1.Recurrence risk prediction models of postoperative patients with renal cell carcinoma based on machine learning
Peipei WANG ; Zhao HOU ; Hui MA ; Dingyang LYU ; Qiwei WANG ; Weibing SHUANG
Journal of Modern Urology 2025;30(3):240-247
Objective: To explore the influencing factors of recurrence in postoperative patients with renal cell carcinoma,construct machine learning prediction models and evaluate their performance. Methods: Clinical data of 915 patients with renal cell carcinoma treated in our hospital during 2013 and 2021 were retrospectively collected.The data were randomly divided into a training set (n=510) and a validation set (n=218) in a 7∶3 ratio.In the training set,LASSO regression algorithm was used to screen important variables,and machine learning prediction models were constructed to predict the recurrence risk.In the validation set,the effectiveness of the models was compared combined with the area under receiver operating characteristic curve (AUC),accuracy rate,F1 value and other indicators. Results: LASSO regression screened out the risk factors,including smoking history,tumor size,N stage,Fuhrman grade,thrombin time and fibrinogen,based on which,the logistic model,decision tree model,random forest model,and Bayes model were constructed.In the validation set,the AUC of the above 4 models was 0.862,0.792,0.843 and 0.861,respectively; the accuracy was 0.917,0.908,0.904 and 0.927,respectively; F1 value was 0.357,0.286,0.323 and 0.600,respectively.The Bayes model had the most stable performance and best differentiation. Conclusion: In this data set,the prediction model based on Bayes algorithm has a good performance and can provide reference for clinical decision making.
2.Research progress on running-related joint injuries and rehabilitation treatment
Yumin LI ; Jie LYU ; Peipei HAN ; Ruiqin WANG ; Haoran XU ; Panjing GUO ; Duoduo WANG
International Journal of Biomedical Engineering 2024;47(1):93-98
Under the backdrop of the "Healthy China 2030" strategy, running has become the most common form of exercise. Fitness running is a kind of endurance aerobic exercise. Compared with swimming, aerobics, and other sports with high activity and intensity, the risk of lower limb fatigue injury during fitness running is higher. In this review paper, the risk factors for running-related injuries were summarized by consulting and analyzing the database and focuses on discussing and analyzing the impact of running on joints. The results showed that hip adduction, knee bending, and ankle joint abnormalities are the three joint-related factors that cause the main injuries during running. Four rehabilitation intervention methods for running-related injuries were proposed, that can guide patients to generate personalized rehabilitation treatment plans through training.
3.Construction of a risk prediction model for 1-year readmission in patients undergoing percutaneous coronary intervention treated with bayaspirin combined with clopidogrel
Yuan LYU ; Peipei CHEN ; Qiongbi WU ; Wei ZHANG
China Pharmacist 2024;28(9):41-48
Objective To explore the risk factors of 1-year readmission in patients after percutaneous coronary intervention(PCI)treated with Bayaspirin combined with Clopidogrel and to construct a risk prediction model.Methods The clinical data of patients with myocardial infarction(MI)who underwent primary PCI in the Department of Cardiovascular Medicine of Lishui People's Hospital from January 2020 to June 2023 were retrospectively analyzed.The patients were divided into the readmission group(RG)and the non-readmission group(NRG)according to whether they were readmitted due to myocardial reinfarction or complications of MI within 1 year.Univariate analysis was used to explore the differential variables between the RG and NRG groups.Multivariate Logistic regression(Stepwise)was used to explore the risk factors of 1-year readmission in patients after PCI and the"optimal model".The"optimal model"was visualized using R software and transformed into a nomogram risk prediction model.The predictive ability of the Nomogram risk prediction model was evaluated using the receiver operating characteristic(ROC)curve.The calibration of the Nomogram risk prediction model was evaluated using the calibration curve(resampling,Bootstrap n=1 000).The net benefit of the nomogram risk prediction model was evaluated using the decision curve.Results A total of 100 patients were included in the study and the readmission rate within 1 year was 34.00%.Age(≥63 years old),diabetes,the number of diseased vessels(≥2),monocyte-high-density lipoprotein ratio(≥0.36),and prognosis nutrition(<39.39)were independent risk factors for readmission in patients with MI after PCI(all P<0.05).ROC analysis showed that the readmission risk prediction model had a good predictive efficiency for readmission in patients with MI after PCI,with an area under ROC curve of 0.903(95%CI:0.836-0.970).The calibration curve showed that the"predicted readmission probability"was approximately consistent with the"actual readmission probability";the decision curve showed that the net benefit of the readmission risk prediction model nomogram was higher than that of the"all"clinical net benefit.Conclusion The readmission prediction model of patients with MI after PCI constructed in this study can accurately identify high-risk groups of readmission and may be beneficial for the standardized management of patients after PCI in clinical practice,improve the long-term prognosis of patients.
4.Research progress of traditional Chinese and Western medicine non-pharmacological prevention strategies for acute high altitude disease
Li LI ; Peipei LU ; Zhiwen CAO ; Bo WEN ; Shanshan SHEN ; Zirong WANG ; Yong TAN ; Cheng LYU
Chinese Critical Care Medicine 2024;36(6):669-672
Acute high altitude disease (AHAD) is a general term for a series of clinical reactions that occur when the body fails to adapt to the low-pressure hypoxic environment of high altitudes. Mild cases can cause symptoms such as headache, nausea and vomiting, while more severe cases can lead to life-threatening conditions such as pulmonary edema, cerebral edema and other critical conditions that can be fatal. With the increasing demand for high altitudes deployment, understanding the common preventive measures of AHAD can reduce its morbidity or mortality to a certain extent, which is of great benefit to those who reside temporarily at high altitudes. In recent years, as people's health awareness has improved, there has been a growing attention towards non-pharmacological methods of disease prevention. At the same time, non-pharmacological therapy has significant therapeutic effects in preventing and treating high-altitude diseases, which has attracted the attention of researchers in this field. This review summarizes the major non-pharmacological preventive components of modern medicine and outlines the current non-pharmacological approaches to AHAD from the perspective of traditional Chinese medicine, intending to serve clinical purposes and improve the onset and prognosis of AHAD.
5.Effects of life events, family environment and coping style on self-injury behavior in adolescents with first-episode depression
Yuanli WANG ; Peipei LYU ; Wenhao LIU ; Shuying LI
Chinese Journal of Behavioral Medicine and Brain Science 2024;33(6):513-518
Objective:To explore the effects of life events, family environment and coping style on self-injury behavior in adolescents with first-episode depression.Methods:From July 2019 to December 2022, a total of 110 adolescent patients with first-episode depression were selected in the Psychiatry Department of the First Affiliated Hospital of Zhengzhou University. According to whether the patients had self-injury behavior, the patients were divided into group without self-injury( n=54)and group with self-injury( n=56).Patients in the two groups were evaluated by a general clinical data questionnaire, adolescent self-rating life events checklist (ASLEC), family environment scale-Chinese version(FES-CV), simplified coping style questionnaire (SCSQ), 24 items Hamilton depression scale (HAMD-24), Hamilton anxiety scale (HAMA) and 90 symptom checklist-90 (SCL-90). Statistical analysis including t-test, χ2 test and binary Logistic regression analysis were performed on the enrolled data by SPSS 25.0 statistical software. Results:Among 110 patients, there were 56 patients(50.9%) exhibited self-injury behavior.The scores of ASLEC(51.04±5.99, 48.02±6.86), intimacy(3.70±1.85, 4.59±1.60), emotional expression(3.84±1.80, 4.69±1.96), positive coping styles(15.84±5.85, 18.22±4.84), negative coping styles(12.50±3.23, 11.06±3.64), and HAMA(20.63±2.86, 19.48±2.55) showed statistically significant differences between the group with and without self-injury ( t=-2.46, 2.72, 2.36, 2.32, -2.20, -2.21, all P<0.05). Binary Logistic regression analysis showed that life events ( B=0.079, OR=1.083, 95% CI=1.008-1.163, P=0.030), negative coping style ( B=0.173, OR=1.188, 95% CI=1.033-1.367, P=0.016), HAMA ( B=0.225, OR=1.252, 95% CI=1.057-1.482, P=0.009) were risk factors for self-injury, while intimacy ( B=-0.264, OR=0.768, 95% CI=0.593-0.995, P=0.046) and positive coping styles ( B=-0.092, OR=0.912, 95% CI=0.834-0.997, P=0.044) were protective factors for self-injury. Conclusion:The self-injury behavior of adolescents with first-episode depression may be related to negative life events, early adverse family environment and coping style.
6.Chain mediating effect of cognitive fusion and sleep beliefs between depressive symptoms and sleep quality in adolescents with first episode depressive disorder
Peipei LYU ; Yuanli WANG ; Wenhao LIU ; Yali WANG ; Quangang MA ; Can YANG ; Yao ZHANG ; Wuyang ZHANG ; Shuying LI
Chinese Journal of Behavioral Medicine and Brain Science 2024;33(10):932-937
Objective:To explore the effects of depressive symptoms on sleep quality in adolescents with depressive disorder, and the mediating roles of cognitive fusion and sleep belief.Methods:A sample of 210 adolescents with first episode depressive disorder aged 12-18 years were recruited to complete 17-item Hamilton depression scale (HAMD-17), Pittsburgh sleep quality index (PSQI), cognitive fusion questionnaire (CFQ), and dysfunctional beliefs and attitudes about sleep scale (DBAS-16) from November 2021 to July 2022. SPSS 26.0 software was used to perform descriptive analysis and correlation analysis. The mediating effect was tested by Bootstrap analysis using PROCESS V 3.4 Macro program.Results:The incidence of low sleep quality in adolescents with depressive disorder was 69.0%(145/210). HAMD-17 score was (22.4±7.9), PSQI score was (9.7±3.7), CFQ score was (51.6±7.8), DBAS-16 score was (43.5±8.4).PSQI was positively correlated with the scores of HAMD-17 and CFQ( r=0.613, 0.463, both P<0.001).HAMD-17 was positively correlated with CFQ score ( r=0.488, P<0.001).DBAS-16 was negatively correlated with scores of PSQI, HAMD-17 and CFQ( r=-0.326, -0.284, -0.354, all P<0.001). The direct effect of depression on sleep quality was 0.230(95% CI=0.169-0.293). The indirect effect of depression on sleep quality through two pathways, the separate mediating effect value of cognitive fusion was 0.041 (95% CI=0.011-0.074), and the chain mediating effect value of cognitive fusion and sleep beliefs was 0.008(95% CI=0.001-0.020). Conclusion:Depressive symptoms can directly affect sleep quality of depressive disorder adolescents and indirectly through cognitive fusion and sleep beliefs.
7.The association of obesity with depressed severity in adolescent patients with first-episode untreated major depressive disorder
Qiurong YANG ; Yuanli WANG ; Wenhao LIU ; Peipei LYU ; Quangang MA ; Shuying LI
Chinese Journal of Behavioral Medicine and Brain Science 2023;32(3):245-249
Objective:To investigate the characteristics of obesity in adolescents with major depressive disorder (MDD) and its association with the depressed severity.Methods:A total of 278 adolescents with MDD were recruited according to the inclusion and exclusion criteria. Their demographic data were collected and 24-item Hamilton depression scale (HAMD-24) was used to evaluate their severity of depression. According to the body mass index (BMI) classification standard of adolescents in China, all subjects were classified into four groups(wasting group, normal BMI group, overweight group and obesity group). SPSS 26.0 statistical software was used for data analysis. The Kruskal-Wallis test and the Chi-square test were separately used for the comparison of the four groups.Spearman correlation was used to explore the relationship between BMI and HAMD-24 scores and severity.Results:Among 278 adolescents with MDD, the prevalence of body abnormality was 32.4% (90/278), among which wasting, overweight and obesity were 9.0% (25/278), 14.4% (40/278) and 9.0% (25/278) respectively. There were statistically differences in gender ( χ2=17.018, P<0.001), HAMD-24 scores ( H=9.427, P=0.024) and depressed severity( H=8.508, P=0.037) among the four groups. Multiple comparisons showed that there were only statistically differences between obesity group and normal BMI group, that was the prevalence of obesity in males was higher than that in females ( χ2=13.631, P<0.001), and the level in HAMD-24 scores ( Z=2.956, P=0.003) and depressed severity ( Z=2.832, P=0.005) was lower in obesity group than that in normal BMI group.Spearman correlation analysis showed that BMI was negatively correlated with HAMD-24 scores ( r=-0.162, P=0.007). Conclusion:There is gender difference in obesity rates among the adolescent patients with first-episode untreated MDD. And the obese patients are less depressed than those with normal BMI.
8.The status quo and influencing factors of the overall clinical performance in nursing students
Xiaoyan LYU ; Binbin ZHANG ; Xiaofang DONG ; Huimei CHI ; Peipei CHAI ; Yunxia SHANG ; Yan ZHAO
Chinese Journal of Practical Nursing 2022;38(21):1657-1662
Objective:To investigate the overall clinical performance of nursing students and analyze its influencing factors to provide evidence for the improvement.Methods:A questionnaire survey was carried out among 288 nursing students from Qilu Hospital of Shandong University in March to May 2020. The survey included a general data questionnaire, Holistic Clinical Assessment Tool, Clinical Learning Environment, Supervision and Nurse Teacher evaluation scale, Medical Student Safety Attitudes and Professionalism Survey of nursing students. The factors associated with overall clinical performance of nursing students were analyzed by t test, analysis of variance, Pearson correlation analysis and multiple linear regression. Results:The total score of Holistic Clinical Assessment Tool was 114.95 ± 22.91. The total score of Clinical Learning Environment, Supervision and Nurse Teacher evaluation scale was 156.70 ± 26.98. The total score of Medical Student Safety Attitudes and Professionalism Survey was 123.65 ± 31.00. The influencing factors included social practice experience and clinical learning environment, which accounted for 28.0% of the total variation of overall clinical performance of nursing students.Conclusions:Educators and managers of nursing students' schools and internship hospitals should actively explore the educational reform practice to promote the improvement of clinical ability, so as to promote the improvement of the overall clinical ability of nursing students.
9.Research progress on sexual health care carried out by nurses
Ruoning LI ; Liming LYU ; Xinyu YANG ; Lijing ZHU ; Shuo WANG ; Peipei LIU
Chinese Journal of Practical Nursing 2021;37(9):711-716
Sexual health is an important part of the overall health of patients.The ability of nurses to carry out sexual health care directly affects the overall level of medical care. This article reviews the concepts of sexual health and sexual health care, the evaluation tools of sexual health care, the practical models and influencing factors of nurses' sexual health care, with a view to providing a reference for improving the practice level of nurses carrying out sexual health care.
10. Clinical and genetic characteristics analysis of Chinese children with glutamate dehydrogenase type of congenital hyperinsulinemia
Ge LYU ; Zidi XU ; Peipei HUI ; Qiao ZENG ; Min LIU ; Jie YAN ; Yuyun WU ; Yanmei SANG
Chinese Journal of Pancreatology 2020;20(1):47-51
Objective:
To analyze the clinical features and genetic characteristics of Chinese children with glutamate dehydrogenase type of congenital hyperinsulinism (GDH-HI).
Methods:
Pedigrees with 10 GDH-HI children admitted to Beijing Children′s Hospital from February 2008 to December 2018 were selected as subjects. Clinical features, the detection of pathogenic genes and follow-up data were retrospectively analyzed. Polymerase chain reaction DNA (PCR-DNA) direct sequencing method and second generation sequencing technique were used to analyze the GLUD1 genetic sequences of 10 GDH-HI children and their relatives.
Results:
Of the 10 GDH-HI children, 9 had normal birth weight and 1 was a giant. Nine patients were accompanied by asymptomatic hyperammonemia, and one had normal blood ammonia. 9 had ever been treated with diazoxide, which was all effective. All 10 children carried GLUD1 gene mutations, 5 patients carried c. 965C>T (p.R322H) GLUD1 gene mutation, and the remaining 5 cases carried c. 1388A>T (p.N463I), c. 1495C>A(p.G499C), c. 1493C>T(p. S498L), c. 1519G>A(p.H507Y) and c. 1388A>G(p.N463S), respectively. 9 cases (90%) had de novo mutations, and 1 case had paternal autosomal dominant inheritance. 8 children were followed up in long term. One child had spontaneous remission in 8 years after being diagnosed, and seven patients required long-term oral diazoxide to maintain normal blood glucose levels, two of whom had epilepsy.
Conclusions
The birth weight of children with GDH-HI in China was usually normal. A small number of GDH-HI children had normal serum ammonia levels. Most of the GLUD1 gene mutations in GDH-HI children in China were de novo mutations, among which the GDH p. R322H mutation was a hot spot mutation in Chinese children with GDH-HI. Most of GDH-HI children were diazoxide-responsive. As the disease progresses, some children may have epilepsy, and a few children have a tendency to relieve by themselves.

Result Analysis
Print
Save
E-mail