N8 Digital Health Community Day
5,272 sound recordings of heartbeats.
1,568 different patients.
4 recording locations.
Patient information such as height, weight, age, …, and whether or not they had been diagnosed with a heart murmur.
1J. H. Oliveira et al. (2021). The CirCor DigiScope Dataset: From Murmur Detection to Murmur Classification. IEEE Journal of Biomedical and Health Informatics.
Aim: predict which time series of recordings belong to those with heart murmurs.
Calculate some features of the time series.
Use the features as input to classification algorithms instead of the raw time series data.
Some time series features will tell us useful things…
… some won’t.
Logistic Regression
Lasso Logistic Regression
Random Forests
Support Vector Machines
Naive Bayes
Accuracy: 0.81
ROC AUC: 0.65
Accuracy: 0.80
ROC AUC: 0.71
Issues with bias
Multinomial classification
Exploiting location information
Feature engineering