<p>The dots represent the observed frequency of pneumonia hospitalization in 10 groups divided by similar predicted probabilities, and a straight line through the dots represents the calibration slope. The bars represent 95% confidence intervals of the proportion of the observed frequency of pneumonia hospitalization in the 10 groups. The black dots and bars indicate our new model, the red indicate Comparative Model 1, and the blue indicate Comparative Model 2.</p
<p>A: Cohort-sequential model estimates for morbidity. B: Hockey stick regression model estimates fo...
<p>Black circles represent significant clusters (p<0.05) identified whilst imposing a 10% upper limi...
Calibration curve with bootstrap resampling validation for predicting the risk of hospitalization.</...
<p>The distortion curve indicates all cut-off points of our new model. The red line indicates Compar...
The solid red line denotes the median prediction, filled spaces denote the 99% credible interval and...
Calibration plots of the ischaemia (left) and bleeding (right) prediction models, showing the predic...
The solid red line denotes the median prediction, filled spaces denote the 99% credible interval and...
Observed hospitalization-level risk is plotted against predicted risk (top row) and patient-level me...
<p>This prediction is plotted with a 10% threshold for the percentage of patients positive on day-3 ...
<p>(A) Calibration plots with calibration slopes for men (B) for women in the model developing cohor...
Observed daily (orange dots) and simulated (blue bands) hospitalisation incidence January to April, ...
<p>The diagonal dashed line represents ideal prediction by the model, the pointed line predicted pro...
<p>(A) Calibration plots with calibration slopes for men and (B) for women in the validation cohort....
<p>(A) shows the distribution of daily incident cholera cases from uncontrolled epidemic simulations...
<p>Calibration plots between model-predicted and observed (LOESS smoothed) probabilities, for (a) en...
<p>A: Cohort-sequential model estimates for morbidity. B: Hockey stick regression model estimates fo...
<p>Black circles represent significant clusters (p<0.05) identified whilst imposing a 10% upper limi...
Calibration curve with bootstrap resampling validation for predicting the risk of hospitalization.</...
<p>The distortion curve indicates all cut-off points of our new model. The red line indicates Compar...
The solid red line denotes the median prediction, filled spaces denote the 99% credible interval and...
Calibration plots of the ischaemia (left) and bleeding (right) prediction models, showing the predic...
The solid red line denotes the median prediction, filled spaces denote the 99% credible interval and...
Observed hospitalization-level risk is plotted against predicted risk (top row) and patient-level me...
<p>This prediction is plotted with a 10% threshold for the percentage of patients positive on day-3 ...
<p>(A) Calibration plots with calibration slopes for men (B) for women in the model developing cohor...
Observed daily (orange dots) and simulated (blue bands) hospitalisation incidence January to April, ...
<p>The diagonal dashed line represents ideal prediction by the model, the pointed line predicted pro...
<p>(A) Calibration plots with calibration slopes for men and (B) for women in the validation cohort....
<p>(A) shows the distribution of daily incident cholera cases from uncontrolled epidemic simulations...
<p>Calibration plots between model-predicted and observed (LOESS smoothed) probabilities, for (a) en...
<p>A: Cohort-sequential model estimates for morbidity. B: Hockey stick regression model estimates fo...
<p>Black circles represent significant clusters (p<0.05) identified whilst imposing a 10% upper limi...
Calibration curve with bootstrap resampling validation for predicting the risk of hospitalization.</...