Natural language processing for suicidal behavior detection in short Spanish clinical notes from first-contact interviews.
- 1Unidad Acadèmica Tepic, Centro de Investigación Científica y de Educación Superior de Ensenada, Tepic, Nayarit, Mexico.
Abstract
Introduction
Suicide is a multifactorial phenomenon influenced by social, cultural, biological, and psychological factors, whose early detection remains challenging. According to the World Health Organization, suicide is the third leading cause of death among individuals aged 15-29 years, representing a major public health concern for young populations worldwide. In first-contact clinical settings, screening opportunities are often constrained by limited time, sparse patient information, and operational workflows. This study evaluates the feasibility of detecting suicidal behavior from short Spanish-language texts collected during initial screening interviews.Methods
The dataset comprises 374 anonymized records labeled as "no suicidal behavior," "ideation," "planning," or "attempt," with a strong imbalance toward "attempt," reflecting operational clinical usage rather than population-representative sampling. To address data scarcity, we applied data augmentation methods (Easy Data Augmentation for Spanish, backtranslation, and large language model-based synthesis), validated through statistical analysis and clinician-based plausibility assessments.Results
Exploratory analyses revealed highly constrained and overlapping lexical patterns across classes, indicating the challenging nature of the task. A Support Vector Machine achieved 0.53 macro F ₁ in binary classification ("suicidal behavior" vs. "no behavior"), while BETO, a Spanish BERT model, reached 0.36 macro F ₁ in multiclass classification. Under the same text-only conditions, human specialists achieved macro F ₁ scores of 0.29 and 0.15 respectively; however, these results were based on only 20 real texts evaluated with double annotation across five specialists and should therefore be interpreted cautiously.Discussion
Although performance is modest compared to studies using full clinical records, these findings suggest that short-text machine learning could support nonspecialists in first-contact settings. Future work should expand datasets and explore multimodal approaches, including voice and text, to improve clinical applicability and early detection.
Related
- Assessing the Impact of Language on Visual Threat Detection: cTBS over the anterior temporal lobe impairs semantic processing but not visual threat detection
- Connectionist models of human language processing : Progress and prospects
- Sometimes you look more when you know less: Goal dependent eye movements during language processing
- Highlighting the strengths of new wearable fNIRS, precision accuracy microgenetic research designs, and new NeuroDOT processing algorithm to measure change over time in clinical populations for Speech-Language and Hearing Researchers
- A comparative analysis of machine learning, deep learning, and ensemble learning models for suicidal ideation detection on social media
BibTeX
@article{villagomezgarcia2026natural,
title = {{Natural language processing for suicidal behavior detection in short Spanish clinical notes from first-contact interviews.}},
author = {Juan Carlos Villagomez-Garcia and Juan Martínez-Miranda and Ansel Y Rodríguez-González},
journal = {Frontiers in neuroinformatics},
year = {2026},
month = oct,
doi = {10.3389/fninf.2026.1919962},
url = {https://europepmc.org/article/MED/42908804},
note = {CC BY},
}
RIS
TY - JOUR
TI - Natural language processing for suicidal behavior detection in short Spanish clinical notes from first-contact interviews.
AU - Juan Carlos Villagomez-Garcia
AU - Juan Martínez-Miranda
AU - Ansel Y Rodríguez-González
PY - 2026
DA - 2026/10/07
JO - Frontiers in neuroinformatics
DO - 10.3389/fninf.2026.1919962
UR - https://europepmc.org/article/MED/42908804
AB - Introduction Suicide is a multifactorial phenomenon influenced by social, cultural, biological, and psychological factors, whose early detection remains challenging. According to the World Health Organization, suicide is the third leading cause of death among individuals aged 15-29 years, representing a major public health concern for young populations worldwide. In first-contact clinical settings, screening opportunities are often constrained by limited time, sparse patient information, and operational workflows. This study evaluates the feasibility of detecting suicidal behavior from short Spanish-language texts collected during initial screening interviews.Methods The dataset comprises 374 anonymized records labeled as "no suicidal behavior," "ideation," "planning," or "attempt," with a strong imbalance toward "attempt," reflecting operational clinical usage rather than population-representative sampling. To address data scarcity, we applied data augmentation methods (Easy Data Augmentation for Spanish, backtranslation, and large language model-based synthesis), validated through statistical analysis and clinician-based plausibility assessments.Results Exploratory analyses revealed highly constrained and overlapping lexical patterns across classes, indicating the challenging nature of the task. A Support Vector Machine achieved 0.53 macro F ₁ in binary classification ("suicidal behavior" vs. "no behavior"), while BETO, a Spanish BERT model, reached 0.36 macro F ₁ in multiclass classification. Under the same text-only conditions, human specialists achieved macro F ₁ scores of 0.29 and 0.15 respectively; however, these results were based on only 20 real texts evaluated with double annotation across five specialists and should therefore be interpreted cautiously.Discussion Although performance is modest compared to studies using full clinical records, these findings suggest that short-text machine learning could support nonspecialists in first-contact settings. Future work should expand datasets and explore multimodal approaches, including voice and text, to improve clinical applicability and early detection.
SN - 1662-5196
ER -