Machine learning based prognostic model of Chinese medicine affecting the recurrence and metastasis of I-III stage colorectal cancer: A retrospective study in China

Abstract

BackgroundTo construct prognostic model of colorectal cancer (CRC) recurrence and metastasis (R&M) with traditional Chinese medicine (TCM) factors based on different machine learning (ML) methods. Aiming to offset the defects in the existing model lacking TCM factors.MethodsPatients with stage I-III CRC after radical resection were included as the model data set. The training set and the internal verification set were randomly divided at a ratio of 7: 3 by the “set aside method”. The average performance index and 95% confidence interval of the model were calculated by repeating 100 tests. Eight factors were used as predictors of Western medicine. Two types of models were constructed by taking “whether to accept TCM intervention” and “different TCM syndrome types” as TCM predictors. The model was constructed by four ML methods: logistic regression, random forest, Extreme Gradient Boosting (XGBoost) and support vector machine (SVM). The predicted target was whether R&M would occur within 3 years and 5 years after radical surgery. The area under curve (AUC) value and decision curve analysis (DCA) curve were used to evaluate accuracy and utility of the model.ResultsThe model data set consisted of 558 patients, of which 317 received TCM intervention after radical resection. The model based on the four ML methods with the TCM factor of “whether to accept TCM intervention” showed good ability in predicting R&M within 3 years and 5 years (AUC value > 0.75), and XGBoost was the best method. The DCA indicated that when the R&M probability in patients was at a certain threshold, the models provided additional clinical benefits. When predicting the R&M probability within 3 years and 5 years in the model with TCM factors of “different TCM syndrome types”, the four methods all showed certain predictive ability (AUC value > 0.70). With the exception of the model constructed by SVM, the other methods provided additional clinical benefits within a certain probability threshold.ConclusionThe prognostic model based on ML methods shows good accuracy and clinical utility. It can quantify the influence degree of TCM factors on R&M, and provide certain values for clinical decision-making.

Meta‐analysis on the efficacy of Traditional Chinese Medicine in enhancing surgical site wound healing post‐colorectal surgery

“…Furthermore, the Yiqi Sanjie (YQSJ) formula has demonstrated clinical efficacy in the treatment of stage III CRC, with studies illustrating its role in modulating molecular and microbiota changes in CRC tissues and cell lines, thereby suggesting new potential therapeutic targets in CRC 12 . Moreover, the integration of TCM factors in prognostic models, leveraging machine learning methods, has shown promise in predicting the recurrence and metastasis in stage I‐III CRC patients, thereby offering a novel approach in the clinical management of CRC 15 …”

“… 12 Moreover, the integration of TCM factors in prognostic models, leveraging machine learning methods, has shown promise in predicting the recurrence and metastasis in stage I‐III CRC patients, thereby offering a novel approach in the clinical management of CRC. 15 …”

“…12 Moreover, the integration of TCM factors in prognostic models, leveraging machine learning methods, has shown promise in predicting the recurrence and metastasis in stage I-III CRC patients, thereby offering a novel approach in the clinical management of CRC. 15 The TTT surgery, an extension of the Ilizarov technique, has been combined with TCM approaches to alleviate ischemic symptoms and enhance wound healing. 4 This synergy between traditional methods and modern surgical techniques exemplifies the adaptability and relevance of TCM in contemporary medical practices, paving the way for a multidisciplinary approach in enhancing wound healing and alleviating ischemic symptoms postsurgery.…”

Machine learning in TCM with natural products and molecules: current status and future perspectives

“…Machine learning has recently been successfully applied in disease treatment and effect evaluation of TCM, such as in prescription recommendation, transition prediction, and treatment prognosis (Table 2 ). The treatment prognosis model has received increasing attention in the context of clinical diagnosis and treatment decision-making [ 84 ]. Zhang [ 85 ] utilized transformer and GAN to develop an auxiliary tool to prescribe TCM prescriptions based on the patient’s clinical electronic health records.…”

“…SVM classification revealed significant white matter network alterations after treatment in the drug groups, with an accuracy of 68.18%. Tang [ 84 ] used RF, SVM, logistic regression, and extreme gradient boosting to predict whether colorectal cancer recurrence and metastasis with TCM factors would occur within 3 years and 5 years after radical surgery. The results showed that the four methods all showed certain predictive ability (area under the curve values > 0.70).…”