Published on Tue Jan 19 2021

Continual Deterioration Prediction for Hospitalized COVID-19 Patients

Jiacheng Liu, Meghna Singh, Catherine ST. Hill, Vino Raj, Lisa Kirkland, Jaideep Srivastava

Leading up to August 2020, COVID-19 has spread to almost every country in the world, causing millions of infected and hundreds of thousands of deaths. Clinical variables could have time-varying effects on outcomes. We develop a temporal stratification approach to make daily predictions.

0
0
0
Abstract

Leading up to August 2020, COVID-19 has spread to almost every country in the world, causing millions of infected and hundreds of thousands of deaths. In this paper, we first verify the assumption that clinical variables could have time-varying effects on COVID-19 outcomes. Then, we develop a temporal stratification approach to make daily predictions on patients' outcome at the end of hospital stay. Training data is segmented by the remaining length of stay, which is a proxy for the patient's overall condition. Based on this, a sequence of predictive models are built, one for each time segment. Thanks to the publicly shared data, we were able to build and evaluate prototype models. Preliminary experiments show 0.98 AUROC, 0.91 F1 score and 0.97 AUPR on continuous deterioration prediction, encouraging further development of the model as well as validations on different datasets. We also verify the key assumption which motivates our method. Clinical variables could have time-varying effects on COVID-19 outcomes. That is to say, the feature importance of a variable in the predictive model varies at different disease stages.

Thu Nov 29 2018
Machine Learning
Leveraging Clinical Time-Series Data for Prediction: A Cautionary Tale
In healthcare, patient risk stratification models are often learned using time-series data extracted from electronic health records. Several formulations exist, depending on how one chooses the time of prediction and the prediction horizon. An outcome-independent scheme outperforms an outcome-dependent scheme on both tasks.
0
0
0
Thu Sep 12 2019
Machine Learning
Using Clinical Notes with Time Series Data for ICU Management
Predicting the condition of patients during their ICU stay can help provide better acute care and plan the hospital's resources. There has been continuous progress in machine learning research for ICU management. Adding clinical notes as another modality improves the performance of the model for three benchmark tasks.
0
0
0
Mon Aug 10 2020
Machine Learning
Individualized Prediction of COVID-19 Adverse outcomes with MLHO
MLHO is an end-to-end Machine Learning framework that leverages iterative feature and algorithm selection to predict Health Outcomes. MLHO implements iterative sequential representation mining, feature and model selection, for predicting the patient-level risk of hospitalization, ICU admission, need for mechanical ventilation, and death.
0
0
0
Sat Nov 28 2020
Machine Learning
Clinical prediction system of complications among COVID-19 patients: a development and validation retrospective multicentre study
Existing prognostic tools mainly focus on predicting the risk of mortality among patients with coronavirus disease 2019. We aimed to develop a prognostic system that predicts complications common to COVID-19. The complications include secondary bacterial infection, AKI, and elevated biomarkers linked to increased patient severity. Our results show that a data-driven approach using machine learning can predict the risk with high accuracy.
0
0
0
Fri Nov 30 2018
Machine Learning
Rethinking clinical prediction: Why machine learning must consider year of care and feature aggregation
Machine learning for healthcare often trains models on de-identified datasets with randomly-shifted calendar dates. We augment MIMIC with the year in which care was provided and show that a model trained using standard feature representations will degrade in quality over time.
0
0
0
Tue Feb 09 2021
Artificial Intelligence
AttDMM: An Attentive Deep Markov Model for Risk Scoring in Intensive Care Units
Clinical practice in intensive care units (ICUs) requires early warnings when a patient's condition is about to deteriorate so that preventive measures can be undertaken. To this end, prediction algorithms have been developed to estimate the risk of mortality in ICUs.
0
0
0