Objectives:To identify the subgroups of self-reported outcomes and associated factors among breast cancer patients undergoing surgery and chemotherapy.Methods:A cross-sectional study was conducted between January and November 2021.We recruited patients from two tertiary hospitals in Shanghai,China,using convenience sampling during their hospitalization.Patients were assessed using a questionnaire that included sociodemographic and clinical characteristics,the Patient Reported Outcomes Measurement Information System profile-29(PROMIS-29),and the PROMIS-cognitive function short form 4a.Latent class analysis was performed to examine possible classes regarding self-reported outcomes.Multiple logistic regression analysis was used to determine the associated factors.Analysis of variance(ANOVA)was conducted for symptoms across the different classes.Results:A total of 640 patients participated in this study.The findings revealed three subgroups in terms of self-reported outcomes among breast cancer patients undergoing surgery and chemotherapy:low physical-social-cognitive function,high physical-low cognitive function,and high physical-socialcognitive function.Multivariable logistic regression analysis showed that age(≥60 years old),menopause,the third chemotherapy cycle,undergoing simple mastectomy and breast reconstruction,duration of disease 3-12 months,stageⅢ/Ⅳcancer,and severe pain were associated factors of the functional decline groups.Besides,significant differences in depression and sleep disorders were observed among the three groups.Conclusions:Breast cancer patients receiving surgery and chemotherapy can be divided into three subgroups.Aging,menopause,chemotherapy cycle,surgery type,duration and stage of disease,and severe pain affected the functional decline groups.Consequently,healthcare professionals should make tailored interventions to address the specific functional rehabilitation and symptom relief needs.
Differences in the imaging subgroups of cerebral small vessel disease(CSVD)need to be further explored.First,we use propensity score matching to obtain balanced datasets.Then random forest(RF)is adopted to classify the subgroups compared with support vector machine(SVM)and extreme gradient boosting(XGBoost),and to select the features.The top 10 important features are included in the stepwise logistic regression,and the odds ratio(OR)and 95%confidence interval(CI)are obtained.There are 41290 adult inpatient records diagnosed with CSVD.Accuracy and area under curve(AUC)of RF are close to 0.7,which performs best in classification compared to SVM and XGBoost.OR and 95%CI of hematocrit for white matter lesions(WMLs),lacunes,microbleeds,atrophy,and enlarged perivascular space(EPVS)are 0.9875(0.9857−0.9893),0.9728(0.9705−0.9752),0.9782(0.9740−0.9824),1.0093(1.0081−1.0106),and 0.9716(0.9597−0.9832).OR and 95%CI of red cell distribution width for WMLs,lacunes,atrophy,and EPVS are 0.9600(0.9538−0.9662),0.9630(0.9559−0.9702),1.0751(1.0686−1.0817),and 0.9304(0.8864−0.9755).OR and 95%CI of platelet distribution width for WMLs,lacunes,and microbleeds are 1.1796(1.1636−1.1958),1.1663(1.1476−1.1853),and 1.0416(1.0152−1.0687).This study proposes a new analytical framework to select important clinical markers for CSVD with machine learning based on a common data model,which has low cost,fast speed,large sample size,and continuous data sources.
Lan LanGuoliang HuRui LiTingting WangLingling JiangJiawei LuoZhiwei JiYilong Wang
