Related Experiment Videos
Admission and mid-stay MedisGroups scores as predictors of hospitalization charges
L I Iezzoni1, A S Ash, G A Coffman
1Evans Memorial Department of Clinical Research and Medicine, Boston University School of Medicine, MA.
Abstract:
This study examines the ability of MedisGroups, a severity measure based on clinical data abstracted from the medical record, to predict hospitalization charges. MedisGroups measures severity both on admission and approximately 1 week into the hospital stay. The data base contained 23,361 admissions of Medicare beneficiaries in six conditions from 836 hospitals in seven states between January 1985, and May 1986. In all six conditions, higher admission and mid-stay severity scores were generally associated with higher charges. Across the six conditions, the R2 values for predicting charges using diagnosis-related group (DRG) class ranged from 0.06 to 0.32 using trimmed data. Adding admission MedisGroups scores to DRG class produced R2 values ranging from 0.09 to 0.33, while adding mid-stay scores yielded R2 values from 0.15 to 0.41, and adding both admission and mid-stay scores produced R2 levels ranging from 0.17 to 0.42. Very little of the superior predictive power of the mid-stay score could be attributed to its serving as a proxy for length of stay.
Insights
This study shows that MedisGroups severity scores, measured on admission and mid-stay, effectively predict hospitalization charges for Medicare beneficiaries. Mid-stay scores offered superior prediction compared to admission scores alone.
Area of Science:
- Healthcare Economics
- Clinical Informatics
- Health Services Research
Background:
- Accurate prediction of hospitalization charges is crucial for healthcare financial management.
- Existing methods like Diagnosis-Related Groups (DRGs) have limitations in capturing patient complexity.
- Clinical data abstraction offers a potential avenue for more precise severity measurement.
Purpose of the Study:
- To evaluate the predictive ability of MedisGroups, a clinical data-based severity measure, for hospitalization charges.
- To compare the predictive power of admission and mid-stay MedisGroups scores against DRG classification.
- To determine if mid-stay scores offer incremental value beyond admission scores and DRGs in predicting costs.
Main Methods:
- Utilized a large dataset of 23,361 Medicare beneficiary admissions across six conditions and 836 hospitals (1985-1986).
- Employed MedisGroups to assess patient severity at admission and approximately one week into the hospital stay.
- Performed regression analyses to predict hospitalization charges using DRG class, MedisGroups scores (admission and mid-stay), and combinations thereof.
Main Results:
- Higher admission and mid-stay MedisGroups severity scores were consistently associated with increased hospitalization charges across all six conditions.
- Diagnosis-Related Group (DRG) class alone explained a modest portion of charge variation (R2: 0.06-0.32).
- Incorporating MedisGroups scores significantly improved charge prediction: admission scores (R2: 0.09-0.33), mid-stay scores (R2: 0.15-0.41), and both (R2: 0.17-0.42).
Conclusions:
- MedisGroups severity measurement, particularly mid-stay assessment, demonstrates substantial predictive power for hospitalization charges.
- Clinical data-based severity measures like MedisGroups offer significant advantages over traditional DRG classification for cost prediction.
- The predictive utility of mid-stay scores is largely independent of length of stay, highlighting its value in capturing evolving patient complexity.