Augmenting K-Means Clustering With Qualitative Data to Discover the Engagement Patterns of Older Adults With Multimorbidity When Using Digital Health Technologies: Proof-of-Concept Trial

Yiyang Sheng, RR Bond, Rajesh Jaiswal, John Dinsmore, Julie Doyle

Research output: Contribution to journalArticlepeer-review

43 Downloads (Pure)

Abstract

Background:

Multiple chronic conditions (multimorbidity) are becomingmore prevalent among aging populations. Digital health technologies have thepotential to assist in the self-management of multimorbidity, improving theawareness and monitoring of health and well-being, supporting a betterunderstanding of the disease, and encouraging behavior change.

Objective:

The aim of this study was to analyze how 60 older adults(mean age 74, SD 6.4; range 65-92 years) with multimorbidity engaged withdigital symptom and well-being monitoring when using a digital health platformover a period of approximately 12 months.

Methods:

Principal component analysis and clustering analysis wereused to group participants based on their levels of engagement, and the dataanalysis focused on characteristics (eg, age, sex, and chronic healthconditions), engagement outcomes, and symptom outcomes of the differentclusters that were discovered.

Results:

Three clusters were identified: the typical user group, theleast engaged user group, and the highly engaged user group. Our findings showthat age, sex, and the types of chronic health conditions do not influenceengagement. The 3 primary factors influencing engagement were whether the samedevice was used to submit different health and well-being parameters, thenumber of manual operations required to take a reading, and the daily routineof the participants. The findings also indicate that higher levels ofengagement may improve the participants’ outcomes (eg, reduce symptomexacerbation and increase physical activity).

Conclusions:

The findings indicate potential factors that influence olderadult engagement with digital health technologies for home-based multimorbidityself-management. The least engaged user groups showed decreased health andwell-being outcomes related to multimorbidity self-management. Addressing thefactors highlighted in this study in the design and implementation ofhome-based digital health technologies may improve symptom management andphysical activity outcomes for older adults self-managing multimorbidity.

Original languageEnglish
Article numbere46287
Pages (from-to)1-23
Number of pages23
JournalJournal of Medical Internet Research
Volume26
Issue number1
Early online date28 Mar 2024
DOIs
Publication statusPublished online - 28 Mar 2024

Bibliographical note

Publisher Copyright:
©Yiyang Sheng, Raymond Bond, Rajesh Jaiswal, John Dinsmore, Julie Doyle. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 28.03.2024.

Keywords

  • Digital health
  • clustering
  • k-means clustering
  • digital health
  • engagement
  • chronic disease
  • multimorbidity
  • aging

Fingerprint

Dive into the research topics of 'Augmenting K-Means Clustering With Qualitative Data to Discover the Engagement Patterns of Older Adults With Multimorbidity When Using Digital Health Technologies: Proof-of-Concept Trial'. Together they form a unique fingerprint.

Cite this