Harrington Katharine, Zenk Shannon N, Van Horn Linda, Giurini Lauren, Mahakala Nithya, Kershaw Kiarri N
Northwestern University Feinberg School of Medicine, Chicago, IL, United States.
National Institute of Nursing Research, Bethesda, MD, United States.
JMIR Form Res. 2021 Dec 2;5(12):e27512. doi: 10.2196/27512.
As poor diet quality is a significant risk factor for multiple noncommunicable diseases prevalent in the United States, it is important that methods be developed to accurately capture eating behavior data. There is growing interest in the use of ecological momentary assessments to collect data on health behaviors and their predictors on a micro timescale (at different points within or across days); however, documenting eating behaviors remains a challenge.
This pilot study (N=48) aims to examine the feasibility-usability and acceptability-of using smartphone-captured and crowdsource-labeled images to document eating behaviors in real time.
Participants completed the Block Fat/Sugar/Fruit/Vegetable Screener to provide a measure of their typical eating behavior, then took pictures of their meals and snacks and answered brief survey questions for 7 consecutive days using a commercially available smartphone app. Participant acceptability was determined through a questionnaire regarding their experiences administered at the end of the study. The images of meals and snacks were uploaded to Amazon Mechanical Turk (MTurk), a crowdsourcing distributed human intelligence platform, where 2 Workers assigned a count of food categories to the images (fruits, vegetables, salty snacks, and sweet snacks). The agreement among MTurk Workers was assessed, and weekly food counts were calculated and compared with the Screener responses.
Participants reported little difficulty in uploading photographs and remembered to take photographs most of the time. Crowdsource-labeled images (n=1014) showed moderate agreement between the MTurk Worker responses for vegetables (688/1014, 67.85%) and high agreement for all other food categories (871/1014, 85.89% for fruits; 847/1014, 83.53% for salty snacks, and 833/1014, 81.15% for sweet snacks). There were no significant differences in weekly food consumption between the food images and the Block Screener, suggesting that this approach may measure typical eating behaviors as accurately as traditional methods, with lesser burden on participants.
Our approach offers a potentially time-efficient and cost-effective strategy for capturing eating events in real time.
由于不良饮食质量是美国多种常见非传染性疾病的重要风险因素，因此开发能够准确获取饮食行为数据的方法至关重要。人们越来越关注使用生态瞬时评估法在微观时间尺度（一天内或多天内的不同时间点）收集健康行为及其预测因素的数据；然而，记录饮食行为仍然是一项挑战。
这项试点研究（N = 48）旨在检验使用智能手机拍摄并经众包标注的图像实时记录饮食行为的可行性、可用性和可接受性。
参与者完成“脂肪/糖/水果/蔬菜摄入量简易筛查工具”以衡量其典型饮食行为，然后连续7天使用一款商用智能手机应用程序拍摄他们的正餐和零食照片，并回答简短的调查问题。通过研究结束时发放的关于参与者体验的问卷来确定其可接受性。正餐和零食的照片被上传到亚马逊土耳其机器人（MTurk），这是一个众包分布式人工智慧平台，由两名工作人员为照片中的食物类别（水果、蔬菜、咸味零食和甜味零食）进行计数。评估了MTurk工作人员之间的一致性，并计算每周食物计数，并与筛查工具的回答进行比较。
参与者报告称上传照片几乎没有困难，并且大部分时间都记得拍照。众包标注的图像（n = 1014）显示，MTurk工作人员对蔬菜的回答之间一致性中等（688/1014，67.85%），对所有其他食物类别的回答一致性较高（水果871/1014，85.89%；咸味零食847/1014，83.53%；甜味零食833/1014，81.15%）。食物图像和简易筛查工具之间的每周食物摄入量没有显著差异，这表明这种方法可能与传统方法一样准确地测量典型饮食行为，且对参与者的负担较小。
我们的方法为实时捕捉饮食事件提供了一种潜在的省时且经济高效的策略。
