# Combining Predictive Models of Mortality and Time-to-Discharge for Improved Outcome Assessment in Intensive Care Units

## TL;DR

This paper introduces a new model called PADS that predicts both mortality and discharge likelihood in ICU patients, helping doctors make better decisions and manage resources more effectively.

## Contribution

The novel contribution is a combined predictive model using LSTM networks to assess mortality and discharge likelihood in real-time for ICU patients.

## Key findings

- PADS achieved an AUCROC of 0.94 for mortality prediction and 0.89 for discharge prediction on training data.
- The model outperformed existing benchmarks like APS III, OASIS, and SAPS II by 7.4% to 19% in accuracy.
- The model's predictions are visualized in an intuitive format to aid clinical interpretation.

## Abstract

Background: The Patient Outcome Assessment and Decision Support (PADS) model is a real-time framework designed to predict both mortality and the likelihood of discharge within 48 h in critically ill patients. By combining these predictions, PADS enables clinically meaningful stratification of patient trajectories, supporting bedside decision-making and the planning of critical care resources such as nursing allocation and surgical scheduling. Methods: PADS integrates routinely collected clinical data: SOFA variables, age, gender, admission type, and comorbidities. It consists of two Long Short-Term Memory (LSTM) neural networks—one predicting the probability of death and the other the probability of discharge within 48 h. The combination places each patient into one of four states: alive/discharged within 48 h, alive/not discharged, dead within 48 h, or dead later. The model was trained using MIMIC-IV data, emphasizing ease of implementation in units with electronic health records. Out of the 76,540 stays present in MIMIC-IV (53,150 patients), 32,875 (25,555 patients) were used after excluding those with short stays (<48 h) or life support treatment limitations. The code is open, well-documented, and designed for reproducibility and external validation. Results: The model achieved strong performance: AUCROC of 0.94 (±0.03) for mortality and 0.89 (±0.07) for discharge on training data, and 0.87 (±0.02) and 0.88 (±0.03), respectively, on the test set. As a comparison, benchmark models obtain worse accuracy (−13.4% for APS III, −19% for OASIS, and −7.4% for SAPS II). Predictions are visualized in an intuitive format to support clinical interpretation. Conclusions: PADS offers a transparent, reproducible, and practical tool that supports both individual patient care and the strategic organization of intensive care resources by anticipating short-term outcomes.