A Data-Driven Typology of Asthma Medication Adherence using Cluster Analysis

Holly Tibble, Amy Chan, Edwin A Mitchell, Elsie Horne, Dimitrios Doudesis, Rob Horne, MA Mizani, Aziz Sheikh, Thanasis Tsanas

Research output: Contribution to journalArticlepeer-review

Abstract

Background:
Asthma preventer medication non-adherence is strongly associated with poor asthma control. One-dimensional measures of adherence may ignore clinically important patterns of medication-taking behavior.
Objective:
We sought to construct a data-driven multi-dimensional typology of medication non-adherence in children with asthma.
Methods:
We analyzed data from an intervention study of electronic inhaler monitoring devices, comprising 211 patients yielding 35,161 person-days of data. Five adherence measures were extracted: the percentage of doses taken, the percentage of days on which zero doses were taken, the percentage of days on which both doses were taken, the number of treatment intermissions per 100 study days, and the duration of treatment intermissions per 100 study days. We applied principal component analysis on the measures and subsequently applied k-means to determine cluster membership. Decision trees identified the measure that could predict cluster assignment with the highest accuracy, increasing interpretability and increasing clinical utility.
Results:
We demonstrate the use of adherence measures towards a three-group categorization of medication non-adherence, which succinctly describes the diversity of patient medication taking patterns in asthma. The percentage of prescribed doses taken during the study contributed to the prediction of cluster assignment most accurately (84% in out-of-sample data).

Original languageEnglish
Pages (from-to)14999
JournalScientific Reports
Volume10
Issue number1
Early online date14 Sep 2020
DOIs
Publication statusE-pub ahead of print - 14 Sep 2020

Fingerprint Dive into the research topics of 'A Data-Driven Typology of Asthma Medication Adherence using Cluster Analysis'. Together they form a unique fingerprint.

Cite this