Data mining for improved cardiac care

ABSTRACT

Cardiovascular Disease (CVD) is the single largest killer in the world. Although, several CVD treatment guidelines have been developed to improve quality of care and reduce healthcare costs, for a number of reasons, adherence to these guidelines remains poor. Further, due to the extremely poor quality of data in medical patient records, most of today's healthcare IT systems cannot provide significant support to improve the quality of CVD care (particularly in chronic CVD situations which contribute to the majority of costs).We present REMIND, a Probabilistic framework for Reliable Extraction and Meaningful Inference from Nonstructured Data. REMIND integrates the structured and unstructured clinical data in patient records to automatically create high-quality structured clinical data. There are two principal factors that enable REMIND to overcome the barriers associated with inference from medical records. First, patient data is highly redundant -- exploiting this redundancy allows us to deal with the inherent errors in the data. Second, REMIND performs inference based on external medical domain knowledge to combine data from multiple sources and to enforce consistency between different medical conclusions drawn from the data -- via a probabilistic reasoning framework that overcomes the incomplete, inconsistent, and incorrect nature of data in medical patient records.This high-quality structuring allows existing patient records to be mined to support guideline compliance and to improve patient care. However, once REMIND is configured for an institution's data repository, many other important clinical applications are also enabled, including: quality assurance; therapy selection for individual patients; automated patient identification for clinical trials; data extraction for research studies; and to relate financial and clinical factors. REMIND provides value across the continuum of healthcare, ranging from small physician practice databases to the most complex hospital IT systems, from acute cardiac care to chronic CVD management, and to experimental research studies. REMIND is currently deployed across multiple disease areas over a total of 5,000,000 patients across the US.

REFERENCES

• 1: Advisory Council to Improve Outcomes Nationwide in Heart Failure. Consensus recommendations for the management of chronic heart failure. Am J Cardiol 1999;83 (2A):1A--38A.
• 2: American College of Cardiology/American Heart Association Task Force on Practice Guidelines. Guidelines for the evaluation and management of heart failure. Report of the ACC/AHA Committee on Evaluation and Management of Heart Failure. J Am Coll Cardiol 1995;26:1376--98.
• 3: American College of Cardiology/American Heart Association Task Force on Practice Guidelines. ACC/AHA Guidelines for the Evaluation and Management of Chronic Heart Failure in the Adult. ACC/AHA Committee to Revise the 1995 Guidelines for the Evaluation and Management of Heart Failure. J Am Coll Cardiol. 2001; 38:2101--13.
• 4: American Heart Association. Heart Disease and Stroke Statistics -- 2005 Update. Dallas, TX, American Heart Association, 2004.
• 5: Barnett, G. O., Cimino, J. J., Hupp, A. J., and Hoffer, E. P. DXplain: an Evolving Diagnostic Decision-Support System, JAMA, 1987, Vol. 258(1), pp. 67--74.
• 6: Bellazzi, R., Larizza, C., De Nicolao, G., Riva, A., Stefanelli, M. Mining biomedical time series by combining structural analysis and temporal abstractions. JAMIA (symposium supplement), vol. 5 (1998), 160--164.
• 7: Benesch, C., Witter Jr, D. M., Wilder, A. L., Duncan, P. W., Samsa, G. P., Matchar, D. B. Inaccuracy of the International Classification of Diseases (ICD-9-CM) in identifying the diagnosis of ischemic cerebrovascular disease. Neurology, 1997, Vol. 49, pp. 660--664.
• 8: Bonow, R. O., Smaha, L. A., Smith Jr, S. C., Mensah, G. A., and Lenfant, C. World Heart Day 2002: The International Burden of Cardiovascular Disease: Responding to the Emerging Global Epidemic. Circulation, 2002, Vol. 106, pp. 1602--1605.
• 9: Braunwald, E., Antman, E. M., Beasley, J. W., et al. ACC/AHA 2002 guideline update for the management of patients with unstable angina and non-ST-segment elevation myocardial infarction: a report of the American College of Cardiology/American Heart Association Task Force on Practice Guidelines. Committee on the Management of Patients With Unstable Angina 2002.
• 10: Broderick, J., Brott, T., Kothari, R., Miller, R., Khoury, J., Pancioli, A., Mills, D., Minneci, L., Shukla, R. The Greater Cincinnati/Northern Kentucky Stroke Study: preliminary first-ever and total incidence rates of stroke among blacks. Stroke. 1998, Vol. 29, pp. 415--421.
• 11: Combi, C., Shahar, Y. Reasoning and Temporal Data Maintenance in Medicine: Issues and Challenges. Computers in Biology and Medicine, Vol. 27(5), 1997, pp. 353--368.
• 12: Committee on Data Standards for Patient Safety, Board on Health Services. Key Capabilities of an Electronic Health Record System: Letter Report. Institute of Medicine of the National Academies, 2004.
• 13: Goldsclager, N. et al. Practical Guidelines for Clinicians Who Treat Patients with Amiodarone. Arch Intern Med. 2000; 160:1741--1748
• 14: Heart Failure Society of America. HFSA practice guidelines. HFSA guidelines for management of patients with heart failure caused by left ventricular systolic dysfunction--pharmacologic approaches. J Card Fail 1999;5:357--82
• 15: Heart Society of America. HFSA Practice Guidelines. HFSA Guidelines for Management of Patients with Heart Failure Caused by Left Ventricular Systolic Dysfunction -- Pharmacological Approaches. Pharmacotherapy. 2000; 20(5):495--522.
• 16: Heckerman, D. A tutorial on learning with Bayesian networks. Microsoft Research Technical Report, MSR-TR-95-06, 1996.
• 17: Holloway, R. G., Witter Jr, D. M., Lawton, K. B., Lipscomb, J., Samsa, G. Inpatient costs of specific cerebrovascular events at five academic medical centers. Neurology, 1996 Vol. 46, pp. 854--860.
• 18: Horn, W., Miksch, S., Egghart, G., Popow, C., Paky, F. Effective Data Validation of High Frequency Data: Time-Point, Time-Interval, and Trend-Based Methods. Computers in Biology and Medicine, 1997.
• 19: Finn V. Jensen , F.V. V. Jensen , F. V. Jensen, Introduction to Bayesian Networks, Springer-Verlag New York, Inc., Secaucus, NJ, 1996
• 20: Joint Commission on Accreditation of Healthcare Organizations (JCAHO), Website: http://www.jcaho.org.
• 21: Kahn, M., Fagan, L., Tu, S. Extensions to the Time-Oriented Database Model to Support Temporal Reasoning in Expert Medical Systems. Methods of Information in Medicine, 1991, Vol. 30, pp. 4--14.
• 22: Kappen, B., Wiegerinck, W., Akay, E., Neijt, J., and Van Beek, A. Promedas: A Clinical Diagnostic Decision Support System in Bayesian Modeling Applications. Proceedings of the 15th Belgian-Dutch Conference on Artificial Intelligence (BNAIC'), Nijmegen, The Netherlands, October 23-24, 2003. pp. 455--456.
• 23: Kayaalp, M., Cooper, G. F., Clermont G. Predicting ICU Mortality: A Comparison of Stationary and Nonstationary Temporal Models. Proceedings of American Medical Informatics Association (AMIA) Symposium, 2000, pp. 418--422.
• 24: Larizza, C., Moglia, A., Stefanelli, M. M-HTP: A System for Monitoring Heart Transplant Patients. Artificial Intelligence in Medicine, 1992, Vol. 4, pp. 111--126
• 25: Leibson, C. L., Naessens, J. M., Brown, R. D., Whisnant, J. P. Accuracy of hospital discharge abstracts for identifying stroke. Stroke, 1994, Vol. 25, pp. 2348--2355.
• 26: Miller, R. A., Fasarie, F. E., and Mayors, J. D. Quick Medical Reference (QMR) for Diagnostic Assistance. MD Computing, Sept-Oct, 1986, Vol. 3(5), pp. 34--48.
• 27: Mitchell, J. B., et al. What role do neurologists play in determining the costs and outcomes of stroke patients? Stroke, 1996, Vol. 27, pp. 1937--1943.
• 28: Ngo, L., Haddawy, P., Krieger, R. A., Helwig, J. Efficient Temporal Probabilistic Reasoning via Context-Sensitive Model Construction. Computers in Biology and Medicine, 1997, Vol. 27(5), pp. 453--476.
• 29: Rao, R. H., and Rao, R. B. Quality Assurance through Comprehensive Extraction from Existing (non-structured) Patient Records. Annual Conference and Exhibition, Healthcare Information and Management Systems Society (HIMSS), San Diego, California, Feb 9-13, 2003.
• 30: Rao, R. B., Sandilya, S., Niculescu, R. S., Germond, C., and Goel, A. Mining Time-dependent Patient Outcomes from Hospital Patient Records. Proceedings of American Medical Informatics Association (AMIA) Annual Symposium, San Antonio, Texas, November 9-13, 2002.
• 31: R. Bharat Rao , Sathyakama Sandilya , Radu Stefan Niculescu , Colin Germond , Harsha Rao, Clinical and financial outcomes analysis with existing hospital patient records, Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, August 24-27, 2003, Washington, D.C. [doi>10.1145/956750.956798]
• 32: Regenstrief Institute. LOINC: Logical Observation Identifiers Names and Codes. http://www.regenstrief.org/loinc/LONIC Homepage
• 33: Sandilya, S., and Rao, R. B. Continuous-Time Bayesian Modeling of Clinical Data. Proceedings of the fourth SIAM International Conference on Data Mining (SDM), Lake Buena Vista, Florida, April 22-24, 2004.
• 34: Shwe, M. A., Middleton, B., Heckerman, D. E., Henrion, M., Horvitz, E. J., and Lehmann, H. P. Probabilistic Diagnosis Using a Reformulation of the INTERNIST-1/QMR Knowledge Base: I. The Probabilistic Model and Inference Algorithms. Methods of Information in Medicine, October 1991, Vol. 30(4), pp.241--255.
• 35: SNOMED International. SNOMED Clinical Terms. College of American Pathologists, http://www.snomed.org/
• 36: Sonel, A. F., et al. What is the Most Efficient Data Extraction Method for Quality Improvement and Research in Cardiology?: A Comparison of REMIND Artificial Intelligence Software vs. Manual Chart Abstraction for Determining ACC/AHA Guideline Adherence in Non-ST Elevation Acute Coronary Syndromes. Annual Scientific Session of American College of Cardiology (ACC 2005), Orlando, Florida, March 6-9, 2005.
• 37: Tsui, F. C., et al. Technical Description of RODS: A Real-time Public Health Surveillance System. Journal Am Med Informatics Assoc 10/5 (Sept/Oct) 399--408, 2003.
• 38: United States Library of Medicine. MeSH: Medical Subject Headings. http://www.nlm.nih.gov/mesh/
• 39: United States Library of Medicine. UMLS: Unified Medical Language System. http://www.nlm.nih.gov/research/umls/
• 40: World Health Organization. Manual of the international statistical classification or diseases, injuries, and causes of death. World Health Organization, Geneva, 1977.
• 41: World Health Organization. Report of the international conferences for the Tenth Revision of International Classification of Diseases. World Health Organization, Geneva, 1992.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.2 DATABASE MANAGEMENT
      H.2.8 Database applications
          Subjects: Data mining

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval

  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.3 Deduction and Theorem Proving
          Subjects: Uncertainty, "fuzzy," and probabilistic reasoning

  J. Computer Applications
  J.3 LIFE AND MEDICAL SCIENCES
      Subjects: Medical information systems

General Terms:
Algorithms, Management