ObjectiveTo develop a machine learning (ML)-based prediction model for neurological rehabilitation outcomes of stroke patients. MethodsA total of 420 stroke patients admitted to the Fuzhou First People's Hospital from October, 2022 to October, 2024 were enrolled as the training set. According to the modified Rankin Scale (mRS) scores three months after discharge, the patients were divided into prognosis group (n = 289) and poor prognosis group (n = 131). An additional 180 stroke patients hospitalized in the same hospital from November, 2024 to April, 2025 were selected as the validation set. Univariate analysis, least absolute shrinkage and selection operator regression, and multivariate logistic regression were performed to identify independent influencing factors for the prognosis of neurological function recovery. Using the screened independent influencing factors as feature variables, six ML models were established, including logistic regression, linear discriminant analysis, naive Bayes, support vector machine, random forest and extreme gradient boosting (XGBoost). The area under the receiver operating characteristic curve (AUC), confusion matrix indicators (accuracy, precision, recall and F1-score), calibration curve and decision curve analysis were adopted to evaluate the predictive efficacy, calibration degree and clinical net benefit of each model, with external validation conducted in the validation set. The SHapley Additive exPlanations framework was used to interpret the optimal model, and bar charts were applied to visualize the feature importance of the best model. ResultsAge, National Institutes of Health Stroke Scale (NIHSS) score, collateral circulation grading, fasting plasma glucose (FPG), lymphocyte percentage (LYMPH%), and homocysteine (Hcy) were independent risk factors for poor neurological rehabilitation prognosis (P < 0.05). For the XGBoost model, the AUC of the training and validation sets were 0.963 (95%CI 0.947 to 0.979) and 0.825 (95%CI 0.764 to 0.885), respectively, while the accuracy was 88.81% and 77.22%, the precision was 92.86% and 68.42%, the recall was 69.47% and 47.27%, and the F1-score was 79.48% and 55.91%, optimal in both calibration and clinical net benefit. The feature importance ranking for the XGBoost model from high to low was NIHSS score, age, collateral circulation grading, FPG, Hcy and LYMPH%. ConclusionThe interpretable XGBoost ML model exhibits excellent predictive efficacy and favorable clinical applicability in predicting neurological rehabilitation outcomes for stroke patients.

Parkinson's disease(PD) is a neurodegenerative disorder characterized by the progressive degeneration of dopaminergic neurons in the substantia nigra and the accumulation of Lewy bodies. While conventional drugs like levodopa can improve early symptoms, their efficacy diminishes over time, and they may cause severe side effects. Traditional Chinese medicine(TCM), with its multi-target therapeutic approach, has shown unique advantages in PD treatment, particularly in slowing disease progression and improving clinical symptoms. The nuclear factor erythroid 2-related factor 2(Nrf2)/heme oxygenase-1(HO-1) signaling pathway plays a critical role in cellular antioxidation, anti-inflammation, and cellular repair mechanisms, which are crucial for neuroprotection against PD. Studies indicate that TCM regulates the Nrf2/HO-1 pathway to enhance neuronal antioxidative capacity, inhibit neuroinflammation, promote dopaminergic neuron repair and survival, and slow pathological progression. This review explores the neuroprotective role of the Nrf2/HO-1 pathway in PD patients, including alleviating oxidative stress, suppressing neuroinflammation, promoting neuronal repair, and regulating iron metabolism and autophagy. It also discusses the mechanisms by which TCM active ingredients(flavonoids, alkaloids, terpenes, saponins, polyphenols, etc.), single herbs(Cistanche deserticola, Uraria crinite, and Melissa officinalis, etc.), and formulas(Bushen Jianpi Decoction, Didang Decoction, and Gancao Yangyin Decoction, etc.) modulate the Nrf2/HO-1 pathway in PD treatment, providing a theoretical basis for the clinical application and new drug development of TCM in PD prevention and treatment.
Humans ; Parkinson Disease/genetics* ; NF-E2-Related Factor 2/genetics* ; Signal Transduction/drug effects* ; Drugs, Chinese Herbal/pharmacology* ; Animals ; Heme Oxygenase-1/genetics* ; Medicine, Chinese Traditional

Objective To investigate the risk factors for bronchopulmonary dysplasia(BPD)in twin preterm infants with a gestational age of<34 weeks,and to provide a basis for early identification of BPD in twin preterm infants in clinical practice.Methods A retrospective analysis was performed for the twin preterm infants with a gestational age of<34 weeks who were admitted to 22 hospitals nationwide from January 2018 to December 2020.According to their conditions,they were divided into group A(both twins had BPD),group B(only one twin had BPD),and group C(neither twin had BPD).The risk factors for BPD in twin preterm infants were analyzed.Further analysis was conducted on group B to investigate the postnatal risk factors for BPD within twins.Results A total of 904 pairs of twins with a gestational age of<34 weeks were included in this study.The multivariate logistic regression analysis showed that compared with group C,birth weight discordance of>25%between the twins was an independent risk factor for BPD in one of the twins(OR=3.370,95%CI:1.500-7.568,P<0.05),and high gestational age at birth was a protective factor against BPD(P<0.05).The conditional logistic regression analysis of group B showed that small-for-gestational-age(SGA)birth was an independent risk factor for BPD in individual twins(OR=5.017,95%CI:1.040-24.190,P<0.05).Conclusions The development of BPD in twin preterm infants is associated with gestational age,birth weight discordance between the twins,and SGA birth.

Objective To investigate the effects of parecoxib sodium injection combined with dexmedetomidine hydrochloride injection on postoperative cognitive function and stress response in patients with osteoporotic compression fractures.Methods The patients with osteoporotic compression fractures were divided into treatment group and control group according to the treatment plan.The control group was given intravenous injection of dexmedetomidine hydrochloride injection 0.2 μg·kg-1load dose,then micro pump injection 0.2 μg·kg-1·min-1 maintenance dose,until 30 min before the end of the operation;patients in the treatment group were intravenously injected with parecoxib sodium injection 20 mg before local anesthesia and 30 min before the end of operation on the basis of the control group.The pain,sedation,hemodynamics[mean arterial pressure(MAP),heart rate(HR)],cognitive function and safety evaluation were compared between the two groups before operation(T0),2 h after operation(T1),6 h after operation(T2),12 h after operation(T3)and 24 h after operation(T4).Results There were 39 cases in the treatment group and 41 cases in the control group.Visual analogue scale(VAS)scores in treatment group and control group were(3.09±0.55)and(3.41±0.62)scores at T1;VAS scores were(3.02±0.57)and(3.35±0.48)scores at T2;VAS scores were(2.64±0.44)and(2.90±0.46)scores at T3;VAS scores were(2.02±0.41)and(2.35±0.47)scores at T4;MMSE scores were(25.28±1.57)and(24.33±1.42)scores at T2;MMSE scores were(28.16±1.01)and(27.25±0.89)scores at T4;MoCA scores were(24.63±1.60)and(23.59±1.25)scores at T2;MoCA scores were(27.20±0.97)and(26.48±0.83)scores at T4.There were statistically significant differences in the above indexes between the treatment group and the control group(all P＜0.05).Adverse drug reactions in the treatment group included bradycardia,hypotension,nausea vomiting and hypokalemia;adverse drug reactions in the control group included bradycardia,hypotension and nausea vomiting.The total incidence rates of adverse drug reactions were 12.82％and 9.76％,without statistically significant difference(P＞0.05).Conclusion Compared with using dexmedetomidine alone,parecoxib sodium combined with dexmedetomidine is beneficial for relieving postoperative pain in patients with osteoporotic compression fractures,improving postoperative cognitive function.

Objective: To analyze clinicopathological features of circumferential superficial esophageal squamous cell carcinoma and precancerous lesions and investigate the risk factors for deep submucosal invasion and angiolymphatic invasion retrospectively. Methods: A total of 116 cases of esophageal squamous epithelial high-grade intraepithelial neoplasia or squamous cell carcinoma diagnosed by gastroscopy, biopsy pathology and endoscopic resection pathology during November 2013 to October 2021 were collected, and their clinicopathological features were analyzed. The independent risk factors of deep submucosal invasion and angiolymphatic invasion were analyzed by logistic regression model. Results: The multivariate logistic regression analysis showed that drinking history (OR=3.090, 95% CI: 1.165-8.200; P<0.05), The AB type of intrapapillary capillary loop (IPCL) (OR=11.215, 95% CI: 3.955-31.797; P<0.05) were the independent risk factors for the depth of invasion. The smoking history (OR=5.824, 95% CI: 1.704-19.899; P<0.05), the presence of avascular area (AVA) (OR=3.393, 95% CI: 1.285-12.072; P<0.05) were the independent factors for the angiolymphatic invasion. Conclusions: The risk of deep submucosal infiltration is greater for circumferential superficial esophageal squamous cell carcinoma patients with drinking history and IPCL type B2-B3 observed by magnifying endoscopy, while the risk of angiolymphatic invasion should be vigilant for circumferential superficial esophageal squamous cell carcinoma patients with smoking history and the presence of AVA observed by magnifying endoscopy. Ultrasound endoscopy combined with narrowband imagingand magnification endoscopy can improve the accuracy of preoperative assessment of the depth of infiltration of superficial squamous cell carcinoma and precancerous lesions and angiolymphaticinvasion in the whole perimeter of the esophagus, and help endoscopists to reasonably grasp the indications for endoscopic treatment.
Humans ; Esophageal Squamous Cell Carcinoma/pathology* ; Esophageal Neoplasms/pathology* ; Retrospective Studies ; Esophagoscopy ; Carcinoma, Squamous Cell/pathology* ; Precancerous Conditions/surgery* ; Margins of Excision ; Risk Factors

Objective: Risk factors related to residual cancer or lymph node metastasis after endoscopic non-curative resection of early colorectal cancer were analyzed to predict the risk of residual cancer or lymph node metastasis, optimize the indications of radical surgical surgery, and avoid excessive additional surgical operations. Methods: Clinical data of 81 patients who received endoscopic treatment for early colorectal cancer in the Department of Endoscopy, Cancer Hospital, Chinese Academy of Medical Sciences from 2009 to 2019 and received additional radical surgical surgery after endoscopic resection with pathological indication of non-curative resection were collected to analyze the relationship between various factors and the risk of residual cancer or lymph node metastasis after endoscopic resection. Results: Of the 81 patients, 17 (21.0%) were positive for residual cancer or lymph node metastasis, while 64 (79.0%) were negative. Among 17 patients with residual cancer or positive lymph node metastasis, 3 patients had only residual cancer (2 patients with positive vertical cutting edge). 11 patients had only lymph node metastasis, and 3 patients had both residual cancer and lymph node metastasis. Lesion location, poorly differentiated cancer, depth of submucosal invasion ≥2 000 μm, venous invasion were associated with residual cancer or lymph node metastasis after endoscopic (P<0.05). Logistic multivariate regression analysis showed that poorly differentiated cancer (OR=5.513, 95% CI: 1.423, 21.352, P=0.013) was an independent risk factor for residual cancer or lymph node metastasis after endoscopic non-curative resection of early colorectal cancer. Conclusions: For early colorectal cancer after endoscopic non-curable resection, residual cancer or lymph node metastasis is associated with poorly differentiated cancer, depth of submucosal invasion ≥2 000 μm, venous invasion and the lesions are located in the descending colon, transverse colon, ascending colon and cecum with the postoperative mucosal pathology result. For early colorectal cancer, poorly differentiated cancer is an independent risk factor for residual cancer or lymph node metastasis after endoscopic non-curative resection, which is suggested that radical surgery should be added after endoscopic treatment.
Humans ; Lymphatic Metastasis ; Neoplasm, Residual ; Retrospective Studies ; Endoscopy ; Risk Factors ; Colorectal Neoplasms/pathology* ; Neoplasm Invasiveness

Objective: To investigate the risk factors for the development of deep infiltration in early colorectal tumors (ECT) and to construct a prediction model to predict the development of deep infiltration in patients with ECT. Methods: The clinicopathological data of ECT patients who underwent endoscopic treatment or surgical treatment at the Cancer Hospital, Chinese Academy of Medical Sciences from August 2010 to December 2020 were retrospectively analyzed. The independent risk factors were analyzed by multifactorial regression analysis, and the prediction models were constructed and validated by nomogram. Results: Among the 717 ECT patients, 590 patients were divided in the within superficial infiltration 1 (SM1) group (infiltration depth within SM1) and 127 patients in the exceeding SM1 group (infiltration depth more than SM1). There were no statistically significant differences in gender, age, and lesion location between the two groups (P>0.05). The statistically significant differences were observed in tumor morphological staging, preoperative endoscopic assessment performance, vascular tumor emboli and nerve infiltration, and degree of tumor differentiation (P<0.05). Multivariate regression analysis showed that only erosion or rupture (OR=4.028, 95% CI: 1.468, 11.050, P=0.007), localized depression (OR=3.105, 95% CI: 1.584, 6.088, P=0.001), infiltrative JNET staging (OR=5.622, 95% CI: 3.029, 10.434, P<0.001), and infiltrative Pit pattern (OR=2.722, 95% CI: 1.347, 5.702, P=0.006) were independent risk factors for the development of deep submucosal infiltration in ECT. Nomogram was constructed with the included independent risk factors, and the nomogram was well distinguished and calibrated in predicting the occurrence of deep submucosal infiltration in ECT, with a C-index and area under the curve of 0.920 (95% CI: 0.811, 0.929). Conclusion: The nomogram prediction model constructed based on only erosion or rupture, local depression, infiltrative JNET typing, and infiltrative Pit pattern has a good predictive efficacy in the occurrence of deep submucosal infiltration in ECT.
Humans ; Retrospective Studies ; Colorectal Neoplasms/pathology* ; Nomograms ; Neoplasm Staging ; Risk Factors

Objective: To explore the feasibility of endoscopic hand-suturing (EHS) for rectal defects closure after endoscopic submucosal dissection (ESD), and the clinical practicability of EHS combined with titanium clips. Methods: This is a prospective study performed by two experienced endoscopists from the Cancer Hospital, Chinese Academy of Medical Sciences who had received EHS training in sixporcine gastric ESD defects in vivo before the study. From December 2022 to February 2022, 20 patients with rectal mucosal lesions or submucosal diseases underwent ESD. Then EHS combined with titanium clips was adopted to close the rectal ESD defects. Specifically, we first sutured the defects as much as possible through EHS, then use titanium clips to fix the tail of the suture, and finally use additional titanium clips to close the residual parts of the defects that cannot be sutured. The main observational indicators were complete closure of the wound and delayed bleeding within one month after surgery. Results: In the 20 rectal cases, the size of defects ranged from 2.2 to 3.6 cm, with a median of 2.7 cm. All cases achieved complete closure without delayed bleeding, of which 12 (60.0%) were completely sutured with EHS and 8 (40.0%) required additional titanium clips to achieve complete closure after suturing. Conclusion: EHS technique is feasible and safe for rectum. EHS combined with titanium clips can also effectively close the rectal ESD defects, prevent postoperative delayed bleeding, and may be easier to be implemented in clinical practice.
Humans ; Rectum/surgery* ; Endoscopic Mucosal Resection/methods* ; Pilot Projects ; Titanium ; Prospective Studies ; Surgical Instruments ; Sutures ; Treatment Outcome ; Retrospective Studies

Objective: To explore the feasibility of endoscopic hand-suturing (EHS) for rectal defects closure after endoscopic submucosal dissection (ESD), and the clinical practicability of EHS combined with titanium clips. Methods: This is a prospective study performed by two experienced endoscopists from the Cancer Hospital, Chinese Academy of Medical Sciences who had received EHS training in sixporcine gastric ESD defects in vivo before the study. From December 2022 to February 2022, 20 patients with rectal mucosal lesions or submucosal diseases underwent ESD. Then EHS combined with titanium clips was adopted to close the rectal ESD defects. Specifically, we first sutured the defects as much as possible through EHS, then use titanium clips to fix the tail of the suture, and finally use additional titanium clips to close the residual parts of the defects that cannot be sutured. The main observational indicators were complete closure of the wound and delayed bleeding within one month after surgery. Results: In the 20 rectal cases, the size of defects ranged from 2.2 to 3.6 cm, with a median of 2.7 cm. All cases achieved complete closure without delayed bleeding, of which 12 (60.0%) were completely sutured with EHS and 8 (40.0%) required additional titanium clips to achieve complete closure after suturing. Conclusion: EHS technique is feasible and safe for rectum. EHS combined with titanium clips can also effectively close the rectal ESD defects, prevent postoperative delayed bleeding, and may be easier to be implemented in clinical practice.
Humans ; Rectum/surgery* ; Endoscopic Mucosal Resection/methods* ; Pilot Projects ; Titanium ; Prospective Studies ; Surgical Instruments ; Sutures ; Treatment Outcome ; Retrospective Studies

Based on the clinical characteristics of multiple sclerosis （MS） in traditional Chinese medicine （TCM） and western medicine and literature analysis， this paper aims to formulate the diagnostic criteria of TCM and western medicine for MS. Moreover， the modeling methods of experimental autoimmune encephalomyelitis （EAE）， animals for the modeling， and characteristics of the models were analyzed and summarized， and the consistency between the EAE models and the diagnostic criteria of TCM and western medicine was evaluated. The results showed that animal models had low consistency with the clinical characteristics in TCM （highest consistency 68%） and western medicine （highest consistency 60%）. Pathological models account for the majority of animal models for MS research， but there is a lack of intuitive performance indicators. Thus， it is difficult to comprehensively evaluate the models. The mental state， limb numbness， lack of strength， loss of muscle tone， tremor， and balance disorders of the mice are among the diagnostic criteria in western medicine. In TCM diagnostic criteria， the major symptoms which are reflected in animal behavior， such as physical fatigue， lack of strength， mental fatigue， distinclination to talk， and weak heavy numb limbs， are consistent with the western diagnostic criteria. The minor symptoms， including mental decline， bitter taste in mouth， frequent and urgent urination， fecal incontinence， and aggravated fever， are not well reflected in the models. According to TCM， MS is caused by deficiency of kidney essence and external contraction of pathogen， but no index is available for evaluating the external contraction of pathogen in existing animal models. The key to experimental research on MS is to establish an appropriate animal model based on the clinical pathogenesis and characteristics. However， there is a lack of MS animal model with TCM characteristics for syndrome classification. Therefore， renewed efforts should be made to prepare animal models with both TCM and western medicine characteristics that can be used in both basic experiments and clinical research.