AI Article Synopsis

  • The study focuses on developing improved event prediction models for intensive care units, addressing issues like temporal skewness in data from electronic medical records and the potential for errors and delays in input.
  • Researchers analyzed data from 21,738 patients to predict three critical events: death, sepsis, and acute kidney injury, using multiple models designed to enhance prediction accuracy and robustness against errors.
  • Results indicated that the new models generally outperformed traditional methods, showing better accuracy, especially under conditions of simulated input errors, while maintaining performance even with delayed information.

Article Abstract

Background: In the era of artificial intelligence, event prediction models are abundant. However, considering the limitation of the electronic medical record-based model, including the temporally skewed prediction and the record itself, these models could be delayed or could yield errors.

Objective: In this study, we aim to develop multiple event prediction models in intensive care units to overcome their temporal skewness and evaluate their robustness against delayed and erroneous input.

Methods: A total of 21,738 patients were included in the development cohort. Three events-death, sepsis, and acute kidney injury-were predicted. To overcome the temporal skewness, we developed three models for each event, which predicted the events in advance of three prespecified timepoints. Additionally, to evaluate the robustness against input error and delays, we added simulated errors and delayed input and calculated changes in the area under the receiver operating characteristic curve (AUROC) values.

Results: Most of the AUROC and area under the precision-recall curve values of each model were higher than those of the conventional scores, as well as other machine learning models previously used. In the error input experiment, except for our proposed model, an increase in the noise added to the model lowered the resulting AUROC value. However, the delayed input did not show the performance decreased in this experiment.

Conclusions: For a prediction model that was applicable in the real world, we considered not only performance but also temporal skewness, delayed input, and input error.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8603167PMC
http://dx.doi.org/10.2196/26426DOI Listing

Publication Analysis

Top Keywords

event prediction
12
input error
12
temporal skewness
12
delayed input
12
prediction model
8
electronic medical
8
intensive care
8
prediction models
8
overcome temporal
8
evaluate robustness
8

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!