TY - UNPB
T1 - 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
AU - Ntakolia, Charis
AU - Priftis, Dimitrios
AU - Kotsis, Konstantinos
AU - Magklara, Konstantina
AU - Rannou, Ioanna
AU - Ladopoulou, Konstantina
AU - Koullourou, Iouliani
AU - Tsalamanios, Emmanouil
AU - Lazaratou, Eleni
AU - Serdari, Aspasia
AU - Grigoriadou, Aliki
AU - Sadeghi, Neda
AU - O'Callaghan, Georgia
AU - Chiu, Kenny
AU - Giannopoulou, Ioanna
PY - 2022/8/10
Y1 - 2022/8/10
N2 - 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.
AB - 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.
M3 - Preprint
BT - 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
PB - SSRN
ER -