Challenge of Detecting Personal Deviations and Trends in Sensor Based Activity Data.

INTRODUCTION: Physical activity and health are closely linked. Therefore, monitoring movement behavior is of great interest e.g., to monitor a patient's physical state. Nowadays it is easy to record movement with a smartphone. The aim of this work was to develop a concept to detect trends based on personalized movement behavior recorded with a smartphone. METHODS: A first prototype with a control chart was designed. Since this approach did not prove suitable for analyzing activity data for trends in practice, a second prototype was subsequently developed with a statistical trend test (Mann-Kendall test (MK test)). It was extended by the Yue-Wang correction approach to be able to deal effectively with serial correlation. Furthermore, the traditional trend modeling using Theil-Sen slope was extended by three additional models to be able to represent non-linear trend shapes. RESULTS: Movement behavior can be highly variable, which leads to wide control limits when using control charts. As the lower control limit was always in the negative range the use of a control chart was impossible for this use case. The evaluation results of the second prototype confirm the choice of a non-parametric test, as well as the decision for the Yue-Wang correction factor. Furthermore, it could be determined that the MK test is robust against outliers. The number of detected trends increases with increasing significance level. The MK test is also suitable for detecting step-like trends. CONCLUSION: Live trend detection is not straightforward with the MK test but can be simulated by overlapping time periods. In the future, trend modeling should be extended even further, as it plays a major role in the concept. The sensitivity of the test can be increased by means of various parameters.

Assessing Quality of Life Using FHIR - How to Combine Patient Reported Outcome with Patient Generated Data for Better Compliance.

Quality of life (QoL) is affected by environmental influences and varies between patients. A combined measurement through Patient Reported Outcomes (PROs) and Patient Generated Data (PGD) may enhance the detection of QoL impairments by a longitudinal survey. Leveraging different approaches of QoL measurement techniques, the challenge is to combine data in a standardized, interoperable way. We developed an app (Lion-App) to semantically annotate data from sensor systems as well as PROs to be merged in an overall analysis of QoL. A FHIR implementation guide was defined for a standardized assessment. To access sensor data the interfaces of Apple Health or Google Fit are used instead of integrating various provider directly into the system. Since QoL cannot be collected exclusively via sensor values, a combination of PROs and PGD is necessary. PGD enable a progression of QoL which offers more insight into personal limitations whereas PROs give insight about personal burden. The use of FHIR enables structured exchange of data while personalized analyses might improve therapy and outcome.

Evaluating Online Consumer Medication Information Systems: Comparative Online Usability Study.

BACKGROUND: Medication is the most common intervention in health care, and the number of online consumer information systems within the pharmaceutical sector is increasing. However, online consumer information systems can be a barrier for users, imposing information asymmetries between stakeholders. OBJECTIVE: The objective of this study was to quantify and compare the usability of an online consumer medication information system (OCMIS) against a reference implementation based on an interoperable information model for patients, physicians, and pharmacists. METHODS: Quantitative and qualitative data were acquired from patients, physicians, and pharmacists in this online usability study. We administered 3 use cases and a post hoc questionnaire per user. Quantitative usability data including effectiveness (task success), efficiency (task time), and user satisfaction (system usability scale [SUS]) was complemented by qualitative and demographic data. Users evaluated 6 existing systems and 1 reference implementation of an OCMIS. RESULTS: A total of 137 patients, 81 physicians, and 68 pharmacists participated in this study. Task success varied from 84% to 92% in patients, 66% to 100% in physicians, and 50% to 91% in pharmacists. Task completion time decreased over the course of the study for all but 2 OCMIS within the patient group. Due to an assumed nonnormal distribution of SUS scores, within-group comparison was done using the Kruskal-Wallis test. Patients showed differences in SUS scores (P=.02) and task time (P=.03), while physicians did not have significant differences in SUS scores (P=.83) and task time (P=.72). For pharmacists, a significant difference in SUS scores (P<.001) and task time (P=.007) was detected. CONCLUSIONS: The vendor-neutral reference implementation based on an interoperable information model was proven to be a promising approach that was not inferior to existing solutions for patients and physicians. For pharmacists, it exceeded user satisfaction scores compared to other OCMIS. This data-driven approach based on an interoperable information model enables the development of more user-tailored features to increase usability. This fosters data democratization and empowers stakeholders within the pharmaceutical sector.