Skip to main content

Table 4 Final predictive models

From: Emergency teleradiological activity is an epidemiological estimator and predictor of the covid-19 pandemic in mainland France

Model

Equation

MAPE in train set

Ljung–Box Test

MAPE in test set

CT(t)

\(H\left( t \right) = ~ - {\boldsymbol{3315.30}} + {\boldsymbol{17.03}} \times ~{\boldsymbol{CT}}\left( {\boldsymbol{t}} \right) + {\boldsymbol{196.63}} \times {\boldsymbol{Ld}}\left( {\boldsymbol{t}} \right) + ~\varepsilon \left( t \right) + ~0.84 \times \varepsilon \left( {t - 1} \right)\),

with \(~\varepsilon \left( t \right)~ \sim {\mathcal{N}}\left( {0,~3420285} \right)\)

6.82

0.0490*

20.02

CT(t − 1)

\(H\left( t \right) = {\boldsymbol{7.05}} \times {\boldsymbol{CT}}\left( {\boldsymbol{t}} - {\boldsymbol{1}} \right) + {\boldsymbol{889.49}} \times {\boldsymbol{Ld}}\left( {\boldsymbol{t}} \right) + \varepsilon \left( t \right) + ~2.27 \times \eta \left( {t - 1} \right) - ~1.93 \times \eta \left( {t - 2} \right) + 0.59 \times ~\eta \left( {t - 3} \right)\),

with \(~\varepsilon \left( t \right)~ \sim {\mathcal{N}}\left( {0,~924814} \right)\)

25.82

0.0387*

20.72

CT(t − 2)

\(H\left( t \right) = {\boldsymbol{29227}}.{\boldsymbol{22}} - {\boldsymbol{2.68}} \times \user2{CT}\left( {{\boldsymbol{t}} -{\boldsymbol{ 2}}} \right) - {\boldsymbol{1024.94}} \times {\boldsymbol{Ld}}\left({\boldsymbol{t}} \right) + ~\varepsilon \left( t \right) + ~1.95 \times \eta \left( {t - 1} \right) - ~0.96 \times \eta \left( {t - 2} \right)\),

with \(~\varepsilon \left( t \right)~ \sim{\mathcal{N}}\left( {0,~968004} \right)\)

30.85

0.2406

127.13

CT(t − 1), CT(t − 2), H(t − 1), H(t − 2)

\(H\left( t \right) = {\boldsymbol{8.60}} \times {\boldsymbol{CT}}\left( {{\boldsymbol{t}} - {\boldsymbol{1}}} \right) -{\boldsymbol{ 4.27}} \times {\boldsymbol{CT}}\left( {\boldsymbol{t}} -{\boldsymbol{ 2}} \right) + {\boldsymbol{149.89}} \times {\boldsymbol{Ld}}\left( {\boldsymbol{t}} \right) + {\boldsymbol{0.97}} \times {\boldsymbol{H}}\left( {{\boldsymbol{t}} -{\boldsymbol{1}}} \right) - {\boldsymbol{0.42}} \times {\boldsymbol{H}}\left( {\boldsymbol{t}} -{\boldsymbol{ 2}} \right) + ~\varepsilon \left( t \right) + ~1.83 \times \eta \left( {t - 1} \right)\),

with \(~\varepsilon \left( t \right)~ \sim{\mathcal{N}}\left( {0,~479558} \right)\)  

24.40

0.1182

5.09

  1. The ‘model’ column gives the predictors entered in the algorithm to predict the number of hospitalisations for the week ‘t’. Hence, ‘t − 1’ and ‘t − 2’ are one and two weeks before (i.e. lag − 1 and lag − 2)
  2. The terms in bold correspond to the regression part of the model, and the other terms to the error η(t) which can be expressed with an auto-regressive integrated moving average (ARIMA) model with ε(t) an uncorrelated error term (i.e. white noise) following a normal law N with variance in parentheses
  3. CT(x), where x in {t, t − 1, t − 2}, corresponds to the number of CT-scans performed in the COVID-19 teleradiological emergency workflow during the week ‘x
  4. H(x′), where x′ in {t − 1, t − 2}, corresponds to the number of patients hospitalised in mainland French hospitals during the week ‘x′’
  5. Ld(t) is a binary variable that takes the value 1 if France is under national lockdown and 0 otherwise
  6. ARIMA auto-regressive integrative moving average, MAPE mean absolute percentage error
  7. *p < 0.05