COMPARISON AND EXPLANABILITY OF MACHINE LEARNING MODELS IN PREDICTIVE SUICIDE ANALYSIS
DYNA NEW TECHNOLOGIES · 2024
DOI: 10.6036/nt11028 ↗At a glance
Journal article in DYNA NEW TECHNOLOGIES, 2024. Written by DANIEL ALEJANDRO BARAJAS ARANDA and 3 co-authors. Cited 1 times so far (Crossref).
Abstract (original language)
In this comparative study of machine learning models for predicting suicidal behavior, three approaches were evaluated: neural network, logistic regression, and decision trees. The results revealed that the neural network showed the best predictive performance, with an accuracy of 82.35%, followed by logistic regression (76.47%) and decision trees (64.71%). Additionally, the explainability analysis revealed that each model assigned different importance to the features in predicting suicidal behavior, highlighting the need to understand how models interpret features and how they influence predictions. The study provides valuable information for healthcare professionals and suicide prevention experts, enabling them to design more effective interventions and better understand the risk factors associated with suicidal behavior. However, it is noted the need to consider other factors, such as model interpretability and its applicability in different contexts or populations. Furthermore, further research and validation in different datasets are recommended to strengthen the understanding and applicability of the models in different contexts. In summary, this study significantly contributes to the field of predicting suicidal behavior using machine learning models, offering a detailed insight into the strengths and weaknesses of each approach and highlighting the importance of model interpretation for better understanding the underlying factors of suicidal behavior. Key words: Suicidal behavior prediction, Machine learning models, Neural network, Logistic regression, Decision tres, Explainability análisis, Healthcare intervention
Cite
APA
ARANDA, D. A. B., URBAN, M. A. S., SOTO, M. D. T., & SOTO, A. T. (2024). COMPARISON AND EXPLANABILITY OF MACHINE LEARNING MODELS IN PREDICTIVE SUICIDE ANALYSIS. DYNA NEW TECHNOLOGIES. https://doi.org/10.6036/nt11028
Vancouver
ARANDA DAB, URBAN MAS, SOTO MDT, SOTO AT. COMPARISON AND EXPLANABILITY OF MACHINE LEARNING MODELS IN PREDICTIVE SUICIDE ANALYSIS. DYNA NEW TECHNOLOGIES. 2024. doi:10.6036/nt11028
BibTeX
@article{ARANDA2024,
author = {ARANDA, DANIEL ALEJANDRO BARAJAS and URBAN, MIGUEL ANGEL SICILIA and SOTO, MARIA DOLORES TORRES and SOTO, AURORA TORRES},
title = {COMPARISON AND EXPLANABILITY OF MACHINE LEARNING MODELS IN PREDICTIVE SUICIDE ANALYSIS},
journal = {DYNA NEW TECHNOLOGIES},
year = {2024},
doi = {10.6036/nt11028}
}
EUVIMED