JMIR Publications

ABSTRACT

Background:

Children with profound intellectual and multiple disabilities (PIMD) or severe motor and intellectual disabilities (SMID) only communicate through movements, vocalizations, body postures, muscle tensions, or facial expressions on a pre- or protosymbolic level. Yet, to the best of our knowledge, hardly any system has been developed to collect, categorize and interpret their behaviors for independent communication and mobility.

Objective:

This paper describes the design and development of ChildSIDE app that collects and transmits children’s behaviors and associated location and environmentdata from data sources (GPS and iBeacon device, ALPS Sensor and OpenWeatherMap API) to the database. The pilot testing aimed to: compare the accuracy of the app and the paper-based collection method in collecting behavior data; measure and compare the server/API performance of the app in collecting behavior and transmitting environment data from the data sources to the database, and; categorize the movements associated with each behavior data as basis for future development and analyses.

Methods:

The pilot testing utilized a cross-sectional-observational study design using multiple single-subject face-to-face and video-recorded sessions purposively sampled child-caregiver dyads (children diagnosed with PIMD/SMID or severe or profound intellectual disability and their primary caregivers) from September 2019 to February 2020. Chi-square test and odds ratio effect sizes were computed to measure the differences in the proportion of correct and missing or incorrect data between the app and the paper-based collection method. To measure the server/API performance of the app in detecting and transmitting data from data sources to the database, frequency distribution and percentages (%) of the 31 location, motion, and environment data types were computed and compared. To categorize which body parts or movements were involved in each behavior, inter-rater agreement Kappa statistics was used.

Results:

The pilot testing comprised of 150 sessions involving 20 child-caregiver dyads. The app was able to collect 371 individual behavior data, of which, 327 had associated data from iBeacon, GPS, ALPS, Sensor, or OpenWeatherMap API data sources. The analyses revealed that ChildSIDE was more likely to collect more correct behavior data than the paper-based method (P< .001) and it had >93% server/API performance rate in detecting and transmitting location and environment data except for iBeacon data (82.3%). Behaviors were manifested mainly through hand (22.8%) and body movements (27.7%), and vocalizations (21.6%).

Conclusions:

ChildSIDE is an effective method in collecting children’s behaviors with a high server/API performance rate of above 93% in detecting and transmitting environment and outdoor location data. The results of the analysis and categorization of behaviors suggest that there is a need for a system that uses motion capture and trajectory analyses for developing algorithms to predict children’s needs in the future.