Use of a Novel Artificial Intelligence Platform on Mobile Devices to Assess Dosing Compliance in a Phase 2 Clinical Trial in Subjects With Schizophrenia

Abstract

BackgroundAccurately monitoring and collecting drug adherence data can allow for better understanding and interpretation of the outcomes of clinical trials. Most clinical trials use a combination of pill counts and self-reported data to measure drug adherence, despite the drawbacks of relying on these types of indirect measures. It is assumed that doses are taken, but the exact timing of these events is often incomplete and imprecise.ObjectiveThe objective of this pilot study was to evaluate the use of a novel artificial intelligence (AI) platform (AiCure) on mobile devices for measuring medication adherence, compared with modified directly observed therapy (mDOT) in a substudy of a Phase 2 trial of the α7 nicotinic receptor agonist (ABT-126) in subjects with schizophrenia.MethodsAI platform generated adherence measures were compared with adherence inferred from drug concentration measurements.ResultsThe mean cumulative pharmacokinetic adherence over 24 weeks was 89.7% (standard deviation [SD] 24.92) for subjects receiving ABT-126 who were monitored using the AI platform, compared with 71.9% (SD 39.81) for subjects receiving ABT-126 who were monitored by mDOT. The difference was 17.9% (95% CI -2 to 37.7; P=.08).ConclusionsUsing drug levels, this substudy demonstrates the potential of AI platforms to increase adherence, rapidly detect nonadherence, and predict future nonadherence. Subjects monitored using the AI platform demonstrated a percentage change in adherence of 25% over the mDOT group. Subjects were able to use the technology successfully for up to 6 months in an ambulatory setting with early termination rates that are comparable to subjects outside of the substudy.Trial RegistrationClinicalTrials.gov NCT01655680 https://clinicaltrials.gov/ct2/show/NCT01655680?term=NCT01655680

Remote Methods for Conducting Tobacco-Focused Clinical Trials

“…Medication-taking can be observed via video connection with a staff member in real time (ie, synchronously 58 , 59 ), recorded via video on a mobile device and uploaded for subsequent staff review (ie, asynchronously 32 , 60 , 61 ), or automatically detected using a mobile app with facial recognition software, such as AICure. 62 Limitations of these methods include high participant burden, required access to technology with video capabilities, and the need for staff to observe dosing in real time or review videos at a later date (for synchronous and asynchronous methods, respectively). Use of REDCap for remote video observation of medication-taking addresses some of these limitations and our group has used this approach to capture medication adherence as part of several clinical trials.…”

Use of a Digital Medication Management System for Effective Assessment and Enhancement of Patient Adherence to Therapy (ReX): Feasibility Study (Preprint)

“…One such idea is photo-or video-assisted direct observation (AiCure, LLC, NY, US). This approach is based on patients using camera/video capable cellphones to transmit images of capsules before ingestion in their mouth or videos of ingestion [19]. This application shares with ReX the recognition that a pill located in the patient's mouth mostly implies intake.…”

Digitally Enabled, Patient‐Centric Clinical Trials: Shifting the Drug Development Paradigm

“…Photographic documentation has been proven successful in several indications, particularly schizophrenia and stroke. [29][30][31][32] This technology is particularly valuable in populations that are on multiple therapies, those that benefit from close or real-time patient/site engagement, where dosing is complex (e.g. requires multiple…”