icuARM-II: improving the reliability of personalized risk prediction in pediatric intensive care units

Abstract

Clinicians in intensive care units (ICUs) rely on standardized scores as risk prediction models to predict a patient's vulnerability to life-threatening events. Conventional Current scales calculate scores from a fixed set of conditions collected within a specific time window. However, modern monitoring technologies generate complex, temporal, and multimodal patient data that conventional prediction models scales cannot fully utilize. Thus, a more sophisticated model is needed to tailor individual characteristics and incorporate multiple temporal modalities for a personalized risk prediction. Furthermore, most scales models focus on adult patients. To address this needdeficiency, we propose a newly designed ICU risk prediction system, called icuARM-II, using a large-scaled pediatric ICU database from Children's Healthcare of Atlanta. This novel database contains clinical data collected in 5,739 ICU visits from 4,975 patients. We propose a temporal association rule mining framework giving clinicians a potential to perform predict risks prediction based on all available patient conditions without being restricted by a fixed observation window. We also develop a new metric that can rigidly assesses the reliability of all all generated association rules. In addition, the icuARM-II features an interactive user interface. Using the icuARM-II, our results demonstrated showed a use case of short-term mortality prediction using lab testing results, which demonstrated a potential new solution for reliable ICU risk prediction using personalized clinical data in a previously neglected population.

Figure 1

Contingency table of a temporal association rule A ⇒ C.

Figure 2

Flow of backward and forward scanning (top) with examples of five different situations (bottom).

Figure 3

Steps of the generation of performance data.

Figure 4

Flow of the creation, storage, and retrieval of rule performance data.

Figure 5

Average reliabilities (light gray) and CBA performance (black) of 12 selected lab tests.

Figure 6

Effects of interactions among four lab tests.

Figure 7

Effects of different observation lengths.

Figure 8

The user interface of icuARM-II for ICU mortality prediction. It demonstrates the setting and the result of a rule: {ABEx2 + SO2x2 + SODx2 + CAx2 |<l-day}⇒ {Death| <2-hr}