Improving Artificial Intelligence-derived Algorithms for Estimating Length and Weight in NEonateS and infanTs up to 6 Months of Age (NEST)

Danone Asia Pacific Holdings Pte, Ltd.60 enrolled

Overview

The NEST study is a prospective, observational research study designed to collect clinical measurements and image data to develop and evaluate artificial intelligence (AI)-derived algorithms for estimating anthropometric parameters in neonates and young infants. The study focuses on infants from birth up to 6 months of age and aims to assess the accuracy of AI-based estimations of length, weight, and head circumference using photographs and/or video recordings captured during routine clinical care. These AI-derived measurements will be compared against standard clinical measurements obtained by trained healthcare professionals in neonatal and infant care settings.

The NEST study is a prospective, observational cohort study designed to collect paired clinical reference measurements, image data, and associated clinical information to support the development and proof-of-concept evaluation of artificial intelligence (AI)-based algorithms for estimating anthropometric parameters in neonates and young infants. Standard clinical anthropometric measurements-including infant length, weight, and head circumference-are obtained by trained healthcare professionals in accordance with site-standard clinical procedures and established neonatal measurement practices. These measurements serve as the clinical reference standard for comparison with AI-derived estimates. All reference measurements collected as part of routine clinical care during the study period may be recorded. In parallel with clinical measurements, non-invasive image data consisting of two-dimensional photographs and/or video recordings of the infant are captured using digital imaging devices. Image capture occurs under real-world clinical conditions and does not require additional physical contact beyond routine care. Image and video data may be collected at multiple timepoints for a given participant, including repeated assessments during hospitalization or follow-up, where applicable. Image-based measurements are not used for clinical decision-making. AI-derived estimates are compared against standard clinical reference measurements using predefined analytical accuracy and agreement metrics. Secondary and exploratory objectives include the evaluation of AI models for additional anthropometric parameters, such as weight and head circumference, as well as assessment of the feasibility of image capture in neonatal and infant care settings. Investigator- and parent-reported perceptions related to the usability and acceptability of image-based measurement approaches are also evaluated. For participants with laboratory test results obtained as part of routine clinical care, selected laboratory values may be recorded. In a subset of participants, additional image data may be collected to support exploratory research related to AI-based estimation of iron status. No additional laboratory testing is performed as part of the study. Questionnaire-based feedback is collected from investigators and parents or caregivers on the image capture process and to define acceptable ranges of differences between AI-derived estimates and standard clinical measurements. and/or experiences and perceptions related to the use of AI-powered digital tools for monitoring infant growth parameters and health. All study data are coded prior to analysis. Image data and clinical measurements are linked using study-specific participant identifiers. No facial recognition or identity verification is performed. Data are stored, processed, and analyzed in accordance with approved data protection and confidentiality measures and applicable regulatory requirements.

Eligibility

Sex: ALLMin age: 0 DaysMax age: 6 Months

Medical Language ↔ Plain English

Inclusion Criteria: 1. Infants up from birth up to 6 months of postnatal age (including neonates) who have been admitted to the NICU or SCN at the time of screening 2. Parent(s) should be able to comprehend the content of the study and be willing for their child to undergo video and photo recording, and to allow access to their blood sampling results (haemoglobin) taken as part of standard clinical practice 3. Written consent from parents and/or legally acceptable representative Exclusion Criteria: 1. Infants who were born with gestational age of less than 28 weeks of gestational age 2. Infants who are intubated (i.e., endotracheal, nasotracheal intubation) at the time of screening 3. The investigator considers for any reason that the participant would not be suitable for the study 4. The participant has an existing medical condition that would prevent standardised measurement of length and/or head circumference e.g. structural abnormality of the lower limbs, orthopaedic conditions, hydrocephalus 5. Employees and/or children/family members or relatives of employees of Danone Global Research \& Innovation Center, Danone Asia Pacific Holdings Pte Ltd, or the participating site

Outcomes

Primary Outcomes

To evaluate the accuracy of the algorithm to estimate length (in cm)

The primary outcome is the proof-of-concept accuracy of an artificial intelligence (AI)-based algorithm for estimating infant length in a neonatal intensive care unit (NICU) or special care nursery (SCN) setting. AI-derived length estimates (in centimeters) obtained from supine images and/or videos are compared with standard clinical length measurements performed by trained investigators using World Health Organization (WHO)-recommended techniques. Accuracy is evaluated using a composite metric that includes bias, mean absolute error, mean absolute percentage error, and the distribution of absolute percentage errors at predefined thresholds.

Time frame: From enrolment (after informed consent) until discharge from NICU/SCN, up to a maximum of 10 weeks

Secondary Outcomes

To evaluate the mean absolute error of the algorithm to estimate weight (in kg)

The secondary outcome is the proof-of-concept accuracy of an artificial intelligence (AI)-based algorithm for estimating infant weight in a neonatal intensive care unit (NICU) or special care nursery (SCN) setting. AI-derived weight estimates (in kilograms) generated from supine images and/or videos are compared with standard clinical weight measurements obtained by trained investigators using World Health Organization (WHO)-recommended techniques. Accuracy is assessed using a composite metric that includes bias, mean absolute error, mean absolute percentage error, and the distribution of absolute percentage errors at predefined thresholds.