Objective:To assess the fall risk of hospitalized patients with cardiovascular diseases, analyze the related influencing factors, and construct a prediction model based on machine learning technology, so as to provide a basis for the fall management of hospitalized patients with cardiovascular diseases.Methods:This study was a retrospective cohort study. A total of 450 patients admitted to the Department of Cardiology, the First Affiliated Hospital of Nanjing Medical University from June 2017 to June 2024 were selected as the research objects by convenience sampling method. By reviewing electronic medical records, trained nurses extracted the patients' general information and Activities of Daily Living Scale (ADL) scores during hospitalization. Lasso regression was used to screen risk factors, and machine learning libraries were used to construct support vector machine (SVM), decision tree, XGBoost, and neural network models. Bootstrap resampling method and area under the curve (AUC) were used to verify the model performance.Results:Among the 450 patients, there were 261 males and 189 females, with a mean age of (66.0 ± 8.4) years. Among them, 90 patients fell during hospitalization and 360 patients did not fall. The results of Lasso regression showed that ADL score ≤60 points, use of hypnotics, hypokalemia, nighttime toilet visits≥2 times, use of antihypertensive drugs, no caregiver, and history of atrial fibrillation were all risk factors for falls in hospitalized patients with cardiovascular diseases (regression coefficients ranging from 0.61 to 1.20, all P<0.01). Among the machine learning models, XGBoost had the best comprehensive performance (AUC=0.98), which was better than decision tree (AUC=0.66), SVM (AUC=0.95), and neural network (AUC=0.87). Conclusions:The fall risk of hospitalized patients with cardiovascular diseases is jointly affected by physiological, medication and behavioral factors, and the XGBoost model can effectively identify high-risk groups. In actual clinical work, nursing strategies can be optimized in combination with risk factors, and the application of intelligent fall prediction and assessment tools can be promoted.

Objective:To assess the fall risk of hospitalized patients with cardiovascular diseases, analyze the related influencing factors, and construct a prediction model based on machine learning technology, so as to provide a basis for the fall management of hospitalized patients with cardiovascular diseases.Methods:This study was a retrospective cohort study. A total of 450 patients admitted to the Department of Cardiology, the First Affiliated Hospital of Nanjing Medical University from June 2017 to June 2024 were selected as the research objects by convenience sampling method. By reviewing electronic medical records, trained nurses extracted the patients' general information and Activities of Daily Living Scale (ADL) scores during hospitalization. Lasso regression was used to screen risk factors, and machine learning libraries were used to construct support vector machine (SVM), decision tree, XGBoost, and neural network models. Bootstrap resampling method and area under the curve (AUC) were used to verify the model performance.Results:Among the 450 patients, there were 261 males and 189 females, with a mean age of (66.0 ± 8.4) years. Among them, 90 patients fell during hospitalization and 360 patients did not fall. The results of Lasso regression showed that ADL score ≤60 points, use of hypnotics, hypokalemia, nighttime toilet visits≥2 times, use of antihypertensive drugs, no caregiver, and history of atrial fibrillation were all risk factors for falls in hospitalized patients with cardiovascular diseases (regression coefficients ranging from 0.61 to 1.20, all P<0.01). Among the machine learning models, XGBoost had the best comprehensive performance (AUC=0.98), which was better than decision tree (AUC=0.66), SVM (AUC=0.95), and neural network (AUC=0.87). Conclusions:The fall risk of hospitalized patients with cardiovascular diseases is jointly affected by physiological, medication and behavioral factors, and the XGBoost model can effectively identify high-risk groups. In actual clinical work, nursing strategies can be optimized in combination with risk factors, and the application of intelligent fall prediction and assessment tools can be promoted.

Objective:To analyze the effect of comprehensive rehabilitation intervention on the physical functioning of frail elderly persons.Methods:A total of 318 frail elderly persons were randomly divided into a control group ( n=164) and an observation group ( n=154) to test different interventions. Propensity score matching was used to balance the baseline information between the two groups 1∶1. A total of 200 cases were successfully matched, with 100 cases in each group. Both groups received drug treatment and routine nursing, while the observation group was additionally provided with comprehensive rehabilitation. Before and after 4 weeks of the treatment, both groups were evaluated using visual analogue scale (VAS) scoring for their perception of pain intensity, hand grip strength, gait speed, 6-minute walking distance (6MWD), 5 sit-up time, and the timed up and go test (TUGT). Results:There were no significant differences between the groups in any of the measurements before the experiment. Afterward, all of the outcome measures except gait speed were significantly better among the experimental group than among the controls, on average.Conclusions:Comprehensive rehabilitation can relieve pain, improve the walking, handgrip strength and exercise endurance of the frail elderly.

【Objective】 To investigate the clinical features and gene analysis of one pedigree with multiple endocrine neoplasia type 2A （MEN2A） so as to clarify the diagnosis and classification of the disease， guide treatment and prevention， and improve prognosis. 【Methods】 The clinical data of a 36-member MEN2A family， including 6 probands， with medullary thyroid carcinoma， were investigated， and the peripheral blood genomic DNA of 28 family members （blood sample of one proband was not collected） was extracted. PCR amplification was performed on exons 8， 10， 11， 13， 14， 15 and 16 of the RET gene， and the products were directly sequenced. 【Results】 Review of the medical history showed that two probands with medullary thyroid carcinoma were accompanied with hyperparathyroidism， and one family member had pheochromocytoma. The RET gene mutation test confirmed that 13 family members， consisting of 5 probands and 8 family members， had the RET proto-oncogene exon 10 missense mutation. The heterozygous missense had mutation c.1852T>A， leading to the conversion of cysteine （TGC） at position 618 to serine （AGC） （Cys618Ser）. All subjects carrying RET gene Cys618Ser mutation had abnormal thyroid ultrasound change， accompanied with elevated calcitonin levels. Subjects carrying wild type of RET gene had normal calcitonin levels. The family was finally diagnosed with MEN2A by RET gene detection. 【Conclusion】 RET gene detection plays key role in the diagnosis and treatment of patients with MEN2A family and has guiding value in the follow-up and prognosis of asymptomatic carriers. There is a positive correlation between calcitonin level and the RET protooncogene mutation Cys618Ser. Patients suspected of MEN2A should be screened in time.