Usability of an artificial intelligence enabled Participation and Environment Measure prototype for family-centered goal setting support in pediatric rehabilitation

BACKGROUND: Family-centered care coordination (FC-CC) in pediatric rehabilitation benefits from tools that support caregivers in contributing to personalized service planning for their children. Participation and Environment Measure (PEM) is a digital application that is being further developed to support FC-CC in early intervention (EI). PEM is being further developed to include the Young Children's Participation and Environment Measure (YC-PEM) electronic patient-reported outcome and a companion PEM-Plus (PEM+) goal setting intervention. This study examined usability of the first artificial intelligence (AI)-enabled PEM prototype. METHODS: Caregivers from an urban EI program met these eligibility criteria: (1) were at least 18 years old; (2) identified as the parent or legal guardian of a child enrolled in EI services; (3) read, wrote, and spoke English; (4) had internet and telephone access; and (5) had a child 0-3 years old who received EI services for 3 or more months. Participants completed the AI-enabled PEM application with access to a debiased prototypic conversational agent. PEM usability was assessed using the System Usability Scale (SUS), and chatbot usability was assessed along four BOT Usability Scale (BUS-11) domains: 1) accessibility of chatbot functions; 2) functional interactive conversation; 3) privacy and security; and 4) timely response. Univariate logistic regression models were used to examine associations between each of the four BUS-11 domains and PEM+ engagement. RESULTS: Eleven female caregivers of children (mean age: 24.5 months) enrolled, 66.7% of whom interacted with the prototypic chatbot during one or more iterations of the PEM+ intervention. Overall PEM usability remained acceptable. While overall chatbot usability was very poor (Mdn = 53.4%, IQR = 50.0, 55.4), caregiver perceptions of chatbot usability were average for accessibility of chatbot functions (Mdn = 3.8, IQR = 3.0, 4.0) and good for privacy and security (M = 3.1, Range = 2.0-5.0). Higher caregiver perceptions of chatbot usability did not significantly increase odds of PEM+ intervention use. CONCLUSIONS: Findings indicate that an AI-enabled PEM retains adequate usability. A chatbot integrated within the PEM+ intervention is accessible and secure, though its functional interactive conversation and timely responses could benefit from further development to increase odds of its use in an EI service context. TRIAL REGISTRATION: NCT06458959 (Registration date: 2024-06-14).

Authors

Institutions

Publication Details

Journal
BMC Medical Informatics and Decision Making
Published
2026-11-18
DOI
https://doi.org/10.1186/s12911-026-03890-7
Primary Topic
Assistive Technology in Communication and Mobility
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Usability of an artificial intelligence enabled Participation and Environment Measure prototype for family-centered goal setting support in pediatric rehabilitation

Natalie Parde, Vivian C. Villegas, Yebin Han, Mary A. Khetani et al.
3 links
BMC Medical Informatics and Decision Making
Assistive Technology in Communication and Mobility
article

Usability of an artificial intelligence enabled Participation and Environment Measure prototype for family-centered goal setting support in pediatric rehabilitation

Natalie Parde, Vivian C. Villegas, Yebin Han, Mary A. Khetani, Lilyanna Patton, Gyeongeun Lee
article en

Abstract

BACKGROUND: Family-centered care coordination (FC-CC) in pediatric rehabilitation benefits from tools that support caregivers in contributing to personalized service planning for their children. Participation and Environment Measure (PEM) is a digital application that is being further developed to support FC-CC in early intervention (EI). PEM is being further developed to include the Young Children's Participation and Environment Measure (YC-PEM) electronic patient-reported outcome and a companion PEM-Plus (PEM+) goal setting intervention. This study examined usability of the first artificial intelligence (AI)-enabled PEM prototype. METHODS: Caregivers from an urban EI program met these eligibility criteria: (1) were at least 18 years old; (2) identified as the parent or legal guardian of a child enrolled in EI services; (3) read, wrote, and spoke English; (4) had internet and telephone access; and (5) had a child 0-3 years old who received EI services for 3 or more months. Participants completed the AI-enabled PEM application with access to a debiased prototypic conversational agent. PEM usability was assessed using the System Usability Scale (SUS), and chatbot usability was assessed along four BOT Usability Scale (BUS-11) domains: 1) accessibility of chatbot functions; 2) functional interactive conversation; 3) privacy and security; and 4) timely response. Univariate logistic regression models were used to examine associations between each of the four BUS-11 domains and PEM+ engagement. RESULTS: Eleven female caregivers of children (mean age: 24.5 months) enrolled, 66.7% of whom interacted with the prototypic chatbot during one or more iterations of the PEM+ intervention. Overall PEM usability remained acceptable. While overall chatbot usability was very poor (Mdn = 53.4%, IQR = 50.0, 55.4), caregiver perceptions of chatbot usability were average for accessibility of chatbot functions (Mdn = 3.8, IQR = 3.0, 4.0) and good for privacy and security (M = 3.1, Range = 2.0-5.0). Higher caregiver perceptions of chatbot usability did not significantly increase odds of PEM+ intervention use. CONCLUSIONS: Findings indicate that an AI-enabled PEM retains adequate usability. A chatbot integrated within the PEM+ intervention is accessible and secure, though its functional interactive conversation and timely responses could benefit from further development to increase odds of its use in an EI service context. TRIAL REGISTRATION: NCT06458959 (Registration date: 2024-06-14).

BMC Medical Informatics and Decision MakingVol. 26(1)
University of Illinois Chicago (US), University of Chicago (US)
National Science Foundation, National Institutes of Health, National Center for Advancing Translational Sciences
Good health and well-being
Assistive Technology in Communication and Mobility
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon