Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes

Zhaozhi Qian, Ahmed Alaa, Alexis Bellot, Mihaela Schaar, Jem Rashbass
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108:3295-3305, 2020.

Abstract

Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic medical records, we only observe onsets of diseases, but not their triggering comorbidities — i.e., the mechanisms underlying temporal relations between diseases need to be inferred. Learning such temporal patterns from event data is crucial for understanding disease pathology and predicting prognoses. To this end, we develop deep diffusion processes (DDP) to model ’dynamic comorbidity networks’, i.e., the temporal relationships between comorbid disease onsets expressed through a dynamic graph. A DDP comprises events modelled as a multi-dimensional point process, with an intensity function parameterized by the edges of a dynamic weighted graph. The graph structure is modulated by a neural network that maps patient history to edge weights, enabling rich temporal representations for disease trajectories. The DDP parameters decouple into clinically meaningful components, which enables serving the dual purpose of accurate risk prediction and intelligible representation of disease pathology. We illustrate these features in experiments using cancer registry data.

Cite this Paper


BibTeX
@InProceedings{pmlr-v108-qian20a, title = {Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes}, author = {Qian, Zhaozhi and Alaa, Ahmed and Bellot, Alexis and van der Schaar, Mihaela and Rashbass, Jem}, booktitle = {Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics}, pages = {3295--3305}, year = {2020}, editor = {Silvia Chiappa and Roberto Calandra}, volume = {108}, series = {Proceedings of Machine Learning Research}, month = {26--28 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v108/qian20a/qian20a.pdf}, url = { http://proceedings.mlr.press/v108/qian20a.html }, abstract = {Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic medical records, we only observe onsets of diseases, but not their triggering comorbidities — i.e., the mechanisms underlying temporal relations between diseases need to be inferred. Learning such temporal patterns from event data is crucial for understanding disease pathology and predicting prognoses. To this end, we develop deep diffusion processes (DDP) to model ’dynamic comorbidity networks’, i.e., the temporal relationships between comorbid disease onsets expressed through a dynamic graph. A DDP comprises events modelled as a multi-dimensional point process, with an intensity function parameterized by the edges of a dynamic weighted graph. The graph structure is modulated by a neural network that maps patient history to edge weights, enabling rich temporal representations for disease trajectories. The DDP parameters decouple into clinically meaningful components, which enables serving the dual purpose of accurate risk prediction and intelligible representation of disease pathology. We illustrate these features in experiments using cancer registry data.} }
Endnote
%0 Conference Paper %T Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes %A Zhaozhi Qian %A Ahmed Alaa %A Alexis Bellot %A Mihaela Schaar %A Jem Rashbass %B Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2020 %E Silvia Chiappa %E Roberto Calandra %F pmlr-v108-qian20a %I PMLR %P 3295--3305 %U http://proceedings.mlr.press/v108/qian20a.html %V 108 %X Comorbid diseases co-occur and progress via complex temporal patterns that vary among individuals. In electronic medical records, we only observe onsets of diseases, but not their triggering comorbidities — i.e., the mechanisms underlying temporal relations between diseases need to be inferred. Learning such temporal patterns from event data is crucial for understanding disease pathology and predicting prognoses. To this end, we develop deep diffusion processes (DDP) to model ’dynamic comorbidity networks’, i.e., the temporal relationships between comorbid disease onsets expressed through a dynamic graph. A DDP comprises events modelled as a multi-dimensional point process, with an intensity function parameterized by the edges of a dynamic weighted graph. The graph structure is modulated by a neural network that maps patient history to edge weights, enabling rich temporal representations for disease trajectories. The DDP parameters decouple into clinically meaningful components, which enables serving the dual purpose of accurate risk prediction and intelligible representation of disease pathology. We illustrate these features in experiments using cancer registry data.
APA
Qian, Z., Alaa, A., Bellot, A., Schaar, M. & Rashbass, J.. (2020). Learning Dynamic and Personalized Comorbidity Networks from Event Data using Deep Diffusion Processes. Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 108:3295-3305 Available from http://proceedings.mlr.press/v108/qian20a.html .

Related Material