Predicting Attrition Patterns from Pediatric Weight Management Programs

被引:0
作者
Fayyaz, Hamed [1 ]
Phan, Thao-Ly T. [2 ]
Bunnell, H. Timothy [2 ]
Beheshti, Rahmatollah [1 ]
机构
[1] Univ Delaware, Newark, DE 19716 USA
[2] Nemours Childrens Hlth, Wilmington, DE USA
来源
MACHINE LEARNING FOR HEALTH, VOL 193 | 2022年 / 193卷
关键词
Childhood obesity; Attrition; Weight trajectories; Transfer learning; Multi-task learning; Deep learning; CHURN PREDICTION; OBESITY; ATTENDANCE; CHILDHOOD; DROPOUT; RISK;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Obesity is a major public health concern. Multidisciplinary pediatric weight management programs are considered standard treatment for children with obesity who are not able to be successfully managed in the primary care setting. Despite their great potential, high dropout rates (referred to as attrition) are a major hurdle in delivering successful interventions. Predicting attrition patterns can help providers reduce the alarmingly high rates of attrition (up to 80%) by engaging in earlier and more personalized interventions. Previous work has mainly focused on finding static predictors of attrition on smaller datasets and has achieved limited success in effective prediction. In this study, we have collected a five-year comprehensive dataset of 4,550 children from diverse backgrounds receiving treatment at four pediatric weight management programs in the US. We then developed a machine learning pipeline to predict (a) the likelihood of attrition, and (b) the change in body-mass index (BMI) percentile of children, at different time points after joining the weight management program. Our pipeline is greatly customized for this problem using advanced machine learning techniques to process longitudinal data, smaller-size data, and interrelated prediction tasks. The proposed method showed strong prediction performance as measured by AUROC scores (average AUROC of 0.77 for predicting attrition, and 0.78 for predicting weight outcomes).
引用
收藏
页码:326 / 342
页数:17
相关论文
共 54 条
[1]  
Abadi M, 2016, PROCEEDINGS OF OSDI'16: 12TH USENIX SYMPOSIUM ON OPERATING SYSTEMS DESIGN AND IMPLEMENTATION, P265
[2]  
Akinbami LJ, 2022, Vital and Health statistics Ser 1, Programs and Collection Procedures, P1
[3]   Dynamic churn prediction framework with more effective use of rare event data: The case of private banking [J].
Ali, Ozden Gur ;
Ariturk, Umut .
EXPERT SYSTEMS WITH APPLICATIONS, 2014, 41 (17) :7889-7903
[4]   Alexithymia Predicts Attrition and Outcome in Weight-Loss Obesity Treatment [J].
Altamura, Mario ;
Porcelli, Piero ;
Fairfield, Beth ;
Malerba, Stefania ;
Carnevale, Raffaella ;
Balzotti, Angela ;
Rossi, Giuseppe ;
Vendemiale, Gianluigi ;
Bellomo, Antonello .
FRONTIERS IN PSYCHOLOGY, 2018, 9
[5]  
[Anonymous], 2017, Keras
[6]  
[Anonymous], 2007, Advances in Psychiatric Treatment
[7]   Strategies to reduce attrition in managing paediatric obesity: A systematic review [J].
Ball, Geoff D. C. ;
Sebastianski, Meghan ;
Wijesundera, Jessica ;
Keto-Lambert, Diana ;
Ho, Josephine ;
Zenlea, Ian ;
Perez, Arnaldo ;
Nobles, James ;
Skelton, Joseph A. .
PEDIATRIC OBESITY, 2021, 16 (04)
[8]   Using data mining to predict success in a weight loss trial [J].
Batterham, M. ;
Tapsell, L. ;
Charlton, K. ;
O'Shea, J. ;
Thorne, R. .
JOURNAL OF HUMAN NUTRITION AND DIETETICS, 2017, 30 (04) :471-478
[9]   Predicting dropout in dietary weight loss trials using demographic and early weight change characteristics: Implications for trial design [J].
Batterham, Marijka ;
Tapsell, Linda C. ;
Charlton, Karen E. .
OBESITY RESEARCH & CLINICAL PRACTICE, 2016, 10 (02) :189-196
[10]  
Cate Pit-Ten, 2017, BMJ Open, V7