Precision ICU Resource Planning: A Multimodal Model for Brain Surgery Outcomes

TL;DR

This paper presents a multimodal predictive model combining clinical and imaging data to improve ICU resource planning for brain surgery patients, addressing class imbalance and outperforming existing clinical-only models.

Contribution

The study introduces a novel multimodal approach that integrates imaging data with clinical data to enhance ICU admission predictions in brain surgery cases.

Findings

Multimodal model improves F1 score from 0.29 to 0.30 with pre-operative data.

Multimodal model improves F1 score from 0.37 to 0.41 with pre- and post-operative data.

Effective data fusion enhances prediction accuracy in severe class imbalance scenarios.

Abstract

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.