Prediction of the risk of severe small bowel obstruction and effects of Houpu Paiqi mixture in patients undergoing surgery for small bowel obstruction.

AIM: Small bowel obstruction is a common condition that requires emergency surgery. Slow recovery of bowel function after surgery or the occurrence of one or more complications can exacerbate the disease and result in severe small bowel obstruction (SSBO), significantly impacting recovery. It is characterized by a failure to regain enteral nutrition promptly, requiring long-term intensive care. Therefore, it is necessary to identify factors that predict SSBO, to allow early intervention for patients likely to develop this condition. METHODS: Of the 260 patients who underwent emergency or elective surgery for small bowel obstruction between January 2018 and December 2022, 45 developed SSBO. The least absolute shrinkage and selection operator regression model was applied to optimize factor selection and multivariable logistic regression analysis was used to construct a predictive model. The performance and clinical utility of the nomogram were determined and internal validation was conducted. In addition, the effects of the Houpu Paiqi mixture on postoperative recovery were analyzed by comparing the clinical data of 28 patients who were treated with the mixture and 61patients who did not receive it. RESULTS: The predictors included in the prediction nomogram were age, peritonitis, intestinal resection and anastomosis, complications, operation time, Acute Physiology and Chronic Health Evaluation II score, white blood cell count, and procalcitonin level. The model had an area under the receiver operating characteristic curve of 0.948 (95% confidence interval: 0.814-0.956). Decision curve analysis demonstrated that the SSBO risk nomogram had a good net clinical benefit. In addition, treatment with the Houpu Paiqi mixture reduced postoperative exhaust time, postoperative defecation time, time to first postoperative liquid feed, and length of stay in hospital. CONCLUSIONS: We developed a nomogram that can assist clinicians in identifying patients at greater risk of SSBO, which may aid in early diagnosis and intervention. Additionally, we found that the Houpu Paiqi mixture promoted postoperative recovery.

Machine learning was used to predict risk factors for distant metastasis of pancreatic cancer and prognosis analysis.

BACKGROUND: The mechanisms of distant metastasis in pancreatic cancer (PC) have not been elucidated, and this study aimed to explore the risk factors affecting the metastasis and prognosis of metastatic patients and to develop a predictive model. METHOD: Clinical data from patients meeting criteria from 1990 to 2019 were obtained from the Surveillance, Epidemiology, and End Results (SEER) database, and two machine learning methods, random forest and support vector machine, combined with logistic regression, were used to explore risk factors influencing distant metastasis and to create nomograms. The performance of the model was validated using calibration curves and ROC curves based on the Shaanxi Provincial People's Hospital cohort. LASSO regression and Cox regression models were used to explore the independent risk factors affecting the prognosis of patients with distant PC metastases. RESULTS: We found that independent risk factors affecting PC distant metastasis were: age, radiotherapy, chemotherapy, T and N; the independent risk factors for patient prognosis were: age, grade, bone metastasis, brain metastasis, lung metastasis, radiotherapy and chemotherapy. CONCLUSION: Together, our study provides a method for risk factors and prognostic assessment for patients with distant PC metastases. The nomogram we developed can be used as a convenient individualized tool to facilitate aid in clinical decision making.