Semi-Supervised Generative Models for Disease Trajectories: A Case Study on Systemic Sclerosis

Cécile Trottet, Manuel Schürch, Ahmed Allam, Imon Shoumitra Barua, Liubov Petelytska, Oliver Distler, Anna-Maria Hoffmann-Vold, Michael Krauthammer
Proceedings of the 9th Machine Learning for Healthcare Conference, PMLR 252, 2024.

Abstract

We propose a deep generative approach using latent temporal processes for modeling and holistically analyzing complex disease trajectories, with a particular focus on Systemic Sclerosis (SSc). We aim to learn temporal latent representations of the underlying generative process that explain the observed patient disease trajectories in an interpretable and comprehensive way. To enhance the interpretability of these latent temporal processes, we develop a semi-supervised approach for disentangling the latent space using established medical knowledge. By combining the generative approach with medical definitions of different characteristics of SSc, we facilitate the discovery of new aspects of the disease. We show that the learned temporal latent processes can be utilized for further data analysis and clinical hypothesis testing, including finding similar patients and clustering SSc patient trajectories into novel sub-types. Moreover, our method enables personalized online monitoring and prediction of multivariate time series with uncertainty quantification.

Cite this Paper

BibTeX
@InProceedings{pmlr-v252-trottet24a, title = {Semi-Supervised Generative Models for Disease Trajectories: A Case Study on Systemic Sclerosis}, author = {Trottet, C\'ecile and Sch\"urch, Manuel and Allam, Ahmed and Barua, Imon Shoumitra and Petelytska, Liubov and Distler, Oliver and Hoffmann-Vold, Anna-Maria and Krauthammer, Michael}, booktitle = {Proceedings of the 9th Machine Learning for Healthcare Conference}, year = {2024}, editor = {Deshpande, Kaivalya and Fiterau, Madalina and Joshi, Shalmali and Lipton, Zachary and Ranganath, Rajesh and Urteaga, Iñigo}, volume = {252}, series = {Proceedings of Machine Learning Research}, month = {16--17 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v252/main/assets/trottet24a/trottet24a.pdf}, url = {https://proceedings.mlr.press/v252/trottet24a.html}, abstract = {We propose a deep generative approach using latent temporal processes for modeling and holistically analyzing complex disease trajectories, with a particular focus on Systemic Sclerosis (SSc). We aim to learn temporal latent representations of the underlying generative process that explain the observed patient disease trajectories in an interpretable and comprehensive way. To enhance the interpretability of these latent temporal processes, we develop a semi-supervised approach for disentangling the latent space using established medical knowledge. By combining the generative approach with medical definitions of different characteristics of SSc, we facilitate the discovery of new aspects of the disease. We show that the learned temporal latent processes can be utilized for further data analysis and clinical hypothesis testing, including finding similar patients and clustering SSc patient trajectories into novel sub-types. Moreover, our method enables personalized online monitoring and prediction of multivariate time series with uncertainty quantification.} }
Endnote
%0 Conference Paper %T Semi-Supervised Generative Models for Disease Trajectories: A Case Study on Systemic Sclerosis %A Cécile Trottet %A Manuel Schürch %A Ahmed Allam %A Imon Shoumitra Barua %A Liubov Petelytska %A Oliver Distler %A Anna-Maria Hoffmann-Vold %A Michael Krauthammer %B Proceedings of the 9th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2024 %E Kaivalya Deshpande %E Madalina Fiterau %E Shalmali Joshi %E Zachary Lipton %E Rajesh Ranganath %E Iñigo Urteaga %F pmlr-v252-trottet24a %I PMLR %U https://proceedings.mlr.press/v252/trottet24a.html %V 252 %X We propose a deep generative approach using latent temporal processes for modeling and holistically analyzing complex disease trajectories, with a particular focus on Systemic Sclerosis (SSc). We aim to learn temporal latent representations of the underlying generative process that explain the observed patient disease trajectories in an interpretable and comprehensive way. To enhance the interpretability of these latent temporal processes, we develop a semi-supervised approach for disentangling the latent space using established medical knowledge. By combining the generative approach with medical definitions of different characteristics of SSc, we facilitate the discovery of new aspects of the disease. We show that the learned temporal latent processes can be utilized for further data analysis and clinical hypothesis testing, including finding similar patients and clustering SSc patient trajectories into novel sub-types. Moreover, our method enables personalized online monitoring and prediction of multivariate time series with uncertainty quantification.
APA
Trottet, C., Schürch, M., Allam, A., Barua, I.S., Petelytska, L., Distler, O., Hoffmann-Vold, A. & Krauthammer, M.. (2024). Semi-Supervised Generative Models for Disease Trajectories: A Case Study on Systemic Sclerosis. Proceedings of the 9th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 252 Available from https://proceedings.mlr.press/v252/trottet24a.html.

Related Material