Using Under-Trained Deep Ensembles to Learn Under Extreme Label Noise: A Case Study for Sleep Apnea Detection

Improper or erroneous labelling can pose a hindrance to reliable generalization for supervised learning. This can have negative consequences, especially for critical fields such as healthcare. We propose an effective new approach for learning under extreme label noise for medical applications like sleep apnea, that is based on under-trained deep ensembles. Each ensemble member is trained with a subset of the training data, to acquire a general overview of the decision boundary separation, without focusing on potentially erroneous details. The accumulated knowledge of the ensemble is combined to form new labels, that determine a better class separation than the original labels. A new model is trained with these labels to generalize reliably despite the label noise. We evaluate our approach on the tasks of sleep apnea detection and sleep apnea severity classification, and observe performance improvement in kappa from 0.02 up-to 0.55.

Automated summary

Improper or erroneous labelling can hinder reliable generalization for supervised learning, especially in critical fields like healthcare. This study presents an effective approach for learning under extreme label noise in medical applications, utilizing under-trained deep ensembles to improve generalization. Performance improvement from 0.02 to 0.55 was observed in sleep apnea detection tasks.