Latent Similarity Gaussian Processes: A Theory-Grounded Approach to Personalized Suicide-Risk Forecasting for Clinical Decision-Support
Abstract
Forecasting suicide risk is difficult due to the high heterogeneity of patients and the low base rate of suicide-related events (SREs). We present Latent Similarity Gaussian Processes (LSGPs), which embed patients in a continuous latent space to jointly model similarity and forecast risk. By selectively drawing information from latent peers, LSGPs better capture individualized risk trajectories, generalizing nomothetic (pooled), idiographic (per-patient), and hierarchical frameworks. Our contributions are: (1) an identifiable two-channel Similarity Kernel; (2) proof that the standard model-fitting algorithm, mean-field variational inference, collapses LSGPs to nomothetic models, along with a fix; and (3) empirical results on intensive longitudinal suicide data showing LSGPs outperform nomothetic, idiographic, and hierarchical models for next-week risk forecasting, with the largest gains in forecasting first-occurrence SREs.
Related
- Quasihelix properties of selected Volterra Gaussian processes
- Gaussian approximation for the integrated intensity of counting processes: application to Hawkes processes
- UPPER TAIL PROBABILITY ESTIMATES OF SUPREMA OF GAUSSIAN PROCESSES BY MATRICES, A NUMBER THEORETIC EXAMPLE
- Forecasting of infectious disease epidemics in sexual networks using attenuated renewal processes
- Gaussian Processes with Sample Paths in Reproducing Kernel Banach Spaces
BibTeX
@misc{yacoby2026latent,
title = {{Latent Similarity Gaussian Processes: A Theory-Grounded Approach to Personalized Suicide-Risk Forecasting for Clinical Decision-Support}},
author = {Yaniv Yacoby and Weiwei Pan and Hope Neveux and Taylor C. McGuire and Franchesca Castro-Ramirez and Anushka R. Patel and Matthew K. Nock},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.06355},
eprint = {2610.06355},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.06355},
}
RIS
TY - UNPB
TI - Latent Similarity Gaussian Processes: A Theory-Grounded Approach to Personalized Suicide-Risk Forecasting for Clinical Decision-Support
AU - Yaniv Yacoby
AU - Weiwei Pan
AU - Hope Neveux
AU - Taylor C. McGuire
AU - Franchesca Castro-Ramirez
AU - Anushka R. Patel
AU - Matthew K. Nock
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2610.06355
UR - https://arxiv.org/abs/2610.06355
AB - Forecasting suicide risk is difficult due to the high heterogeneity of patients and the low base rate of suicide-related events (SREs). We present Latent Similarity Gaussian Processes (LSGPs), which embed patients in a continuous latent space to jointly model similarity and forecast risk. By selectively drawing information from latent peers, LSGPs better capture individualized risk trajectories, generalizing nomothetic (pooled), idiographic (per-patient), and hierarchical frameworks. Our contributions are: (1) an identifiable two-channel Similarity Kernel; (2) proof that the standard model-fitting algorithm, mean-field variational inference, collapses LSGPs to nomothetic models, along with a fix; and (3) empirical results on intensive longitudinal suicide data showing LSGPs outperform nomothetic, idiographic, and hierarchical models for next-week risk forecasting, with the largest gains in forecasting first-occurrence SREs.
ER -