Deep Poisson Case Time Series Model for Complex Environmental Exposure Modeling on Acute Health Outcome

Keyu Li, Elaona Lemoto, Zachary D. Calhoun, Charles T Wood, Nrupen A. Bhavsar, David Carlson
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:1056-1088, 2026.

Abstract

Modern environmental health studies increasingly collect rich spatio-temporal exposure data, yet existing methods for assessing acute health effects still rely on low-dimensional summaries that discard informative structure. Self-matched designs, such as the case time series, effectively control for stable between-area confounding but do not readily extend to complex, high-dimensional exposure histories. To address this limitation, we introduce the Deep Poisson Case Time Series (DPCTS), a self-matched deep learning framework for area-level health outcomes that integrates within-unit stratification with end-to-end representation learning from complex exposures. DPCTS employs a neural exposure encoder trained with a Poisson objective, incorporates temporal context and multi-scale supervision to capture lagged effects across multiple resolutions, and supports tabular, image-based, and multimodal inputs. In addition, we propose novel evaluation metrics that isolate exposure-driven performance from between-area baseline differences by measuring within-stratum fit, predictive accuracy, and discrimination. Across synthetic, semi-synthetic, and real-world experiments, DPCTS recovers nonlinear exposure-response relationships and fine-scale risk patterns more accurately than classical baselines. These findings establish that representation learning can be embedded within self-matched epidemiologic study designs to analyze complex exposure data while preserving the within-unit comparisons essential for studying short-term health risk.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-li26c, title = {Deep Poisson Case Time Series Model for Complex Environmental Exposure Modeling on Acute Health Outcome}, author = {Li, Keyu and Lemoto, Elaona and Calhoun, Zachary D. and Wood, Charles T and Bhavsar, Nrupen A. and Carlson, David}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {1056--1088}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/li26c/li26c.pdf}, url = {https://proceedings.mlr.press/v340/li26c.html}, abstract = {Modern environmental health studies increasingly collect rich spatio-temporal exposure data, yet existing methods for assessing acute health effects still rely on low-dimensional summaries that discard informative structure. Self-matched designs, such as the case time series, effectively control for stable between-area confounding but do not readily extend to complex, high-dimensional exposure histories. To address this limitation, we introduce the Deep Poisson Case Time Series (DPCTS), a self-matched deep learning framework for area-level health outcomes that integrates within-unit stratification with end-to-end representation learning from complex exposures. DPCTS employs a neural exposure encoder trained with a Poisson objective, incorporates temporal context and multi-scale supervision to capture lagged effects across multiple resolutions, and supports tabular, image-based, and multimodal inputs. In addition, we propose novel evaluation metrics that isolate exposure-driven performance from between-area baseline differences by measuring within-stratum fit, predictive accuracy, and discrimination. Across synthetic, semi-synthetic, and real-world experiments, DPCTS recovers nonlinear exposure-response relationships and fine-scale risk patterns more accurately than classical baselines. These findings establish that representation learning can be embedded within self-matched epidemiologic study designs to analyze complex exposure data while preserving the within-unit comparisons essential for studying short-term health risk.} }
Endnote
%0 Conference Paper %T Deep Poisson Case Time Series Model for Complex Environmental Exposure Modeling on Acute Health Outcome %A Keyu Li %A Elaona Lemoto %A Zachary D. Calhoun %A Charles T Wood %A Nrupen A. Bhavsar %A David Carlson %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-li26c %I PMLR %P 1056--1088 %U https://proceedings.mlr.press/v340/li26c.html %V 340 %X Modern environmental health studies increasingly collect rich spatio-temporal exposure data, yet existing methods for assessing acute health effects still rely on low-dimensional summaries that discard informative structure. Self-matched designs, such as the case time series, effectively control for stable between-area confounding but do not readily extend to complex, high-dimensional exposure histories. To address this limitation, we introduce the Deep Poisson Case Time Series (DPCTS), a self-matched deep learning framework for area-level health outcomes that integrates within-unit stratification with end-to-end representation learning from complex exposures. DPCTS employs a neural exposure encoder trained with a Poisson objective, incorporates temporal context and multi-scale supervision to capture lagged effects across multiple resolutions, and supports tabular, image-based, and multimodal inputs. In addition, we propose novel evaluation metrics that isolate exposure-driven performance from between-area baseline differences by measuring within-stratum fit, predictive accuracy, and discrimination. Across synthetic, semi-synthetic, and real-world experiments, DPCTS recovers nonlinear exposure-response relationships and fine-scale risk patterns more accurately than classical baselines. These findings establish that representation learning can be embedded within self-matched epidemiologic study designs to analyze complex exposure data while preserving the within-unit comparisons essential for studying short-term health risk.
APA
Li, K., Lemoto, E., Calhoun, Z.D., Wood, C.T., Bhavsar, N.A. & Carlson, D.. (2026). Deep Poisson Case Time Series Model for Complex Environmental Exposure Modeling on Acute Health Outcome. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:1056-1088 Available from https://proceedings.mlr.press/v340/li26c.html.

Related Material