Development and Validation of Multivariable Prediction Algorithms to Estimate Future Walking Behavior in Adults: Retrospective Cohort Study.
Development and Validation of Multivariable Prediction Algorithms to Estimate Future Walking Behavior in Adults: Retrospective Cohort Study.
复制标题
DOI：
10.2196/44296
复制
发表时间：
2023-01-27
影响因子：
5
通讯作者：
中科院分区：
文献类型：
--
作者：
缺乏身体活动与许多健康风险有关，包括癌症、心血管疾病、2型糖尿病、卫生保健支出增加以及可预防的过早死亡。大多数美国人没有达到临床指导目标（即每天8000- 10000步）。行为预测算法可以通过在适当的时间促进轻推，从而实现有效的干预，促进身体活动。本文的目的是开发和验证算法，预测未来3小时内的步行（即bbbb5分钟），预测来自参与者前5周的每分钟步数数据。我们对2015年进行的一项为期6周的HeartSteps移动健康体育活动干预的微随机试验进行了回顾性、封闭队列、二次分析。评估了6种算法的预测性能，分别是逻辑回归、径向基函数支持向量机、极限梯度增强（XGBoost）、多层感知器（MLP）、决策树和随机森林。对于MLP，测试了90个随机层架构进行优化。前5周的每小时步行数据，包括失踪者，被用作预测因子。参与者在接下来的3个小时内是否行走被用作结果。采用K-fold交叉验证（K=10）进行内部验证。主要结局指标为分类准确性、马修相关系数、敏感性和特异性。总样本量包括44名参与者6周的数据。在44名参与者中，31名（71%）是女性，26名（59%）是白人，36名（82%）拥有大学以上学历，15名（34%）已婚。平均年龄35.9岁（SD 14.7）。没有足够数据（天数<10）的参与者（n= 3.7%）被排除在外，结果有41名（93%）参与者。优化层结构的MLP在准确率上表现最佳（82.0%,SD 1.1），而XGBoost （76.3%, SD 1.5）、随机森林（69.5%,SD 1.0）、支持向量机（69.3%,SD 1.0）和决策树（63.6%,SD 1.5）算法的准确率低于逻辑回归（77.2%,SD 1.2）。MLP在Mathew相关系数（0.643,SD 0.021）、灵敏度（86.1%,SD 3.0）和特异性（77.8%,SD 3.3）方面也表现出优于所有其他尝试过的算法的总体性能。建立并验证了步行行为预测模型。在所有尝试的算法中，MLP表现出最高的总体性能。随机搜索最优层结构是一种很有前途的预测引擎开发方法。未来的研究可以测试该算法在促进身体活动的“智能”干预中的实际应用。
Physical inactivity is associated with numerous health risks, including cancer, cardiovascular disease, type 2 diabetes, increased health care expenditure, and preventable, premature deaths. The majority of Americans fall short of clinical guideline goals (ie, 8000-10,000 steps per day). Behavior prediction algorithms could enable efficacious interventions to promote physical activity by facilitating delivery of nudges at appropriate times. The aim of this paper is to develop and validate algorithms that predict walking (ie, >5 min) within the next 3 hours, predicted from the participants’ previous 5 weeks’ steps-per-minute data. We conducted a retrospective, closed cohort, secondary analysis of a 6-week microrandomized trial of the HeartSteps mobile health physical-activity intervention conducted in 2015. The prediction performance of 6 algorithms was evaluated, as follows: logistic regression, radial-basis function support vector machine, eXtreme Gradient Boosting (XGBoost), multilayered perceptron (MLP), decision tree, and random forest. For the MLP, 90 random layer architectures were tested for optimization. Prior 5-week hourly walking data, including missingness, were used for predictors. Whether the participant walked during the next 3 hours was used as the outcome. K-fold cross-validation (K=10) was used for the internal validation. The primary outcome measures are classification accuracy, the Mathew correlation coefficient, sensitivity, and specificity. The total sample size included 6 weeks of data among 44 participants. Of the 44 participants, 31 (71%) were female, 26 (59%) were White, 36 (82%) had a college degree or more, and 15 (34%) were married. The mean age was 35.9 (SD 14.7) years. Participants (n=3, 7%) who did not have enough data (number of days <10) were excluded, resulting in 41 (93%) participants. MLP with optimized layer architecture showed the best performance in accuracy (82.0%, SD 1.1), whereas XGBoost (76.3%, SD 1.5), random forest (69.5%, SD 1.0), support vector machine (69.3%, SD 1.0), and decision tree (63.6%, SD 1.5) algorithms showed lower performance than logistic regression (77.2%, SD 1.2). MLP also showed superior overall performance to all other tried algorithms in Mathew correlation coefficient (0.643, SD 0.021), sensitivity (86.1%, SD 3.0), and specificity (77.8%, SD 3.3). Walking behavior prediction models were developed and validated. MLP showed the highest overall performance of all attempted algorithms. A random search for optimal layer structure is a promising approach for prediction engine development. Future studies can test the real-world application of this algorithm in a “smart” intervention for promoting physical activity.
登录
查看更多内容
影响因子：
25.8
作者：
Gustafson, David H.;McTavish, Fiona M.;Chih, Ming-Yuan;Atwood, Amy K.;Johnson, Roberta A.;Boyle, Michael G.;Levy, Michael S.;Driscoll, Hilary;Chisholm, StevenM.;Dillenburg, Lisa;Isham, Andrew;Shah, Dhavan
通讯作者：
Shah, Dhavan
DOI：
10.1056/nejmsr1809937
发表时间：
2019-08-15
期刊：
The New England journal of medicine
影响因子：
--
作者：
All of Us Research Program Investigators;Denny JC;Rutter JL;Goldstein DB;Philippakis A;Smoller JW;Jenkins G;Dishman E
通讯作者：
Dishman E
DOI：
10.1037/hea0000306
发表时间：
2015-12
期刊：
Health psychology : official journal of the Division of Health Psychology, American Psychological Association
影响因子：
--
作者：
Nahum-Shani I;Hekler EB;Spruijt-Metz D
通讯作者：
Spruijt-Metz D
影响因子：
4.4
作者：
Chicco, Davide;Jurman, Giuseppe
通讯作者：
Jurman, Giuseppe
影响因子：
168.9
作者：
Ding, Ding;Lawson, Kenny D.;Pratt, Michael
通讯作者：
Pratt, Michael