Detection of Medication Taking Using a Wrist-Worn Commercially Available Wearable Device

PURPOSE

Medication nonadherence is a persistent and costly problem across health care. Measures of medication adherence are ineffective. Methods such as self-report, prescription claims data, or smart pill bottles have been used to monitor medication adherence, but these are subject to recall bias, lack real-time feedback, and are often expensive.

METHODS

We proposed a method for monitoring medication adherence using a commercially available wearable device. Passively collected motion data were analyzed on the basis of the Movelet algorithm, a dictionary learning framework that builds person-specific chapters of movements from short frames of elemental activities within the movements. We adapted and extended the Movelet method to construct a within-patient prediction model that identifies medication-taking behaviors.

RESULTS

Using 15 activity features recorded from wrist-worn wearable devices of 10 patients with breast cancer on endocrine therapy, we demonstrated that medication-taking behavior can be predicted in a controlled clinical environment with a median accuracy of 85%.

CONCLUSION

These results in a patient-specific population are exemplar of the potential to measure real-time medication adherence using a wrist-worn commercially available wearable device.

Assessing the utility of an IoS application in the perioperative care of spine surgery patients: the NeuroPath Pilot study

BACKGROUND

In an attempt to improve care while decreasing costs and postoperative pain, we developed a novel IoS mobile health application, NeuroPath. The objective of this innovative app is to integrate enhanced recovery after surgery (ERAS) principles, patient education, and real-time pain and activity monitoring in a home setting with unencumbered two-way communication.

METHODS

The NeuroPath application was built over 18 months, with support from Apple, Medable, the Department of Information-Technology and the Department of Neurosurgery. Target areas addressed by NeuroPath include patient prep for surgery, perioperative risk mitigation, activity monitoring, wound care, and opioid use management. These target areas are monitored through a provider app, which is downloaded to the care providers IPad Mini. The provider app permits real time viewing of wound healing (patient incision photographs), activity levels, pain levels, and narcotic usage. Participants are given a daily To-Do list, via the Care Card section of the interface. The To-Do list presents the patient with specific tasks for exercise, instructions to wash incision area, pre-operative instructions, directions for discussing medication with care team, among other patient specific recommendations.

RESULTS

Of the 30 patients enrolled in the pilot study, there was a range of activity on the app. Patients with high involvement in the app logged in nearly every day from a week pre-op to >45 days post-op. Data for patients that utilized the app and uploaded regularly show trends of appropriately healing wounds, decreasing levels of pain, increasing step counts, and discontinuation of narcotics.

CONCLUSIONS

This pilot study of the NeuroPath app demonstrates its potential utility for improving quality of patient care without increased costs. Participants who regularly used the app showed consistent improvement throughout the post-operative recovery period (increasing ambulation, decreasing pain and guided reduction in narcotic usage).