Department of Biomedical Informatics, Columbia University, New York, NY, USA.
Columbia University School of Nursing and College of Dental Medicine, Columbia University Medical Center, New York, NY, USA.
J Am Med Inform Assoc. 2018 Oct 1;25(10):1366-1374. doi: 10.1093/jamia/ocy054.
To develop and test a visual analytics tool to help clinicians identify systematic and clinically meaningful patterns in patient-generated data (PGD) while decreasing perceived information overload.
Participatory design was used to develop Glucolyzer, an interactive tool featuring hierarchical clustering and a heatmap visualization to help registered dietitians (RDs) identify associative patterns between blood glucose levels and per-meal macronutrient composition for individuals with type 2 diabetes (T2DM). Ten RDs participated in a within-subjects experiment to compare Glucolyzer to a static logbook format. For each representation, participants had 25 minutes to examine 1 month of diabetes self-monitoring data captured by an individual with T2DM and identify clinically meaningful patterns. We compared the quality and accuracy of the observations generated using each representation.
Participants generated 50% more observations when using Glucolyzer (98) than when using the logbook format (64) without any loss in accuracy (69% accuracy vs 62%, respectively, p = .17). Participants identified more observations that included ingredients other than carbohydrates using Glucolyzer (36% vs 16%, p = .027). Fewer RDs reported feelings of information overload using Glucolyzer compared to the logbook format. Study participants displayed variable acceptance of hierarchical clustering.
Visual analytics have the potential to mitigate provider concerns about the volume of self-monitoring data. Glucolyzer helped dietitians identify meaningful patterns in self-monitoring data without incurring perceived information overload. Future studies should assess whether similar tools can support clinicians in personalizing behavioral interventions that improve patient outcomes.
开发并测试一种可视分析工具，帮助临床医生在减少感知信息过载的同时，识别患者生成数据（PGD）中的系统和有临床意义的模式。
采用参与式设计开发了 Glucolyzer，这是一种交互式工具，具有层次聚类和热图可视化功能，可帮助注册营养师（RD）识别 2 型糖尿病（T2DM）个体的血糖水平与每餐宏量营养素组成之间的关联模式。10 名 RD 参与了一项被试内实验，以比较 Glucolyzer 与静态日志本格式。对于每种表示形式，参与者都有 25 分钟的时间来检查 1 个月由 T2DM 个体记录的糖尿病自我监测数据，并识别有临床意义的模式。我们比较了使用每种表示形式生成的观察结果的质量和准确性。
与使用日志本格式（64 个）相比，使用 Glucolyzer 时参与者生成的观察结果增加了 50%（98 个），而准确性没有任何损失（分别为 69%和 62%，p=0.17）。与使用 Glucolyzer 相比，参与者识别出更多包含碳水化合物以外成分的观察结果（36%对 16%，p=0.027）。与日志本格式相比，使用 Glucolyzer 的 RD 报告信息过载感的人数较少。研究参与者对层次聚类的接受程度存在差异。
可视分析有可能减轻提供者对自我监测数据量的担忧。Glucolyzer 帮助营养师在不产生感知信息过载的情况下识别自我监测数据中的有意义模式。未来的研究应评估类似的工具是否可以支持临床医生制定个性化的行为干预措施，以改善患者的结果。
