Menachem M. Kiwak Ph.D, LMHC

As mental health concerns continue to rise globally, innovative and scalable methods for early detection and diagnosis have become crucial. Internet-based psychological assessments are among the most promising tools for broad-reaching, large-scale screenings. However, traditional methods of psychological evaluation often face challenges related to non-genuine responses and lack of objective metrics. A recent study conducted at Xinxiang Medical University addresses these challenges by incorporating response time data into psychological assessments, offering a novel dataset for exploring mental health diagnostics.

This blog post draws on the comprehensive work published in Scientific Data by Zhao Su, Rongxun Liu, Yange Wei, and their colleagues titled “Temporal dynamics in psychological assessments: a novel dataset with scales and response times” .

The Role of Internet-Based Assessments in Mental Health

Internet-based psychological assessments have become indispensable for large-scale mental health screening. By enabling remote participation, these tools have the potential to reach vast, diverse populations, offering early insight into psychological conditions such as depression, anxiety, and stress.

Despite their scalability and accessibility, internet-based surveys often suffer from participants providing careless responses (CRs), which can dramatically affect the reliability of the results. In fact, as the study from Xinxiang Medical University points out, the proportion of careless responses in online surveys can range from 1% to 50%, depending on various factors .

The novel approach in this study was the inclusion of response time data to better understand participant behavior during psychological screenings. In cognitive psychology, response time—the time a participant takes to respond to a stimulus—is often used as a key metric, and applying it to mental health assessments can help identify non-genuine responses .

The Xinxiang Medical University Study

Between February 27 and March 17, 2021, 24,292 students at Xinxiang Medical University were surveyed using four well-established psychological scales:

• PHQ-9 (Patient Health Questionnaire-9) for depression

• GAD-7 (General Anxiety Disorder-7) for anxiety

• ISI (Insomnia Severity Index) for insomnia

• PSS (Perceived Stress Scale) for stress

What made this study stand out was that it also meticulously recorded the response times for each question, offering an objective layer of behavioral data that complements the subjective responses .

Why Response Time Matters

Response time serves as a vital tool in this study, allowing researchers to measure participant engagement and identify careless responses. The research found that irregularities in response times often correlate with non-genuine answers. For example, participants who completed certain sections of the survey too quickly were flagged as potentially careless respondents.

By using this data, the research team was able to partially filter out non-genuine responses and improve the accuracy of their findings. This approach also paves the way for using response time data in combination with machine learning algorithms to predict outcomes such as insomnia severity with high accuracy .

Key Insights from the Dataset

The response time data offers a unique opportunity for researchers to explore psychological assessment in a way that was not possible before. For instance, variations in response times could help identify subtypes of participants based on their answering behaviors, offering a more detailed understanding of mental health status.

This dataset also opens the door for the future development of adaptive psychological assessments, where the length and complexity of the survey are tailored to individual participants based on their response times and behavior .

Implications for Mental Health Diagnostics

This study marks an essential step in improving the reliability of internet-based psychological screenings. By combining traditional psychological scales with behavioral data like response times, researchers can more accurately diagnose mental health conditions and reduce the likelihood of false negatives or positives. The large-scale dataset collected at Xinxiang Medical University is a significant asset for researchers aiming to enhance the precision and efficiency of mental health diagnostics.

Looking Ahead

The inclusion of response time in psychological screenings is just one example of how data-driven approaches are reshaping mental health diagnostics. This study from Xinxiang Medical University represents a merging of traditional psychological tools with modern data analytics, setting the stage for further innovations.

As highlighted in other projects I’ve worked on, such as Krulasms and the OWAL Android app, leveraging technology to develop scalable, reliable solutions is key. Whether in mental health, communication services, or computer vision, the future lies in combining robust data with advanced algorithms to address critical challenges.

The dataset and insights provided by Zhao Su and his team offer a valuable resource for future research into mental health during the COVID-19 pandemic and beyond, showing how technology can bring new depth and accuracy to psychological assessments.

Attribution:

This blog post is based on the article “Temporal dynamics in psychological assessments: a novel dataset with scales and response times” by Zhao Su, Rongxun Liu, Yange Wei, Ran Zhang, Xiao Xu, Yang Wang, Yue Zhu, Lifei Wang, Lijuan Liang, Fei Wang & Xizhe Zhang, originally published in Scientific Data.