A Deep Learning Approach to Imputation of Dynamic Pupil Size Data and Prediction of ADHD

被引:2
|
作者
Choi, Seongyune [1 ]
Jang, Yeonju [1 ]
Kim, Hyeoncheol [1 ]
机构
[1] Korea Univ, Dept Comp Sci & Engn, 145 Anam Ro, Seoul, South Korea
关键词
Attention-deficit/hyperactivity disorder (ADHD); eye tracking; deep learning; pupil size; ATTENTION-DEFICIT/HYPERACTIVITY DISORDER; CHILDREN; DIAGNOSIS; NETWORKS; ANXIETY; EEG;
D O I
10.1142/S0218213023500203
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Attention-deficit/hyperactivity disorder (ADHD) is a common neurodevelopmental disorder in children and adolescents. Traditional diagnosis methods of ADHD focus on observed behavior and reported symptoms, which may lead to a misdiagnosis. Studies have focused on computer-aided systems to improve the objectivity and accuracy of ADHD diagnosis by utilizing psychophysiological data measured from devices such as EEG and MRI. Despite their performance, their low accessibility has prevented their widespread adoption. We propose a novel ADHD prediction method based on the pupil size dynamics measured using eye tracking. Such data typically contain missing values owing to anomalies including blinking or outliers, which negatively impact the classification. We therefore applied an end-to-end deep learning model designed to impute the dynamic pupil size data and predict ADHD simultaneously. We used the recorded dataset of an experiment involving 28 children with ADHD and 22 children as a control group. Each subject conducted an eight-second visuospatial working memory task 160 times. We treated each trial as an independent data sample. The proposed model effectively imputes missing values and outperforms other models in predicting ADHD (AUC of 0.863). Thus, given its high accessibility and low cost, the proposed approach is promising for objective ADHD diagnosis.
引用
收藏
页数:23
相关论文
共 50 条
  • [21] Practical applications of deep learning to imputation of drug discovery data
    Whitehead, Thomas
    Irwin, Benedict
    Hunt, Peter
    Segall, Matthew
    Conduit, Gareth
    [J]. ABSTRACTS OF PAPERS OF THE AMERICAN CHEMICAL SOCIETY, 2019, 258
  • [22] Energetic Map Data Imputation: A Machine Learning Approach
    Straub, Tobias
    Nagy, Madalina Mandy
    Sidorov, Maxim
    Tonetto, Leonardo
    Frey, Michael
    Gauterin, Frank
    [J]. ENERGIES, 2020, 13 (04)
  • [23] Numerical Data Imputation: Choose kNN over Deep Learning
    Lalande, Florian
    Doya, Kenji
    [J]. SIMILARITY SEARCH AND APPLICATIONS (SISAP 2022), 2022, 13590 : 3 - 10
  • [24] Deep-STEP: A Deep Learning Approach for Spatiotemporal Prediction of Remote Sensing Data
    Das, Monidipa
    Ghosh, Soumya K.
    [J]. IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2016, 13 (12) : 1984 - 1988
  • [25] Toward a prediction approach based on deep learning in Big Data analytics
    Omar Haddad
    Fethi Fkih
    Mohamed Nazih Omri
    [J]. Neural Computing and Applications, 2023, 35 : 6043 - 6063
  • [26] A deep learning approach for anomaly detection and prediction in power consumption data
    Chahla, C.
    Snoussi, H.
    Merghem, L.
    Esseghir, M.
    [J]. ENERGY EFFICIENCY, 2020, 13 (08) : 1633 - 1651
  • [27] Toward a prediction approach based on deep learning in Big Data analytics
    Haddad, Omar
    Fkih, Fethi
    Omri, Mohamed Nazih
    [J]. NEURAL COMPUTING & APPLICATIONS, 2023, 35 (08): : 6043 - 6063
  • [28] A deep learning approach for anomaly detection and prediction in power consumption data
    C. Chahla
    H. Snoussi
    L. Merghem
    M. Esseghir
    [J]. Energy Efficiency, 2020, 13 : 1633 - 1651
  • [29] Obesity Prediction with EHR Data: A Deep Learning Approach with Interpretable Elements
    Gupta, Mehak
    Phan, Thao-Ly T.
    Bunnell, H. Timothy
    Beheshti, Rahmatollah
    [J]. ACM Transactions on Computing for Healthcare, 2022, 3 (03):
  • [30] A Big Data Based Deep Learning Approach for Vehicle Speed Prediction
    Cheng, Zheyuan
    Chow, Mo-Yuen
    Jung, Daebong
    Jeon, Jinyong
    [J]. 2017 IEEE 26TH INTERNATIONAL SYMPOSIUM ON INDUSTRIAL ELECTRONICS (ISIE), 2017, : 389 - 394