Download PDF
Methods Inf Med 2017; 56(05): 391-400
DOI: 10.3414/ME16-01-0135
Paper
Schattauer GmbH

Mining Major Transitions of Chronic Conditions in Patients with Multiple Chronic Conditions[*]

Adel Alaeddini
1   Department of Mechanical Engineering, University of Texas at San Antonio, San Antonio, TX, USA
,
Carlos A. Jaramillo
2   South Texas Veterans Healthcare System, San Antonio, TX, USA
,
Syed H. A. Faruqui
1   Department of Mechanical Engineering, University of Texas at San Antonio, San Antonio, TX, USA
,
Mary J. Pugh
2   South Texas Veterans Healthcare System, San Antonio, TX, USA
› Author Affiliations Funding Supported by National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health under award number 1SC2GM118266-01, and VA Health Services Research and Development under award number VA HSR&D; DHI-09-237-2.
Further Information

Publication History

received: 22 November 2016

accepted in revised form: 15 August 2017

Publication Date:
24 January 2018 (online)

    Permissions and Reprints

Summary

Objectives: Evolution of multiple chronic conditions (MCC) follows a complex stochastic process, influenced by several factors including the inter-relationship of existing conditions, and patient-level risk factors. Nearly 20% of citizens aged 18 years and older are burdened with two or more (multiple) chronic conditions (MCC). Treatment for people living with MCC currently accounts for an estimated 66% of the Nation’s healthcare costs. However, it is still not known precisely how MCC emerge and accumulate among individuals or in the general population. This study investigates major patterns of MCC transitions in a diverse population of patients and identifies the risk factors affecting the transition process.

Methods: A Latent regression Markov clustering (LRMCL) algorithm is proposed to identify major transitions of four MCC that include hypertension (HTN), depression, Post- Traumatic Stress Disorder (PTSD), and back pain. A cohort of 601,805 individuals randomly selected from the population of Iraq and Afghanistan war Veterans (IAVs) who received VA care during three or more years between 2002-2015, is used for training the proposed LRMCL algorithm.

Results: Two major clusters of MCC transition patterns with 78% and 22% probability of membership respectively were identified. The primary cluster demonstrated the possibility of improvement when the number of MCC is small and an increase in probability of MCC accumulation as the number of co- morbidities increased. The second cluster showed stability (no change) of MCC overtime as the major pattern. Age was the most significant risk factor associated with the most probable cluster for each IAV.

Conclusions: These findings suggest that our proposed LRMCL algorithm can be used to describe and understand MCC transitions, which may ultimately allow healthcare systems to support optimal clinical decision- making. This method will be used to describe a broader range of MCC transitions in this and non-VA populations, and will add treatment information to see if models including treatments and MCC emergence can be used to support clinical decision-making in patient care.

Keywords

Multiple chronic conditions - Markov clustering - latent regression model - Markov mixture model

* Supplementary material published on our website https://doi.org/10.3414/ME16-01-0135


 

  • References

  • 1 Elsayed EA. Reliability engineering. 2nd ed. Hoboken, NJ: John Wiley & Sons; 2012
    Google Scholar
  • 2 WHO. Diet, nutrition, and the prevention of chronic diseases: report of a WHO Study Group: World Health Organization; 1990.
    PubMed
  • 3 Schaefer AJ, Bailey MD, Shechter SM, Roberts MS. Modeling medical treatment using Markov decision processes. Handbook of Operations Research/Management Science Applications in Health Care.. Boston, MA: Kluwer Academic Publishers; 2004: 593-612.
    Google Scholar
  • 4 Hauskrecht M, Fraser H. Planning treatment of ischemic heart disease with partially observable Markov decision processes. Artificial Intelligence in Medicine 2000; 18 (03) 221-244.
    CrossrefPubMedGoogle Scholar
  • 5 Alagoz O, Maillart LM, Schaefer AJ, Roberts MS. Choosing among living-donor and cadaveric livers. Management Science 2007; 53 (11) 1702-1715.
    CrossrefPubMedGoogle Scholar
  • 6 Shechter SM, Bailey MD, Schaefer AJ, Roberts MS. The optimal time to initiate HIV therapy under ordered health states. Operations Research 2008; 56 (01) 20-33.
    CrossrefPubMedGoogle Scholar
  • 7 Faissol DM, Griffin PM, Swann JL. Timing of testing and treatment of hepatitis C and other diseases. INFORMS International Meeting. 2007
    PubMedGoogle Scholar
  • 8 Maillart LM, Ivy JS, Ransom S, Diehl K. Assessing dynamic breast cancer screening policies. Operations Research 2008; 56 (06) 1411-1427.
    CrossrefPubMedGoogle Scholar
  • 9 Denton BT, Kurt M, Shah ND, Bryant SC, Smith SA. Optimizing the start time of statin therapy for patients with diabetes. Medical Decision Making 2009; 29 (03) 351-567.
    CrossrefPubMedGoogle Scholar
  • 10 Kurt M, Denton B, Schaefer AJ, Shah N, Smith S. At what lipid ratios should a patient with type 2 diabetes initiate statins. Available from: http://www.ie.pitt.edu/~schaefer/Papers/StatinInitiation.pdf.
    PubMedGoogle Scholar
  • 11 Kreke JE, Bailey MD, Schaefer AJ, Angus DC, Roberts MS. Modeling hospital discharge policies for patients with pneumonia-related sepsis. IIE Transactions 2008; 40 (09) 853-860.
    CrossrefPubMedGoogle Scholar
  • 12 Kreke JE. Modeling disease management decisions for patients with pneumonia-related sepsis [dissertation].. Pittsburgh, PA: University of Pittsburgh; 2007
  • 13 Hu C, Lovejoy WS, Shafer SL. Comparison of some suboptimal control policies in medical drug therapy. Operations Research 1996; 44 (05) 696-709.
    CrossrefPubMedGoogle Scholar
  • 14 Alterovitz R, Branicky M, Goldberg K. Constant- curvature motion planning under uncertainty with applications in image-guided medical needle steering. Akella S, Amato NM, Huang WH, Mishra B. Algorithmic Foundation of Robotics VII. Springer Tracts in Advanced Robotics vol 47.. Berlin, Heidelberg: Springer; 2008: 319-334.
    Google Scholar
  • 15 Zhao Y, Zeng D, Socinski MA, Kosorok MR. Reinforcement learning strategies for clinical trials in nonsmall cell lung cancer. Biometrics 2011; 67 (04) 1422-1433.
    CrossrefPubMedGoogle Scholar
  • 16 Waltz JA, Frank MJ, Robinson BM, Gold JM. Selective reinforcement learning deficits in schizophrenia support predictions from computational models of striatal-cortical dysfunction. Biological Psychiatry 2007; 62 (07) 756-764.
    CrossrefPubMedGoogle Scholar
  • 17 Lighthall NR, Gorlick MA, Schoeke A, Frank MJ, Mather M. Stress modulates reinforcement learning in younger and older adults. Psychology and Aging 2013; 28 (01) 35.
    CrossrefPubMedGoogle Scholar
  • 18 Laber EB, Linn K, Stefanski L. Interactive Q-learning. J Stat Softw 2015; 64 (01) i01.
    PubMedGoogle Scholar
  • 19 Kharoufeh JP, Cox SM. Stochastic models for degradation-based reliability. IIE Transactions 2005; 37 (06) 533-542.
    CrossrefPubMedGoogle Scholar
  • 20 Centers for Medicare and Medicaid Services. Chronic Conditions among Medicare Beneficiaries. Chartbook, 2012 Edition.. Baltimore, MD: 2012. Available from: https://www.cms.gov/Research-Statistics-Data-and-Systems/Statistics-Trends-and-Reports/Chronic-Conditions/Downloads/2012Chartbook.pdf.
    Google Scholar
  • 21 Prados-Torres A, Calderón-Larrañaga A, Hancco-Saavedra J, Poblador-Plou B, van den Akker M. Multimorbidity patterns: a systematic review. Journal of Clinical Epidemiology 2014; 67 (03) 254-266.
    CrossrefPubMedGoogle Scholar
  • 22 Vogeli C, Shields AE, Lee TA, Gibson TB, Marder WD, Weiss KB. et al. Multiple chronic conditions: prevalence, health consequences, and implications for quality, care management, and costs. Journal of General Internal Medicine 2007; 22 (03) 391-395.
    CrossrefPubMedGoogle Scholar
  • 23 Lehnert T, Heider D, Leicht H, Heinrich S, Corrieri S, Luppa M. et al. Review: health care utilization and costs of elderly persons with multiple chronic conditions. Medical Care Research and Review 2011; 68 (04) 387-420.
    CrossrefPubMedGoogle Scholar
  • 24 Fried TR, Tinetti ME, Iannone L, O’Leary JR, Towle V, Van Ness PH. Health outcome prioritization as a tool for decision making among older persons with multiple chronic conditions. Archives of Internal Medicine 2011; 171 (20) 1856-1858.
    CrossrefPubMedGoogle Scholar
  • 25 Hempstead K, DeLia D, Cantor JC, Nguyen T, Brenner J. The fragmentation of hospital use among a cohort of high utilizers: implications for emerging care coordination strategies for patients with multiple chronic conditions. Medical Care 2014; 52: S67-S74.
    CrossrefPubMedGoogle Scholar
  • 26 Piette JD, Richardson C, Valenstein M. Addressing the needs of patients with multiple chronic illnesses: the case of diabetes and depression. American Journal of Managed Care 2004; 10 (02) PART 2 152-62.
    PubMedGoogle Scholar
  • 27 Pugh MJV, Finley EP, Copeland LA, Wang C-P, Noel PH, Amuan ME. et al. Complex comorbidity clusters in OEF/OIF veterans: the polytrauma clinical triad and beyond. Medical Care 2014; 52 (02) 172-181.
    CrossrefPubMedGoogle Scholar
  • 28 Pujades-Rodriguez M, George J, Shah AD, Rapsomaniki E, Denaxas S, West R. et al. Heterogeneous associations between smoking and a wide range of initial presentations of cardiovascular disease in 1 937 360 people in England: lifetime risks and implications for risk prediction. International Journal of Epidemiology 2015; 44 (01) 129-141.
    CrossrefPubMedGoogle Scholar
  • 29 Wu M-F, Wen C-Y. A novel shuttle walking model using networked sensing and control for chronic obstructive pulmonary disease: A preliminary study. Pervasive Computing Technologies for Healthcare (PervasiveHealth), 2012 6th International Conference on. 2012. IEEE.;
    Google Scholar
  • 30 Ward BW, Schiller JS, Goodman RA. Peer Reviewed: Multiple Chronic Conditions Among US Adults: A 2012 Update. Prev Chronic Dis 2014; 11: E62.
    PubMedGoogle Scholar
  • 31 Health UDo, Services H. Multiple chronic conditions – a strategic framework: optimum health and quality of life for individuals with multiple chronic conditions. Washington, DC: US Department of Health and Human Services; 2010
    Google Scholar
  • 32 Tangri N, Stevens LA, Griffith J, Tighiouart H, Djurdjev O, Naimark D. et al. A predictive model for progression of chronic kidney disease to kidney failure. JAMA 2011; 305 (15) 1553-1559.
    CrossrefPubMedGoogle Scholar
  • 33 Xun L, Linsheng L, Li L, Tanqi L. A Markov model study on the hierarchical prognosis and risk factors in patients with chronic kidney disease. Computer Science and Electronics Engineering (ICCSEE), 2012 International Conference on. 2012. IEEE.;
    Google Scholar
  • 34 Boshuizen HC, Lhachimi SK, van Baal PH, Hoogenveen RT, Smit HA, Mackenbach JP. et al. The DYNAMO-HIA model: an efficient implementation of a risk factor/chronic disease Markov model for use in Health Impact Assessment (HIA). Demography 2012; 49 (04) 1259-1283.
    CrossrefPubMedGoogle Scholar
  • 35 Neumann M, Wirtz M, Ernstmann N, Ommen O, Längler A, Edelhäuser F. et al. Identifying and predicting subgroups of information needs among cancer patients: an initial study using latent class analysis. Supportive Care in Cancer 2011; 19 (08) 1197-1209.
    CrossrefPubMedGoogle Scholar
  • 36 Zhang B, Mitchell SL, Bambauer KZ, Jones R, Prigerson HG. Depressive symptom trajectories and associated risks among bereaved Alzheimer disease caregivers. The American Journal of Geriatric Psychiatry 2008; 16 (02) 145-155.
    CrossrefPubMedGoogle Scholar
  • 37 Jaffe A, Shoptaw S, Stein JA, Reback CJ, Rotheram-Fuller E. Depression ratings, reported sexual risk behaviors, and methamphetamine use: latent growth curve models of positive change among gay and bisexual men in an outpatient treatment program. Experimental and Clinical Psychophar- macology 2007; 15 (03) 301.
    PubMedGoogle Scholar
  • 38 Wolfe F. A reappraisal of HAQ disability in rheumatoid arthritis. Arthritis & Rheumatism 2000; 43 (12) 2751-2761.
    CrossrefPubMedGoogle Scholar
  • 39 Paulli M, Berti E, Rosso R, Boveri E, Kindl S, Klersy C. et al. CD30/Ki-1-positive lymphoprolife- rative disorders of the skin – clinicopathologic correlation and statistical analysis of 86 cases: a multicentric study from the European Organization for Research and Treatment of Cancer Cutaneous Lymphoma Project Group. Journal of Clinical Oncology 1995; 13 (06) 1343-1354.
    CrossrefPubMedGoogle Scholar
  • 40 Kenter W. Exploring Markov modeling approaches for the health economic assessment of circulating tumor cells in the management of metastatic prostate cancer patients [dissertation]. Enschede: University of Twente; 2015
    Google Scholar
  • 41 Kemere C, Santhanam G, Byron MY, Afshar A, Ryu SI, Meng TH. et al. Detecting neural-state transitions using hidden Markov models for motor cortical prostheses. Journal of Neurophysiology 2008; 100 (04) 2441-2452.
    CrossrefPubMedGoogle Scholar
  • 42 Dumont J, Hernandez A, Fleureau J, Carrault G. Modelling temporal evolution of cardiac electrophysiological features using hidden semi-Markov models. Engineering in Medicine and Biology Society, 2008 EMBS 2008 30th Annual International Conference of the IEEE. 2008. IEEE.;
    Google Scholar
  • 43 Dobra A, Lenkoski A. Copula Gaussian graphical models and their application to modeling functional disability data. The Annals of Applied Statistics 2011; 5 2A 969-993.
    CrossrefPubMedGoogle Scholar
  • 44 Acuna E, Rodriguez C. The treatment of missing values and its effect on classifier accuracy. Banks D, House L, McMorris FR, Arabie P, Gaul W. Classification, Clustering and Data Mining Applications.. Berlin, Heidelberg: Springer; 2004: 639-648.
    Google Scholar
  • 45 Pugh MJ, Finley EP, Wang C-P, Copeland LA, Jaramillo CA, Swan AA. et al. A retrospective cohort study of comorbidity trajectories associated with traumatic brain injury in veterans of the Iraq and Afghanistan wars. Brain Injury 2016; 30 (12) 1481-1490.
    CrossrefPubMedGoogle Scholar
  • 46 Jaramillo CA, Cooper DB, Wang C-P, Tate DF, Eapen BC, York GE. et al. Subgroups of US IRAQ and Afghanistan veterans: associations with traumatic brain injury and mental health conditions. Brain Imaging and Behavior 2015; 9 (03) 445-455.
    CrossrefPubMedGoogle Scholar
  • 47 Elixhauser A, Steiner C, Harris DR, Coffey RM. Comorbidity measures for use with administrative data. Medical Care 1998; 36 (01) 8-27.
    CrossrefPubMedGoogle Scholar
  • 48 Rajarshi M. Markov Chains and Their Extensions. Statistical Inference for Discrete Time Stochastic Processes.. India: Springer; 2013: 19-38.
    Google Scholar
  • 49 Agresti A, Kateri M. Categorical data analysis. Springer; 2011
    Google Scholar
  • 50 Fahrmeir L, Tutz G. Multivariate statistical modelling based on generalized linear models. Springer Science & Business Media; 2013
    Google Scholar
  • 51 Dempster AP, Laird NM, Rubin DB. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society Series B (Methodological). 1977: 1-38.
    PubMedGoogle Scholar
  • 52 Chung H, Loken E, Schafer JL. Difficulties in drawing inferences with finite-mixture models. The American Statistician. 2004 58. 02.
    PubMedGoogle Scholar
  • 53 Vlasblom J, Wodak SJ. Markov clustering versus affinity propagation for the partitioning of protein interaction graphs. BMC Bioinformatics 2009; 10 (01) 99.
    CrossrefPubMedGoogle Scholar
  • 54 Enright AJ, Van Dongen S, Ouzounis CA. An efficient algorithm for large-scale detection of protein families. Nucleic Acids Research 2002; 30 (07) 1575-1584.
    CrossrefPubMedGoogle Scholar
  • 55 Hospedales T, Gong S, Xiang T. A markov clustering topic model for mining behaviour in video. Computer Vision, 2009 IEEE 12th International Conference on. 2009. IEEE.;
    Google Scholar
  • 56 Copeland LA FE, Bollinger MJ, Amuan ME, Pugh MJ. Comorbidity Correlates of Death among New Veterans of Iraq and Afghanistan Deployment. Medical Care. 2016 forthcoming.
    PubMedGoogle Scholar
  • 57 Kibler JL, Tursich M, Ma M, Malcolm L, Greenbarg R. Metabolic, autonomic and immune markers for cardiovascular disease in posttrau- matic stress disorder. World J Cardiol 2014; 6 (06) 455-461.
    CrossrefPubMedGoogle Scholar
  • 58 Leino-Arjas P, Solovieva S, Kirjonen J, Reunanen A, Riihimäki H. Cardiovascular risk factors and low-back pain in a long-term follow-up of industrial employees. Scandinavian Journal of Work, Environment & Health. 2006: 12-9.
    PubMedGoogle Scholar
  • 59 Strine TW, Hootman JM. US national prevalence and correlates of low back and neck pain among adults. Arthritis Care & Research 2007; 57 (04) 656-665.
    CrossrefPubMedGoogle Scholar
  • 60 Sugiyama T, Kiraku J-i, Ashida T, Fujii J. Remission of hypertension: retrospective observations over a period of 20 years. Hypertension Research 1998; 21 (02) 103-108.
    CrossrefPubMedGoogle Scholar
  • 61 Meng L, Chen D, Yang Y, Zheng Y, Hui R. Depression increases the risk of hypertension incidence: a meta-analysis of prospective cohort studies. Journal of Hypertension 2012; 30 (05) 842-851.
    CrossrefPubMedGoogle Scholar
  • 62 Rubio-Guerra AF, Rodriguez-Lopez L, Vargas-Ayala G, Huerta-Ramirez S, Serna DC, Lozano-Nuevo JJ. Depression increases the risk for uncontrolled hypertension. Experimental & Clinical Cardiology 2013; 18 (01) 10.
    PubMedGoogle Scholar
  • 63 Licht CM, De Geus EJ, Seldenrijk A, Van Hout HP, Zitman FG, Van Dyck R. et al. Depression is associated with decreased blood pressure, but antidepressant use increases the risk for hypertension. Hypertension 2009; 53 (04) 631-638.
    CrossrefPubMedGoogle Scholar
  • 64 Pugh MJ FE, Wang CP, Copeland LA, Jaramillo CA, Swan AA, Elnitsky CA, Leykum LK, Mortensen EM, Eapen BA, Noel PH, Pugh JA. A Retrospective Cohort Study of Comorbidity Trajectories Associated with Traumatic Brain Injury in Veterans of the Iraq and Afghanistan Wars. Brain Injury. under review.
    PubMedGoogle Scholar
  • 65 Fried LP, Tangen CM, Walston J, Newman AB, Hirsch C, Gottdiener J. et al. Frailty in older adults evidence for a phenotype. The Journals of Gerontology Series A: Biological Sciences and Medical Sciences 2001; 56 (03) M146-M57.
    PubMedGoogle Scholar