Predicting ADHD Risk from Touch Interaction Data

被引：9

作者：

Mock, Philipp ^{[1
]}

Tibus, Maike ^{[2
]}

Ehlis, Ann-Christine ^{[3
]}

Baayen, Harald ^{[4
]}

Gerjets, Peter ^{[1
]}

机构：

[1] Leibniz Inst Wissensmedien, Tubingen, Germany

[2] Univ Tubingen, Hector Res Inst Educ Sci, Tubingen, Germany

[3] Univ Hosp Tubingen, Dept Psychiat & Psychotherapy, Tubingen, Germany

[4] Univ Tubingen, Dept Linguist, Tubingen, Germany

来源：

ICMI'18: PROCEEDINGS OF THE 20TH ACM INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION | 2018年

关键词：

Multi-Touch; Machine-Learning; User Modeling; ADHD; ATTENTION-DEFICIT/HYPERACTIVITY DISORDER; CHILDREN; DIAGNOSIS;

D O I：

10.1145/3242969.3242986

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper presents a novel approach for automatic prediction of risk of ADHD in schoolchildren based on touch interaction data. We performed a study with 129 fourth-grade students solving math problems on a multiple-choice interface to obtain a large dataset of touch trajectories. Using Support Vector Machines, we analyzed the predictive power of such data for ADHD scales. For regression of overall ADHD scores, we achieve a mean squared error of 0.0962 on a four-point scale (R-2 = 0.5667). Classification accuracy for increased ADHD risk (upper vs. lower third of collected scores) is 91.1%.

引用

页码：446 / 454

页数：9

共 50 条

[11] Understanding Pen and Touch Interaction for Data Exploration on Interactive Whiteboards
Walny, Jagoda
Lee, Bongshin
Johns, Paul
Riche, Nathalie Henry
Carpendale, Sheelagh
IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS, 2012, 18 (12) : 2779 - 2788
[12] Predicting breast cancer risk from the interaction of multiple genetic polymorphisms.
Jupe, ER
Mulvihill, JJ
Ralph, DA
Aston, CE
Lalo, DP
Manjeshwar, S
Defreese, DC
Gramling, BA
Craft, MA
Mitchell, DS
JOURNAL OF CLINICAL ONCOLOGY, 2004, 22 (14) : 837S - 837S
[13] Predicting Affect from Gaze Data during Interaction with an Intelligent Tutoring System
Jaques, Natasha
Conati, Cristina
Harley, Jason M.
Azevedo, Roger
INTELLIGENT TUTORING SYSTEMS, ITS 2014, 2014, 8474 : 29 - 38
[14] Predicting protein function from protein/protein interaction data: a probabilistic approach
Letovsky, Stanley
Kasif, Simon
BIOINFORMATICS, 2003, 19 : i197 - i204
[15] Interaction Assessment: A modeling tool for predicting population dynamics from field data
Emlen, JM
Duda, JJ
Kirchhoff, MD
Freeman, DC
ECOLOGICAL MODELLING, 2006, 192 (3-4) : 557 - 570
[16] Google's MIDAS Touch: Predicting UK Unemployment with Internet Search Data
Smith, Paul
JOURNAL OF FORECASTING, 2016, 35 (03) : 263 - 284
[17] Touch in Social Interaction: Touch, Language, and Body
Robles, Jessica S.
SYMBOLIC INTERACTION, 2021, 44 (01) : 244 - 246
[18] Suicide Risk Among Adolescents With ADHD An Overview From the National Inpatient Sample Data Set
Trivedi, Chintan
Nandakumar, Aiswarya Lakshmi
Yousefzadehfard, Yashar
Goriparthi, Tulasi S. K.
Chaudhari, Gaurav
Vora, Darshini
Mansuri, Zeeshan
Jain, Shailesh
JOURNAL OF NERVOUS AND MENTAL DISEASE, 2023, 211 (03) : 216 - 220
[19] EARLY IDENTIFICATION OF RISK FOR ADHD FROM PREGNANCY TO PRESCHOOL: FINDINGS FROM THE EARLY ADHD CONSORTIUM
Joseph, Heather Marie
Constantino, John N.
JOURNAL OF THE AMERICAN ACADEMY OF CHILD AND ADOLESCENT PSYCHIATRY, 2024, 63 (10): : S354 - S354
[20] Social Interaction Rules in Cooperative Learning Groups for Students At Risk for ADHD
Kuester, Deitra A.
Zentall, Sydney S.
JOURNAL OF EXPERIMENTAL EDUCATION, 2012, 80 (01): : 69 - 95

← 1 2 3 4 5 →