Authors' Responses to Peer Review of “Machine Learning and Medication Adherence: Scoping Review”

Interest in patient adherence has increased in recent years, with a growing literature that shows the pervasiveness of poor adherence to appropriately prescribed medications. However, four decades of adherence research has not resulted in uniformity in the terminology used to describe deviations from prescribed therapies. The aim of this review was to propose a new taxonomy, in which adherence to medications is conceptualized, based on behavioural and pharmacological science, and which will support quantifiable parameters. A systematic literature review was performed using MEDLINE, EMBASE, CINAHL, the Cochrane Library and PsycINFO from database inception to 1 April 2009. The objective was to identify the different conceptual approaches to adherence research. Definitions were analyzed according to time and methodological perspectives. A taxonomic approach was subsequently derived, evaluated and discussed with international experts. More than 10 different terms describing medication-taking behaviour were identified through the literature review, often with differing meanings. The conceptual foundation for a new, transparent taxonomy relies on three elements, which make a clear distinction between processes that describe actions through established routines ('Adherence to medications', 'Management of adherence') and the discipline that studies those processes ('Adherence-related sciences'). 'Adherence to medications' is the process by which patients take their medication as prescribed, further divided into three quantifiable phases: 'Initiation', 'Implementation' and 'Discontinuation'. In response to the proliferation of ambiguous or unquantifiable terms in the literature on medication adherence, this research has resulted in a new conceptual foundation for a transparent taxonomy. The terms and definitions are focused on promoting consistency and quantification in terminology and methods to aid in the conduct, analysis and interpretation of scientific studies of medication adherence. © 2012 The Authors. British Journal of Clinical Pharmacology © 2012 The British Pharmacological Society.

Background This is the first scoping review to focus broadly on the topics of machine learning and medication adherence. Objective This review aims to categorize, summarize, and analyze literature focused on using machine learning for actions related to medication adherence. Methods PubMed, Scopus, ACM Digital Library, IEEE, and Web of Science were searched to find works that meet the inclusion criteria. After full-text review, 43 works were included in the final analysis. Information of interest was systematically charted before inclusion in the final draft. Studies were placed into natural categories for additional analysis dependent upon the combination of actions related to medication adherence. The protocol for this scoping review was created using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. Results Publications focused on predicting medication adherence have uncovered 20 strong predictors that were significant in two or more studies. A total of 13 studies that predicted medication adherence used either self-reported questionnaires or pharmacy claims data to determine medication adherence status. In addition, 13 studies that predicted medication adherence did so using either logistic regression, artificial neural networks, random forest, or support vector machines. Of the 15 studies that predicted medication adherence, 6 reported predictor accuracy, the lowest of which was 77.6%. Of 13 monitoring systems, 12 determined medication administration using medication container sensors or sensors in consumer electronics, like smartwatches or smartphones. A total of 11 monitoring systems used logistic regression, artificial neural networks, support vector machines, or random forest algorithms to determine medication administration. The 4 systems that monitored inhaler administration reported a classification accuracy of 93.75% or higher. The 2 systems that monitored medication status in patients with Parkinson disease reported a classification accuracy of 78% or higher. A total of 3 studies monitored medication administration using only smartwatch sensors and reported a classification accuracy of 78.6% or higher. Two systems that provided context-aware medication reminders helped patients to achieve an adherence level of 92% or higher. Two conversational artificial intelligence reminder systems significantly improved adherence rates when compared against traditional reminder systems. Conclusions Creation of systems that accurately predict medication adherence across multiple data sets may be possible due to predictors remaining strong across multiple studies. Higher quality measures of adherence should be adopted when possible so that prediction algorithms are based on accurate information. Currently, medication adherence can be predicted with a good level of accuracy, potentially allowing for the development of interventions aimed at preventing nonadherence. Monitoring systems that track inhaler use currently classify inhaler-related actions with an excellent level of accuracy, allowing for tracking of adherence and potentially proper inhaler technique. Systems that monitor medication states in patients with Parkinson disease can currently achieve a good level of classification accuracy and have the potential to inform medication therapy changes in the future. Medication administration monitoring systems that only use motion sensors in smartwatches can currently achieve a good level of classification accuracy but only when differentiating between a small number of possible activities. Context-aware reminder systems can help patients achieve high levels of medication adherence but are also intrusive, which may not be acceptable to users. Conversational artificial intelligence reminder systems can significantly improve adherence.