Guardado en:
Detalles Bibliográficos
Autores principales: Hang, Genesis, Chen, Annie, Neveux, Hope, Nock, Matthew K., Yacoby, Yaniv
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:https://arxiv.org/abs/2511.18199
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917099826315264
author Hang, Genesis
Chen, Annie
Neveux, Hope
Nock, Matthew K.
Yacoby, Yaniv
author_facet Hang, Genesis
Chen, Annie
Neveux, Hope
Nock, Matthew K.
Yacoby, Yaniv
contents Ecological Momentary Assessment provides real-time data on suicidal thoughts and behaviors, but predicting suicide attempts remains challenging due to their rarity and patient heterogeneity. We show that single models fit to all patients perform poorly, while individualized models improve performance but still overfit to patients with limited data. To address this, we introduce Latent Similarity Gaussian Processes (LSGPs) to capture patient heterogeneity, enabling those with little data to leverage similar patients' trends. Preliminary results show promise: even without kernel-design, we outperform all but one baseline while offering a new understanding of patient similarity.
format Preprint
id arxiv_https___arxiv_org_abs_2511_18199
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improving Forecasts of Suicide Attempts for Patients with Little Data
Hang, Genesis
Chen, Annie
Neveux, Hope
Nock, Matthew K.
Yacoby, Yaniv
Machine Learning
Ecological Momentary Assessment provides real-time data on suicidal thoughts and behaviors, but predicting suicide attempts remains challenging due to their rarity and patient heterogeneity. We show that single models fit to all patients perform poorly, while individualized models improve performance but still overfit to patients with limited data. To address this, we introduce Latent Similarity Gaussian Processes (LSGPs) to capture patient heterogeneity, enabling those with little data to leverage similar patients' trends. Preliminary results show promise: even without kernel-design, we outperform all but one baseline while offering a new understanding of patient similarity.
title Improving Forecasts of Suicide Attempts for Patients with Little Data
topic Machine Learning
url https://arxiv.org/abs/2511.18199