Comparative Analysis of Machine Learning Models to Predict Depression, Anxiety and Stress

Singh, Srishti; Gupta, Harsh; Singh, Prashant Kumar; Agrawal, Arun Prakash

doi:10.1109/smart55829.2022.10047752

Cited by 3 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DASS 42 is a questionnaire with 42 questions, consisting of 3 emotional scales: depression, anxiety, and stress with levels as shown in Table 5; normal, mild, moderate, severe, and very severe [31]. The DASS 42 scale can be classified into 3 [32], which are the depression scale (questions number 3,5,10,13,16,17,21,24,26,31,34,37,38,42), the anxiety scale (questions number 2, 4, 7, 9, 15, 19, 20, 23, 25, 28, 30, 36, 40, 41.3), and the stress scale (questions number 1,6,8,11,12,14,18,22,27,29,32,33,35,39).…”

Section: Dass 42 Testmentioning

confidence: 99%

Fuzzy logic method-based stress detector with blood pressure and body temperature parameters

Fajrin,

Sasmeri,

Riski Prilia

et al. 2024

IJECE

View full text Add to dashboard Cite

In this study, using the fuzzy logic method, a stress detection tool was created with body temperature and blood pressure parameters as indicators to determine a person's stress level. This tool uses the LM35DZ sensor to detect body temperature, the MPX5100GP sensor to read blood pressure values, and Arduino Uno as a data processor from sensor readings which are then calculated using the fuzzy logic method as a stress level decision-maker. The resulting output measures blood pressure, body temperature, and the stress level experienced by a person, which will be displayed on the liquid crystal display. Based on the results of testing the body temperature parameter, the highest error generated was 1.17%, and for the blood pressure parameter, the highest error was 2.5% for systole and 0.93% for diastole. Furthermore, testing the stress level displayed on the tool is compared to the depression, anxiety, and stress scales 42 (DASS 42), a psychological stress measuring instrument. From the results of testing the tool with the questionnaire, the average conformity level is 74%.

show abstract

Section: Dass 42 Testmentioning

confidence: 99%

Fuzzy logic method-based stress detector with blood pressure and body temperature parameters

Fajrin,

Sasmeri,

Riski Prilia

et al. 2024

IJECE

View full text Add to dashboard Cite

show abstract

“…To evaluate and select the models with the best performance, we use the popular measurement metrics, including precision (P), recall (R), F1-scores, and accuracy in prediction issues [43][44][45][46][47][48][49].…”

Section: Performance Measuresmentioning

confidence: 99%

An Analysis of Machine Learning for Detecting Depression, Anxiety, and Stress of Recovered COVID-19 Patients

Tuan,

Trang,

et al. 2024

J. Hum. Earth Future

View full text Add to dashboard Cite

Objectives: This study explores different machine learning models (KNN: k-nearest neighbor, MLP: Multilayer Perceptron, SVM: Support Vector Machine) to identify the optimal model for accurate and rapid mental health detection among the recovered COVID-19 patients. Other techniques are also investigated, such as feature selection (Recursive Feature Elimination (RFE) and Extra Trees (ET) methods) and hyper-parameter tuning, to achieve a system that could effectively and quickly indicate mental health. Method/Analysis: To achieve the objectives, the study employs a dataset collected from recovered COVID-19 patients, encompassing information related to depression, anxiety, and stress. Machine learning models are utilized in the analysis. Additionally, feature selection methods and hyper-parameter tuning techniques are explored to enhance the model’s predictive capabilities. The performance of each model is assessed based on accuracy metrics. Findings: The experimental results show that SVM is the most suitable model for accurately predicting an individual’s mental health among recovered COVID-19 patients (accuracy ≥ 0.984). Furthermore, the ET method is more effective than the RFE method for feature selection in the anxiety and stress datasets. Novelty/Improvement:The study lies in the understanding of predictive modeling for mental health and provides insights into the choice of models and techniques for accurate and early detection. Doi: 10.28991/HEF-2024-05-01-01 Full Text: PDF

show abstract

A Review of "Machine Learning Approaches to Assess Psychological Health: A Comparative Analysis of Non-Meditators and Meditators"

M G,

Kaur

2023

2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT)

View full text Add to dashboard Cite

Comparative Analysis of Machine Learning Models to Predict Depression, Anxiety and Stress

Cited by 3 publications

References 10 publications

Fuzzy logic method-based stress detector with blood pressure and body temperature parameters

Fuzzy logic method-based stress detector with blood pressure and body temperature parameters

An Analysis of Machine Learning for Detecting Depression, Anxiety, and Stress of Recovered COVID-19 Patients

A Review of "Machine Learning Approaches to Assess Psychological Health: A Comparative Analysis of Non-Meditators and Meditators"

Contact Info

Product

Resources

About