Lung cancer， with persistently high incidence and mortality rates， remains a significant global health challenge. By taking the study on the experience in diagnosis and treatment of lung cancer with phlegm-dampness and blood stasis syndrome by distinguished traditional Chinese medicine physicians of the Sichuan School as an example， the diagnosis and treatment system for lung cancer with phlegm-dampness and blood stasis syndrome， which was formed in response to the humid and foggy environment of the Sichuan Basin， possesses unique value. However， traditional inheritance modes face challenges such as fragmentation， lack of standardization， and insufficient quantification， which hinder the promotion and application of this experience. This research focused on how to leverage multimodal data and artificial intelligence-generated content （AIGC） to achieve precise analysis， intelligent inheritance， and clinical innovation of the experience in diagnosis and treatment of lung cancer with phlegm-dampness and blood stasis syndrome by distinguished traditional Chinese medicine physicians of the Sichuan School. By integrating multimodal data （encompassing four diagnostic methods of traditional Chinese medicine， modern medical imaging， clinical laboratory tests， molecular biology， and regional environmental information）， a precise diagnosis and treatment system integrating macro and micro perspectives for the "disease， syndrome， and pathogenesis" was constructed. The research yielded the following results： （1） In precise syndrome differentiation， the objective quantification of the phlegm-dampness and blood stasis syndrome was achieved. By constructing a "four diagnostic methods， imaging， and molecule" correlation model， the study revealed intrinsic links between tongue and pulse parameters and the tumor microenvironment， as well as between regional climatic factors and syndrome characteristics， enabling real-time dynamic monitoring of efficacy. （2） In elucidating patterns， the study systematically explored the syndrome differentiation thoughts of Sichuan School physicians， such as the timing of purgation and tonification. A "pathogenesis， syndrome complex， and prescriptions and herb" network model was constructed， which accurately elucidated the synergistic action mechanisms of core herb pairs and quantified the dynamic compatibility patterns of reinforcing healthy Qi and eliminating pathogenic factors. （3） In intelligent empowerment， an auxiliary system integrating intelligent syndrome differentiation， treatment plan generation， and efficacy evaluation was built. This system can fuse regional characteristics with individual data， dynamically generate and optimize personalized prescriptions aligned with the experience of Sichuan School， and predict efficacy trends and potential adverse reactions. The integration of multimodal data and AIGC can effectively facilitate the structured inheritance and clinical translation of distinguished physicians' experience. The established intelligent diagnosis and treatment model integrating traditional Chinese medicine and Western medicine demonstrates clear potential in prolonging patients' progression-free survival， alleviating symptoms， and reducing adverse reactions to treatment. This study provides a referential methodological framework for the traditional Chinese medicine experience in diagnosis and treatment of lung cancer， especially the empirical inheritance and modernized development of regional academic schools. It contributes to advancing clinical diagnosis and treatment toward greater precision and personalization.

Background Manganese is an essential trace element for the human body and maintains normal development of many organs including the brain. However, long-term exposure to a high manganese environment or excessive manganese intake will lead to manganese poisoning and result in neurological diseases, and currently no effective treatment plan is available. Objective To develop an animal model for subchronic manganese exposure and assess the impact of Dendrobium nobile Lindl. alkaloids (DNLA) on manganese associated behavioral and hippocampal effects in rats. Methods Fifty male SPF SD rats were randomly allocated into a control group (0.9% normal saline by intraperitoneal injection), two experimental groups [7.5 mg·kg⁻¹ (low) or 15 mg·kg⁻¹ (high) of MnCl₂·4H₂O by intraperitoneal injection], and two DNLA antagonistic groups [15 mg·kg⁻¹ MnCl₂·4H₂O by intraperitoneal injection then either 20 mg·kg⁻¹ (low) or 40 mg·kg⁻¹ (high) DNLA by oral administration]. All groups of rats were adminaistered 5 d per wek, once a day, for consecutive 13 weeks. Following modeling, neurobehavioral assessments were conducted using open field, Morris water maze, and Y maze. Inductively coupled plasma mass spectrometry (ICP-MS) was utilized to measure manganese levels in the blood and brain tissues of the rats, and hematoxylin-eosin (HE) staining was employed to examine neuronal morphological changes in the hippocampal tissues of the rats. Results The neurobehavioral tests revealed that the manganese-exposed rats exhibited decreased total movement distance, prolonged central zone dwelling time, and reduced motor activity in the open field test, indicating tendencies toward depression and anxiety (P<0.05). In the Y-maze test, the mean exploration distance in the novel arm, the number of entries into the novel arm, and the time spent in the novel arm of the managanses-exposed rats were all reduced, while the latency period increased, suggesting impaired spatial exploration and learning-memory functions (P<0.05). In the Morris water maze navigation test, the escape latency was significantly longer in the manganese-exposed rats compared to the control group, and the number of platform crossings decreased in the spatial probe test, indicating a significant decline in spatial learning and memory (P<0.05). The ICP-MS analysis showed elevated manganese concentrations in the blood and hippocampus of the exposed rats (P<0.05), and the histopathological observation revealed hippocampal damage. Following the DNLA intervention, the manganese-exposed rats showed increased total movement distance and reduced central zone dwelling time in the open field test (P<0.05). In the Y-maze test, the mean exploration distance in the novel arm, the number of entries into the novel arm, and the time spent in the novel arm increased, while the latency period decreased, suggesting alleviation of anxiety and improved exploratory behavior (P<0.05). In the Morris water maze test, the escape latency gradually shortened, and both the number of platform crossings and the percentage of time spent in the target quadrant increased, indicating improved spatial learning and memory (P<0.05). Additionally, the manganese levels in the blood and hippocampus decreased (P<0.05), and the hippocampal pathological changes were partially restored. Conclusion DNLA demonstrates the ability to counteract multiple neurotoxic effects following the elevation of manganese levels in the blood and hippocampal tissues of rats induced by subchronic manganese exposure. Specifically, DNLA is shown to ameliorate the behavioral alterations observed in rats after manganese exposure, and mitigate the hippocampal damage in manganese-exposed rats.

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

BackgroundPrevious studies have identified a close relationship among psychological neglect and abuse， negative affect， different stages of adolescence， and suicidal ideation. However， the mechanisms underlying the impact of psychological abuse and neglect on suicidal ideation among left-behind adolescents remain unclear， and this field of research is still in its relative infancy. ObjectiveTo explore the relationship between psychological neglect/abuse and suicidal ideation among left-behind adolescents， as well as the mediating role of negative affect and the moderating effect of different stages of adolescence， so as to provide insights for preventing and intervening suicidal ideation in this population. MethodsFrom November 2021 to May 2022， a cluster random sampling technique was utilized to select 2 309 left-behind adolescents in western China. Assessments were conducted using the Child Psychological Abuse and Neglect Scale （CPANS）， the Positive and Negative Suicide Ideation （PANSI） and the Positive and Negative Affect Schedule for Children （PANAS-C）. Spearman correlation coefficients were calculated across all samples， and Process 4.1 was employed to test the mediating role of negative affect and the moderating role of different stages of adolescence in the pathway linking psychological abuse/neglect to suicidal ideation. ResultsA total of 2 119 left-behind adolescents （mean age： 14.94±1.20 years） completed the study， with males comprising 51.34% （1 088/2 119） and females 48.66% （1 031/2 119）.Among left-behind adolescents， scores on CPANS psychological neglect subscale showed positive correlations with both psychological abuse subscale scores and PANAS-C negative affect subscale scores （r=0.446， 0.496， P<0.01）. Additionally， CPANS psychological neglect and psychological abuse subscale scores were also positively correlated with PANSI scores （r=0.487， 0.508， P<0.01）. Furthermore， PANAS-C negative affect subscale scores demonstrated a positive correlation with PANSI scores （r=0.499， P<0.01）. Negative affect partially mediated the relationship between psychological abuse/psychological neglect and suicidal ideation， with effect sizes of 0.166 （95% CI： 0.141~0.191） and 0.131 （95% CI： 0.112~0.152）. Different stages of adolescence moderated the latter part （negative emotion → suicidal ideation） of the indirect mediation path from psychological neglect to suicidal ideation through negative affect （β=-0.066， P<0.01）. ConclusionBoth psychological neglect and psychological abuse may influence suicidal ideation among left-behind adolescents via negative affect. Moreover， different stages of adolescence may moderate the indirect path from psychological neglect to suicide ideation through negative affect.

Obstructive sleep apnea (OSA) is an increasingly widespread sleep-breathing disordered disease, and is an independent risk factor for many high-risk chronic diseases such as hypertension, coronary heart disease, stroke, arrhythmias and diabetes, which is potentially fatal. The key to the prevention and treatment of OSA is early diagnosis and treatment, so the assessment and diagnostic technologies of OSA have become a research hotspot. This paper reviews the research progresses of severity assessment parameters and diagnostic technologies of OSA, and discusses their future development trends. In terms of severity assessment parameters of OSA, apnea hypopnea index (AHI), as the gold standard, together with the percentage of duration of apnea hypopnea (AH%), lowest oxygen saturation (LSpO₂), heart rate variability (HRV), oxygen desaturation index (ODI) and the emerging biomarkers, constitute a multi-dimensional evaluation system. Specifically, the AHI, which measures the frequency of sleep respiratory events per hour, does not fully reflect the patients’ overall sleep quality or the extent of their daytime functional impairments. To address this limitation, the AH%, which measures the proportion of the entire sleep cycle affected by apneas and hypopneas, deepens our understanding of the impact on sleep quality. The LSpO₂ plays a critical role in highlighting the potential severe hypoxic episodes during sleep, while the HRV offers a different perspective by analyzing the fluctuations in heart rate thereby revealing the activity of the autonomic nervous system. The ODI provides a direct and objective measure of patients’ nocturnal oxygenation stability by calculating the number of desaturation events per hour, and the biomarkers offers novel insights into the diagnosis and management of OSA, and fosters the development of more precise and tailored OSA therapeutic strategies. In terms of diagnostic techniques of OSA, the standardized questionnaire and Epworth sleepiness scale (ESS) is a simple and effective method for preliminary screening of OSA, and the polysomnography (PSG) which is based on recording multiple physiological signals stands for gold standard, but it has limitations of complex operations, high costs and inconvenience. As a convenient alternative, the home sleep apnea testing (HSAT) allows patients to monitor their sleep with simplified equipment in the comfort of their own homes, and the cardiopulmonary coupling (CPC) offers a minimal version that simply analyzes the electrocardiogram (ECG) signals. As an emerging diagnostic technology of OSA, machine learning (ML) and artificial intelligence (AI) adeptly pinpoint respiratory incidents and expose delicate physiological changes, thus casting new light on the diagnostic approach to OSA. In addition, imaging examination utilizes detailed visual representations of the airway’s structure and assists in recognizing structural abnormalities that may result in obstructed airways, while sound monitoring technology records and analyzes snoring and breathing sounds to detect the condition subtly, and thus further expands our medical diagnostic toolkit. As for the future development directions, it can be predicted that interdisciplinary integrated researches, the construction of personalized diagnosis and treatment models, and the popularization of high-tech in clinical applications will become the development trends in the field of OSA evaluation and diagnosis.

Objective　To analyze the clinical distribution of carbapenem-resistant Enterobacter cloacae (CR-ECL) and changes in carbapenemase enzyme types in Ningbo and to provide a guide for the rational application of antibiotics in clinical practice. Methods　Clinical isolates of CR-ECL were selected in a hospital in Ningbo from 2012 to 2022. Bacterial identification and drug sensitivity testing were performed using the VITEK-2 COMPACT automated microbiology system. Strain confirmation was conducted using the VITEK MS mass spectrometry system. The presence of CR-ECL was confirmed using the E-Test method. Carbapenemase production in CR-ECL was determined using a rapid carbapenemase detection kit and polymerase chain reaction (PCR). Results　A total of 1 428 isolates of ECL were detected in a hospital in Ningbo from 2012 to 2022, of which 36 strains were CR-ECL, accounting for 2.52%. The top three sample sources of CR-ECL were sputum (52.78%), urine (19.44%), and bile (13.89%). The patients were mainly from neurosurgery wards (22.22%), general surgery (13.89%), and ICU wards (11.11%). The separation rate of CR-ECL showed no significant difference between different genders and age groups. The resistance rates of CR-ECL to ertapenem, imipenem, and meropenem were 94.44%, 58.33%, and 36.11% respectively. The resistance rates of CR-ECL to third/fourth generation cephalosporins, aztreonam, enzyme-inhibitor complexes, and quinolones were all above 69.50%, significantly higher than those of non-carbapenem-resistant Enterobacter cloacae (NCR-ECL) strains (P<0.05). For aminoglycosides, CR-ECL and NCR-ECL both maintained low resistance rates (0% and 0.22%, respectively). Among the 36 CR-ECL strains, 31 strains (86.11%) were carbapenemase producers, including three types: NDM (28 strains, 77.78%), KPC (4 strains, 11.11%), and IMP (2 strains, 5.56%). The other two carbapenemase types, OXA-48 and VIM, were not detected. The consistency rate between the rapid detection of carbapenem enzyme type and PCR detection was 100%. Conclusions　The detection rate of CR-ECL in a hospital in Ningbo showed a trend of fluctuation. CR-ECL strains are distributed across different departments and various samples of hospitals, with no differences in distribution observed between genders or age groups. Clinical isolated CR-ECL mainly produced NDM-type carbapenemases, but the enzyme types such as KPC and IMP have also emerged in recent years. The rapid identification of carbapenemase types can play an important guiding role in the clinical treatment of CR-ECL infection.

Objective To compare the benefits and drawbacks of primary patch expansion versus pericardial tube right ventricular-pulmonary artery connection in patients diagnosed with pulmonary atresia with ventricular septal defect (PA/VSD). Methods A retrospective study was conducted on patients diagnosed with PA/VSD who underwent primary right ventricular-pulmonary artery connection surgery at our center between 2010 and 2020. Patients were categorized into two groups based on the type of right ventricular-pulmonary artery connection: a pericardial tube group and a patch expansion group. Clinical data and imaging findings were compared between the two groups. Results A total of 51 patients were included in the study, comprising 31 males and 20 females, with a median age of 12.57 (4.57, 49.67) months. The pericardial tube group included 19 patients with a median age of 17.17 (7.33, 49.67) months, while the patch expansion group consisted of 32 patients with a median age of 8.58 (3.57, 52.72) months. In both groups, the diameter of pulmonary artery, McGoon index, and Nakata index significantly increased after treatment (P<0.001). However, the pericardial tube group exhibited a longer extracorporeal circulation time (P<0.001). The reoperation rate was notably high, with 74.51% of patients requiring further surgical intervention, including 26 (81.25%) patients in the patch expansion group and 12 (63.16%) patients in the pericardial tube group. No statistical differences were observed in long-term cure rates or mortality between the two groups (P＞0.005). Conclusion In patients with PA/VSD, both patch expansion and pericardial tube right ventricular-pulmonary artery connection serve as effective initial palliative treatment strategies that promote pulmonary vessel development and provide a favorable foundation for subsequent radical operations. However, compared to the pericardial tube approach, the patch expansion technique is simpler to perform and preserves some intrinsic potential for pulmonary artery development, making it the preferred procedure.

Objective:To investigate the value of habitat radiomic features based on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced MRI in establishing a predictive model for cytokeratin 19 (CK19) expression in hepatocellular carcinoma (HCC) and to evaluate its role in prognostic risk stratification.Methods:This multicenter case-control study retrospectively enrolled 489 patients with pathologically confirmed HCC who underwent Gd-EOB-DTPA-enhanced MRI between June 2016 and June 2024. Among them, 346 patients from the First Affiliated Hospital of Soochow University were divided into a training cohort ( n=245) and an internal test cohort ( n=101) via stratified sampling at a 7∶3 ratio. And 143 patients from Nantong Third Hospital Affiliated to Nantong University served as an external validation cohort. The training cohort included 53 CK19-positive and 192 CK19-negative patients. The internal test cohort included 21 CK19-positive and 80 CK19-negative patients. The external validation cohort included 30 CK19-positive and 113 CK19-negative patients. Univariate logistic regression analysis was performed to identify potential factors associated with CK19 expression, and a clinical-radiologic model was constructed. The k-means clustering algorithm was applied to segment target HCC lesions into 3 subregions. Radiomic features were extracted and selected from these habitat subregions. Habitat radiomics models were constructed for the arterial phase (AP), portal venous phase, hepatobiliary phase (HBP), and combined phases (CP). Multivariate logistic regression analysis identified independent clinical and radiologic predictors of CK19 expression, and the optimal habitat model score was integrated to build a clinical-radiologic-habitat combined model. The area under the receiver operating characteristic curve (AUC) was used to evaluate model predictive performance. Recurrence-free survival (RFS) was analyzed using the Kaplan-Meier method and the differences in survival curves were compared with the log-rank test. Results:Univariate logistic regression analysis revealed that alpha-fetoprotein (AFP) ( OR=2.629, 95% CI 1.412-4.896, P=0.002), AP enhancement ( OR=3.636, 95% CI 1.642-8.052, P=0.001), AP peritumoral enhancement ( OR=2.219, 95% CI 1.084-4.542, P=0.029), and HBP peritumoral hypointensity ( OR=2.010, 95% CI 1.004-4.021, P=0.049) were potential factors associated with CK19 expression, which were incorporated into the clinical-radiologic model. In the internal and external validation cohorts, the AUC of the clinical-radiologic model was 0.690 (95% CI 0.590-0.778) and 0.650 (95% CI 0.565-0.727), respectively. The habitat radiomics model based on CP images demonstrated the highest performance. It achieved AUC of 0.729 (95% CI 0.622-0.836) and 0.725 (95% CI 0.607-0.842) in the internal and external validation cohorts, respectively. Multivariate analysis identified AFP ( OR=2.494, 95% CI 1.163-5.348, P=0.019), AP enhancement ( OR=5.230, 95% CI 1.868-14.643, P=0.002) and habitat radiomics model score ( OR=4.105, 95% CI 2.643-6.368, P<0.001) as independent predictors of CK19 positivity. Based on these factors, a combined clinical-radiologic-habitat combined model was established. The clinical-radiologic-habitat combined model achieved AUCs of 0.767 (95% CI 0.671-0.846) and 0.730 (95% CI 0.649-0.801) in the internal and external validation cohorts, respectively. Significant differences in RFS were observed between the CK19-positive group (25.1 month) and CK19-negative group (51.0 month) as predicted by the clinical-radiologic-habitat model ( χ2=4.17, P=0.041). Conclusion:The clinical-radiologic-habitat combined model based on Gd-EOB-DTPA-enhanced MRI habitat radiomics demonstrates good predictive performance for CK19 expression in HCC and offers valuable prognostic stratification for clinical practice.

Objective:To explore the value of the deep learning model based on gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid (Gd-EOB-DTPA) enhanced MRI in preoperatively predicting vessels completely encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC).Methods:This study adopted a case-control design to retrospectively analyze 420 patients with HCC confirmed by postoperative pathology who underwent Gd-EOB-DTPA enhanced MRI between June 2016 and March 2023. A total of 420 patients were divided into a training set ( n=305) from the First Affiliated Hospital of Soochow University and an external validation set ( n=115) from Affiliated Nantong Hospital 3 of Nantong University. Based on postoperative pathological findings, patients were stratified into VETC-positive and VETC-negative groups. The training set comprised 161 VETC-positive cases and 144 VETC-negative cases, while the external validation set included 55 VETC-positive cases and 60 VETC-negative cases. Tumor regions of interest in arterial, portal venous, and hepatobiliary phases were manually delineated using ITK-SNAP software. Pre-trained Vgg19, Densenet121, and Vision Transformer (ViT) models were employed for transfer learning, extracting deep learning features from each image. Feature data were processed using FAE software, and 12 logistic regression models (arterial phase, portal venous phase, hepatobiliary phase, and combined three-phase models) were constructed to select the optimal deep learning model. Independent predictors in clinical characteristics were identified through univariate and multivariate logistic analyses to establish a clinical model for predicting VETC pattern. Subsequently, a clinical-deep learning fusion model was developed by integrating these clinical predictors with the optimal deep learning features. Model performance in predicting VETC-positive HCC was evaluated using receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA). Results:In the external validation set, the area under the curve (AUC) of the Vgg19 model in the arterial phase, portal venous phase, hepatobiliary phase, and combined three-phase, respectively were 0.799,0.756,0.789,0.821, which were higher than those of Densenet121 (AUC: 0.544,0.581,0.544,0.583) and ViT (AUC: 0.740,0.752,0.785,0.767) model. The three-phase combined Vgg19 model achieved the highest AUC of 0.821 (95% CI 0.746-0.897). Multivariate logistic regression identified alpha-fetoprotein level ( OR=1.826,95% CI 1.069-3.120, P=0.028) and tumor diameter ( OR=1.329,95% CI 1.206-1.466, P<0.001) as independent predictors of VETC-positive HCC, forming the clinical model with an AUC of 0.789 (95% CI 0.703-0.859). The clinical-deep learning fusion model further achieved the AUC of 0.825 (95% CI 0.749-0.900). Calibration curves confirmed high concordance between predicted and actual probabilities for the three-phase Vgg19 model, while DCA revealed greater net clinical benefit for the combined Vgg19 and fusion models compared with the clinical model alone. Conclusions:The deep learning model based on Gd-EOB-DTPA enhanced MRI can be used to predict VETC of HCC preoperatively, among which the three-phase combined Vgg19 model and the clinical-deep learning model provide high predictive value.

Ferroptosis is a programmed cell death depends on iron and lipid peroxidation,which has been recognized as the key pathogenic factor for the occurrence of various diseases in recent years,especially playing a significant role in neurodegenerative diseases.Ferroptosis triggers lipid peroxidation and oxidative stress in neuronal cells,leading to neuronal damage and death,thereby accelerating disease progression.Hydrogen sulfide,as an endogenous gaseous signaling molecule,exhibits multiple protective effects,including anti-inflammatory,antioxidant,and anti-ferroptosis properties.Hydrogen sulfide can effectively inhibit the occurrence of ferroptosis through various mechanisms,such as regulating iron metabolism,inhibiting lipid peroxidation,and enhancing the activity of antioxidant enzymes,thereby slowing down the progression of neurodegenerative diseases.This article reviews the related research progress on hydrogen sulfide and ferroptosis and ferroptosis-mediated neurodegenerative diseases,and analyzes the underlying mechanisms,aims to provide new insights and theoretical foundations for the treatment of neurodegenerative diseases.