Learning models for forecasting hospital resource utilization for COVID-19 patients in Canada

Abstract

Hospitals in Canada are facing a crisis-level shortage of critical supplies and equipment during the COVID-19 pandemic. This motivates us to create predictive models that can use Canada COVID-19 data and pandemic-related factors to accurately forecast 5 quantities-three related to hospital resource utilization (i.e., the number of hospital beds, ICU beds, and ventilators that will be needed by COVID-19 patients) and two to the pandemic progress (i.e., the number of COVID-19 cases and COVID-19 deaths)-several weeks in advance. We developed a machine learning method that can use information (i.e., resource utilization, pandemic progress, population mobility, weather condition, and public policy) currently known about a region since March 2020, to learn multiple temporal convolutional network (TCN) models every week; each used for forecasting the weekly average of one of these 5 quantities in Canada (respectively, in six specific provinces) for each, in the next 1 (resp., 2,3,4) weeks. To validate the effectiveness of our method, we compared our method, versus other standard models, on the COVID-19 data and hospital resource data, on the tasks of predicting the 116 values (for Canada and its six most populated provinces), every week from Oct 2020 to July 2021, and the 20 values (only for Canada) for four specific times within 9 July to 31 Dec 2021. Experimental results show that our 4640 TCN models (each forecasting a regional target for a specific future time, on a specific date) can produce accurate 1,2,3,4-week forecasts of the utilization of every hospital resource and pandemic progress for each week from 2 Oct 2020 to 2 July 2021, as well as 80 TCN models for each of the four specified times within 9 July and 31 Dec 2021. Compared to other baseline and state-of-the-art predictive models, our TCN models yielded the best forecasts, with the lowest mean absolute percentage error (MAPE). Additional experiments, on the IHME COVID-19 data, demonstrate the effectiveness of our TCN models, in comparison with IHME forecasts. Each of our TCN models used a pre-defined set of features; we experimentally validate the effectiveness of these features by showing that these models perform better than other models that instead used other features. Overall, these experimental results demonstrate that our method can accurately forecast hospital resource utilization and pandemic progress for Canada and for each of the six provinces.

Figure 1

An example of target-region-horizon-specific forecast: forecasting the weekly average number of ICU beds (target) needed by COVID-19 patients in Ontario (region) for 4-week (horizon)—i.e., for 22 to 28 days after 20 Nov 2020 (that is, 12–18 / Dec).

Figure 2

ICU-ON-1, ICU-ON-2, ICU-ON-3, and ICU-ON-4 forecasts, each made on 20 Nov 2020.

Figure 3

TCN’s 1-,2-,3-,4-week forecasts of the weekly average number of hospital beds, ICU beds, ventilators, cases, and deaths in Canada between 2 Oct 2020 and 2 July 2021.

Figure 4

The true and ICU-ON-4 forecast number of ICU beds between 18 Dec 2020 and 22 Jan 2021.

Figure 5

Comparison of the performance (in terms of MAPE) of TCN models using the various factors as input.

Figure 6

Comparison of the performance (in terms of MAPE) of TCN models using various past values as input.

Figure 7

Models’ performance, in terms of MAPE (%) of the 1-,2-,3-,4-week forecasts in Canada.

Figure 8

Models’ performance on IHME data, in terms of MAPE (%) of the forecasts in Canada.

Figure 9

Forecasts made by TCN and PHAC-SEIR on 30 July, 10 Sept, 22 Oct, and 3 Dec 2021 in Canada.