ABSTRACT
Hospitals routinely collect admitted patients' data for administrative purposes and for reporting to the government and health insurers. These heterogeneous and mostly untapped data contain rich semantic information about patients' health conditions in the form of standard disease codes. These traces of clinical information can be aggregated over patients to understand how their health progresses over time. When applied on particular chronic disease patients, this approach can potentially help in understanding chronic disease comorbidities as well as in the knowledge discovery on how the chronic disease progresses over time. In this paper, we propose a network-based approach to extract semantic information from hospital administrative data in order to develop a representation of chronic disease progression specifically - type 2 diabetes. We then propose measures for attribution adjustment that ranks the more prevalent comorbidities in chronic patients higher, compared to the non-chronic ones. We also have applied the framework on the administrative data of 2,760 sampled patients to understand how diabetes progresses over time through different comorbidities. This understanding can be effectively converted to actionable intelligence that can be useful in the formulation of better health policy and resource management.
- World Health Organization, 2012. Preventing chronic diseases: a vital investment. Geneva: WHO, 2005.Google Scholar
- Ward, B., Schiller, J., and Goodman, R., 2014. Multiple chronic conditions among US adults: a 2012 update. Prev. Chronic Dis. 11.Google Scholar
- Australian Institute of Health and Welfare (AIHW), 2014. Australia's Health 2014.Google Scholar
- Kopelman, P.G., 2000. Obesity as a medical problem. Nature 404, 6778, 635--643.Google Scholar
- Rathmann, W., Haastert, B., Icks, A.a., Löwel, H., Meisinger, C., Holle, R., and Giani, G., 2003. High prevalence of undiagnosed diabetes mellitus in Southern Germany: target populations for efficient screening. The KORA survey 2000. Diabetologia 46, 2, 182--189.Google ScholarCross Ref
- Gregg, E.W., Cadwell, B.L., Cheng, Y.J., Cowie, C.C., Williams, D.E., Geiss, L., Engelgau, M.M., and Vinicor, F., 2004. Trends in the prevalence and ratio of diagnosed to undiagnosed diabetes according to obesity levels in the US. Diabetes Care 27, 12, 2806--2812.Google ScholarCross Ref
- Taubert, G., Winkelmann, B.R., Schleiffer, T., März, W., Winkler, R., Gök, R., Klein, B., Schneider, S., and Boehm, B.O., 2003. Prevalence, predictors, and consequences of unrecognized diabetes mellitus in 3266 patients scheduled for coronary angiography. Am. Heart J. 145, 2, 285--291.Google ScholarCross Ref
- MacKenzie, E.J., Morris Jr, J.A., and Eeelstein, S.L., 1989. Effect of pre-existing disease on length of hospital stay in trauma patients. Journal of Trauma and Acute Care Surgery 29, 6, 757--765.Google ScholarCross Ref
- Umpierrez, G.E., Isaacs, S.D., Bazargan, N., You, X., Thaler, L.M., and Kitabchi, A.E., 2002. Hyperglycemia: an independent marker of in-hospital mortality in patients with undiagnosed diabetes. The Journal of Clinical Endocrinology & Metabolism 87, 3, 978--982.Google ScholarCross Ref
- Lauruschkat, A.H., Arnrich, B., Albert, A.A., Walter, J.A., Amann, B., Rosendahl, U.P., Alexander, T., and Ennker, J., 2005. Prevalence and risks of undiagnosed diabetes mellitus in patients undergoing coronary artery bypass grafting. Circulation 112, 16, 2397--2402.Google ScholarCross Ref
- Tenenbaum, A., Motro, M., Fisman, E.Z., Boyko, V., Mandelzweig, L., Reicher-Reiss, H., Graff, E., Brunner, D., and Behar, S., 2000. Clinical impact of borderline and undiagnosed diabetes mellitus in patients with coronary artery disease. The American journal of cardiology 86, 12, 1363--1366.Google Scholar
- Kapur, V., Sandblom, R.E., Hert, R., James, B., and Sean, D., 1999. The medical cost of undiagnosed sleep apnea. Sleep 22, 6, 749.Google ScholarCross Ref
- Harris, M.I., 1993. Undiagnosed NIDDM: clinical and public health issues. Diabetes Care 16, 4, 642--652.Google ScholarCross Ref
- Khan, A., Uddin, S., and Srinivasan, U., 2016. Adapting graph theory and social network measures on healthcare data: a new framework to understand chronic disease progression. In Proceedings of the Australasian Computer Science Week Multiconference ACM, 66. Google ScholarDigital Library
- Charlson, M.E., Pompei, P., Ales, K.L., and MacKenzie, C.R., 1987. A new method of classifying prognostic comorbidity in longitudinal studies: development and validation. J. Chronic Dis. 40, 5, 373--383.Google ScholarCross Ref
- Elixhauser, A., Steiner, C., Harris, D.R., and Coffey, R.M., 1998. Comorbidity measures for use with administrative data. Med. Care 36, 1, 8--27.Google ScholarCross Ref
- Sharabiani, M.T., Aylin, P., and Bottle, A., 2012. Systematic review of comorbidity indices for administrative data. Med. Care 50, 12, 1109--1118.Google ScholarCross Ref
- Wong, D.T. and Knaus, W.A., 1991. Predicting outcome in critical care: the current status of the APACHE prognostic scoring system. Can. J. Anaesth. 38, 3, 374--383.Google ScholarCross Ref
- Breslow, M.J. and Badawi, O., 2012. Severity scoring in the critically ill: part 1---interpretation and accuracy of outcome prediction scoring systems. CHEST Journal 141, 1, 245--252.Google ScholarCross Ref
- Barabási, A.-L., 2007. Network medicine---from obesity to the "diseasome". N. Engl. J. Med. 357, 4, 404--407.Google ScholarCross Ref
- Loscalzo, J., Kohane, I., and Barabasi, A.L., 2007. Human disease classification in the postgenomic era: a complex systems approach to human pathobiology. Mol. Syst. Biol. 3, 1.Google ScholarCross Ref
- Burton, P.R., Clayton, D.G., Cardon, L.R., Craddock, N., Deloukas, P., Duncanson, A., Kwiatkowski, D.P., McCarthy, M.I., Ouwehand, W.H., and Samani, N.J., 2007. Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls. Nature 447, 7145, 661--678.Google Scholar
- Hidalgo, C.A., Blumm, N., Barabási, A.-L., and Christakis, N.A., 2009. A dynamic network approach for the study of human phenotypes. PLoS Comput. Biol. 5, 4, e1000353.Google ScholarCross Ref
- Ideker, T. and Sharan, R., 2008. Protein networks in disease. Genome Res. 18, 4, 644--652.Google ScholarCross Ref
- Davis, D.A., Chawla, N.V., Christakis, N.A., and Barabási, A.-L., 2010. Time to CARE: a collaborative engine for practical disease prediction. Data Mining and Knowledge Discovery 20, 3, 388--415. Google ScholarDigital Library
- Davis, D.A., Chawla, N.V., Blumm, N., Christakis, N., and Barabási, A.-L., 2008. Predicting individual disease risk based on medical history. In Proceedings of the 17th ACM conference on Information and knowledge management ACM, 769--778. Google ScholarDigital Library
- Breault, J.L., Goodall, C.R., and Fos, P.J., 2002. Data mining a diabetic data warehouse. Artif. Intell. Med. 26, 1, 37--54. Google ScholarDigital Library
- Baglioni, M., Pieroni, S., Geraci, F., Mariani, F., Molinaro, S., Pellegrini, M., and Lastres, E., 2013. A New Framework for Distilling Higher Quality Information from Health Data via Social Network Analysis. In Data Mining Workshops (ICDMW), 2013 IEEE 13th International Conference on IEEE, 48--55.Google Scholar
- Anderson, J.G., 2002. Evaluation in health informatics: social network analysis. Comput. Biol. Med. 32, 3, 179--193.Google ScholarCross Ref
- World health Organization, 2014. WHO | International Classification of Diseases (ICD).Google Scholar
- Luijks, H., Schermer, T., Bor, H., van Weel, C., Lagro-Janssen, T., Biermans, M., and de Grauw, W., 2012. Prevalence and incidence density rates of chronic comorbidity in type 2 diabetes patients: an exploratory cohort study. BMC Med. 10, 1, 128.Google ScholarCross Ref
- Folino, F., Pizzuti, C., and Ventura, M., 2010. A comorbidity network approach to predict disease risk. In Information Technology in Bio-and Medical Informatics, ITBAM 2010 Springer, 102--109. Google ScholarDigital Library
- Fetter, R.B., Shin, Y., Freeman, J.L., Averill, R.F., and Thompson, J.D., 1980. Case mix definition by diagnosis-related groups. Med. Care, i--53.Google Scholar
- Quan, H., Sundararajan, V., Halfon, P., Fong, A., Burnand, B., Luthi, J.-C., Saunders, L.D., Beck, C.A., Feasby, T.E., and Ghali, W.A., 2005. Coding algorithms for defining comorbidities in ICD-9-CM and ICD-10 administrative data. Med. Care, 1130--1139.Google Scholar
- Garland, A., Fransoo, R., Olafson, K., Ramsey, C., Yogendren, M., Chateau, D., and McGowan, K., 2012. The epidemiology and outcomes of critical illness in Manitoba. University of Manitoba, Faculty of Medicine, Department of Community Health Sciences.Google Scholar
- American Diabetes Association, 2013. Kidney Disease (Nephropathy). In Living With Diabetes.Google Scholar
- National Heart, L., and Blood Institute, 2015. Who Is at Risk for Heart Valve Disease? In Heart Valve Diseases.Google Scholar
- Benjamin, E.J., Levy, D., Vaziri, S.M., D'Agostino, R.B., Belanger, A.J., and Wolf, P.A., 1994. Independent risk factors for atrial fibrillation in a population-based cohort: the Framingham Heart Study. JAMA 271, 11, 840--844.Google ScholarCross Ref
Index Terms
- Understanding chronic disease comorbidities from baseline networks: knowledge discovery utilising administrative healthcare data
Recommendations
Understanding the Comorbidity of Multiple Chronic Diseases Using a Network Approach
ACSW '19: Proceedings of the Australasian Computer Science Week MulticonferenceChronic diseases and associated conditions are the leading causes of death in most of the countries worldwide. Due to this, governments all over the world are concerned about the burden of chronic diseases. These diseases often pose severe health risks ...
Adapting graph theory and social network measures on healthcare data: a new framework to understand chronic disease progression
ACSW '16: Proceedings of the Australasian Computer Science Week MulticonferenceGovernments all over the world are concerned about the disease burden caused by chronic conditions. A significant portion of this comes from potentially preventable hospital admissions. By adopting preventive measures, these admissions can be avoided ...
Chronic disease prediction using administrative data and graph theory: The case of type 2 diabetes
Highlights- Administrative healthcare data is used to identify high-risk chronic patients.
- ...
AbstractClinical diagnosis and regular monitoring of the population at risk of chronic diseases is clinically and financially resource-intensive. Mining administrative data could be an effective alternative way to identify this high-risk ...
Comments