PMID- 33810146
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20210413
IS  - 2075-4418 (Print)
IS  - 2075-4418 (Electronic)
IS  - 2075-4418 (Linking)
VI  - 11
IP  - 3
DP  - 2021 Mar 22
TI  - Use of Machine Learning to Investigate the Quantitative Checklist for Autism in 
      Toddlers (Q-CHAT) towards Early Autism Screening.
LID - 10.3390/diagnostics11030574 [doi]
LID - 574
AB  - In the past two decades, several screening instruments were developed to detect 
      toddlers who may be autistic both in clinical and unselected samples. Among 
      others, the Quantitative CHecklist for Autism in Toddlers (Q-CHAT) is a 
      quantitative and normally distributed measure of autistic traits that 
      demonstrates good psychometric properties in different settings and cultures. 
      Recently, machine learning (ML) has been applied to behavioral science to improve 
      the classification performance of autism screening and diagnostic tools, but 
      mainly in children, adolescents, and adults. In this study, we used ML to 
      investigate the accuracy and reliability of the Q-CHAT in discriminating young 
      autistic children from those without. Five different ML algorithms (random forest 
      (RF), naive Bayes (NB), support vector machine (SVM), logistic regression (LR), 
      and K-nearest neighbors (KNN)) were applied to investigate the complete set of 
      Q-CHAT items. Our results showed that ML achieved an overall accuracy of 90%, and 
      the SVM was the most effective, being able to classify autism with 95% accuracy. 
      Furthermore, using the SVM-recursive feature elimination (RFE) approach, we 
      selected a subset of 14 items ensuring 91% accuracy, while 83% accuracy was 
      obtained from the 3 best discriminating items in common to ours and the 
      previously reported Q-CHAT-10. This evidence confirms the high performance and 
      cross-cultural validity of the Q-CHAT, and supports the application of ML to 
      create shorter and faster versions of the instrument, maintaining high 
      classification accuracy, to be used as a quick, easy, and high-performance tool 
      in primary-care settings.
FAU - Tartarisco, Gennaro
AU  - Tartarisco G
AUID- ORCID: 0000-0001-9467-2024
AD  - National Research Council of Italy (CNR)-Institute for Biomedical Research and 
      Innovation (IRIB), 98164 Messina, Italy.
FAU - Cicceri, Giovanni
AU  - Cicceri G
AUID- ORCID: 0000-0002-1498-2215
AD  - Department of Engineering, University of Messina, 98166 Messina, Italy.
FAU - Di Pietro, Davide
AU  - Di Pietro D
AUID- ORCID: 0000-0002-0011-103X
AD  - Department of Engineering, University of Messina, 98166 Messina, Italy.
FAU - Leonardi, Elisa
AU  - Leonardi E
AD  - National Research Council of Italy (CNR)-Institute for Biomedical Research and 
      Innovation (IRIB), 98164 Messina, Italy.
FAU - Aiello, Stefania
AU  - Aiello S
AD  - National Research Council of Italy (CNR)-Institute for Biomedical Research and 
      Innovation (IRIB), 98164 Messina, Italy.
FAU - Marino, Flavia
AU  - Marino F
AD  - National Research Council of Italy (CNR)-Institute for Biomedical Research and 
      Innovation (IRIB), 98164 Messina, Italy.
FAU - Chiarotti, Flavia
AU  - Chiarotti F
AUID- ORCID: 0000-0003-0084-6914
AD  - Center for Behavioral Sciences and Mental Health, National Institute of Health, 
      00161 Rome, Italy.
FAU - Gagliano, Antonella
AU  - Gagliano A
AUID- ORCID: 0000-0001-9367-7739
AD  - Child and Adolescent Neuropsychiatry Unit, Department of Biomedical Sciences, 
      University of Cagliari and "G. Brotzu" Hospital Trust, 09124 Cagliari, Italy.
FAU - Arduino, Giuseppe Maurizio
AU  - Arduino GM
AD  - Centro Autismo e Sindrome di Asperger ASLCN1, 12084 Mondovi, Italy.
FAU - Apicella, Fabio
AU  - Apicella F
AUID- ORCID: 0000-0001-7390-3241
AD  - IRCCS Stella Maris Foundation, Calambrone, 56128 Pisa, Italy.
FAU - Muratori, Filippo
AU  - Muratori F
AD  - IRCCS Stella Maris Foundation, Calambrone, 56128 Pisa, Italy.
AD  - Department of Clinical and Experimental Medicine, University of Pisa, 56126 Pisa, 
      Italy.
FAU - Bruneo, Dario
AU  - Bruneo D
AUID- ORCID: 0000-0002-6080-9077
AD  - Department of Engineering, University of Messina, 98166 Messina, Italy.
FAU - Allison, Carrie
AU  - Allison C
AUID- ORCID: 0000-0003-2272-2090
AD  - Autism Research Centre, Department of Psychiatry, University of Cambridge, 
      Cambridge CB2 8AH, UK.
FAU - Cohen, Simon Baron
AU  - Cohen SB
AD  - Autism Research Centre, Department of Psychiatry, University of Cambridge, 
      Cambridge CB2 8AH, UK.
FAU - Vagni, David
AU  - Vagni D
AD  - National Research Council of Italy (CNR)-Institute for Biomedical Research and 
      Innovation (IRIB), 98164 Messina, Italy.
FAU - Pioggia, Giovanni
AU  - Pioggia G
AUID- ORCID: 0000-0002-8089-7449
AD  - National Research Council of Italy (CNR)-Institute for Biomedical Research and 
      Innovation (IRIB), 98164 Messina, Italy.
FAU - Ruta, Liliana
AU  - Ruta L
AD  - National Research Council of Italy (CNR)-Institute for Biomedical Research and 
      Innovation (IRIB), 98164 Messina, Italy.
LA  - eng
PT  - Journal Article
DEP - 20210322
PL  - Switzerland
TA  - Diagnostics (Basel)
JT  - Diagnostics (Basel, Switzerland)
JID - 101658402
PMC - PMC8004748
OTO - NOTNLM
OT  - Q-CHAT
OT  - autism
OT  - early screening
OT  - machine learning
COIS- All authors declare no potential conflicts of interest, including any financial, 
      personal or other relationships with other people or organizations relevant to 
      the subject of their manuscript.
EDAT- 2021/04/04 06:00
MHDA- 2021/04/04 06:01
PMCR- 2021/03/22
CRDT- 2021/04/03 01:35
PHST- 2021/02/22 00:00 [received]
PHST- 2021/03/16 00:00 [revised]
PHST- 2021/03/19 00:00 [accepted]
PHST- 2021/04/03 01:35 [entrez]
PHST- 2021/04/04 06:00 [pubmed]
PHST- 2021/04/04 06:01 [medline]
PHST- 2021/03/22 00:00 [pmc-release]
AID - diagnostics11030574 [pii]
AID - diagnostics-11-00574 [pii]
AID - 10.3390/diagnostics11030574 [doi]
PST - epublish
SO  - Diagnostics (Basel). 2021 Mar 22;11(3):574. doi: 10.3390/diagnostics11030574.