Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 May 13;15(1):16518.
doi: 10.1038/s41598-025-00386-8.

Early detection of mental health disorders using machine learning models using behavioral and voice data analysis

Sunil Kumar Sharma  1   2 , Ahmed Ibrahim Alutaibi  3 , Ahmad Raza Khan  4 , Ghanshyam G Tejani  5   6 , Fuzail Ahmad  7   8 , Seyed Jalaleddin Mousavirad  9
Affiliations

Early detection of mental health disorders using machine learning models using behavioral and voice data analysis

Sunil Kumar Sharma et al. Sci Rep. .

Abstract

People of all demographics are impacted by mental illness, which has become a widespread and international health problem. Effective treatment and support for mental illnesses depend on early discovery and precise diagnosis. Notably, delayed diagnosis may lead to suicidal thoughts, destructive behaviour, and death. Manual diagnosis is time-consuming and laborious. With the advent of AI, this research aims to develop a novel mental health disorder detection network with the objective of maximum accuracy and early discovery. For this reason, this study presents a novel framework for the early detection of mental illness disorders using a multi-modal approach combining speech and behavioral data. This framework preprocesses and analyzes two distinct datasets to handle missing values, normalize data, and eliminate outliers. The proposed NeuroVibeNet combines Improved Random Forest (IRF) and Light Gradient-Boosting Machine (LightGBM) for behavioral data and Hybrid Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) for voice data. Finally, a weighted voting mechanism is applied to consolidate predictions. The proposed model achieves robust performance and a competitive accuracy of 99.06% in distinguishing normal and pathological conditions. This framework validates the feasibility of multi-modal data integration for reliable and early mental illness detection.

Keywords: Behavioral data; Deep learning; Machine learning; Mental health disorders; Voice data.

PubMed Disclaimer

Conflict of interest statement

Declarations. Competing interests: The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Block diagram of proposed model.
Algorithm. 1
Algorithm. 1
Pseudocode of Developed IDTW
Algorithm. 2
Algorithm. 2
Pseudocode of Developed MRFE
Algorithm. 3
Algorithm. 3
Overall Proposed Mental Illness Detection Framework
Fig. 2
Fig. 2
Workflow of MRFE.
Fig. 3
Fig. 3
Graphical Representation of Performance of Proposed NeuroVibeNet over Other Models for 70:30 and 80:20 Learning Samples with respect to (a) Accuracy, (b) Precision, (c) Specificity, (d) Sensitivity, (e) F1-Score, (f) MCC, (g) NPV, (h), FPR, and (i) FNR.
Fig. 3
Fig. 3
Graphical Representation of Performance of Proposed NeuroVibeNet over Other Models for 70:30 and 80:20 Learning Samples with respect to (a) Accuracy, (b) Precision, (c) Specificity, (d) Sensitivity, (e) F1-Score, (f) MCC, (g) NPV, (h), FPR, and (i) FNR.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. Merino, M. et al. Body perceptions and psychological well-being: A review of the impact of social media and physical measurements on self-esteem and mental health with a focus on body image satisfaction and its relationship with cultural and gender factors. Healthcare12(14), 1396 (2024). - PMC - PubMed
    1. Chen, X. & Pan, Z. A convenient and low-cost model of depression screening and early warning based on voice data using for public mental health. Int. J. Environ. Res. Public Health18(12), 6441 (2021). - PMC - PubMed
    1. Pourkeyvan, A., Safa, R. & Sorourkhah, A. Harnessing the power of hugging face transformers for predicting mental health disorders in social networks. IEEE Access12, 28025–28035 (2024).
    1. Khan, S. & Alqahtani, S. Hybrid machine learning models to detect signs of depression. Multimed. Tools Appl.83(13), 38819–38837 (2024).
    1. Ku, W. L. & Min, H. Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors. Healthcare12(6), 625 (2024). - PMC - PubMed

LinkOut - more resources