Exploring the relationship between response time sequence in scale answering process and severity of insomnia - Machine learning approach

Q: What is the main goal of the study?

The study investigates the relationship between insomnia and response time sequence, and develops a machine learning model to predict insomnia presence from response-time data.

Q: How was response time data collected?

A mobile application administered scale tests and collected response time data from 2,729 participants during the answering process.

Q: What did the results show about response time?

Participants with insomnia symptoms had a statistically significant difference in total response time, and severity of specific insomnia aspects correlated with response times at the individual question level.

Q: How accurate was the machine learning model?

The model achieved a predictive accuracy of 0.743 for identifying insomnia symptoms using response time data.

Aug 4, 2026

Upload by Ava Thompson

Study objectives focus on clarifying how insomnia relates to response time behavior and on building a machine learning model that predicts insomnia presence using response-time data. A mobile application administered insomnia scale tests and collected response time from 2,729 participants. Analyses examined associations between symptom severity and response time, including differences between individuals with and without insomnia symptoms and correlations at the individual-question level. Results showed significant total response-time differences and a machine learning model with predictive accuracy of 0.743.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages27

Reading Time1 h 8 min

AccessFree to download

Introduction

Objectives

Methods

Results

Conclusions

Exploring the relationship between response time sequence in scale answering process and severity of insomnia: a machine learning approach Zhao Su1*, Rongxun Liu2,3*, Keyin Zhou2, Xinru Wei1, Ning Wang2,4, Zexin Lin2, Yuanchen Xie5, Jie Wang1, Fei Wang2\#, Shenzhong Zhang1\#, Xizhe Zhang1\# 1School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, Jiangsu, China. 2Early Intervention Unit, Department of Psychiatry, Affiliated Nanjing Brain Hospital, Nanjing Medical University, Nanjing, Jiangsu, China. 3School of Psychology, Xinxiang Medical University, Xinxiang, Henan, China 4School of Public Health, Xinxiang Medical University, Xinxiang, Henan, China 5The Fourth School of Clinical Medicine, Nanjing Medical University, Nanjing, Jiangsu, China. *The two authors contributed equally to this work: Zhao Su, Rongxun Liu \#Corresponding authors: [Fei Wang ](Fei Wang fei.wang@yale.edu)[fei.wang@yale.edu](Fei Wang fei.wang@yale.edu), [Shenzhong Zhang ](Shenzhong Zhang zsz@njmu.edu.cn)[zsz@njmu.edu.cn](Shenzhong Zhang zsz@njmu.edu.cn), [Xizhe Zhang ](Xizhe Zhang zhangxizhe@njmu.edu.cn)[zhangxizhe@njmu.edu.cn](Xizhe Zhang zhangxizhe@njmu.edu.cn). Manuscript Details Word Count: 3,987 words Figure Count: 6 figures Table Count: 2 tables Reference Count: 29 references Supplement Count: 1 figure, 5 tables Abstract Word Count: 168 words Abstract Objectives: The study aims to investigate the relationship between insomnia and response time. Additionally, it aims to develop a machine learning model to predict the presence of insomnia in participants using response time data. Methods: A mobile application was designed to administer scale tests and collect response time data from 2729 participants. The relationship between symptom severity and response time was explored, and a machine learning model was developed to predict the presence of insomnia. Results: The result revealed a statistically significant difference (p<.001) in the total response time between participants with or without insomnia symptoms. A correlation was observed between the severity of specific insomnia aspects and response times at the individual questions level. The machine learning model demonstrated a high predictive accuracy of 0.743 in predicting insomnia symptoms based on response time data. Conclusions: These findings highlight the potential utility of response time data to evaluate cognitive and psychological measures, demonstrating the effectiveness of using response time as a diagnostic tool in the assessment of insomnia. Keywords: response time; machine learning; insomnia; behavioral data. Introduction Psychological self-assessment scales are widely used to evaluate various mental health factors, including insomnia. However, these scales often come with the subjective bias of the participants, leading to potential inconsistencies in severity and symptom expression 1,2. Especially for self-assessment scales, the reports of people on their own thoughts, feelings, and behaviors often result in subjective bias 3. For instance, the Insomnia Severity Index (ISI) scale, employed in this study, may yield divergent assessments of insomnia severity and symptoms even when two individuals report identical scores. With the advent of information technology, participants can conveniently answer assessment scales on their personal device 4. At the same time, their behavioral data during the answering process can also be collected 5. This behavioral data can offer an objective perspective on the participant's state during the scale completion, and could significantly assist in the interpretation of scale results 6. Response Time (RT), which represents the duration taken by a participant to respond to a stimulus or complete a task, is a meaningful metric commonly used in various experiments in cognitive psychology 7. In cognitive psychology research, RT functions as a dependent variable, influenced by manipu

FAQs

What is the main goal of the study?

The study investigates the relationship between insomnia and response time sequence, and develops a machine learning model to predict insomnia presence from response-time data.

How was response time data collected?

A mobile application administered scale tests and collected response time data from 2,729 participants during the answering process.

What did the results show about response time?

Participants with insomnia symptoms had a statistically significant difference in total response time, and severity of specific insomnia aspects correlated with response times at the individual question level.

How accurate was the machine learning model?

The model achieved a predictive accuracy of 0.743 for identifying insomnia symptoms using response time data.

Aug 4, 2026

Upload by Ava Thompson