Toolkit to Compute Time-Based Elixhauser Comorbidity Indices and Extension to Common Data Models

Area of Science:

• Health Informatics
• Clinical Epidemiology
• Data Science in Healthcare

Background:

• Longitudinal study of comorbidities offers insights into disease progression.
• Understanding time-dependent disease characteristics can improve clinical outcomes and intervention timing.

Purpose of the Study:

• To develop an efficient and installable toolkit, the Time-based Elixhauser Comorbidity Index (TECI).
• To pre-calculate time-based Elixhauser comorbidities and enable extension to common data models (CDMs).

Main Methods:

• Developed a Structured Query Language (SQL)-based toolkit (TECI) for pre-calculating time-specific Elixhauser comorbidity indices.
• Extended TECI to Informatics for Integrating Biology and the Bedside (I2B2) and Observational Medical Outcomes Partnership (OMOP) CDMs.
• Validated TECI-calculated scores against existing databases and algorithms.

Main Results:

• Successfully installed and implemented TECI at the University of Arkansas for Medical Sciences (UAMS), integrating scores into I2B2 and OMOP CDMs.
• Validated TECI scores against the Nationwide Readmissions Database (NRD) and a previously validated algorithm, achieving 100% accuracy.
• Identified 18,846 UAMS patients with changing comorbidity scores between 2013 and 2019.

Conclusions:

• TECI facilitates the time-dependent study of comorbidities, enhancing understanding of disease associations and trajectories.
• The toolkit has the potential to improve clinical outcomes through better-informed, timely interventions.