Assessing a Height Artificial Intelligence Algorithm to Estimate Height of Children (INFER)

A Study to Collect Data to Build Artificial INtelligence Derived Algorithms For Estimating Height and Weight in childRen (INFER)

An exploratory study to explore the possibility of using computer vision algorithms to estimate a child's height using images taken by a healthcare professional or parents.

Study Overview

• Status: Completed
• Conditions: Growth; Stunting, Nutritional
• Intervention / Treatment: Other: Physical height measurement

Detailed Description

This is an exploratory, observation, data-collection study that aims to evaluate the performance of a Height Artificial Intelligence (HAI) algorithm in a real world setting. Images will be collected by parents or healthcare professionals, together with physical height measurements. This data will be used to evaluate the accuracy of the algorithm and to explore potential improvements. Data on the acceptance and experience of using the algorithm will be collected for improvements.

• Study Type: Observational
• Enrollment (Actual): 250

Contacts and Locations

Study Locations

• Singapore
  • Singapore, Singapore
    • KK Women's and Children's Hospital

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

Children aged above 24 months old and below 6 years of age with no physical deformities

Description

Inclusion Criteria:

• Children aged above 24 months old and below 6 years old.
• Parent(s) should have access to the internet and a smartphone or table to complete study questionnaires, take images and upload images.
• Parent(s) should be able to comprehend the content of the study and complete the study questionnaires in English.
• Written consent from parents and/or legally acceptable representative

Exclusion Criteria:

• Children who are unable to stand upright against a wall
• Children who are unable to cooperate with standing height measurement

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Children aged above 24 months old and below 6 years of age; Children aged above 24 months old and below 6 years of age with no structural abnormalities of the lower limbs or orthopaedic conditions	Other: Physical height measurement; Physical height will be measured and images will be collected for AI to estimate the height

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of the height AI (cm)	Accuracy of the Height AI (cm) in a clinic and in a home setting, derived from: The height AI prediction from images collected; The physical height measurements of subjects using WHO standard height measurement	2 days

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Accuracy of the Weight AI (kg)	Accuracy of the Weight AI (kg) in a clinic and in a home setting, derived from: The weight prediction from the standing images collected in this study; The WHO standard weight measurement of subjects	2 days

Other Outcome Measures

Outcome Measure	Measure Description	Time Frame
Assessments by the parent on usability of the AI in a home-setting via study questionnaire	Ease of collecting images (very easy to very difficult); Acceptable range of height & weight difference between AI prediction & WHO measurement (between ≤1cm and >5cm); Frequency of measuring child's height & weight at home (never,< 1/month, at least <1/month, at least 1 per 2 weeks,at least 1/week,> 1/week,daily); Usefulness of using digital tool to measure child's height & weight at home (Very useful to Not very useful); Frequency of using digital tool to measure child's height & weight at home (never,<1/month, at least 1/month, at least 1 per 2 weeks,at least 1/week,>1/week,daily); Likelihood and reason of using a digital tool to measure child's height & weight at home (Very Likely to Very unlikely); Sharing the child's height & weight measured using digital tool with others (Very Likely to Very unlikely); Use of mobile apps to track child's height & weight (free text); Other features/tools useful to measure child's height & weight (free text)	2 days
Assessments by the investigator on usability of the AI in a clinic-setting via a questionnaire	Acceptable range of height and weight difference between the height and weight AI from the WHO measurement (≤ 1cm, ≤ 2cm, ≤ 3cm, ≤ 4cm, ≤5cm, >5cm); Likelihood of using a digital tool to measure a child's height and weight in a clinical setting (Very Likely, Likely, Neutral, Unlikely, Very unlikely); Likelihood of recommending parents to use a digital tool to measure their child's height and weight in a clinical setting (Very Likely, Likely, Neutral, Unlikely, Very unlikely); Other features/tools they find useful to measure the child's height and weight (free text)	2 days
Assessments by the investigator on ease of collecting images in a clinic-setting via a questionnaire	Investigator's assessment on the ease of collecting the images [Very Easy, Easy, Normal, Difficult, Very Difficult]	2 days

Collaborators and Investigators

• Sponsor: Danone Asia Pacific Holdings Pte, Ltd.
• Collaborators: KK Women's and Children's Hospital
• Investigators: Principal Investigator: Fabian Yap, MBBS, KK Women's and Children's Hospital

Publications and helpful links

General Publications

• Schmidhuber J. Deep learning in neural networks: an overview. Neural Netw. 2015 Jan;61:85-117. doi: 10.1016/j.neunet.2014.09.003. Epub 2014 Oct 13.
• Yap F, Lee YS, Aw MMH. Growth Assessment and Monitoring during Childhood. Ann Acad Med Singap. 2018 Apr;47(4):149-155.

Study record dates

Study Major Dates

• Study Start (Actual): September 9, 2024
• Primary Completion (Actual): March 4, 2025
• Study Completion (Actual): March 4, 2025

Study Registration Dates

• First Submitted: August 5, 2024
• First Submitted That Met QC Criteria: August 27, 2024
• First Posted (Actual): August 29, 2024

Study Record Updates

• Last Update Posted (Actual): February 4, 2026
• Last Update Submitted That Met QC Criteria: February 2, 2026
• Last Verified: February 1, 2026

More Information

Terms related to this study

• Keywords: Growth; Artificial Intelligence; Algorithm; Height
• Additional Relevant MeSH Terms: Pathologic Processes; Pathological Conditions, Signs and Symptoms; Growth Disorders
• Other Study ID Numbers: SBB20R&31696-A

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No