracture, and hemoglobin (Hb) as key feature variables for predicting intraoperative blood transfusion risk. In model evaluation, the SVM model outperforms the other three models across multiple metrics, including the area under the receiver operating characteristic curve (AUC), recall, recall gain, accuracy, precision, F1 score, and the area under the precision-recall curve (PRC-AUC). The SVM model, interpreted and visualized based on SHAP values, effectively predicted intraoperative blood transfusion risk in patients with hip fracture. A visual online application was developed based on the SVM model (https://pbo-nomogram.shinyapps.io/blood/). Conclusion: Preoperative low ALB and Hb levels, prolonged APTT, general anesthesia, and intertrochanteric fractures are risk factors for intraoperative blood transfusion in hip fracture patients. The risk prediction model for intraoperative blood transfusion constructed based on the SVM algorithm has optimal performance, which provides new ideas and methods for the clinical early identification of hip fracture patients with high transfusion risk and the implementation of targeted interventions.
2.Clinical Study of Acupoint Application Combined with Daqinglong Decoction for Treatment of Children Asthma with Syndrome of Exterior Cold and Interior Heat
Peiqun XU ; Dekui YU ; Shuanghong XU ; Yuli CHEN ; Hong LI ; Geling ZHONG
Journal of Guangzhou University of Traditional Chinese Medicine 2014;(5):752-755,761
Objective To investigate the therapeutic effect of acupoint application combined with Daqinglong Decoction (DD) for children asthma with the syndrome of exterior cold and interior heat. Methods One hundred and five children with mild and moderate persistent asthma were evenly randomized into combination group, DD group and Montelukast group. The three groups were separately given acupoint application combined with oral use of DD, oral use of DD, oral use of Montelukast, respectively. The treatment for the three groups lasted for 12 weeks. The scores of traditional Chinese medical syndromes in the three groups were recorded before and after treatment. The control of asthmatic symptoms, acute asthmatic attack frequency, and the course of disease were evaluated at the end of follow-up week 12. Results (1) At the end of treatment week 4 and 16, the syndrome scores were obviously decreased in the three groups (P<0.05 compared with those before treatment). At the end of treatment week 4, the decrease of syndrome scores in the combination group was superior to that in DD group (P<0.05), but did not differ from that in Montelukast group (P>0.05) . At the end of follow-up week 12, the decrease of syndrome scores in the combination group was superior to that in DD group and Montelukast group (P<0.05). (2) The effect of the combination group on controlling the asthmatic symptoms was superior to that of the other two groups ( P<0.01). ( 3) The combination group had lower acute asthmatic attack frequency and shorter disease course than DD group and Montelukast group ( P<0.01). Conclusion Acupoint application combined with oral use of Daqinglong Decoction is effective for children asthma with the syndrome of exterior cold and interior heat by relieving symptoms, enhancing the control of asthma, reducing acute asthmatic attack frequency and shortening disease course.

Result Analysis
Print
Save
E-mail