Literature DB >> 30543022

Applying Machine Learning Algorithms to Segment High-Cost Patient Populations.

Jiali Yan1, Kristin A Linn2, Brian W Powers3,4,5,6, Jingsan Zhu7, Sachin H Jain5, Jennifer L Kowalski8, Amol S Navathe9,10.   

Abstract

BACKGROUND: Efforts to improve the value of care for high-cost patients may benefit from care management strategies targeted at clinically distinct subgroups of patients.
OBJECTIVE: To evaluate the performance of three different machine learning algorithms for identifying subgroups of high-cost patients.
DESIGN: We applied three different clustering algorithms-connectivity-based clustering using agglomerative hierarchical clustering, centroid-based clustering with the k-medoids algorithm, and density-based clustering with the OPTICS algorithm-to a clinical and administrative dataset. We then examined the extent to which each algorithm identified subgroups of patients that were (1) clinically distinct and (2) associated with meaningful differences in relevant utilization metrics. PARTICIPANTS: Patients enrolled in a national Medicare Advantage plan, categorized in the top decile of spending (n = 6154). MAIN MEASURES: Post hoc discriminative models comparing the importance of variables for distinguishing observations in one cluster from the rest. Variance in utilization and spending measures. KEY
RESULTS: Connectivity-based, centroid-based, and density-based clustering identified eight, five, and ten subgroups of high-cost patients, respectively. Post hoc discriminative models indicated that density-based clustering subgroups were the most clinically distinct. The variance of utilization and spending measures was the greatest among the subgroups identified through density-based clustering.
CONCLUSIONS: Machine learning algorithms can be used to segment a high-cost patient population into subgroups of patients that are clinically distinct and associated with meaningful differences in utilization and spending measures. For these purposes, density-based clustering with the OPTICS algorithm outperformed connectivity-based and centroid-based clustering algorithms.

Entities:  

Keywords:  high-cost patients; machine learning; patient segmentation

Mesh:

Year:  2018        PMID: 30543022      PMCID: PMC6374273          DOI: 10.1007/s11606-018-4760-8

Source DB:  PubMed          Journal:  J Gen Intern Med        ISSN: 0884-8734            Impact factor:   5.128


  21 in total

1.  Subgroups of High-Cost Medicare Advantage Patients: an Observational Study.

Authors:  Brian W Powers; Jiali Yan; Jingsan Zhu; Kristin A Linn; Sachin H Jain; Jennifer L Kowalski; Amol S Navathe
Journal:  J Gen Intern Med       Date:  2018-12-03       Impact factor: 5.128

2.  Use of cluster analysis to define COPD phenotypes.

Authors:  M Weatherall; P Shirtcliffe; J Travers; R Beasley
Journal:  Eur Respir J       Date:  2010-09       Impact factor: 16.671

3.  Identifying subgroups of complex patients with cluster analysis.

Authors:  Sophia R Newcomer; John F Steiner; Elizabeth A Bayliss
Journal:  Am J Manag Care       Date:  2011-08-01       Impact factor: 2.229

4.  Tailoring Complex Care Management for High-Need, High-Cost Patients.

Authors:  David Blumenthal; Melinda K Abrams
Journal:  JAMA       Date:  2016-10-25       Impact factor: 56.272

5.  Patterns of care for clinically distinct segments of high cost Medicare beneficiaries.

Authors:  Jeffrey D Clough; Gerald F Riley; Melissa Cohen; Sheila M Hanley; Darshak Sanghavi; Darren A DeWalt; Rahul Rajkumar; Patrick H Conway
Journal:  Healthc (Amst)       Date:  2015-10-01

Review 6.  Approach for Achieving Effective Care for High-Need Patients.

Authors:  Jose F Figueroa; Ashish K Jha
Journal:  JAMA Intern Med       Date:  2018-06-01       Impact factor: 21.873

7.  Data-driven identification of prognostic tumor subpopulations using spatially mapped t-SNE of mass spectrometry imaging data.

Authors:  Walid M Abdelmoula; Benjamin Balluff; Sonja Englert; Jouke Dijkstra; Marcel J T Reinders; Axel Walch; Liam A McDonnell; Boudewijn P F Lelieveldt
Journal:  Proc Natl Acad Sci U S A       Date:  2016-10-10       Impact factor: 11.205

8.  Using population segmentation to provide better health care for all: the "Bridges to Health" model.

Authors:  Joanne Lynn; Barry M Straube; Karen M Bell; Stephen F Jencks; Robert T Kambic
Journal:  Milbank Q       Date:  2007-06       Impact factor: 4.911

9.  Using cluster analysis to identify phenotypes and validation of mortality in men with COPD.

Authors:  Chiung-Zuei Chen; Liang-Yi Wang; Chih-Ying Ou; Cheng-Hung Lee; Chien-Chung Lin; Tzuen-Ren Hsiue
Journal:  Lung       Date:  2014-10-07       Impact factor: 2.584

10.  Cluster analysis for identifying sub-groups and selecting potential discriminatory variables in human encephalitis.

Authors:  Jemila S Hamid; Christopher Meaney; Natasha S Crowcroft; Julia Granerod; Joseph Beyene
Journal:  BMC Infect Dis       Date:  2010-12-31       Impact factor: 3.090

View more
  7 in total

1.  Subgroups of High-Cost Medicare Advantage Patients: an Observational Study.

Authors:  Brian W Powers; Jiali Yan; Jingsan Zhu; Kristin A Linn; Sachin H Jain; Jennifer L Kowalski; Amol S Navathe
Journal:  J Gen Intern Med       Date:  2018-12-03       Impact factor: 5.128

2.  Temporal Patterns of High-Spend Subgroups Can Inform Service Strategy for Medicare Advantage Enrollees.

Authors:  Samuel J Amodeo; Henrik F Kowalkowski; Halley L Brantley; Nicholas W Jones; Lauren R Bangerter; David J Cook
Journal:  J Gen Intern Med       Date:  2021-06-07       Impact factor: 6.473

3.  Simulation-derived best practices for clustering clinical data.

Authors:  Caitlin E Coombes; Xin Liu; Zachary B Abrams; Kevin R Coombes; Guy Brock
Journal:  J Biomed Inform       Date:  2021-04-20       Impact factor: 8.000

4.  A machine learning approach to identify distinct subgroups of veterans at risk for hospitalization or death using administrative and electronic health record data.

Authors:  Ravi B Parikh; Kristin A Linn; Jiali Yan; Matthew L Maciejewski; Ann-Marie Rosland; Kevin G Volpp; Peter W Groeneveld; Amol S Navathe
Journal:  PLoS One       Date:  2021-02-19       Impact factor: 3.240

5.  Unsupervised machine learning and prognostic factors of survival in chronic lymphocytic leukemia.

Authors:  Caitlin E Coombes; Zachary B Abrams; Suli Li; Lynne V Abruzzo; Kevin R Coombes
Journal:  J Am Med Inform Assoc       Date:  2020-07-01       Impact factor: 4.497

6.  Use of Data-Driven Methods to Predict Long-term Patterns of Health Care Spending for Medicare Patients.

Authors:  Julie C Lauffenburger; Mufaddal Mahesri; Niteesh K Choudhry
Journal:  JAMA Netw Open       Date:  2020-10-01

7.  Not there yet: using data-driven methods to predict who becomes costly among low-cost patients with type 2 diabetes.

Authors:  Julie C Lauffenburger; Mufaddal Mahesri; Niteesh K Choudhry
Journal:  BMC Endocr Disord       Date:  2020-08-17       Impact factor: 2.763

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.