Projects

Digital Medicine

Digital medicine project summary here.

Project Overview

Medication non-adherence remains the leading cause of relapse in serious mental illnesses such as depression, bipolar disorder, and schizophrenia. Predicting non-adherence, however, remains challenging. This study aims to create predictive models of medication non-adherence (or adherence) by using digital markers that identify high risk environmental triggers, times, and behavioral patterns that represent clinically critical situations for carefully monitoring and responding to digital medicine ingestion data. It offers the potential to build predictive models of medication adherence and non-adherence based on knowing a medication was taken and what were the environmental, social, physical activity, and cognitive states at that time.

Evaluated with the groups Below

Individuals with Schizophrenia, Bipolar I Disorder, and Major Depressive Disorder in active treatment.

Funding
Collection

Abilify MyCite tablets include an ingestible sensor to confirm ingestion when the sensor in the medication is activated in the stomach. Abilify MyCite offers the only FDA approved means to monitor actual ingestion of a psychiatric medication and thus represents a critical tool for our research in non-adherence. Participants already taking Abilify are prescribed the digital tablets for three months while social, behavioral, and cognitive markers using smartphone-based digital phenotyping are simultaneously tracked. Six study visits are scheduled over the course of a five-month period to ensure patients are comfortable with the digital monitoring, data is being captured by their smartphone correctly, and to collect information from the patient through neuropsychiatry assessments.

Interpretation

Our team analyzes the dense data collected from the Abilify Mycite digital tablet system and identifies features of passively (and actively) collected data that are associated with non-adherence (and adherence). Additionally, we assess the ease of use to patients and clinical staff of the digital tablet as well as the acceptability of combining digital medication and digital phenotyping.

Implementation

Data collected through the Mycite monitoring system, paired with qualitative data gathered from neuropsychiatry assessments and direct feedback from patients, will provide a complete assessment of the effectiveness and feasibility of a digital tablet. Our findings will inform future use cases in predicting medication adherence and identifying digital signatures of symptom changes in mental illnesses.

...

Relevant Reading
  • Lacro JP, Dunn LB, Dolder CR, Leckband SG, Jeste DV. Prevalence of and risk factorsfor medication nonadherence in patients with schizophrenia: a comprehensivereview of recent literature. The Journal of clinical psychiatry. 2002 Oct.
  • Gibson S, Brand SL, Burt S, Boden ZV, Benson O. Understanding treatment non-adherencein schizophrenia and bipolar disorder: a survey of what service users do and why. BMC psychiatry. 2013 Dec;13(1):153.
  • Higashi K, Medic G, Littlewood KJ, Diez T, Granstrom O, De Hert M. Medication adherence in schizophrenia: factors influencing adherence and consequences of non adherence, a systematic literature review. Therapeutic advances in psychopharmacology. 2013 Aug;3(4):200-18.
  • Bain EE, Shafner L, Walling DP, Othman AA, Chuang-Stein C, Hinkle J, Hanina A. Useof a novel artificial intelligence platform on mobile devices to assess dosing compliance in a phase 2 clinical trial in subjects with schizophrenia. JMIRmHealth and uHealth. 2017 Feb;5(2).
  • BarnettI, Torous J, Staples P, Sandoval L, Keshavan M, Onnela JP. Relapse prediction in schizophrenia through digital phenotyping: a pilot study.Neuropsychopharmacology. 2018 Feb 22:1.

Featured Projects