ABSTRACT
Since the start of the COVID-19 pandemic, hospitals have been overwhelmed with the high number of ill and critically ill patients. The surge in ICU demand led to ICU wards running at full capacity, with no signs of demand falling. As a result, resource management of ICU beds and ventilators has been a bottleneck in providing adequate healthcare to those in need. Short-term ICU demand forecasts have become a critical tool for hospital administrators. Therefore, using the existing COVID-19 patient data, we build models to predict if a patient's health will deteriorate below safe thresholds to deem admission into ICU in the next 24 to 96 hours. We identify the most important clinical features responsible for the prediction and narrow down the health indicators to focus on, thereby assisting the hospital staff in increasing responsiveness. These models can help the hospital staff better forecast ICU demand in near real-time and triage patients for ICU admissions as per the risk of deterioration. Using a retrospective study with a dataset of 1411 COVID-19 patients from an actual hospital in the USA, we run experiments and find XGBoost performs the best among the models tested when tuning parameters for sensitivity (recall). The most important feature for the four prediction tasks is the maximum respiratory rate, but subsequent features in order of importance vary between models predicting ICU transfer in the next 24 to 48 hours and those predicting ICU transfer in the next 72 to 96 hours. © 2022 IEEE.
ABSTRACT
At the beginning of the breakout of a new disease, the healthcare community almost always has little experience in treating patients of this kind. Similarly, due to insufficient patient records at the early stage of a pandemic, it is difficult to train an in-hospital mortality prediction model specific to the new disease. We call this the 'cold start' problem of mortality prediction models. In this paper, we aim to study the cold start problem of 3-days ahead COVID-19 mortality prediction models by the following two steps: (i) Train XGBoost [1] and logistic regression 3-days ahead mortality prediction models on MIMIC3, a publicly available ICU patient dataset [2];(ii) Apply those MIMIC3 models to COVID-19 patients and then use the prediction scores as a new feature to train COVID-19 3-days ahead mortality prediction models. Retrospective experiments are conducted on a real-world COVID-19 patient dataset(n = 1,287) collected in US from June 2020 to February 2021 with a mixed cohort of both ICU and Non-ICU patients. Since the dataset is imbalanced(death rate = 7.8%), we primarily focus on the relative improvement of AUPR. We trained models with and without MIMIC3 scores on the first 200, 400,..., 1000 patients respectively and then tested on the next 200 incoming patients. The results show a diminishing positive transfer effect of AUPR from 5.36% for the first 200 patients(death rate = 5.5%) to 3.58% for all 1,287 patients. Meanwhile the AUROC scores largely remain unchanged, regardless of the number of patients in the training set. What's more, the p-value of t-test suggests that the cold start problem disappears for a dataset larger than 600 COVID-19 patients. To conclude, we demonstrate the possibility of mitigating the cold start problem via the proposed method. © 2022 IEEE.