Using gradient boosting with stability selection on health insurance claims data to identify disease trajectories in chronic obstructive pulmonary disease

Abstract

Objective

We propose a data-driven method to detect temporal patterns of disease progression in high-dimensional claims data based on gradient boosting with stability selection.

Materials and methods

We identified patients with chronic obstructive pulmonary disease in a German health insurance claims database with 6.5 million individuals and divided them into a group of patients with the highest disease severity and a group of control patients with lower severity. We then used gradient boosting with stability selection to determine variables correlating with a chronic obstructive pulmonary disease diagnosis of highest severity and subsequently model the temporal progression of the disease using the selected variables.

Results

We identified a network of 20 diagnoses (e.g. respiratory failure), medications (e.g. anticholinergic drugs) and procedures associated with a subsequent chronic obstructive pulmonary disease diagnosis of highest severity. Furthermore, the network successfully captured temporal patterns, such as disease progressions from lower to higher severity grades.

Discussion

The temporal trajectories identified by our data-driven approach are compatible with existing knowledge about chronic obstructive pulmonary disease showing that the method can reliably select relevant variables in a high-dimensional context.

Conclusion

We provide a generalizable approach for the automatic detection of disease trajectories in claims data. This could help to diagnose diseases early, identify unknown risk factors and optimize treatment plans.

Keywords

Gradient boosting stability selection claims data disease trajectory chronic obstructive pulmonary disease

Get full access to this article

View all access options for this article.

References

World Health Organization (WHO). New WHO report: deaths from noncommunicable diseases on the rise, with developing world hit hardest, www.who.int/mediacentre/news/releases/2011/ncds_20110427/en/ (2011, accessed 15 June 2020).

Bates

Saria

Ohno-Machado

, et al. Big data in health care: using analytics to identify and manage high-risk and high-cost patients. Health Aff (Millwood) 2014; 33: 1123–1131.

Roy

Stewart

WF.

Prediction modeling using EHR data: challenges, strategies, and a comparison of machine learning approaches.

Med Care 2010; 48: S106.

Jay

Nuemi

Gadreau

, et al. A data mining approach for grouping and analyzing trajectories of care using claim data: the example of breast cancer. BMC Med Inform Decis Mak 2013; 13: 130.

Petri

Maldonato

Robinson

NJ.

Data-driven identification of co-morbidities associated with rheumatoid arthritis in a large US health plan claims database.

BMC Musculoskelet Disord 2010; 11: 247.

Murray

Kendall

Boyd

, et al. Illness trajectories and palliative care. BMJ 2005; 330: 1007–1011.

Chen

Blumm

Christakis

, et al. Cancer metastasis networks and the prediction of progression patterns. Br J Cancer 2009; 101: 749–758.

Hidalgo

Blumm

Barabási

A-L

, et al. A dynamic network approach for the study of human phenotypes. PLOS Comput Biol 2009; 5: e1000353.

Jensen

Moseley

Oprea

, et al. Temporal disease trajectories condensed from population-wide registry data covering 6.2 million patients. Nat Commun 2014; 5: 4022.

10.

Hofner

Boccuto

Göker

Controlling false discoveries in high-dimensional situations: boosting with stability selection.

BMC Bioinform 2015; 16: 144.

11.

Meinshausen

Bühlmann

Stability selection. J R Stat Soc Ser B Stat Methodol 2010; 72: 417–473.

12.

Wang

Sontag

Wang

Unsupervised learning of disease progression models. In: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining, ACM, 2014, pp. 85–94.

13.

Global Initiative for Chronic Obstructive Lung Disease (GOLD). Pocket guide to COPD diagnosis, management and prevention, http://goldcopd.org/pocket-guide-copd-diagnosis-management-prevention-2016/ (2017, accessed 15 June 2020).

14.

Andersohn

Walker

Characteristics and external validity of the German Health Risk Institute (HRI) Database.

Pharmacoepidemiol Drug Saf 2016; 25: 106–109.

15.

Grimes

Schulz

KF.

Cohort studies: marching towards outcomes. Lancet Lond Engl 2002; 359: 341–345.

16.

Sekhon

JS.

Multivariate and propensity score matching software with automated balance optimization: the matching package for R.

J Stat Softw 2011; 42: 1–52.

17.

Poole

Chacko

Wood-Baker

RWB

, et al. Influenza vaccine for patients with chronic obstructive pulmonary disease. Cochrane Database Syst Rev 2006; CD002733.

18.

Hofner

Mayr

Robinzonov

, et al. Model-based boosting in R: a hands-on tutorial using the R package mboost. Comput Stat 2014; 29: 3–35.

19.

Hothorn

Buehlmann

Kneib

, et al. Model-based Boosting 2.0. J Mach Learn Res 2010; 11: 2109–2113.

20.

Bühlmann

Boosting with the L₂ Loss: regression and classification. J Am Stat Assoc 2003; 98: 324–339.

21.

Hofner

Hothorn

stabs: Stability Selection with Error Control, https://CRAN.R-project.org/package=stabs (accessed 15 June 2020).

22.

Bühlmann

Hothorn

Boosting algorithms: regularization, prediction and model fitting. Stat Sci 2007; 22: 477–505.

23.

Mayr

Hofner

Schmid

The importance of knowing when to stop. Methods Inf Med 2012; 51: 178–186.

24.

Microsoft RCT. Microsoft R Open. Redmond, WA: Microsoft, https://mran.microsoft.com/ (2017, accessed 15 June 2020).

25.

Dowle

Srinivasan

data.table: Extension of ‘data.frame’, https://CRAN.R-project.org/package=data.table (2018, accessed 15 June 2020).

26.

Hofner

Hothorn

stabs: Stability Selection with Error Control, https://CRAN.R-project.org/package=stabs (2017, accessed 15 June 2020).

27.

Grolemund

Wickham

Dates and times made easy with lubridate. J Stat Softw 2011; 40: 1–25.

28.

Wickham

stringr: Simple, Consistent Wrappers for Common String Operations, https://CRAN.R-project.org/package=stringr (2018, accessed 15 June 2020).

29.

Zeileis

Grothendieck

zoo: S3 infrastructure for regular and irregular time series. J Stat Softw 2005; 14: 1–27.

30.

Bates

Maechler

Matrix: Sparse and Dense Matrix Classes and Methods, https://CRAN.R-project.org/package=Matrix (2018, accessed 15 June 2020).

31.

Hothorn

Buehlmann

Kneib

, et al. mboost: Model-Based Boosting, https://CRAN.R-project.org/package=mboost (2018, accessed 15 June 2020).

32.

Allaire

Gandrud

Russell

, et al. networkD3: D3 JavaScript Network Graphs from R, https://CRAN.R-project.org/package=networkD3 (2017, accessed 15 June 2020).

33.

van Eerd

EAM

van der Meer

van Schayck

OCP

, et al. Smoking cessation for people with chronic obstructive pulmonary disease. Cochrane Database Syst Rev 2016; 8: CD010744.

34.

Naeije

Pulmonary hypertension and right heart failure in chronic obstructive pulmonary disease.

Proc Am Thorac Soc 2005; 2: 20–22.

35.

Wongsurakiat

Maranetra

Wasi

, et al. Acute respiratory illness in patients with COPD and the effectiveness of influenza vaccination: a randomized controlled study. Chest 2004; 125: 2011–2020.

36.

Lachkar

Bouassida

Drug-induced acute angle closure glaucoma. Curr Opin Ophthalmol 2007; 18: 129.

Supplementary Material

Please find the following supplemental material available below.

For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.

For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.

0.00 MB

0.14 MB

0.38 MB

0.09 MB