A Predictive Model for Paediatric Autism Screening

Benjamin Wingfield, Shane Miller, Y Pratheepan, Dermot Kerr, Bryan Gardiner, Sudarshi Seneviratne, Pradeepa Samarasinghe, Sonya Coleman

Research output: Contribution to journalArticle

Abstract

Autism Spectrum Disorder (ASD) is an umbrella term for a group of neurodevelopmental disorders that is associated with impairments to social interaction, communication, and behaviour. Typically, ASD is first detected with a screening tool (e.g. M-CHAT). However, the interpretation of ASD behavioural symptoms varies across cultures: the sensitivity of M-CHAT is as low as 25% in Sri Lanka. A culturally-sensitive screening tool called Pictorial Autism Assessment Schedule (PAAS) has overcome this problem. Low and Middle-Income Countries (LMIC) have a shortage of mental health specialists, which is a key barrier for obtaining an early ASD diagnosis. Early identification of ASD enables intervention before atypical patterns of behaviour and brain function become established. This article proposes a culturally sensitive ASD screening mobile application. The proposed application embeds an intelligent machine learning model and uses a clinically validated symptom checklist to monitor and detect ASD in LMIC for the first time. Machine learning models were trained on clinical PAAS data and their predictive performance evaluated, which demonstrated that the Random Forest was the optimal classifier (AUROC 0.98) for embedding into the mobile screening tool. Additionally, feature selection demonstrated that many PAAS questions are redundant, and can be removed to optimise the screening process.
LanguageEnglish
JournalHealth Informatics Journal
Publication statusAccepted/In press - 3 Oct 2019

Fingerprint

Autistic Disorder
Pediatrics
Appointments and Schedules
Mobile Applications
Sri Lanka
Behavioral Symptoms
Social Behavior
Interpersonal Relations
Autism Spectrum Disorder
Checklist
Mental Health
Communication
Brain

Keywords

  • decision-support systems
  • machine learning
  • Autism Spectrum Disorder (ASD)
  • Data Mining
  • Computer aided screening tool

Cite this

@article{06fd8907a4634b4e934bb24f51943f98,
title = "A Predictive Model for Paediatric Autism Screening",
abstract = "Autism Spectrum Disorder (ASD) is an umbrella term for a group of neurodevelopmental disorders that is associated with impairments to social interaction, communication, and behaviour. Typically, ASD is first detected with a screening tool (e.g. M-CHAT). However, the interpretation of ASD behavioural symptoms varies across cultures: the sensitivity of M-CHAT is as low as 25{\%} in Sri Lanka. A culturally-sensitive screening tool called Pictorial Autism Assessment Schedule (PAAS) has overcome this problem. Low and Middle-Income Countries (LMIC) have a shortage of mental health specialists, which is a key barrier for obtaining an early ASD diagnosis. Early identification of ASD enables intervention before atypical patterns of behaviour and brain function become established. This article proposes a culturally sensitive ASD screening mobile application. The proposed application embeds an intelligent machine learning model and uses a clinically validated symptom checklist to monitor and detect ASD in LMIC for the first time. Machine learning models were trained on clinical PAAS data and their predictive performance evaluated, which demonstrated that the Random Forest was the optimal classifier (AUROC 0.98) for embedding into the mobile screening tool. Additionally, feature selection demonstrated that many PAAS questions are redundant, and can be removed to optimise the screening process.",
keywords = "decision-support systems, machine learning, Autism Spectrum Disorder (ASD), Data Mining, Computer aided screening tool",
author = "Benjamin Wingfield and Shane Miller and Y Pratheepan and Dermot Kerr and Bryan Gardiner and Sudarshi Seneviratne and Pradeepa Samarasinghe and Sonya Coleman",
year = "2019",
month = "10",
day = "3",
language = "English",
journal = "Health Informatics Journal",
issn = "1460-4582",

}

A Predictive Model for Paediatric Autism Screening. / Wingfield, Benjamin; Miller, Shane; Pratheepan, Y; Kerr, Dermot; Gardiner, Bryan; Seneviratne, Sudarshi ; Samarasinghe, Pradeepa ; Coleman, Sonya.

In: Health Informatics Journal, 03.10.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Predictive Model for Paediatric Autism Screening

AU - Wingfield, Benjamin

AU - Miller, Shane

AU - Pratheepan, Y

AU - Kerr, Dermot

AU - Gardiner, Bryan

AU - Seneviratne, Sudarshi

AU - Samarasinghe, Pradeepa

AU - Coleman, Sonya

PY - 2019/10/3

Y1 - 2019/10/3

N2 - Autism Spectrum Disorder (ASD) is an umbrella term for a group of neurodevelopmental disorders that is associated with impairments to social interaction, communication, and behaviour. Typically, ASD is first detected with a screening tool (e.g. M-CHAT). However, the interpretation of ASD behavioural symptoms varies across cultures: the sensitivity of M-CHAT is as low as 25% in Sri Lanka. A culturally-sensitive screening tool called Pictorial Autism Assessment Schedule (PAAS) has overcome this problem. Low and Middle-Income Countries (LMIC) have a shortage of mental health specialists, which is a key barrier for obtaining an early ASD diagnosis. Early identification of ASD enables intervention before atypical patterns of behaviour and brain function become established. This article proposes a culturally sensitive ASD screening mobile application. The proposed application embeds an intelligent machine learning model and uses a clinically validated symptom checklist to monitor and detect ASD in LMIC for the first time. Machine learning models were trained on clinical PAAS data and their predictive performance evaluated, which demonstrated that the Random Forest was the optimal classifier (AUROC 0.98) for embedding into the mobile screening tool. Additionally, feature selection demonstrated that many PAAS questions are redundant, and can be removed to optimise the screening process.

AB - Autism Spectrum Disorder (ASD) is an umbrella term for a group of neurodevelopmental disorders that is associated with impairments to social interaction, communication, and behaviour. Typically, ASD is first detected with a screening tool (e.g. M-CHAT). However, the interpretation of ASD behavioural symptoms varies across cultures: the sensitivity of M-CHAT is as low as 25% in Sri Lanka. A culturally-sensitive screening tool called Pictorial Autism Assessment Schedule (PAAS) has overcome this problem. Low and Middle-Income Countries (LMIC) have a shortage of mental health specialists, which is a key barrier for obtaining an early ASD diagnosis. Early identification of ASD enables intervention before atypical patterns of behaviour and brain function become established. This article proposes a culturally sensitive ASD screening mobile application. The proposed application embeds an intelligent machine learning model and uses a clinically validated symptom checklist to monitor and detect ASD in LMIC for the first time. Machine learning models were trained on clinical PAAS data and their predictive performance evaluated, which demonstrated that the Random Forest was the optimal classifier (AUROC 0.98) for embedding into the mobile screening tool. Additionally, feature selection demonstrated that many PAAS questions are redundant, and can be removed to optimise the screening process.

KW - decision-support systems

KW - machine learning

KW - Autism Spectrum Disorder (ASD)

KW - Data Mining

KW - Computer aided screening tool

M3 - Article

JO - Health Informatics Journal

T2 - Health Informatics Journal

JF - Health Informatics Journal

SN - 1460-4582

ER -