背景:不运动与许多健康风险有关,包括癌症,心血管疾病,2型糖尿病,增加医疗保健支出,而且是可以预防的,过早死亡。大多数美国人没有达到临床指南目标(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的传递来实现有效的干预以促进身体活动。
目的:本文的目的是开发和验证预测步行的算法(即,>5分钟)在接下来的3小时内,从参与者“前5周”每分钟步数数据预测。
方法:我们进行了回顾性研究,封闭队列,对2015年进行的HeartSteps移动健康运动干预的6周微随机试验进行二次分析。评估了6种算法的预测性能,如下:逻辑回归,径向基函数支持向量机,极限梯度提升(XGBoost),多层感知器(MLP),决策树,和随机森林。对于MLP来说,对90个随机层架构进行了优化测试。先前5周每小时步行数据,包括不幸,用于预测因子。参与者在接下来的3小时内是否行走被用作结果。K-折交叉验证(K=10)用于内部验证。主要结果指标是分类准确性,马修相关系数,灵敏度,和特异性。
结果:总样本量包括44名参与者的6周数据。在44名参与者中,31(71%)为女性,26(59%)是白人,36(82%)拥有大学或以上学位,15人(34%)结婚。平均年龄为35.9(SD14.7)岁。没有足够数据(天数<10)的参与者(n=3,7%)被排除在外,41名(93%)参与者。具有优化层架构的MLP在精度方面表现出最佳性能(82.0%,SD1.1),而XGBoost(76.3%,SD1.5),随机森林(69.5%,SD1.0),支持向量机(69.3%,SD1.0),和决策树(63.6%,SD1.5)算法的性能低于逻辑回归(77.2%,SD1.2)。MLP在Mathew相关系数(0.643,SD0.021)方面也显示出优于所有其他尝试算法的整体性能,灵敏度(86.1%,SD3.0),和特异性(77.8%,SD3.3)。
结论:建立并验证了步行行为预测模型。MLP在所有尝试的算法中显示出最高的整体性能。随机搜索最佳层结构是预测引擎开发的一种有前途的方法。未来的研究可以测试这种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.