Supervised Nonnegative Matrix Factorization to Predict ICU Mortality Risk

TL;DR

This paper introduces a supervised nonnegative matrix factorization method that enhances ICU mortality risk prediction by combining interpretability with improved accuracy, validated through simulations and real data.

Contribution

It proposes a supervised SANMF algorithm integrating logistic regression loss, improving prediction performance while maintaining interpretability in ICU mortality risk analysis.

Findings

Supervised SANMF outperforms conventional supervised NMF methods.

The method effectively predicts ICU mortality risk.

Simulation studies confirm the approach's effectiveness.

Abstract

ICU mortality risk prediction is a tough yet important task. On one hand, due to the complex temporal data collected, it is difficult to identify the effective features and interpret them easily; on the other hand, good prediction can help clinicians take timely actions to prevent the mortality. These correspond to the interpretability and accuracy problems. Most existing methods lack of the interpretability, but recently Subgraph Augmented Nonnegative Matrix Factorization (SANMF) has been successfully applied to time series data to provide a path to interpret the features well. Therefore, we adopted this approach as the backbone to analyze the patient data. One limitation of the raw SANMF method is its poor prediction ability due to its unsupervised nature. To deal with this problem, we proposed a supervised SANMF algorithm by integrating the logistic regression loss function into the NMF framework and solved it with an alternating optimization procedure. We used the simulation data to verify the effectiveness of this method, and then we applied it to ICU mortality risk prediction and demonstrated its superiority over other conventional supervised NMF methods.