AIM:To construct a risk prediction model for postoperative dry eye in glaucoma patients using the XGBoost algorithm.METHODS:A retrospective analysis was performed on glaucoma patients who received surgical treatment at the hospital from July 2022 to June 2025. All patients were divided into a dry eye group and a non-dry eye group according to the occurrence of postoperative dry eye disease. Clinical data of the patients were collected, and univariate and multivariate logistic regression analyses were employed to screen out the risk factors for postoperative dry eye. The patients were randomly allocated into a training set and a validation set at a ratio of 7:3. An XGboost risk prediction model was built with the risk factors as feature variables, and the SHapley Additive exPlanations(SHAP)bar plot and beeswarm plot were used for visual interpretation of the model. The predictive efficacy of the model was evaluated via receiver operating characteristic(ROC)curve analysis. RESULTS:The study included 300 glaucoma patients(300 eyes). The non-dry eye group comprised 204 patients(204 eyes, 104 males and 100 females), and the dry eye group comprised 96 patients(96 eyes, 55 males and 41 females). The incidence rate of postoperative dry eye was 32.0%. Univariate analysis revealed statistically significant differences between the two groups in terms of age, comorbid diabetes, meibum viscosity grade, tear film breakup time, meibomian gland dysfunction, and operative time(all P<0.05). Multivariate logistic regression analysis showed that all the above factors were risk factors for postoperative dry eye(all P<0.01). The XGBoost model showed that these risk factors were ranked in descending order of predictive importance as: tear film breakup time, comorbid diabetes, operative time, age, meibomian gland dysfunction, and meibum viscosity grade. ROC curve analysis demonstrated that the area under the curve(AUC)of the XGboost model was 0.84(95%CI: 0.78-0.90)for the training set and 0.83(95%CI: 0.74-0.92)for the validation set, with both values showing statistical significance(both P<0.05).CONCLUSION:The XGboost algorithm-based risk prediction model for postoperative dry eye in glaucoma patients exhibits favorable predictive performance. It can be clinically applied to identify patients at high risk of developing postoperative dry eye, thereby facilitating targeted interventions for preventive purposes.

Objective:To analyze the exercise rehabilitation preference of stroke patients, and provide reference for clinical medical staff to formulate personalized exercise rehabilitation scheme, construct precise rehabilitation decision support system, and develop exercise rehabilitation intelligent service platform.Methods:A convenience sampling approach was employed to select the stroke patients in Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University from June to December 2024, a face to face cross-sectional survey was conducted using the questionnaire on exercise rehabilitation preferences of stroke patients based on the method of discrete choice experiments. The obtained data were analyzed using conditional Logit model.Results:Finally, 242 stroke patients were included, including 152 males and 90 females, aged 64 (56, 69) years. The six attributes included in this study: rehabilitation goal, rehabilitation setting, exercise intensity, exercise duration, exercise supervision method, and payment method. The relative importance of each attribute was ranked as follows: payment method (37.1%), exercise duration (15.5%), supervision method (14.3%), rehabilitation setting (14.1%), exercise intensity (11.4%), and rehabilitation goal (7.6%). The most preferred combination was identified as a rehabilitation goal of ≥70% recovery, professional institution/hospital as the setting, supervision by wearable device combined with professional guidance, low-intensity exercise, a duration of 30-60 minutes per session, and a self-payment rate of <30%. Under this combination, the probability of patients choosing the rehabilitation program was 75.4%.Conclusions:Stroke patients' preferences for exercise rehabilitation are influenced by multiple factors, with substantial heterogeneity observed across individuals. Rehabilitation programs should be tailored according to patients' preferences regarding goals, settings, duration, and other key attributes to enhance adherence and optimize rehabilitation outcomes.

Objective:To evaluate the efficacy and safety of daratumumab in treating patients with monoclonal immunoglobulin deposition disease (MIDD) with renal injury.Methods:A case-series analysis study was conducted in MIDD patients with renal injury who received daratumumab treatment at the Department of Nephrology, Ruijin Hospital, affiliated to Shanghai Jiao Tong University School of Medicine, from December 2021 to October 2023. The clinical data of patients at the time of diagnosis and during the follow-up period were collected. Hematological and renal responses were assessed and adverse reaction events were recorded.Results:Seven patients diagnosed with MIDD were included in this study, with a male-to-female ratio of 5∶2 and age of 46 (43, 52) years. One patient was light-heavy chain deposition disease, and the remaining 6 patients were light chain deposition disease. Among them, 5 patients had received prior treatment (1-2 lines of treatment with the regimen of cyclophosphamide, bortezomib and dexamethasone), while 2 patients were newly treated, one of whom had already started hemodialysis at diagnosis. Prior to receiving monoclonal antibody treatment, difference of serum free light chain (dFLC) among the 7 patients was 52 (7, 295) mg/L. Excluding 1 patient on dialysis, the remaining 6 patients had 24-hour urinary protein of 1.1 (0.2, 4.7) g, serum creatinine of 178.5 (157.8, 279.8) μmol/L and estimated glomerular filtration rate of 33.9 (24.2, 41.1) ml·min -1·（1.73 m 2） -1. The daratumumab treatment was 17 (10, 20) infusions, with treatment duration of 17 (9, 23) months and follow-up time of 24 (13, 32) months. After treatment, among 5 previously treated patients, hematological response evaluation showed that 1 patient with baseline dFLC <20 mg/L and minimal residual disease negativity upon re-examination, while the remaining 4 patients achieved hematological responses of complete response or better. Renal response evaluation revealed that, except for 1 patient with partial response, the other 4 patients achieved very good partial response (VGPR) or better. Among 2 newly diagnosed patients, both achieved hematological efficacy at least VGPR, with one achieving renal complete response, while the other one remaining dialysis- dependent. Overall, dFLC of 7 patients was 4.9 (2.1, 11.5) mg/L. Among 6 non-dialysis patients, 24-hour urinary protein was 0.19 (0.06, 0.42) g, serum creatinine was 153.0 (120.8, 188.0) μmol/L and estimated glomerular filtration rate was 40.4 (35.2, 57.3) ml·min -1·(1.73 m 2) -1. No severe adverse reactions were observed during daratumumab treatment. Conclusion:The application of daratumumab in the treatment of MIDD with renal injury is effective and well tolerated, achieving high-quality hematological responses, with high renal responses reaching or exceeding VGPR and improvement of renal function.

Objective To propose a dynamic electrical impedance tomography imaging algorithm based on complementary information fusion network(CIFN)to enhance image quality of dynamic electrical impedance imaging.Methods There were three modules for initialization,multi-frame complementary information extraction and information fusion involved in the CIFN.Firstly,multi-frame dynamic conductivity distribution images were obtained by the initialization module;secondly,spatial complementary information was extracted from the images by using the multi-frame complementary information extraction module;finally,the fusion of lesion target distribution information and target re-reconstruction were realized by the information fusion module to aquire high-quality EIT images.With a 16-electrode multilayer cranial simulation model,the CIFN-based imaging method was compared with Tikhonov regularization algorithm,spectral constraint algorithm and U-Net algorithm in terms of imaging results of types of lesions to verify its performance.Results Compared with the Tikhonov regularization algorithm,spectral constraint algorithm and U-Net algorithm,the proposed CIFN-based algorithm exhibited the lowest mean absolute error(MAE)and the highest structural similarity(SSIM)when used to image different lesion targets,which accurately reconstructed the distribution of lesion targets and gained high imaging stability under common noise levels.Conclusion The proposed CIFN-based imaging algorithm obtains high imaging quality on a cranial simulation model and reconstruction results close to the real model distribution,which provides algorithmic support for subsequent clinical studies on electrical impedance imaging.[Chinese Medical Equipment Journal,2025,46(6):1-6]

Objective:To explore the trajectory and influencing factors of oral frailty in first-onset elderly patients with ischemic stroke.Methods:A total of 240 inpatients from the neurology departments of Wutaishan Hospital and Northern Jiangsu People's Hospital between October 2022 and February 2024 were selected by convenience sampling. Oral frailty scores were assessed dynamically at four time points: 1 day before discharge (T 1) , 1 month after discharge (T 2) , 3 months after discharge (T 3) , and 6 months after discharge (T 4) . Latent growth modeling was used to identify potential trajectory categories and analyze their influencing factors. Results:A total of 240 questionnaires were distributed, with 220 valid responses, yielding a response rate of 91.67%. A total of three trajectory types of oral frailty were identified: non-oral frailty group ( n=92) , low-decline group ( n=66) , and high-decline group ( n=62) . Age, marital status, smoking history, dysphagia, National Institute of Health Stroke Scale score, oral health, nutritional status, oral health-related self-efficacy, monthly per capita household income, polypharmacy, denture use, and cognitive function were influencing factors of oral frailty in first-onset elderly patients with ischemic stroke ( P<0.05) . Conclusions:From 1 day before discharge to 6 months after discharge, there are 3 distinct oral frailty trajectories in first-onset elderly patients with ischemic stroke. Medical staff should implement individualized interventions based on the identified influencing factors.

Objective To compare the efficacy of testicular repositioning and fixation combined with decompression of the testicular fascial compartment (testicular leucotomy+sheath flap repair) versus conventional testicular repositioning and fixation in surgery for testicular torsion in children. Methods Fifty-six patients with testicular torsion admitted to Hebei Provincial Children's Hospital from January 2019 to October 2023 were selected and divided into the observation group (26 cases) and the control group (30 cases),and the observation group was treated with testicular reorientation and fixation+testicular fascial compartment decompression,while the control group was treated with conventional testicular reorientation and fixation. There was no statistically significant difference in the age and left and right sides of the patients in the two groups (P>0.05). The intraop-erative bleeding,postoperative testicular atrophy,the presence of postoperative scrotal infection and postoperative hospitalization time of the two groups were compared. Results All patients successfully completed the operation without intraoperative complications. There was no statistically significant difference between the observation group and the control group in terms of intraoperative bleeding,postoperative scrotal infection rate and postoperative hospitalization time (P>0.05);the postoperative testicular atrophy rate of the observation group was significantly lower than that of the control group (P<0.05). Conclusions Testicular restoration and fixation+testicular fascial compartment decompression can effectively reduce the pressure of testicular fascial compartment,reduce the ischemia-reperfusion injury of testis,and reduce the occurrence of testicular atrophy,which is safe and effective in the treatment of testicular torsion in children.

[Purpose]To analyze the incidence and mortality of oral and pharyngeal cancer in can-cer registration areas of Hunan Province in 2021 and the trend changes from 2012 to 2021.[Methods]Data on oral and pharyngeal cancer incidence and mortality from 2012 to 2021 were collected from 78 quality-controlled cancer registries in Hunan Province,with population data sourced from household registration statistics provided by public security authorities.Indicators such as crude incidence and mortality rates,age-standardized incidence and mortality rates by Chinese standard population(ASIRC/ASMRC),and world standard population(ASIRW,ASMRW)in 2021 were calculated.The Chinese standard population(2000 national census)and Segi's world standard population were used for standardization.Joinpoint Regression Program 4.9.0.0 software was used to fit a Log-linear regression model,and the average annual percentage change(AAPC)of ASIRC/ASMRC of oral and pharyngeal cancer from 2012 to 2021 was calculated to analyze the changing trends.[Results]In 2021,the crude incidence rate of oral and pharyngeal cancer in cancer registration areas of Hunan Province was 9.28/105(15.14/105 for males and 3.07/105 for fe-males),with an ASIRC of 6.10/105;the crude mortality rate was 3.75/105(6.19/105 for males and 1.16/105 for females),with an ASMRC of 2.16/105.Both the incidence and mortality rates in male were significantly higher than those in female.Age distribution analysis showed that the incidence rate of oral and pharyngeal cancer increased with age after 30 years old,peaking in the age group of 60～64 years old(22.29/105);the mortality rate continued to rise after 35 years old,reaching the peak in the population aged ≥85 years old(14.52/105).Trend analysis from 2012 to 2021 indicated that the crude incidence rate and ASIRC of oral and pharyngeal cancer increased from 3.50/105 and 2.63/105 in 2012 to 9.28/105 and 6.10/105 in 2021,with AAPC of 12.33％and 10.80％,re-spectively;the crude mortality rate and ASMRC also showed upward trends(AAPC of 9.87％and 7.21％,respectively);all trend changes were statistically significant(all P＜0.05).Sex stratification revealed that the AAPC of ASIRC and ASMRC of oral and pharyngeal cancer in male were higher than those in female(AAPC of ASIRC:12.65％for males vs 4.28％for females;AAPC of ASMRC:8.79％for males vs 4.13％for females).Age-specific trend analysis found that the ASIRC of oral and pharyngeal cancer in the population aged ≤ 44 years old showed an upward trend(AAPC=11.73％,P＜0.001),with the AAPC of male in this group reaching 14.57％;the AAPC of ASIRC for the age groups of 45～64 years old and ≥65 years old were 11.03％and 9.74％,respectively,and the AAPC of ASMRC for these two groups were 10.05％and 8.19％,respectively,with all trend changes being statistically significant(all P＜0.05);there was no statistically significant change in the ASMRC of the population aged ≤44 years old(AAPC=5.66％,P=0.087).[Conclusion]The incidence and mortality rates of oral and pharyngeal cancer in cancer registration areas of Hunan Province remain high and show an upward trend,with a tendency of younger onset.Males and middle-aged and elderly populations are the key focuses of prevention and control.

Objective:To investigate the clinical manifestations, histological features, immunophenotype, molecular characteristics, and treatments of uterine inflammatory myofibroblastic tumor (UIMT).Methods:Clinical and pathological data of 4 UIMT cases diagnosed at the Peking Union Medical College Hospital, Beijing, China from 2020 to 2024 were collected. Their clinicopathological and genetic characteristics were analyzed.Results:The patients′ ages were 63, 42, 53 and 37 years, respectively. The tumors were located in the submucosa and intermuscular walls of the uterus, with a diameter ranging from 1.5 to 6.0 cm. All tumors were suspected by the clinician as leiomyosarcoma. Histologically, 3 of the 4 tumors showed spindle cells that appeared like leiomyoma. Prominent myxoid stroma and inflammatory cells infiltration were observed, with mitotic figures of 1-2 per 10 high-power fields. One case was primarily composed of spindle cells arranged in fascicles, with inflammatory cell infiltration, inconspicuous myxoid stroma and mitotic figures of 3 per 10 high-power fields. Two cases exhibited a pushing pattern of invasion and slightly unclear boundaries, while the other two showed infiltrative growth with unclear boundaries. The immunohistochemistry revealed diffuse and strong, cytoplasmic granular staining of ALK in all 4 cases. RNA sequencing was performed in 3 cases, of which 2 cases showed ALK gene rearrangements, and 1 case did not. One case underwent FISH testing and showed ALK gene translocation. Follow-up showed that no recurrence or metastasis was observed after surgery in all patients.Conclusions:UIMT is a rare mesenchymal tumor of the uterus and lacks specific clinical manifestations. When tumor cells exhibit mild atypia, indistinct borders, myxoid stroma, inflammatory cell infiltration, and decreased expression of ER and PR on immunohistochemistry, immunohistochemical staining of ALK is recommended to confirm the diagnosis of UIMT. This tumor shares many features with myogenic tumors and endometrial stromal sarcomas. Molecular testing may also be needed to assist in diagnosis when necessary. For patients who are not suitable for surgery or have recurrence and metastasis, targeted therapy with ALK inhibitors can be used.

OBJECTIVE: As an age-related neurodegenerative disease, the prevalence of mild cognitive impairment (MCI) increases with age. Within the framework of traditional Chinese medicine, spleen-kidney deficiency syndrome (SKDS) is recognized as the most frequent MCI subtype. Due to the covert and gradual onset of MCI, in community settings it poses a significant challenge for patients and their families to discern between typical aging and pathological changes. There exists an urgent need to devise a preliminary diagnostic tool designed for community-residing older adults with MCI attributed to SKDS (MCI-SKDS). METHODS: This investigation enrolled 312 elderly individuals diagnosed with MCI, who were randomly distributed into training and test datasets at a 3:1 ratio. Five machine learning methods, including logistic regression (LR), decision tree (DT), naive Bayes (NB), support vector machine (SVM), and gradient boosting (GB), were used to build a diagnostic prediction model for MCI-SKDS. Accuracy, sensitivity, specificity, precision, F1 score, and area under the curve were used to evaluate model performance. Furthermore, the clinical applicability of the model was evaluated through decision curve analysis (DCA). RESULTS: The accuracy, precision, specificity and F1 score of the DT model performed best in the training set (test set), with scores of 0.904 (0.845), 0.875 (0.795), 0.973 (0.875) and 0.973 (0.875). The sensitivity of the training set (test set) of the SVM model performed best among the five models with a score of 0.865 (0.821). The area under the curve of all five models was greater than 0.9 for the training dataset and greater than 0.8 for the test dataset. The DCA of all models showed good clinical application value. The study identified ten indicators that were significant predictors of MCI-SKDS. CONCLUSION The risk prediction index derived from machine learning for the MCI-SKDS prediction model is simple and practical; the model demonstrates good predictive value and clinical applicability, and the DT model had the best performance. Please cite this article as: Ai YT, Zhou S, Wang M, Zheng TY, Hu H, Wang YC, Li YC, Wang XT, Zhou PJ. Development of a machine learning-based risk prediction model for mild cognitive impairment with spleen-kidney deficiency syndrome in the elderly. J Integr Med. 2025; 23(4): 390-397.
Humans ; Cognitive Dysfunction/diagnosis* ; Aged ; Male ; Female ; Machine Learning ; Spleen ; Aged, 80 and over ; Kidney ; Medicine, Chinese Traditional

BACKGROUND: Poly adenosine-diphosphate-ribose polymerase (PARP) inhibitors (PARPi) have been approved to act as first-line maintenance (FL-M) therapy and as platinum-sensitive recurrent maintenance (PSR-M) therapy for ovarian cancer in China for >5 years. Herein, we have analyzed the clinical-application characteristics of olaparib and niraparib in ovarian cancer-maintenance therapy in a real-world setting to strengthen our understanding and promote their rational usage. METHODS: A retrospective chart review identified patients with newly diagnosed or platinum-sensitive recurrent ovarian cancer, who received olaparib or niraparib as maintenance therapy at Sichuan Cancer Hospital between August 1, 2018, and December 31, 2021. Patient medical records were reviewed. We grouped and analyzed patients based on the type of PARPi they used (the olaparib group and the niraparib group) and the line of PARPi maintenance therapy (the FL-M setting and the PSR-M setting). The primary endpoint was the 24-month progression-free survival (PFS) rate. RESULTS: In total, 131 patients (olaparib: n = 67, 51.1%; niraparib: n = 64, 48.9%) were enrolled. Breast cancer susceptibility genes ( BRCA ) mutations ( BRCA m) were significantly less common in the niraparib group than in the olaparib group [9.4% (6/64) vs . 62.7% (42/67), P <0.001], especially in the FL-M setting [10.4% (5/48) vs . 91.4% (32/35), P <0.001]. The 24-month progression-free survival (PFS) rates in the FL-M and PSR-M settings were 60.4% and 45.7%, respectively. In patients with BRCA m, the 24-month PFS rates in the FL-M and PSR-M settings were 62.2% and 72.7%, respectively. CONCLUSIONS Olaparib and niraparib were effective in patients with ovarian cancer without any new safety signals except for skin pigmentation. In patients with BRCA m, the 24-month PFS of the PARPi used in the PSR-M setting was even higher than that used in the FL-M setting.
Humans ; Female ; Ovarian Neoplasms/drug therapy* ; Piperazines/therapeutic use* ; Middle Aged ; Retrospective Studies ; Phthalazines/therapeutic use* ; Piperidines/therapeutic use* ; Indazoles/therapeutic use* ; Poly(ADP-ribose) Polymerase Inhibitors/therapeutic use* ; Adult ; Aged ; China ; Neoplasm Recurrence, Local/drug therapy* ; Progression-Free Survival