Predicting Group-Based Trajectories of Oral Health-Related Quality of Life From Late Adolescence to Early Adulthood Using K-Means Clustering Algorithm

Chukwuebuka Ogwo; Grant Brown; John Warren; Erliang Zeng; Murray Thomson; Steven Levy

doi:10.1111/jphd.70007

Back

Predicting Group-Based Trajectories of Oral Health-Related Quality of Life From Late Adolescence to Early Adulthood Using K-Means Clustering Algorithm

Journal article

Open access

Peer reviewed

Predicting Group-Based Trajectories of Oral Health-Related Quality of Life From Late Adolescence to Early Adulthood Using K-Means Clustering Algorithm

Chukwuebuka Ogwo, Grant Brown, John Warren, Erliang Zeng, Murray Thomson and Steven Levy

Journal of public health dentistry, Vol.85(4), pp.440-448

Autumn 2025

DOI: 10.1111/jphd.70007

PMCID: PMC12689277

PMID: 40955538

Appears in UI Libraries Support Open Access

Files and links (1)

url

https://doi.org/10.1111/jphd.70007View

Published (Version of record) Open Access

Abstract

Objectives To identify and analyze the patterns of change in Oral Health-Related Quality of Life (OHRQoL) from late adolescence to early adulthood (ages 17 to 23) using a machine learning algorithm. Methods This longitudinal trajectory study used data from the Iowa Fluoride Study (IFS). Participants were recruited at birth from eight Iowa hospitals between 1992 and 1995. OHRQoL was assessed at ages 17, 19, and 23 using three validated questionnaires: the Child Perceptions Questionnaire (CPQ11-14), Global Oral Health Rating (GOHR), and Visual Analog Scale of Quality of Life (VisQoL). Of the 437 individuals assessed at age 17, 402 were re-assessed at age 19 and 367 at age 23 (91% retention rate). The K-Means for Longitudinal data (KmL) algorithm was applied to identify distinct trajectory groups for each measure. Associations between trajectory group membership and sociodemographic variables were examined using logistic regression. All analyses were performed in R (version 4.1.3). Results Two distinct trajectory groups were identified for each OHRQoL measure, representing consistently better versus persistently worsening oral health experiences. For the CPQ11-14, 84.8% of participants were in the “Favorable” group and 15.2% in the “Unfavorable” group. GOHR classified 57.2% as “Favorable” and 42.8% as “Unfavorable,” while VisQoL showed 67.5% and 32.5%, respectively. Despite differing proportions, all instruments reflected similar directional trends. Higher socioeconomic status was associated with favorable trajectory group membership (p < 0.05). Conclusion Most participants followed a favorable OHRQoL trajectory and were from higher socioeconomic backgrounds. These findings highlight the value of longitudinal, multi-measure approaches in identifying at-risk subgroups.

Machine Learning

prediction

oral health?related quality of life

K?means

trajectories

longitudinal data

UIOWA OA Agreement

Details

Title: Subtitle: Predicting Group-Based Trajectories of Oral Health-Related Quality of Life From Late Adolescence to Early Adulthood Using K-Means Clustering Algorithm
Creators: Chukwuebuka Ogwo - Harvard University
Grant Brown - University of Iowa, Biostatistics
John Warren - University of Iowa
Erliang Zeng - University of Otago
Murray Thomson - Division of Biostatistics and Computational Biology, The University of Iowa College of Dentistry, Iowa City, Iowa, USA
Steven Levy - University of Iowa
Resource Type: Journal article
Publication Details: Journal of public health dentistry, Vol.85(4), pp.440-448
DOI: 10.1111/jphd.70007
PMID: 40955538
PMCID: PMC12689277
NLM abbreviation: J Public Health Dent
ISSN: 0022-4006
eISSN: 1752-7325
Publisher: Wiley
Grant note: 1 R03 DE031220-01A1 / NIH HHS
Language: English
Electronic publication date: 09/16/2025
Date published season: Autumn 2025
Date published: 2025
Academic Unit: Preventive and Community Dentistry; Epidemiology; Biostatistics
Record Identifier: 9984963630102771

Metrics

19 Record Views