
New Book on Distributionally Robust Learning
A central problem in machine learning is to learn from data (``big''...
We examined records of 2,566 consecutive COVID-19 patients at five Massachusetts hospitals and sought to predict level-of-care requirements based on clinical and laboratory data. Several classification methods were applied and compared against standard pneumonia severity scores. The need for hospitalization, ICU care, and mechanical ventilation were predicted with a validation accuracy of 88%, 87%, and 86%, respectively. In contrast, standard pneumonia severity scores achieve respective accuracies of 73% and 74% for ICU care and ventilation. When predictions are limited to patients with more complex disease, the accuracy of the ICU and ventilation prediction models achieved accuracy of 83% and 82%, respectively. Vital signs, age, BMI, dyspnea, and comorbidities were the most important predictors of hospitalization. Opacities on chest imaging, age, admission vital signs and symptoms, male gender, admission laboratory results, and diabetes were the most important risk factors for ICU admission and mechanical ventilation. The factors identified collectively form a signature of the novel COVID-19 disease.
Reference: The work is published in Boran Hao, Shahabeddin Sotudian, Taiyao Wang, Tingting Xu, Yang Hu, Apostolos Gaitanidis, Kerry Breen, George C. Velmahos, and Ioannis Ch. Paschalidis, “Early prediction of level of care requirements in patients with COVID-19,” eLife, 2020;9:e60519,
doi: 10.7554/eLife.60519.
The calculators are applicable to patients who have tested positive for COVID-19 and are based on the parsimonious models corresponding to Tables 1–5 of the paper. Please cite the above reference if you use the calculators.