Online Retraining

Select a model.
Select a previously trained model.
Train a new predictive model for Sleep Staging or Sleep Disordered Breathing. While training is in progress, you may navigate away from the page or close your browser. Trained models may be saved for later use in the Analysis section of the platform. Select an existing model to test on out-of-sample data, or configure and train a new model.

Sleep Staging

Model configuration.
Configuration
Select between training a binary classifier to predict whether the AHI of a child is at least 5 or to classify recording as Sleep or Wake, or a regressor to produce a point estimate of the AHI. Select a Linear, Gaussian, or Polynomial kernel. The Linear kernel allows for better model interpretability, while the Gaussian kernel is more flexible and may capture non-linearities. Polynomial kernels offer a balance in complexity and the degree of non-linearity is configurable.Cost-sensitive Support Vector Classification may be used for imbalanced datasets. When different costs are applied, rescaling occurs so that the average C value across both classes is equal to the C value that is set during the hyperparameter search.
Model Information
Feature Selection
Feature Description
Sats Mean Ratio Ratio of the first statistical moment of the oxygen saturation in the current epoch compared to the total recording.
Sats Variance Ratio Ratio of the second statistical moment in the oxygen saturation.
Sats Skewness Ratio Ratio of the third statistical moment in the oxygen saturation.
Sats Kurtosis Ratio Ratio of the fourth statistical moment in the oxygen saturation.
Sats CTM1 Ratio Ratio of the oxygen saturation Central Tendency Measure where the radius equals 1. A measure of variability.
Sats CTM3 Ratio Ratio of the oxygen saturation Central Tendency Measure where the radius equals 3. A measure of variability.
Sats CTM6 Ratio Ratio of the oxygen saturation Central Tendency Measure where the radius equals 6. A measure of variability.
Sats Complexity Ratio Ratio of the Lempel-Ziv Complexity of the binarised oxygen saturation. A measure of repeating sequences.
Sats RMSSD Ratio Ratio of the root mean square of successive differences in the oxygen saturation. RMSSD is commonly used as a measure of heart rate variability.
Sats Shannon Entropy Ratio Ratio of the Shannon entropy of the oxygen saturation. A static measure of regularity.
Sats Permutation Entropy Ratio of the Permutation entropy of the oxygen saturation where the embedding delay equals 1, and m equals 3. A dynamic measure of regularity.
Sats Sample Entropy Ratio of the Sample entropy of the oxygen saturation where the template length equals 2, and the tolerance equals the product of 0.2 and the standard deviation of the oxygen saturation. A dynamic measure of regularity.
Sats AutoCorr 1 Ratio Ratio of the first-order autocorrelation of the oxygen saturation. Measures the correlation of the oxygen saturation with a delayed copy of itself.
Sats AutoCorr 2 Ratio Ratio of the second-order autocorrelation of the oxygen saturation. Measures the correlation of the oxygen saturation with a delayed copy of itself.
Sats AutoCorr 3 Ratio Ratio of the third-order autocorrelation of the oxygen saturation. Measures the correlation of the oxygen saturation with a delayed copy of itself.
Sats AutoCorr 4 Ratio Ratio of the fourth-order autocorrelation of the oxygen saturation. Measures the correlation of the oxygen saturation with a delayed copy of itself.
Pulse Rate Mean Ratio Ratio of the first statistical moment of the pulse rate.
Pulse Rate Variance Ratio Ratio of the second statistical moment in the pulse rate.
Pulse Rate Skewness Ratio Ratio of the third statistical moment in the pulse rate.
Pulse Rate Kurtosis Ratio Ratio of the fourth statistical moment in the pulse rate.
Pulse Rate CTM1 Ratio Ratio of the pulse rate Central Tendency Measure where the radius equals 1. A measure of variability.
Pulse Rate CTM3 Ratio Ratio of the pulse rate Central Tendency Measure where the radius equals 3. A measure of variability.
Pulse Rate CTM6 Ratio Ratio of the pulse rate Central Tendency Measure where the radius equals 6. A measure of variability.
Pulse Rate Complexity Ratio Ratio of the Lempel-Ziv Complexity of the binarised pulse rate. A measure of repeating sequences.
Pulse Rate RMSSD Ratio Ratio of the root mean square of successive differences in the pulse rate. RMSSD is commonly used as a measure of heart rate variability.
Pulse Rate Shannon Entropy Ratio Ratio of the Shannon entropy of the pulse rate. A static measure of regularity.
Pulse Rate Permutation Entropy Ratio of the Permutation entropy of the pulse rate where the embedding delay equals 1, and m equals 3. A dynamic measure of regularity.
Pulse Rate Sample Entropy Ratio of the Sample entropy of the pulse rate where the template length equals 2, and the tolerance equals the product of 0.2 and the standard deviation of the oxygen saturation. A dynamic measure of regularity.
Pulse Rate AutoCorr 1 Ratio Ratio of the first-order autocorrelation of the pulse rate. Measures the correlation of the pulse rate with a delayed copy of itself.
Pulse Rate AutoCorr 2 Ratio Ratio of the second-order autocorrelation of the pulse rate. Measures the correlation of the pulse rate with a delayed copy of itself.
Pulse Rate AutoCorr 3 Ratio Ratio of the third-order autocorrelation of the pulse rate. Measures the correlation of the pulse rate with a delayed copy of itself.
Pulse Rate AutoCorr 4 Ratio Ratio of the fourth-order autocorrelation of the pulse rate. Measures the correlation of the pulse rate with a delayed copy of itself.
Select training data.
Select a precomputed dataset to use for model training. Only datasets specifically configured for training are available. Cross-validation results are available during model testing.
Training dashboard.
Bayesian Optimisation
Number of objective function evaluations.
Number of candidates evaluated per iteration.
Configure the Bayesian Optimiser and search space for each hyperparameter. The number of iterations determines how many points are evaluated, and the number of candidates controls the resolution of the acquisition search.
Training Progress
Training in progress. You may use the analysis functionality or close your browser.

Optimiser Iteration 18 of 30

Current Parameters: C=82.927
0
5
10
15
20
25
30
Iteration
Misclassification Rate (%)
Bayesian Optimisation is used to search the hyperparameter ranges provided. This process attempts to balance exploration and exploitation to select the optimal values for the trained model. Gaussian Process Regression (GPR) and the Expected Improvement acquisition function are used. For each set of hyperparameters, models are trained using the appropriate solver. K-fold cross-validation is used to produce a validation error which is input into the GPR that underpins the Bayesian Optimisation. The most optimal hyperparameters, as determined by the optimisation process, are then used to train the final model. Models are calibrated using cross-validation data when training is complete so that predictions are accompanied by estimates of uncertainty. A trained Ridge Logistic Regression model is embedded within Gaussian Process and Support Vector Classifiers to produce a probability point-estimate during prediction, and a Laplace distribution is computed and embedded within Gradient Boosting, Linear, and Support Vector Regressors to produce confidence intervals that accompany the AHI point-estimate during prediction. Trained models may be saved and are immediately accessible through the Analysis and Batch Analysis areas of the platform.