Table 4 Predictabilities of the prediction models for the number of heatstrokes of hospital admission and death cases among 6 modelsa.

From: Heatstroke predictions by machine learning, weather information, and an all-population registry for 12-hour heatstroke alerts

 

GLM using WBGT only

GLM

GAM

RF

XGBoost

Consolidation of 16 GAMs specific to each cityb

 

The number of heatstrokes of hospital admission and death cases

Overall predictive accuracies per city per 12 h

   RMSE in training

0.68

0.62

0.62

0.3

0.44

0.61

   RMSE in testing

1.14

0.92

0.83

1.09

1.08

1.42

Predictive accuracies on days when the number of heatstrokes spikedc

   MAPE per 1-day (%)c in training

28.3

23.5

23.3

9.4

13.2

23.4

   MAPE per 1-day (%)c in testing

37.7

23.7

10.6

21.2

24.9

10.4

   Total absolute percentage error (%) in training

21.8

11.5

11.7

5.0

7.2

11.8

   Total absolute percentage error (%) in testing

42.9

25.8

7.5

26.9

29.7

2.7

  1. GLM generalized linear model, GAM generalized additive model, RF random forest, XGBoost extreme gradient boosting decision tree, WBGT wet bulb globe temperature, RMSE root-mean-square error, MAPE mean absolute percentage error.
  2. a Smaller RMSE, MAPE, and total absolute percentage error show better predictabilities.
  3. b Prediction models specific to each of the 16 cities were developed for city-specific prediction.
  4. c MAPE and total absolute percentage error were calculated after observed and predicted values were summed up per day (for MAPE) per the entire period (for total absolute percentage error) on days when the number of heatstrokes of hospital admission (i.e., moderate and severe cases) and death cases was 80th percentile (corresponding to 15.6 in 2015, 16 in 2016, 17 in 2017, and 23 in 2018) and over in each year. MAPE is a mean value of absolute errors divided by observed values.
Back to article page