Learning as We Go: An Examination of the Statistical Accuracy of COVID19 Daily Death Count Predictions
Marchant, R.; Samia, N. I.; Rosen, O.; Tanner, M. A.; Cripps, S.
Show abstract
A recent model developed at the Institute for Health Metrics and Evaluation (IHME) provides forecasts for ventilator use and hospital beds required for the care of COVID19 patients on a state-by-state basis throughout the United States over the period March 2020 through August 2020 (See the related website https://covid19.healthdata.org/projections for interactive data visualizations). In addition, the manuscript and associated website provide projections of deaths per day and total deaths throughout this period for the entire US, as well as for the District of Columbia. This research has received extensive attention in social media, as well as in the mass media. Moreover, this work has influenced policy makers at the highest levels of the United States government, having been mentioned at White House Press conferences, including March 31, 2020. In this paper, we evaluate the predictive validity of model forecasts for COVID19 outcomes as data become sequentially available, using the IHME prediction of daily deaths. We have found that the predictions for daily number of deaths provided by the IHME model have been highly inaccurate. The model has been found to perform poorly even when attempting to predict the number of next day deaths. In particular, the true number of next day deaths has been outside the IHME prediction intervals as much as 70% of the time.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A framework for making predictive models useful in practice 93%
- Learning from local to global - an efficient distributed algorithm for modeling time-to-event data 93%
- Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models 92%
Similar papers in this journal
- A Bayesian Susceptible-Infectious-Hospitalized-Ventilated-Recovered Model to Predict Demand for COVID-19 Inpatient Care in a Large Healthcare System 94%
- Identification of high-risk COVID-19 patients using machine learning 93%
- On the use of growth models for forecasting epidemic outbreaks with application to COVID-19 data 93%
Similar papers in this journal
- Developing Machine Learning Models for Predicting Intensive Care Unit Resource Use During the COVID-19 Pandemic 94%
- Mitigating Machine Learning Bias Between High Income and Low-Middle Income Countries for Enhanced Model Fairness and Generalizability 93%
- Early risk assessment for COVID-19 patients from emergency department data using machine learning 93%
Similar papers in this journal
Similar papers in this journal
- Implicit bias in Critical Care Data: Factors affecting sampling frequencies and missingness patterns of clinical and biological variables in ICU Patients 93%
- An Interpretable Risk Prediction Model for Healthcare with Pattern Attention 93%
- Causal Analysis for Multivariate Integrated Clinical and Environmental Exposures Data 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.