ObjectiveTo delineate imaging findings using an imaging platform and investigate the correlation between MRI characteristics of spinal cord atrophy and clinical diagnosis in children with spinal cord injury (SCI). MethodsImaging data of 150 children with SCI admitted to Beijing Bo'ai Hospital, China Rehabilitation Research Center, from January, 2002 to March, 2024 were collected and imported into the imaging platform. The anteroposterior and transverse diameters of the middle part of the spinal cord at the cross-section with the most severe atrophy were measured, and the relevant indicators of the previous normal spinal cord segment were measured as controls; the radiomic features were extracted. Clinical data of the children including gender, age, cause of injury, sensory level, motor level, spinal cord injury level, injury severity and disease course were collected. ResultsSpinal cord atrophy was identified in 81 cases (54%), among which 78 cases (96%) were American Spinal Injury Association Impairment Scale (AIS) grade A and 3 cases (4%) were AIS grade C. The upper boundary of the spinal cord atrophy site strongly correlated with the injury level, motor level and sensory level (r > 0.8, P < 0.001). ConclusionMore than half of children with SCI may develop secondary spinal cord atrophy, the vast majority of whom suffer from complete spinal cord injury; the upper boundary of spinal cord atrophy is correlated with the injury level.

ObjectiveCleft palate (CP) is a common congenital deformity often associated with velopharyngeal insufficiency (VPI), which disrupts the physiological coupling between respiration and speech. Conventional clinical assessments, such as nasometry and spirometry, provide limited static data and fail to visualize the dynamic spatiotemporal distribution of lung ventilation during phonation. This study introduces spatiotemporal electrical impedance tomography (ST-EIT) to evaluate speech-respiratory functional features in CP patients compared to normal controls (NC). The aim is to characterize multi-domain respiratory patterns and to validate an interpretable machine learning framework for providing objective, quantitative evidence for clinical assessment. MethodsSeventy-five participants were enrolled in this study, comprising 37 patients with surgically repaired CP and 38 healthy volunteers matched for age, gender, and body mass index (BMI). All subjects performed standardized sustained phonation tasks while undergoing synchronous monitoring with a 16-electrode EIT system and a pneumotachograph. A comprehensive feature engineering pipeline was developed to extract physiological parameters across 3 complementary domains. (1) Temporal domain: including inspiratory/expiratory phase duration (tPhase), time constants (Tau), and inspiratory-to-expiratory time ratios (TI/TE); (2) airflow domain: comprising mean flow, peak flow, and instantaneous flow at 25%, 50%, and 75% of tidal volume; and (3) spatial domain: quantifying global and regional tidal impedance variation (TIV), global inhomogeneity (GI), and center of ventilation (CoV). Extreme Gradient Boosting (XGBoost) classifiers were trained using 5 distinct data sources (Spirometry, Nasometry, Inspiratory-EIT, Expiratory-EIT, and fused ST-EIT). Model performance was rigorously evaluated via stratified 5-fold cross-validation, and Shapley additive explanations (SHAP) were employed to quantify global and local feature contributions. ResultsThe CP group exhibited a distinct respiratory phenotype compared to controls. In the temporal domain, CP patients showed significantly shorter inspiratory (1.60 s vs.1.85 s, P<0.001) and expiratory phase durations (2.45 s vs. 3.95 s, P<0.001), indicating a rapid, shallow breathing rhythm. In the airflow domain, while inspiratory flows were comparable, the CP group demonstrated significantly elevated mean and peak flows during the expiratory phase (P<0.001), reflecting compensatory respiratory effort. Spatially, CP patients presented significant ventilation redistribution, characterized by higher regional TIV in the right-anterior (ROI1) and left-posterior (ROI4) quadrants, but lower TIV in the left-anterior (ROI2) quadrant. In terms of diagnostic accuracy, the multi-modal ST-EIT model achieved the highest performance (AUC: 0.915±0.012, Accuracy: 0.843±0.019, F1-score: 0.872±0.017), substantially outperforming models based on spirometry (AUC: 0.721) or nasometry (AUC: 0.625) alone. Interpretability analysis revealed that spatial domain features were the most critical, contributing 53.4% to the model’s decision-making, followed by temporal (25.0%) and airflow (21.6%) features. ConclusionST-EIT successfully captures the temporal, airflow, and spatial deviations in CP speech respiration that are undetectable by conventional methods—specifically, rapid phase transitions, hyperdynamic expiratory airflow, and regional ventilation heterogeneity. This study validates ST-EIT as a robust, non-invasive, and radiation-free tool for characterizing speech-respiratory dysfunction, offering high clinical value for bedside screening, rehabilitation planning, and longitudinal monitoring of patients with cleft palate.

ObjectiveCleft palate (CP) is a common congenital deformity often associated with velopharyngeal insufficiency (VPI), which disrupts the physiological coupling between respiration and speech. Conventional clinical assessments, such as nasometry and spirometry, provide limited static data and fail to visualize the dynamic spatiotemporal distribution of lung ventilation during phonation. This study introduces spatiotemporal electrical impedance tomography (ST-EIT) to evaluate speech-respiratory functional features in CP patients compared to normal controls (NC). The aim is to characterize multi-domain respiratory patterns and to validate an interpretable machine learning framework for providing objective, quantitative evidence for clinical assessment. MethodsSeventy-five participants were enrolled in this study, comprising 37 patients with surgically repaired CP and 38 healthy volunteers matched for age, gender, and body mass index (BMI). All subjects performed standardized sustained phonation tasks while undergoing synchronous monitoring with a 16-electrode EIT system and a pneumotachograph. A comprehensive feature engineering pipeline was developed to extract physiological parameters across 3 complementary domains. (1) Temporal domain: including inspiratory/expiratory phase duration (tPhase), time constants (Tau), and inspiratory-to-expiratory time ratios (TI/TE); (2) airflow domain: comprising mean flow, peak flow, and instantaneous flow at 25%, 50%, and 75% of tidal volume; and (3) spatial domain: quantifying global and regional tidal impedance variation (TIV), global inhomogeneity (GI), and center of ventilation (CoV). Extreme Gradient Boosting (XGBoost) classifiers were trained using 5 distinct data sources (Spirometry, Nasometry, Inspiratory-EIT, Expiratory-EIT, and fused ST-EIT). Model performance was rigorously evaluated via stratified 5-fold cross-validation, and Shapley additive explanations (SHAP) were employed to quantify global and local feature contributions. ResultsThe CP group exhibited a distinct respiratory phenotype compared to controls. In the temporal domain, CP patients showed significantly shorter inspiratory (1.60 s vs.1.85 s, P<0.001) and expiratory phase durations (2.45 s vs. 3.95 s, P<0.001), indicating a rapid, shallow breathing rhythm. In the airflow domain, while inspiratory flows were comparable, the CP group demonstrated significantly elevated mean and peak flows during the expiratory phase (P<0.001), reflecting compensatory respiratory effort. Spatially, CP patients presented significant ventilation redistribution, characterized by higher regional TIV in the right-anterior (ROI1) and left-posterior (ROI4) quadrants, but lower TIV in the left-anterior (ROI2) quadrant. In terms of diagnostic accuracy, the multi-modal ST-EIT model achieved the highest performance (AUC: 0.915±0.012, Accuracy: 0.843±0.019, F1-score: 0.872±0.017), substantially outperforming models based on spirometry (AUC: 0.721) or nasometry (AUC: 0.625) alone. Interpretability analysis revealed that spatial domain features were the most critical, contributing 53.4% to the model’s decision-making, followed by temporal (25.0%) and airflow (21.6%) features. ConclusionST-EIT successfully captures the temporal, airflow, and spatial deviations in CP speech respiration that are undetectable by conventional methods—specifically, rapid phase transitions, hyperdynamic expiratory airflow, and regional ventilation heterogeneity. This study validates ST-EIT as a robust, non-invasive, and radiation-free tool for characterizing speech-respiratory dysfunction, offering high clinical value for bedside screening, rehabilitation planning, and longitudinal monitoring of patients with cleft palate.

ObjectiveGastric hemorrhage is one of the most common and life-threatening emergencies of the upper digestive tract. Early identification and continuous monitoring are essential for reducing rebleeding rates and mortality, particularly within the critical early hours after onset. Although endoscopy and radiological imaging can accurately localize bleeding sites, these approaches are invasive, resource-intensive, and unsuitable for continuous bedside monitoring. Electrical impedance tomography (EIT), as a noninvasive and radiation-free functional imaging technique, offers real-time visualization of conductivity distribution and has the potential for detecting intragastric bleeding based on the electrical contrast between blood and surrounding gastric tissues. In this study, a three-dimensional gastric EIT (3D-gEIT) framework is proposed to achieve noninvasive, real-time, and dynamic monitoring of gastric hemorrhage, with emphasis on spatial localization and quantitative volume assessment. MethodsA three-dimensional upper-abdominal simulation model incorporating the stomach, gastric wall, gastric contents, and surrounding tissues was established. Three electrode configurations, namely the dual layer ring, the four layer staggered ring, and the opposed dual plane array, were designed and systematically compared to evaluate their influence on depth sensitivity and spatial resolution. Based on the Tikhonov-Noser hybrid regularization scheme, a region-clustering constraint was introduced to develop the TK-Noser-RCC algorithm. This approach aggregates spatially adjacent elements with similar conductivity variations, thereby enhancing structural continuity and suppressing isolated noise artifacts. To validate the proposed framework, an upper-abdominal physical phantom was constructed using agar to simulate background tissue conductivity. Hemispherical high-conductivity inclusions with volumes ranging from 10 ml to 50 ml were attached to the inner gastric wall to mimic localized bleeding under different gastric filling states. Boundary voltages were acquired under a 120 kHz excitation current and reconstructed using the TK-Noser-RCC algorithm. Furthermore, an in vivo animal experiment was performed using a porcine model with adult-scale abdominal dimensions. A total of 100 ml of autologous blood was injected incrementally into the stomach to simulate progressive gastric hemorrhage, and time-difference EIT reconstruction was conducted at each injection stage to assess the dynamic system response under physiological conditions. ResultsSimulation results demonstrated that the opposed dual-plane electrode array achieved superior depth sensitivity distribution and spatial resolution. For a 40 ml hemorrhage model, the average ICC and SSIM improved by 55.9% and 38.8% compared with the dual-layer ring configuration, and by 64.0% and 39.5% compared with the four-layer staggered configuration. The proposed region-clustering constraint significantly enhanced reconstruction stability. Under added Gaussian noise of 40 dB and 30 dB, ICC values remained approximately 0.85, indicating effective artifact suppression and preservation of boundary integrity. In physical phantom experiments, reconstructed hemorrhage volumes increased approximately linearly with the preset hemispherical volumes, and the reconstructed high-conductivity regions closely matched the actual bleeding locations. Both empty-stomach and full-stomach conditions were evaluated, demonstrating that the opposed dual-plane configuration maintained stable imaging performance across varying gastric contents. In the animal experiment, reconstructed low-impedance regions expanded progressively with increasing injected blood volume. The spatial localization of the hemorrhage remained stable throughout the procedure, and no significant artifacts were observed. Quantitative analysis showed that reconstructed volume and average conductivity variation exhibited an approximately linear growth trend with injected blood volume, confirming the sensitivity of the system to dynamic intragastric conductivity changes. ConclusionThe proposed 3D-gEIT framework enables quantitative reconstruction of gastric hemorrhage volume and spatial distribution with improved depth sensitivity, structural continuity, and noise robustness compared with conventional EIT approaches. By integrating optimized electrode configuration and a region-clustering-constrained reconstruction algorithm, the system provides stable dynamic monitoring under both controlled phantom conditions and in vivo physiological environments. This method offers a noninvasive, real-time, and low-cost imaging strategy for early diagnosis, postoperative monitoring, and bedside surveillance of gastric bleeding.

Background/Aims: Regorafenib is recommended by guidelines and trials as a sequential second-line therapy following progression on first-line sorafenib or lenvatinib in hepatocellular carcinoma (HCC). However, efficacy is limited, highlighting the urgent need to screen suitable patients and develop sensitization strategies. Methods: Acquired sorafenib- or lenvatinib-resistant (SR or LR) HCC cell lines and organoids were established. Genome-wide CRISPR library screen was performed in SR or LR cell strains to identify synthetic lethal targets of regorafenib. RNA-seq and FITC-regorafenib efflux assay were used to elucidate ERBB3-driven downstream signaling. Preclinical mouse models of cell line- and patient-derived xenografts and clinical cohorts of HCC patients were employed to validate the efficacy of ERBB3-guided patient stratification. Results: Screening with CRISPR library, we showed that inhibition of ERBB3 was synthetic lethal with regorafenib in SR or LR cell strains and organoids. Mechanistically, SR or LR triggered feedback activation of ERBB3 signaling and mediated regorafenib efflux via ERBB3-HIF1A-ABCB1 cascade pathway, limiting sensitivity to regorafenib. Moreover, ERBB3-low tumors following SR or LR exhibited significant sensitivity to regorafenib, suggesting its potential as a predictive biomarker to screen optimal candidates for sequential therapy. Seribantumab, an ERBB3-targeting monoclonal antibody, inhibited ERBB3-HIF1A-ABCB1 cascade, and its combination with regorafenib exerted marked synergistic anti-tumor effects on ERBB3-high tumors resistant to sorafenib or lenvatinib both in vitro and in vivo. Conclusions This study revealed that ERBB3 was a key resistance factor driving limited efficacy to sequential regorafenib, but also an effective therapeutic target whose inhibition enhanced regorafenib sensitivity after SR or LR.

In modern society， the comorbidity of insomnia with amnesia has shown a significantly increasing incidence and become increasingly severe， emerging as a public health issue that endangers people's physical and mental health and quality of life. Anmei Dan （AMD）， originally recorded in the Shishi Milu by CHEN Shiduo in the Qing Dynasty， possesses profound theoretical foundations and distinct clinical advantages in ameliorating insomnia with amnesia. Basic research has unequivocally confirmed its definite therapeutic effects on insomnia with amnesia and revealed partial mechanisms. AMD is therefore a veritable classic prescription embodying the principle of treating different diseases with the same method for insomnia and amnesia. However， few researchers have reviewed the related research progress. This article systematically summarized the theoretical connotations of traditional Chinese medicine in treating insomnia with amnesia， delineated the multi-component material basis of AMD in ameliorating insomnia with amnesia （including various chemical components such as ginsenosides， jujubosides， and salvianolic acids）， and evaluate its multi-dimensional clinical efficacy （e.g.， prolonging total sleep time， improving sleep efficiency， and enhancing memory）. Moreover， it systematically summarizes the multi-pathway mechanisms of action. The results indicate that AMD has a clear material basis， definite clinical efficacy， and a favorable safety profile in ameliorating insomnia and amnesia. AMD may exert the therapeutic effect by regulating sleep-wake rhythms， enhancing synaptic plasticity， inhibiting neuroimmune inflammation， and modulating autophagy， oxidative stress， and energy metabolism. In conclusion， AMD exerts synergistic effects through multi-component， multi-dimensional， and multi-pathway approaches， serving as an important prescription for enriching and developing the theory of treating different diseases with the same method for insomnia with amnesia.

Objective To explore the effectiveness of an integrated laparoscopic simulation training course (best essential surgical technique training, BEST) in enhancing laparoscopic peritoneal suturing techniques in surgical residents.Methods As an integrated two-stage program, the BEST course applied basic laparoscopic training system with simple molds in phase Ⅰ training, and then adopted advanced laparoscopic training system, 3D Laparoscope and ex-vivo animal models in phase Ⅱ training. The laparoscopic suturing techniques were practiced in phase Ⅱ training. From August 2021 to July 2024, surgical residents in the second year of the national standardized training program were divided into pilot and control groups based on whether they had undergone the BEST course. Two cases of laparoscopic peritoneal suture were performed by the surgical residents under supervision in the department of gastrointestinal surgery. The operative time, quality of suture, and independent completion rate were compared between the two groups.Results A total of 33 surgical residents (19 in pilot group and 14 in control group) were included in this study, and a total of 66 cases of laparoscopic peritoneal suture were performed (38 in pilot group and 28 in control group). The operative time was significantly shorter in pilot group than that in control group (15.7 min vs. 17.5 min, P=0.025). The quality of suture was significantly better in pilot group compared to control group (P=0.023). In pilot group, all peritoneal sutures were performed by residents independently, whereas in control group, 3 cases (10.7%) were assisted by the supervisor, and the independent completion rate was different significantly (P=0.039).Conclusions The BEST course can help improve surgical residents′ laparoscopic peritoneal suturing techniques and could be promoted in the national standardized training program for surgical residents.

Objective:To evaluate the effect of toric collamer lens (TICL) rotation on myopia combined with astigmatism correction after V4c TICL implantation using standardized vector analysis.Methods:An observational case series study was performed.A total of 152 patients (268 eyes) who underwent V4c TICL implantation for the correction of myopia and myopic astigmatism were enrolled at Henan Eye Hospital from January to December 2021.The preoperative spherical diopter, cylindrical diopter, and spherical equivalent (SE) were -15.00 to -3.25 D, -5.00 to -0.50 D, -16.50 to -3.88 D, respectively.Postoperative TICL vault and axis were measured by anterior segment optical coherence tomography, and postoperative TICL rotation was calculated.Uncorrected visual acuity (UCVA), best corrected visual acuity (BCVA), spherical diopter, cylindrical diopter, SE, and target astigmatism vector were recorded before and 1 month after surgery.The effectiveness index, safety index, surgically induced astigmatism vector (SIA), margin of error (ME), absolute value of the difference vector |DV|, correction index (CI), and achievement index (IS) were calculated based on the subjective refraction results 1 month after surgery and the cylindrical axis of the V4c TICL.Vector analysis parameters was compared among patients with different preoperative astigmatism, intraoperative TICL fixation, postoperative TICL rotation, and postoperative vault.The correlation between postoperative TICL rotation and TICL fixed angle deviation, postoperative vault, visual acuity and refraction, and vector analysis parameters were evaluated.This study adhered to the Declaration of Helsinki.The study protocol was approved by the Ethics Committee of Henan Eye Hospital (No.HNEECKY-2021[13]).Written informed consent was obtained from each subject.Results:At 1 month postoperatively, the mean safety and efficacy indices were 1.27 and 1.29, respectively.There was no statistically significant difference between the predicted SE of (-0.11±0.13)D and the postoperative SE of (-0.07±0.52)D ( t=-0.994, P=0.321).UCVA, BCVA and cylinder diopter in the operative eyes were all improved after surgery compared to before surgery and the differences were statistically significant ( t=17.854, 5.446, -25.634; all P<0.001).The rotation of V4c TICL was 0° to 25°, with a mean of (5.41±4.35)°, which was positively correlated with the V4c TICL fixed angle deviation ( rs=0.461, P<0.001), negatively correlated with postoperative cylindrical diopter and positively correlated with postoperative UCVA, |DV| and SIA ( r=-0.360, 0.191, 0.205, 0.142; all P<0.05).Vector analysis between groups showed that vault, SIA and |DV| were higher and CI and IS were lower in low astigmatism group than in high astigmatism group ( Z=-3.017, -13.569, -2.793, -2.761, -4.779; all P<0.05).V4c TICL rotation and |DV| were lower in low fixation angle difference group than in high fixation angle difference group ( Z=-7.865, -2.080; both P<0.05).Preoperative cylindrical diopter, intraoperative V4c TICL fixed angle deviation, SIA and |DV| were lower in low rotation group than in high rotation group ( Z=-2.104, -4.578, -2.456, -2.090; all P<0.05).There were no statistically significant differences in the TICL rotation or in each vector between patients with different vault after the surgery (all P>0.05). Conclusions:V4c TICL implantation can achieve good results for the correction of myopia and myopic astigmatism.There is a slight difference between the fixation axis and the target axis of V4c TICL, which affects the rotation of V4c TICL and |DV|.Postoperative V4c TICL rotation is related to TICL fixed angle deviation, postoperative UCVA, SIA, |DV| and postoperative cylindrical diopter.Postoperative vault has no significant effect on TICL rotation and differences in each vector.

Objective To investigate the anesthesia effects of different concentrations of sevoflurane combined with propofol during primary liver cancer resection surgery,as well as the changes in immune function in patients.Methods Using single-blind method,120 cases of primary hepatocellular carcinoma admitted to the Third Affiliated Hospital of Naval Military Medical University from January 2023 to September 2023 were prospectively selected as the study subjects,and the patients were randomly(using the randomized numerical table method)included in the control group(60 cases)and the observation group(60 cases).During hepatic cancer resection,the control group was given 0.5 alveolar minimum effective concentration(MAC)sevoflurane combined with propofol target-controlled infusion anesthesia,and the observation group was given 1.0 MAC sevoflurane combined with propofol target-controlled infusion anesthesia,and both groups were observed for 3 d postoperatively.The perioperative related indexes,the sedation and quality of awakening in the immediate moment of extubation,15 min after extubation,and 30 min after extubation,the cognitive function before and at 1 and 3 d postoperatively,vital signs before induction of anesthesia,after induction of anesthesia,at the moment of intubation,at the end of surgery,immune function before and 1 d postoperative,and adverse reactions during the observation period were compared between the two groups.Results The time for extubation,recovery of spontaneous respiration,recovery of orientation,and awakening in the observation group were(11.25±1.69)min,(9.76±1.34)min,(69.23±3.35)min,and(10.13±1.43)min,and the control group were(14.57±2.28)min,(13.55±2.76)min,(73.44±4.52)min,(14.26±2.25)min,all of which were shorter in the observation group than in the control group(P＜0.05).The Ramsay sedation score at the immediate moment of extubation was(4.16±0.22)in the observation group,and(3.21±0.10)in the control group;the standardized(Aldrete)score in the awakening room of the observation group at the immediate moment of extubation,and 15 min after extubation were(9.56±0.12)and(9.77±0.20),respectively,and the control group was(9.02±0.13),respectively,(9.05±0.17)points;the scores of the brief mental state examination(MMSE)scale in the observation group were(26.23±1.12)points and(25.17±0.98)points in the control group in the 1 d postoperative period,which were higher than those of the control group(P＜0.05).The heart rate(HR)at the moment of intubation and at the end of operation in the observation group were(73.08±4.10)beats/min,(75.27±6.03)beats/min,and the mean arterial pressure(MAP)was(81.56±4.49)mmHg and(86.07±5.48)mmHg,respectively,and in the control group the HR was(75.47±5.78)beats/min,(77.91±6.79)beats/min,and the MAP was(85.22±5.08)mmHg and(88.25±6.01)mmHg in the observation group,respectively,which were lower than those in the control group(P＜0.05).The whole blood natural killer(NK)cells,CD4+and CD4+/CD8+in the observation group at 1 d postoperatively were(35.62±5.54)％,(50.09±3.32)％,and(1.42±0.25),the control group were(24.12±4.09)％,(43.17±4.20)％,and(1.20±0.19),the observation group was higher than the control group(P＜0.05);whole blood CD8+was(26.55±3.02)％in the observation group and(28.71±4.45)％in the control group,the observation group was lower than the control group(P＜0.05).The total incidence of adverse reactions during the observation period was 16.67％in the observation group and 5.00％in the control group,which was higher than the control group(P＜0.05).Conclusion Compared with 0.5 MAC sevoflurane combined with propofol target-controlled infusion anesthesia,1.0 MAC sevoflurane combined with propofol target-controlled infusion anesthesia had less effect on hemodynamics and immune function in patients undergoing resection for primary hepatocellular carcinoma,and it could improve the quality of patients'awakening,cognitive function,and promote postoperative recovery,and the anesthesia was more effective,but it had more adverse effects.

Objective This study aimed to develop an automated method for syndrome element differenti-ation in Traditional Chinese Medicine(TCM).Methods We first constructed and trained an Instruction-tuned Multi-Task TCM text embedding model(Instr-MT-TCM)using four distinct TCM task datasets,including domain knowledge,synonymous terminology,syndrome differentiation and treatment,and TCM case labels.Subsequently,five TCM diagnostics experts holding master's degrees or higher were organized to screen a real-world TCM case dataset and annotate symptoms and signs.The purpose was to evaluate the F1-score of the proposed method—the combination of Instr-MT-TCM and a Large Language Model(LLM)—by comparing its performance against the manual annotation result on the syndrome element differentiation task.Finally,to validate its feasibility in real-world clinical settings,the method was applied to 48 prostate cancer cases to calculate the syndrome element scores.Results The Instr-MT-TCM model showed rapid performance improvement in its early training phase,achieving a Recall@1(R@1)of 0.848.Experts curated a dataset of 1,793 real-world clinical cases,covering 34 common diseases and 66 syndrome patterns.In the syndrome element differentiation task,the collaborative framework of LLM and Instr-MT-TCM achieved a mean F1-score of 0.927,outperforming the 0.512 from manual annota-tion.The syndrome element analysis revealed that the predominant elements of disease nature were fire(heat)and yin deficiency,while the main elements of disease location were bladder and kidney.Conclusion This study proposes and validates a novel method for automated TCM syndrome element dif-ferentiation based on the synergy between LLM and our custom Instr-MT-TCM model.Achieving a high F1-score(0.927)on real-world data,the method demonstrates excellent accuracy and generalization ability.Its application in prostate cancer analysis highlights its significant clinical potential,offering effective technical support,and a new research direction for intelligent TCM syndrome element differentiation.