Objective:To construct an ensemble machine learning model for predicting the occurrence of clinically relevant postoperative pancreatic fistula (CR-POPF) after pancreaticoduodenectomy and evaluate its application value.Methods:This is a research on predictive model. Clinical data of 421 patients undergoing pancreaticoduodenectomy in the Department of Pancreatic Surgery,Union Hospital, Tongji Medical College,Huazhong University of Science and Technology from June 2020 to May 2023 were retrospectively collected. There were 241 males (57.2%) and 180 females (42.8%) with an age of (59.7±11.0)years (range: 12 to 85 years).The research objects were divided into training set (315 cases) and test set (106 cases) by stratified random sampling in the ratio of 3∶1. Recursive feature elimination is used to screen features,nine machine learning algorithms are used to model,three groups of models with better fitting ability are selected,and the ensemble model was constructed by Stacking algorithm for model fusion. The model performance was evaluated by various indexes,and the interpretability of the optimal model was analyzed by Shapley Additive Explanations(SHAP) method. The patients in the test set were divided into different risk groups according to the prediction probability (P) of the alternative pancreatic fistula risk score system (a-FRS). The a-FRS score was validated and the predictive efficacy of the model was compared.Results:Among 421 patients,CR-POPF occurred in 84 cases (20.0%). In the test set,the Stacking ensemble model performs best,with the area under the curve (AUC) of the subject′s work characteristic curve being 0.823,the accuracy being 0.83,the F1 score being 0.63,and the Brier score being 0.097. SHAP summary map showed that the top 9 factors affecting CR-POPF after pancreaticoduodenectomy were pancreatic duct diameter,CT value ratio,postoperative serum amylase,IL-6,body mass index,operative time,albumin difference before and after surgery,procalcitonin and IL-10. The effects of each feature on the occurrence of CR-POPF after pancreaticoduodenectomy showed a complex nonlinear relationship. The risk of CR-POPF increased when pancreatic duct diameter<3.5 mm,CT value ratio<0.95,postoperative serum amylase concentration>150 U/L,IL-6 level>280 ng/L,operative time>350 minutes,and albumin decreased by more than 10 g/L. The AUC of a-FRS in the test set was 0.668,and the prediction performance of a-FRS was lower than that of the Stacking ensemble machine learning model.Conclusion:The ensemble machine learning model constructed in this study can predict the occurrence of CR-POPF after pancreaticoduodenectomy,and has the potential to be a tool for personalized diagnosis and treatment after pancreaticoduodenectomy.

Objective:To construct an ensemble machine learning model for predicting the occurrence of clinically relevant postoperative pancreatic fistula (CR-POPF) after pancreaticoduodenectomy and evaluate its application value.Methods:This is a research on predictive model. Clinical data of 421 patients undergoing pancreaticoduodenectomy in the Department of Pancreatic Surgery,Union Hospital, Tongji Medical College,Huazhong University of Science and Technology from June 2020 to May 2023 were retrospectively collected. There were 241 males (57.2%) and 180 females (42.8%) with an age of (59.7±11.0)years (range: 12 to 85 years).The research objects were divided into training set (315 cases) and test set (106 cases) by stratified random sampling in the ratio of 3∶1. Recursive feature elimination is used to screen features,nine machine learning algorithms are used to model,three groups of models with better fitting ability are selected,and the ensemble model was constructed by Stacking algorithm for model fusion. The model performance was evaluated by various indexes,and the interpretability of the optimal model was analyzed by Shapley Additive Explanations(SHAP) method. The patients in the test set were divided into different risk groups according to the prediction probability (P) of the alternative pancreatic fistula risk score system (a-FRS). The a-FRS score was validated and the predictive efficacy of the model was compared.Results:Among 421 patients,CR-POPF occurred in 84 cases (20.0%). In the test set,the Stacking ensemble model performs best,with the area under the curve (AUC) of the subject′s work characteristic curve being 0.823,the accuracy being 0.83,the F1 score being 0.63,and the Brier score being 0.097. SHAP summary map showed that the top 9 factors affecting CR-POPF after pancreaticoduodenectomy were pancreatic duct diameter,CT value ratio,postoperative serum amylase,IL-6,body mass index,operative time,albumin difference before and after surgery,procalcitonin and IL-10. The effects of each feature on the occurrence of CR-POPF after pancreaticoduodenectomy showed a complex nonlinear relationship. The risk of CR-POPF increased when pancreatic duct diameter<3.5 mm,CT value ratio<0.95,postoperative serum amylase concentration>150 U/L,IL-6 level>280 ng/L,operative time>350 minutes,and albumin decreased by more than 10 g/L. The AUC of a-FRS in the test set was 0.668,and the prediction performance of a-FRS was lower than that of the Stacking ensemble machine learning model.Conclusion:The ensemble machine learning model constructed in this study can predict the occurrence of CR-POPF after pancreaticoduodenectomy,and has the potential to be a tool for personalized diagnosis and treatment after pancreaticoduodenectomy.

BACKGROUND:Heterotopic ossification is a dynamic growth process.Diverse heterotopic ossification subtypes have diverse etiologies or induction factors,but they exhibit a similar clinical process in the intermediate and later phases of the disease.Acquired heterotopic ossification produced by trauma and other circumstances has a high incidence. OBJECTIVE:To summarize the molecular biological mechanisms linked to the occurrence and progression of acquired heterotopic ossification in recent years. METHODS:The keywords"molecular biology,heterotopic ossification,mechanisms"were searched in CNKI,Wanfang,PubMed,Embase,Web of Science,and Google Scholar databases for articles published from January 2016 to August 2022.Supplementary searches were conducted based on the obtained articles.After the collected literature was screened,131 articles were finally included and summarized. RESULTS AND CONCLUSION:(1)The occurrence and development of acquired heterotopic ossification is a dynamic process with certain concealment,making diagnosis and treatment of the disease difficult.(2)By reviewing relevant literature,it was found that acquired heterotopic ossification involves signaling pathways such as bone morphogenetic protein,transforming growth factor-β,Hedgehog,Wnt,and mTOR,as well as core factors such as Runx-2,vascular endothelial growth factor,hypoxia-inducing factor,fibroblast growth factor,and Sox9.The core mechanism may be the interaction between different signaling pathways,affecting the body's osteoblast precursor cells,osteoblast microenvironment,and related cytokines,thereby affecting the body's bone metabolism and leading to the occurrence of acquired heterotopic ossification.(3)In the future,it is possible to take the heterotopic ossification-related single-cell osteogenic homeostasis as the research direction,take the osteoblast precursor cells-osteogenic microenvironment-signaling pathways and cytokines as the research elements,explore the characteristics of each element under different temporal and spatial conditions,compare the similarities and differences of the osteogenic homeostasis of different types and individuals,observe the regulatory mechanism of the molecular signaling network of heterotopic ossification from a holistic perspective.It is beneficial to the exploration of new methods for the future clinical prevention and treatment of heterotopic ossification.(4)Meanwhile,the treatment methods represented by traditional Chinese medicine and targeted therapy have become research hotspots in recent years.How to link traditional Chinese medicine with the osteogenic homeostasis in the body and combine it with targeted therapy is also one of the future research directions.(5)At present,the research on acquired heterotopic ossification is still limited to basic experimental research and the clinical prevention and treatment methods still have defects such as uncertain efficacy and obvious side effects.The safety and effectiveness of relevant targeted prevention and treatment drugs in clinical application still need to be verified.Future research should focus on clinical prevention and treatment based on basic experimental research combined with the mechanism of occurrence and development.

Objective:To establish a set of artificial intelligence (AI) verification rules for blood routine analysis.Methods:Blood routine analysis data of 18 474 hospitalized patients from the First Hospital of Jilin University during August 1st to 31st, 2019, were collected as training group for establishment of the AI verification rules,and the corresponding patient age, microscopic examination results, and clinical diagnosis information were collected. 92 laboratory parameters, including blood analysis report parameters, research parameters and alarm information, were used as candidate conditions for AI audit rules; manual verification combining microscopy was considered as standard, marked whether it was passed or blocked. Using decision tree algorithm, AI audit rules are initially established through high-intensity, multi-round and five-fold cross-validation and AI verification rules were optimized by setting important mandatory cases. The performance of AI verification rules was evaluated by comparing the false negative rate, precision rate, recall rate, F1 score, and pass rate with that of the current autoverification rules using Chi-square test. Another cohort of blood routine analysis data of 12 475 hospitalized patients in the First Hospital of Jilin University during November 1sr to 31st, 2023, were collected as validation group for validation of AI verification rules, which underwent simulated verification via the preliminary AI rules, thus performance of AI rules were analyzed by the above indicators. Results:AI verification rules consist of 15 rules and 17 parameters and do distinguish numeric and morphological abnormalities. Compared with auto-verification rules, the true positive rate, the false positive rate, the true negative rate, the false negative rate, the pass rate, the accuracy, the precision rate, the recall rate and F1 score of AI rules in training group were 22.7%, 1.6%, 74.5%, 1.3%, 75.7%, 97.2%, 93.5%, 94.7%, 94.1, respectively.All of them were better than auto-verification rules, and the difference was statistically significant ( P<0.001), and with no important case missed. In validation group, the true positive rate, the false positive rate, the true negative rate, the false negative rate, the pass rate, the accuracy, the precision rate, the recall rate and F1 score were 19.2%, 8.2%, 70.1%, 2.5%, 72.6%, 89.2%, 70.0%, 88.3%, 78.1, respectively, Compared with the auto-verification rules, The false negative rate was lower, the false positive rate and the recall rate were slightly higher, and the difference was statistically significant ( P<0.001). Conclusion:A set of the AI verification rules are established and verified by using decision tree algorithm of machine learning, which can identify, intercept and prompt abnormal results stably, and is moresimple, highly efficient and more accurate in the report of blood analysis test results compared with auto-vefication.