Predicting Disease Progression with a Model for Multivariate Longitudinal Clinical Data

Joseph Futoma, Mark Sendak, Blake Cameron, Katherine Heller
; Proceedings of the 1st Machine Learning for Healthcare Conference, PMLR 56:42-54, 2016.

Abstract

Accurate prediction of the future trajectory of a disease is an important challenge in personalized medicine and population health management. However, many complex chronic diseases exhibit large degrees of heterogeneity, and furthermore there is not always a single readily available biomarker to quantify disease severity. Even when such a clinical variable exists, there are often additional related biomarkers that may help improve prediction of future disease state. To this end, we propose a novel probabilistic generative model for multivariate longitudinal data that captures dependencies between multivariate trajectories of clinical variables. We use a Gaussian process based regression model for each individual trajectory, and build off ideas from latent class models to induce dependence between their mean functions. We develop a scalable variational inference algorithm that we use to fit our model to a large dataset of longitudinal electronic patient health records. Our model’s dynamic predictions have significantly lower errors compared to a recent state of the art method for modeling disease trajectories, and they are being incorporated into a population health rounding tool to be used by clinicians at our local accountable care organization.

Cite this Paper


BibTeX
@InProceedings{pmlr-v56-Futoma16, title = {Predicting Disease Progression with a Model for Multivariate Longitudinal Clinical Data}, author = {Joseph Futoma and Mark Sendak and Blake Cameron and Katherine Heller}, booktitle = {Proceedings of the 1st Machine Learning for Healthcare Conference}, pages = {42--54}, year = {2016}, editor = {Finale Doshi-Velez and Jim Fackler and David Kale and Byron Wallace and Jenna Wiens}, volume = {56}, series = {Proceedings of Machine Learning Research}, address = {Northeastern University, Boston, MA, USA}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v56/Futoma16.pdf}, url = {http://proceedings.mlr.press/v56/Futoma16.html}, abstract = {Accurate prediction of the future trajectory of a disease is an important challenge in personalized medicine and population health management. However, many complex chronic diseases exhibit large degrees of heterogeneity, and furthermore there is not always a single readily available biomarker to quantify disease severity. Even when such a clinical variable exists, there are often additional related biomarkers that may help improve prediction of future disease state. To this end, we propose a novel probabilistic generative model for multivariate longitudinal data that captures dependencies between multivariate trajectories of clinical variables. We use a Gaussian process based regression model for each individual trajectory, and build off ideas from latent class models to induce dependence between their mean functions. We develop a scalable variational inference algorithm that we use to fit our model to a large dataset of longitudinal electronic patient health records. Our model’s dynamic predictions have significantly lower errors compared to a recent state of the art method for modeling disease trajectories, and they are being incorporated into a population health rounding tool to be used by clinicians at our local accountable care organization.} }
Endnote
%0 Conference Paper %T Predicting Disease Progression with a Model for Multivariate Longitudinal Clinical Data %A Joseph Futoma %A Mark Sendak %A Blake Cameron %A Katherine Heller %B Proceedings of the 1st Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2016 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Byron Wallace %E Jenna Wiens %F pmlr-v56-Futoma16 %I PMLR %J Proceedings of Machine Learning Research %P 42--54 %U http://proceedings.mlr.press %V 56 %W PMLR %X Accurate prediction of the future trajectory of a disease is an important challenge in personalized medicine and population health management. However, many complex chronic diseases exhibit large degrees of heterogeneity, and furthermore there is not always a single readily available biomarker to quantify disease severity. Even when such a clinical variable exists, there are often additional related biomarkers that may help improve prediction of future disease state. To this end, we propose a novel probabilistic generative model for multivariate longitudinal data that captures dependencies between multivariate trajectories of clinical variables. We use a Gaussian process based regression model for each individual trajectory, and build off ideas from latent class models to induce dependence between their mean functions. We develop a scalable variational inference algorithm that we use to fit our model to a large dataset of longitudinal electronic patient health records. Our model’s dynamic predictions have significantly lower errors compared to a recent state of the art method for modeling disease trajectories, and they are being incorporated into a population health rounding tool to be used by clinicians at our local accountable care organization.
RIS
TY - CPAPER TI - Predicting Disease Progression with a Model for Multivariate Longitudinal Clinical Data AU - Joseph Futoma AU - Mark Sendak AU - Blake Cameron AU - Katherine Heller BT - Proceedings of the 1st Machine Learning for Healthcare Conference PY - 2016/12/10 DA - 2016/12/10 ED - Finale Doshi-Velez ED - Jim Fackler ED - David Kale ED - Byron Wallace ED - Jenna Wiens ID - pmlr-v56-Futoma16 PB - PMLR SP - 42 DP - PMLR EP - 54 L1 - http://proceedings.mlr.press/v56/Futoma16.pdf UR - http://proceedings.mlr.press/v56/Futoma16.html AB - Accurate prediction of the future trajectory of a disease is an important challenge in personalized medicine and population health management. However, many complex chronic diseases exhibit large degrees of heterogeneity, and furthermore there is not always a single readily available biomarker to quantify disease severity. Even when such a clinical variable exists, there are often additional related biomarkers that may help improve prediction of future disease state. To this end, we propose a novel probabilistic generative model for multivariate longitudinal data that captures dependencies between multivariate trajectories of clinical variables. We use a Gaussian process based regression model for each individual trajectory, and build off ideas from latent class models to induce dependence between their mean functions. We develop a scalable variational inference algorithm that we use to fit our model to a large dataset of longitudinal electronic patient health records. Our model’s dynamic predictions have significantly lower errors compared to a recent state of the art method for modeling disease trajectories, and they are being incorporated into a population health rounding tool to be used by clinicians at our local accountable care organization. ER -
APA
Futoma, J., Sendak, M., Cameron, B. & Heller, K.. (2016). Predicting Disease Progression with a Model for Multivariate Longitudinal Clinical Data. Proceedings of the 1st Machine Learning for Healthcare Conference, in PMLR 56:42-54

Related Material