Predictive Hierarchical Clustering: Learning clusters of CPT codes for improving surgical outcomes

Elizabeth C. Lorenzi, Stephanie L. Brown, Zhifei Sun, Katherine Heller
Proceedings of the 2nd Machine Learning for Healthcare Conference, PMLR 68:231-242, 2017.

Abstract

We develop a novel algorithm, Predictive Hierarchical Clustering (PHC), for agglomerative hierarchical clustering of current procedural terminology (CPT) codes. Our predictive hierarchical clustering aims to cluster subgroups, not individual observations, found within our data, such that the clusters discovered result in optimal performance of a classification model. Therefore, merges are chosen based on a Bayesian hypothesis test, which chooses pairings of the subgroups that result in the best model fit, as measured by held out predictive likelihoods. We place a Dirichlet prior on the probability of merging clusters, allowing us to adjust the size and sparsity of clusters. The motivation is to predict patient-specific surgical outcomes using data from ACS NSQIP (American College of Surgeon’s National Surgical Quality Improvement Program). An important predictor of surgical outcomes is the actual surgical procedure performed as described by a CPT code. We use PHC to cluster CPT codes, represented as subgroups, together in a way that enables us to better predict patient-specific outcomes compared to currently used clusters based on clinical judgment.

Cite this Paper

BibTeX
@InProceedings{pmlr-v68-lorenzi17a, title = {Predictive Hierarchical Clustering: Learning clusters of CPT codes for improving surgical outcomes}, author = {Lorenzi, Elizabeth C. and Brown, Stephanie L. and Sun, Zhifei and Heller, Katherine}, booktitle = {Proceedings of the 2nd Machine Learning for Healthcare Conference}, pages = {231--242}, year = {2017}, editor = {Doshi-Velez, Finale and Fackler, Jim and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {68}, series = {Proceedings of Machine Learning Research}, month = {18--19 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v68/lorenzi17a/lorenzi17a.pdf}, url = {https://proceedings.mlr.press/v68/lorenzi17a.html}, abstract = {We develop a novel algorithm, Predictive Hierarchical Clustering (PHC), for agglomerative hierarchical clustering of current procedural terminology (CPT) codes. Our predictive hierarchical clustering aims to cluster subgroups, not individual observations, found within our data, such that the clusters discovered result in optimal performance of a classification model. Therefore, merges are chosen based on a Bayesian hypothesis test, which chooses pairings of the subgroups that result in the best model fit, as measured by held out predictive likelihoods. We place a Dirichlet prior on the probability of merging clusters, allowing us to adjust the size and sparsity of clusters. The motivation is to predict patient-specific surgical outcomes using data from ACS NSQIP (American College of Surgeon’s National Surgical Quality Improvement Program). An important predictor of surgical outcomes is the actual surgical procedure performed as described by a CPT code. We use PHC to cluster CPT codes, represented as subgroups, together in a way that enables us to better predict patient-specific outcomes compared to currently used clusters based on clinical judgment.} }
Endnote
%0 Conference Paper %T Predictive Hierarchical Clustering: Learning clusters of CPT codes for improving surgical outcomes %A Elizabeth C. Lorenzi %A Stephanie L. Brown %A Zhifei Sun %A Katherine Heller %B Proceedings of the 2nd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2017 %E Finale Doshi-Velez %E Jim Fackler %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v68-lorenzi17a %I PMLR %P 231--242 %U https://proceedings.mlr.press/v68/lorenzi17a.html %V 68 %X We develop a novel algorithm, Predictive Hierarchical Clustering (PHC), for agglomerative hierarchical clustering of current procedural terminology (CPT) codes. Our predictive hierarchical clustering aims to cluster subgroups, not individual observations, found within our data, such that the clusters discovered result in optimal performance of a classification model. Therefore, merges are chosen based on a Bayesian hypothesis test, which chooses pairings of the subgroups that result in the best model fit, as measured by held out predictive likelihoods. We place a Dirichlet prior on the probability of merging clusters, allowing us to adjust the size and sparsity of clusters. The motivation is to predict patient-specific surgical outcomes using data from ACS NSQIP (American College of Surgeon’s National Surgical Quality Improvement Program). An important predictor of surgical outcomes is the actual surgical procedure performed as described by a CPT code. We use PHC to cluster CPT codes, represented as subgroups, together in a way that enables us to better predict patient-specific outcomes compared to currently used clusters based on clinical judgment.
APA
Lorenzi, E.C., Brown, S.L., Sun, Z. & Heller, K.. (2017). Predictive Hierarchical Clustering: Learning clusters of CPT codes for improving surgical outcomes. Proceedings of the 2nd Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 68:231-242 Available from https://proceedings.mlr.press/v68/lorenzi17a.html.

Related Material