Implication of machine learning models versus traditional models for the prediction of suicidal thoughts or ideation in west of Iran; data mining approaches on a population-based cross-sectional study

By
Arezoo Sarmand
Mohammad Raiszadeh
Khadijeh Najafi-Ghobadi
Ebadallah Shiri Malekabadi
Babak Shekarchi
Reza Pakzad
Mojgan Mohajeri Irvani
Ramin Afrah
May 25, 2026
0 min

Digital Health

Objective:

To identify the most significant variables influencing suicidal thoughts or ideation in Ilam City during 2023 by comparing machine learning models with traditional predictive models.

Key Findings:

Machine learning models (DT, RF, SVM, NNs) were compared with a classical logistic regression model.
Previous studies indicated mixed results regarding the performance of traditional classifiers versus data mining methods.

Interpretation:

Limitations:

The study relies on secondary data, which may limit the depth of analysis.
Potential biases in self-reported data from questionnaires.

Implication of machine learning models versus traditional models for the prediction of suicidal thoughts or ideation in west of Iran; data mining approaches on a population-based cross-sectional study

Objective:

Key Findings:

Interpretation:

Limitations:

Conclusion:

Original Source(s)

Implication of machine learning models versus traditional models for the prediction of suicidal thoughts or ideation in west of Iran; data mining approaches on a population-based cross-sectional study

Related Content

Could Digital Twins Forecast Forensic Risk?

Network structure analysis of depression, anxiety, and stress symptoms among college students: identification of central and bridge symptoms

Sleep quality and its associated factors among women of reproductive age in Ethiopia: a systematic review and meta-analysis