A Case Study in Model Failure? COVID-19 Daily Deaths and ICU Bed Utilisation Predictions in New York State

TL;DR

This study critically evaluates COVID-19 death and ICU bed prediction models in New York, revealing significant inaccuracies and emphasizing the importance of reliable data and real-time validation for trustworthy forecasts.

Contribution

It provides a detailed analysis of prediction inaccuracies and highlights the necessity for rigorous data validation and performance testing of models used in public health decision-making.

Findings

All models performed poorly in prediction accuracy.

Only one model accurately estimated uncertainty, but too late for early decisions.

The IHME ICU model was highly inaccurate until the pandemic waned.

Abstract

Forecasting models have been influential in shaping decision-making in the COVID-19 pandemic. However, there is concern that their predictions may have been misleading. Here, we dissect the predictions made by four models for the daily COVID-19 death counts between March 25 and June 5 in New York state, as well as the predictions of ICU bed utilisation made by the influential IHME model. We evaluated the accuracy of the point estimates and the accuracy of the uncertainty estimates of the model predictions. First, we compared the "ground truth" data sources on daily deaths against which these models were trained. Three different data sources were used by these models, and these had substantial differences in recorded daily death counts. Two additional data sources that we examined also provided different death counts per day. For accuracy of prediction, all models fared very poorly. Only 10.2% of the predictions fell within 10% of their training ground truth, irrespective of distance into the future. For accurate assessment of uncertainty, only one model matched relatively well the nominal 95% coverage, but that model did not start predictions until April 16, thus had no impact on early, major decisions. For ICU bed utilisation, the IHME model was highly inaccurate; the point estimates only started to match ground truth after the pandemic wave had started to wane. We conclude that trustworthy models require trustworthy input data to be trained upon. Moreover, models need to be subjected to prespecified real time performance tests, before their results are provided to policy makers and public health officials.