Stage-Aware Event-Based Modeling (SA-EBM) for Disease Progression

Hongtao Hao, Vivek Prabhakaran, Veena A Nair, Nagesh Adluru, Joseph Austerweil
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

As diseases progress, the number of cognitive and biological biomarkers they impact increases. By formulating probabilistic models with this basic assumption, Event-Based Models (EBMs) enable researchers to discover the progression of a disease that makes earlier diagnosis and effective clinical interventions possible. We build on prior EBMs with two major improvements: (1) dynamic estimation of healthy and pathological biomarker distributions, and (2) explicit modeling of the distribution of disease stages. We tested existing approaches and our novel approach on a benchmark of 9,000 synthetic datasets, inspired from real-world data. We found that our stage-aware EBM (SA-EBM) significantly outperforms prior methods, such as Gaussian Mixture Model (GMM) EBM, Kernel Density Estimation EBM and Discriminative EBM, on ordering and staging tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-hao25a, title = {Stage-Aware Event-Based Modeling ({SA}-{EBM}) for Disease Progression}, author = {Hao, Hongtao and Prabhakaran, Vivek and Nair, Veena A and Adluru, Nagesh and Austerweil, Joseph}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/hao25a/hao25a.pdf}, url = {https://proceedings.mlr.press/v298/hao25a.html}, abstract = {As diseases progress, the number of cognitive and biological biomarkers they impact increases. By formulating probabilistic models with this basic assumption, Event-Based Models (EBMs) enable researchers to discover the progression of a disease that makes earlier diagnosis and effective clinical interventions possible. We build on prior EBMs with two major improvements: (1) dynamic estimation of healthy and pathological biomarker distributions, and (2) explicit modeling of the distribution of disease stages. We tested existing approaches and our novel approach on a benchmark of 9,000 synthetic datasets, inspired from real-world data. We found that our stage-aware EBM (SA-EBM) significantly outperforms prior methods, such as Gaussian Mixture Model (GMM) EBM, Kernel Density Estimation EBM and Discriminative EBM, on ordering and staging tasks.} }
Endnote
%0 Conference Paper %T Stage-Aware Event-Based Modeling (SA-EBM) for Disease Progression %A Hongtao Hao %A Vivek Prabhakaran %A Veena A Nair %A Nagesh Adluru %A Joseph Austerweil %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-hao25a %I PMLR %U https://proceedings.mlr.press/v298/hao25a.html %V 298 %X As diseases progress, the number of cognitive and biological biomarkers they impact increases. By formulating probabilistic models with this basic assumption, Event-Based Models (EBMs) enable researchers to discover the progression of a disease that makes earlier diagnosis and effective clinical interventions possible. We build on prior EBMs with two major improvements: (1) dynamic estimation of healthy and pathological biomarker distributions, and (2) explicit modeling of the distribution of disease stages. We tested existing approaches and our novel approach on a benchmark of 9,000 synthetic datasets, inspired from real-world data. We found that our stage-aware EBM (SA-EBM) significantly outperforms prior methods, such as Gaussian Mixture Model (GMM) EBM, Kernel Density Estimation EBM and Discriminative EBM, on ordering and staging tasks.
APA
Hao, H., Prabhakaran, V., Nair, V.A., Adluru, N. & Austerweil, J.. (2025). Stage-Aware Event-Based Modeling (SA-EBM) for Disease Progression. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/hao25a.html.

Related Material