Timezone: »

Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
Patrick Schwab · Emanuela Keller · Carl Muroi · David J. Mack · Christian Strässle · Walter Karlen

Thu Jul 12 09:15 AM -- 12:00 PM (PDT) @ Hall B #108

Patients in the intensive care unit (ICU) require constant and close supervision. To assist clinical staff in this task, hospitals use monitoring systems that trigger audiovisual alarms if their algorithms indicate that a patient's condition may be worsening. However, current monitoring systems are extremely sensitive to movement artefacts and technical errors. As a result, they typically trigger hundreds to thousands of false alarms per patient per day - drowning the important alarms in noise and adding to the exhaustion of clinical staff. In this setting, data is abundantly available, but obtaining trustworthy annotations by experts is laborious and expensive. We frame the problem of false alarm reduction from multivariate time series as a machine-learning task and address it with a novel multitask network architecture that utilises distant supervision through multiple related auxiliary tasks in order to reduce the number of expensive labels required for training. We show that our approach leads to significant improvements over several state-of-the-art baselines on real-world ICU data and provide new insights on the importance of task selection and architectural choices in distantly supervised multitask learning.

Author Information

Patrick Schwab (ETH Zurich)
Emanuela Keller (University Hospital Zurich)
Carl Muroi (University Hospital Zurich)
David J. Mack (University Hospital Zurich)
Christian Strässle (University Hospital Zurich)
Walter Karlen (ETH Zurich)

Related Events (a corresponding poster, oral, or spotlight)