Precision ICU Resource Planning: A Multimodal Model for Brain Surgery Outcomes
This work addresses the high cost of routine ICU transfers for brain surgery patients, though it is incremental as it builds on existing predictive methods by adding imaging data.
The paper tackled the problem of optimizing ICU admission for brain surgery patients by developing a multimodal model that combines clinical and imaging data, resulting in improved prediction accuracy from 0.29 to 0.30 F1 for pre-operative data and from 0.37 to 0.41 F1 for pre- and post-operative data.
Although advances in brain surgery techniques have led to fewer postoperative complications requiring Intensive Care Unit (ICU) monitoring, the routine transfer of patients to the ICU remains the clinical standard, despite its high cost. Predictive Gradient Boosted Trees based on clinical data have attempted to optimize ICU admission by identifying key risk factors pre-operatively; however, these approaches overlook valuable imaging data that could enhance prediction accuracy. In this work, we show that multimodal approaches that combine clinical data with imaging data outperform the current clinical data only baseline from 0.29 [F1] to 0.30 [F1], when only pre-operative clinical data is used and from 0.37 [F1] to 0.41 [F1], for pre- and post-operative data. This study demonstrates that effective ICU admission prediction benefits from multimodal data fusion, especially in contexts of severe class imbalance.