Transforming appeal decisions: machine learning triage for hospital admission denials

To develop and validate a machine learning model that helps physician advisors efficiently identify hospital admission denials likely to be overturned on appeal.

Analysis of 2473 appealed hospital admission denials with known outcomes, split 90:10 for training and testing.

Six binary classifier models were trained and evaluated using accuracy, precision, recall, and F1 score metrics.

An elastic net logistic regression model was selected based on computational efficiency and optimal performance with 84% accuracy, 84% precision, 98% recall, and an F1 score of 0.9.

The predictive model addresses the risk of physician advisors accepting inappropriate denials due to biased perceptions of appeal success. Model implementation improved denial screening efficiency and was a key feature of a more successful appeal strategy.

By addressing data quality problems inherent to electronic health data, and expanding the feature space, machine learning can be an effective tool in the healthcare provider space.