Severity of illness, Prognosis, multiple comorbidities
Background: The Multi-Morbidity (MM) Index predicts the prognosis of patients from their diagnostic history. In contrast to existing approaches with broad diagnostic categories, it treats each diagnosis as a separate independent variable using individual ICD-9 codes.
Objective: This paper describes the MM Index, reviews the published data on its accuracy, and provides procedures for implementing the Index within electronic health record (EHR) systems.
Methods: The MM Index was tested on various patient populations by using data from the Veterans Affairs data warehouse and claims data within the Healthcare Cost and Utilization Project of the Agency for Health Care Research and Quality.
Results: In cross-validated studies, the MM Index was more accurate than prognostic indices based on physiological markers; such as CD4 cell counts in HIV/AIDS, HbA1c levels in diabetes, ejection fractions in heart failure, or the13 physiological markers commonly used for patients in Intensive Care Units. When predicting the prognosis of nursing home patients by using the cross-validated area under a receiver operating characteristic curve (ROC), the MM Index was 15% more accurate than the Quan variant of the Charlson Index, 27% more accurate than the Deyo variant of the Charlson Index, and 22% more accurate than the von Walraven variant of the Elixhauser Index. For patients in Intensive Care Units, the MM Index was 13% more accurate than the cross-validated ROC associated with Elixhauser’s categories. The MM Index also demonstrated greater accuracy than a number of commercially available measures of severity of illness; including a five-fold greater accuracy than the All Patient Refined Diagnosis-Related Groups and a three-fold greater accuracy than All Payer Severity-adjusted Diagnosis-Related Groups.
Conclusion: The MM Index is statistically more accurate than many existing measures of prognosis. The magnitude of improvement may lead to a clinically meaningful difference in patient care or policy analysis.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 License.
Alemi, Farrokh; Levy, Cari R.; and Kheirbek, Raya E. MD, FACP
"The Multi-Morbidity Index: A Tool for Assessing the Prognosis of Patients from History of Illness,"
eGEMs (Generating Evidence & Methods to improve patient outcomes):
1, Article 19.
Available at: http://repository.edm-forum.org/egems/vol4/iss1/19