Due to its synergistic effects and reduced side effects, combination therapy has become an important strategy for treating complex diseases. In traditional Chinese medicine (TCM), the "monarch, minister, assistant, envoy" compatibilities theory provides a systematic framework for drug compatibility and has guided the formation of a large number of classic formulas. However, due to the complex compositions and diverse mechanisms of action of TCM, it is difficult to comprehensively reveal its potential synergistic patterns using traditional methods. Synergistic prediction based on molecular compatibility theory provides new ideas for identifying combinations of active compounds in TCM. Compared to resource-intensive traditional experimental methods, artificial intelligence possesses the ability to mine synergistic patterns from multi-omics and structural data, providing an efficient means for modeling and optimizing TCM combinations. This paper systematically reviews the application progress of AI in the synergistic prediction of TCM active compounds and explores the challenges and prospects of its application in modeling combination relationships, thereby contributing to the modernization of TCM theory and methodological innovation.
Artificial Intelligence ; Medicine, Chinese Traditional/methods* ; Drugs, Chinese Herbal/pharmacology* ; Humans ; Drug Synergism

Surgical resection remains the only potentially curative treatment for pancreatic cancer to date.However,pancreatic cancer surgery is also one of procedures carrying the highest risks among all malignant tumor surgeries,in terms of perioperative complications and long-term prognosis,posing a significant challenge to surgeons.In recent years,the centralization of pancreatic surgery in high-volume centers,advancements in surgical techniques,and improvements in perioperative management of pancreatic cancer resection have significantly reduced the incidence of perioperative complications and mortality.In addition,surgeons have begun exploring minimally invasive approaches,such as laparoscopic and robot-assisted surgeries,for radical resection of pancreatic cancer,aiming to reduce surgical trauma,accelerate patient recovery,and improve quality of life.The technical feasibility of minimally invasive approaches has been validated in multiple studies through comparisons of the perioperative safety of minimally invasive pancreatic resection with that of conventional open surgery.However,research on the long-term oncologic prognosis of minimally invasive surgery for pancreatic cancer remains limited,and controversy persists regarding the suitability of minimally invasive methods for radical resection of pancreatic cancer.Therefore,surgeons should adhere to the fundamental principles of surgical oncology,including en bloc resection and the no-touch isolation technique,when they perform minimally invasive pancreatic cancer surgery.Additionally,more comparative studies are warranted to determine whether minimally invasive pancreatic cancer surgery offers survival benefits in the long term.This review aims to provide an objective evaluation of the role of minimally invasive techniques in radical resection of pancreatic cancer,while cautioning against compromising the principles of surgical oncology in the pursuit of minimally invasive approaches.

Severe acute pancreatitis(SAP)is one of the common surgical acute abdomen conditions,often accompanied by systemic or local complications.It is characterized by rapid onset,fast progression,and severe condition.Early detection and early treatment remain important ways to reduce the mortality rate of SAP.In clinical practice,personalized early intervention treatments tailored to patients with different etiologies and symptoms can achieve certain therapeutic effects in controlling the disease.With the updating of treatment concepts and techniques,minimally invasive surgery has replaced traditional open surgery and is widely applied in SAP,bringing about breakthrough changes in surgical methods.There are certain differences in the application of different surgical procedures in SAP.

Pancreatic cystic neoplasm (PCN) has multiple pathological types, with an increasing incidence year by year. PCN exhibits strong heterogeneity, and the risk of malignancy and malignant transformation varies significantly among different pathological types. Additionally, pancreatic resection carries high surgical risks, so multiple factors must be considered when making treatment decisions for PCN. Among various pathological types of PCN, intraductal papillary mucinous tumors, mucinous cystic neoplasms, and serous cystic neoplasms share similar imaging characteristics and relatively high incidence rates, but their treatment strategies differ markedly. This article, based on recommendations from domestic and international guidelines, literature reviews, and the author′s clinical experience, offers insights and solutions to the challenges in diagnosing and treating these three types of PCN. It emphasizes that it is essential to diagnose as accurately as possible through existing examination methods and MDT discussions; for patients who cannot be definitively diagnosed and have no risk factors, a close follow-up strategy should be adopted, and surgery should not be performed arbitrarily.

Pancreatic ductal adenocarcinoma is profoundly treatment-resistant, due to intrinsic properties of the tumor cells and the complex tumor microenvironment. Consequently, surgical resection of the primary tumor is still the only intervention that significantly prolongs patient survival. This points at an urgent need for more effective (neo)adjuvant strategies to increase the fraction of patients eligible to surgery and to counter post-surgery disease recurrence. The advent of single-cell RNA-sequencing has created an opportunity for the development of a highly potent, patient-tailored adjuvant treatment that is based on the infusion of genetically engineered autologous T-cells armed with tumor-reactive T-cell receptors as identified in the patient′s own tumor sample.

Severe acute pancreatitis(SAP)is one of the common surgical acute abdomen conditions,often accompanied by systemic or local complications.It is characterized by rapid onset,fast progression,and severe condition.Early detection and early treatment remain important ways to reduce the mortality rate of SAP.In clinical practice,personalized early intervention treatments tailored to patients with different etiologies and symptoms can achieve certain therapeutic effects in controlling the disease.With the updating of treatment concepts and techniques,minimally invasive surgery has replaced traditional open surgery and is widely applied in SAP,bringing about breakthrough changes in surgical methods.There are certain differences in the application of different surgical procedures in SAP.

Pancreatic cystic neoplasm (PCN) has multiple pathological types, with an increasing incidence year by year. PCN exhibits strong heterogeneity, and the risk of malignancy and malignant transformation varies significantly among different pathological types. Additionally, pancreatic resection carries high surgical risks, so multiple factors must be considered when making treatment decisions for PCN. Among various pathological types of PCN, intraductal papillary mucinous tumors, mucinous cystic neoplasms, and serous cystic neoplasms share similar imaging characteristics and relatively high incidence rates, but their treatment strategies differ markedly. This article, based on recommendations from domestic and international guidelines, literature reviews, and the author′s clinical experience, offers insights and solutions to the challenges in diagnosing and treating these three types of PCN. It emphasizes that it is essential to diagnose as accurately as possible through existing examination methods and MDT discussions; for patients who cannot be definitively diagnosed and have no risk factors, a close follow-up strategy should be adopted, and surgery should not be performed arbitrarily.

Pancreatic ductal adenocarcinoma is profoundly treatment-resistant, due to intrinsic properties of the tumor cells and the complex tumor microenvironment. Consequently, surgical resection of the primary tumor is still the only intervention that significantly prolongs patient survival. This points at an urgent need for more effective (neo)adjuvant strategies to increase the fraction of patients eligible to surgery and to counter post-surgery disease recurrence. The advent of single-cell RNA-sequencing has created an opportunity for the development of a highly potent, patient-tailored adjuvant treatment that is based on the infusion of genetically engineered autologous T-cells armed with tumor-reactive T-cell receptors as identified in the patient′s own tumor sample.

Alzheimer's disease(AD)is gradually increasing in prevalence and the complexity of its pathogenesis has led to a lengthy process of developing therapeutic drugs with limited success.Faced with this challenge,we proposed using a state-of-the-art drug screening algorithm to identify potential therapeutic com-pounds for AD from traditional Chinese medicine formulas with strong empirical support.We developed four deep neural network(DNN)models for AD drugs screening at the disease and target levels.The AD model was trained with compounds labeled for AD activity to predict active compounds at the disease level,while the acetylcholinesterase(AChE),monoamine oxidase-A(MAO-A),and 5-hydroxytryptamine 6(5-HT6)models were trained for specific AD targets.All four models performed excellently and were used to identify potential AD agents in the Kaixinsan(KXS)formula.High-scoring compounds underwent experimental validation at the enzyme,cellular,and animal levels.Compounds like 2,4-di-tert-butyl-phenol and elemicin showed significant binding and inhibitory effects on AChE and MAO-A.Additionally,13 compounds,including α-asarone,penetrated the blood-brain barrier(BBB),indicating potential brain target binding,and eight compounds enhanced microglial β-amyloid phagocytosis,aiding in clearing AD pathological substances.Our results demonstrate the effectiveness of deep learning models in devel-oping AD therapies and provide a strong platform for AD drug discovery.

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.