Deep learning based analysis of factors associated with breast and cervical cancer using matched case control data

Breast and cervical cancers remain leading causes of morbidity among women worldwide, with a disproportionate burden in low- and middle-income countries. Although numerous environmental, behavioral, and reproductive risk factors have been identified, their complex interrelationships are insufficiently explored using conventional statistical approaches. Advanced analytical methods may better capture multidimensional exposure patterns relevant to public health prevention. We conducted a case–control study including 632 women (confirmed breast or cervical cancer cases and age-matched controls). Standardized data collection assessed environmental exposures, lifestyle behaviors, and reproductive history. To address high-dimensional data and non-linear correlations, we implemented a deep learning framework using an autoencoder neural network for latent feature extraction and dimensionality reduction. This approach enabled the identification of complex interaction patterns beyond traditional regression models. Established environmental and behavioral factors were significantly associated with cancer status. The autoencoder-based model improved discrimination between cases and controls and revealed synergistic interaction effects between selected lifestyle and environmental exposures. These combined effects substantially strengthened predictive performance compared with models based solely on individual risk factors. Integrating Deep Learning techniques into epidemiological research provides added value for understanding the multifactorial etiology of women’s cancers. Identifying latent interaction patterns supports more refined risk stratification and informs targeted prevention strategies. This approach contributes to advancing precision public health initiatives aimed at improving women’s health outcomes and optimizing resource allocation.

Authors

Institutions

Publication Details

Journal
Discover Public Health
Published
2026-11-20
DOI
https://doi.org/10.1186/s12982-026-03290-2
Primary Topic
Cancer Risks and Factors
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Deep learning based analysis of factors associated with breast and cervical cancer using matched case control data

Bachir El Bouhali, Sakhr Dadda, Karima Azekour, Hajiba Abraou et al.
3 links
Discover Public Health
Cancer Risks and Factors
article

Deep learning based analysis of factors associated with breast and cervical cancer using matched case control data

Bachir El Bouhali, Sakhr Dadda, Karima Azekour, Hajiba Abraou, Azeddine Hlali
article en

Abstract

Breast and cervical cancers remain leading causes of morbidity among women worldwide, with a disproportionate burden in low- and middle-income countries. Although numerous environmental, behavioral, and reproductive risk factors have been identified, their complex interrelationships are insufficiently explored using conventional statistical approaches. Advanced analytical methods may better capture multidimensional exposure patterns relevant to public health prevention. We conducted a case–control study including 632 women (confirmed breast or cervical cancer cases and age-matched controls). Standardized data collection assessed environmental exposures, lifestyle behaviors, and reproductive history. To address high-dimensional data and non-linear correlations, we implemented a deep learning framework using an autoencoder neural network for latent feature extraction and dimensionality reduction. This approach enabled the identification of complex interaction patterns beyond traditional regression models. Established environmental and behavioral factors were significantly associated with cancer status. The autoencoder-based model improved discrimination between cases and controls and revealed synergistic interaction effects between selected lifestyle and environmental exposures. These combined effects substantially strengthened predictive performance compared with models based solely on individual risk factors. Integrating Deep Learning techniques into epidemiological research provides added value for understanding the multifactorial etiology of women’s cancers. Identifying latent interaction patterns supports more refined risk stratification and informs targeted prevention strategies. This approach contributes to advancing precision public health initiatives aimed at improving women’s health outcomes and optimizing resource allocation.

Discover Public HealthVol. 23(1)
Instituts Supérieurs des Professions Infirmières et Techniques de Santé (MA), Université Moulay Ismail de Meknes (MA), Sidi Mohamed Ben Abdellah University (MA)
Good health and well-being, Reduced inequalities
Cancer Risks and Factors
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon