Explainable Ai-Based Identification of Contributing Factors to the Mood State Change of Children and Adolescents with Pre-Existing Psychiatric Disorders in the Context of COVID-19 Related Lockdowns in Greece

18 Pages Posted: 10 Aug 2022

See all articles by Charis Ntakolia

Charis Ntakolia

University Mental Health Research Institute

Dimitrios Priftis

University Mental Health Research Institute

Konstantinos Kotsis

University of Ioannina - School of Medicine

Konstantina Magklara

National and Kapodistrian University of Athens - Eginition Hospital

Mariana Charakopoulou Travlou

University Mental Health Research Institute; University of Oxford

Ioanna Rannou

University Mental Health Research Institute

Konstantina Ladopoulou

General Children’s Hospital ‘Pan. & Aglaia Kyriakou

Iouliani Koullourou

General Hospital ‘G. Hatzikosta’

Emmanouil Tsalamanios

Asklepieio General Hospital of Voula

Eleni Lazaratou

National and Kapodistrian University of Athens - Eginition Hospital

Aspasia Serdari

University Hospital of Alexandroupolis

Aliki Grigoriadou

Hellenic Centre for Mental Health and Research, Athens

Neda Sadeghi

National Institutes of Health, Bethesda

Georgia O’Callaghan

National Institutes of Health, Bethesda

Kenny Chiu

University of East Anglia (UEA) - Norwich Medical School

Ioanna Giannopoulou

National and Kapodistrian University of Athens - Attikon University Hospital

Abstract

The COVID-19 pandemic and accompanying restrictions have significantly impacted lives globally. There is an increasing interest in examining the influence of this unprecedented situation on our mental well-being, with less attention towards the impact of elongation of COVID-19 related measures on youth with a pre-existing psychiatric/developmental disorder. The majority of studies are focusing on individuals, such as students, adults, youths, among others, with little attention to be given to the elongation of COVID-19 related measures and their impact to a special group of individuals, such as children and adolescents with diagnosed developmental and psychiatric disorders. In addition, most of these studies adopt statistical methodologies to identify pair-wise relationships among factors, an approach that limits the ability to understand and interpret the impact of various factors. In response, this study aims to adopt an explainable machine learning approach to identify factors that explain the deterioration or amelioration of mood state in youth clinical sample. The purpose of this study is to identify and interpret the impact of the most contributing features of mood states change to the prediction output, via an explainable machine learning pipeline. Among all the machine learning classifiers, Random Forest model achieved the highest accuracy, with 76% Best AUC-ROC Score and 13 features. Explainability analysis showed that stress or positive changes derived from the imposing restrictions and COVID-19 pandemic are the top two factors that could affect mood state.

Note:

Funding Information: None.

Declaration of Interests: None.

Ethics Approval Statement: Institutional Review Board Statement: Each CAMHS contacted the parents of all children and adolescents who attended the service from 1 March 2019 to 1 March 2020 and from 16 December 2020 to 8 February 2021. All parents interested in taking part in the survey were sent an email containing information about the study, along with a unique identification code number and the link to log into Google Forms Survey app. After reading the information about the goals of the study, the process of data collection and confidentiality, and providing informed consent online, they proceeded to answer the questionnaire. The study was approved by the Ethics Committee of each hospital, with which the service is affiliated. The study was performed in line with the principles of the Declaration of Helsinki. Informed Consent Statement: Informed consent was obtained from all subjects involved in the study.

Keywords: COVID-19 pandemic, mental health, Machine Learning, explainability, children and adolescents

Suggested Citation

Ntakolia, Charis and Priftis, Dimitrios and Kotsis, Konstantinos and Magklara, Konstantina and Charakopoulou Travlou, Mariana and Rannou, Ioanna and Ladopoulou, Konstantina and Koullourou, Iouliani and Tsalamanios, Emmanouil and Lazaratou, Eleni and Serdari, Aspasia and Grigoriadou, Aliki and Sadeghi, Neda and O’Callaghan, Georgia and Chiu, Kenny and Giannopoulou, Ioanna, Explainable Ai-Based Identification of Contributing Factors to the Mood State Change of Children and Adolescents with Pre-Existing Psychiatric Disorders in the Context of COVID-19 Related Lockdowns in Greece. Available at SSRN: https://ssrn.com/abstract=4180441 or http://dx.doi.org/10.2139/ssrn.4180441

Charis Ntakolia (Contact Author)

University Mental Health Research Institute ( email )

Athens
Greece

Dimitrios Priftis

University Mental Health Research Institute ( email )

Athens
Greece

Konstantinos Kotsis

University of Ioannina - School of Medicine ( email )

Konstantina Magklara

National and Kapodistrian University of Athens - Eginition Hospital ( email )

Mariana Charakopoulou Travlou

University Mental Health Research Institute ( email )

Athens
Greece

University of Oxford ( email )

Mansfield Road
Oxford, Oxfordshire OX1 4AU
United Kingdom

Ioanna Rannou

University Mental Health Research Institute ( email )

Athens
Greece

Konstantina Ladopoulou

General Children’s Hospital ‘Pan. & Aglaia Kyriakou ( email )

Iouliani Koullourou

General Hospital ‘G. Hatzikosta’ ( email )

Emmanouil Tsalamanios

Asklepieio General Hospital of Voula ( email )

Eleni Lazaratou

National and Kapodistrian University of Athens - Eginition Hospital ( email )

Aspasia Serdari

University Hospital of Alexandroupolis ( email )

Aliki Grigoriadou

Hellenic Centre for Mental Health and Research, Athens ( email )

Neda Sadeghi

National Institutes of Health, Bethesda ( email )

Georgia O’Callaghan

National Institutes of Health, Bethesda ( email )

Kenny Chiu

University of East Anglia (UEA) - Norwich Medical School ( email )

Ioanna Giannopoulou

National and Kapodistrian University of Athens - Attikon University Hospital ( email )

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
55
Abstract Views
227
rank
526,128
PlumX Metrics