Phenotyping with Prior Knowledge using Patient Similarity

Asif Rahman, Yale Chang, Bryan Conroy, Minnan Xu-Wilson
Proceedings of the 5th Machine Learning for Healthcare Conference, PMLR 126:331-351, 2020.

Abstract

Prior medical knowledge, like the relationships between diseases or treatments and their corresponding risk factors are widely available in electronic health records (EHR), can be generated by domain experts, and extracted from knowledge graphs. Although informative for predictive modeling tasks, most of the patient-specific knowledge in EHR are not utilized because of practical constraints on data availability or cost of acquiring the data to make inferences. We present a method to learn from prior knowledge using a mixture of experts model where gating probabilities are tuned by an adjacency matrix created using side information available during training, like comorbidities, interventions, outcomes, vital signs and laboratory measurements. The adjacency matrix of a nearest neighbor graph is used to discover subgroups of intensive care unit (ICU) patients. Experts are shown to specialize based on how patients are grouped in the adjacency matrix on two real-world decision support tasks: predicting hemodynamic interventions and stratifying patients at risk for developing a sustained period of hypoxemia. The proposed prior knowledge-guided learning (PKL) model discovers clinically meaningful cohorts in patients with respiratory compromise that match well known sub-phenotypes described in the literature.

Cite this Paper

BibTeX
@InProceedings{pmlr-v126-rahman20a, title = {Phenotyping with Prior Knowledge using Patient Similarity}, author = {Rahman, Asif and Chang, Yale and Conroy, Bryan and Xu-Wilson, Minnan}, booktitle = {Proceedings of the 5th Machine Learning for Healthcare Conference}, pages = {331--351}, year = {2020}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {126}, series = {Proceedings of Machine Learning Research}, month = {07--08 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v126/rahman20a/rahman20a.pdf}, url = {https://proceedings.mlr.press/v126/rahman20a.html}, abstract = {Prior medical knowledge, like the relationships between diseases or treatments and their corresponding risk factors are widely available in electronic health records (EHR), can be generated by domain experts, and extracted from knowledge graphs. Although informative for predictive modeling tasks, most of the patient-specific knowledge in EHR are not utilized because of practical constraints on data availability or cost of acquiring the data to make inferences. We present a method to learn from prior knowledge using a mixture of experts model where gating probabilities are tuned by an adjacency matrix created using side information available during training, like comorbidities, interventions, outcomes, vital signs and laboratory measurements. The adjacency matrix of a nearest neighbor graph is used to discover subgroups of intensive care unit (ICU) patients. Experts are shown to specialize based on how patients are grouped in the adjacency matrix on two real-world decision support tasks: predicting hemodynamic interventions and stratifying patients at risk for developing a sustained period of hypoxemia. The proposed prior knowledge-guided learning (PKL) model discovers clinically meaningful cohorts in patients with respiratory compromise that match well known sub-phenotypes described in the literature.} }
Endnote
%0 Conference Paper %T Phenotyping with Prior Knowledge using Patient Similarity %A Asif Rahman %A Yale Chang %A Bryan Conroy %A Minnan Xu-Wilson %B Proceedings of the 5th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2020 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v126-rahman20a %I PMLR %P 331--351 %U https://proceedings.mlr.press/v126/rahman20a.html %V 126 %X Prior medical knowledge, like the relationships between diseases or treatments and their corresponding risk factors are widely available in electronic health records (EHR), can be generated by domain experts, and extracted from knowledge graphs. Although informative for predictive modeling tasks, most of the patient-specific knowledge in EHR are not utilized because of practical constraints on data availability or cost of acquiring the data to make inferences. We present a method to learn from prior knowledge using a mixture of experts model where gating probabilities are tuned by an adjacency matrix created using side information available during training, like comorbidities, interventions, outcomes, vital signs and laboratory measurements. The adjacency matrix of a nearest neighbor graph is used to discover subgroups of intensive care unit (ICU) patients. Experts are shown to specialize based on how patients are grouped in the adjacency matrix on two real-world decision support tasks: predicting hemodynamic interventions and stratifying patients at risk for developing a sustained period of hypoxemia. The proposed prior knowledge-guided learning (PKL) model discovers clinically meaningful cohorts in patients with respiratory compromise that match well known sub-phenotypes described in the literature.
APA
Rahman, A., Chang, Y., Conroy, B. & Xu-Wilson, M.. (2020). Phenotyping with Prior Knowledge using Patient Similarity. Proceedings of the 5th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 126:331-351 Available from https://proceedings.mlr.press/v126/rahman20a.html.

Related Material