Leveraging implicit expert knowledge for non-circular machine learning in sepsis prediction
Sepsis is the leading cause of death in non-coronary intensive care units. Moreover, a delay of antibiotic treatment of patients with severe sepsis by only few hours is associated with increased mortality. This insight makes accurate models for early prediction of sepsis a key task in machine learni...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
24 September 2019
|
| In: |
Artificial intelligence in medicine
Year: 2019, Volume: 100 |
| ISSN: | 1873-2860 |
| DOI: | 10.1016/j.artmed.2019.101725 |
| Online Access: | Verlag, Volltext: https://doi.org/10.1016/j.artmed.2019.101725 Verlag, Volltext: http://www.sciencedirect.com/science/article/pii/S0933365718305700 
|
| Author Notes: | Shigehiko Schamoni, Holger A. Lindner, Verena Schneider-Lindner, Manfred Thiel, Stefan Riezler |
| Summary: | Sepsis is the leading cause of death in non-coronary intensive care units. Moreover, a delay of antibiotic treatment of patients with severe sepsis by only few hours is associated with increased mortality. This insight makes accurate models for early prediction of sepsis a key task in machine learning for healthcare. Previous approaches have achieved high AUROC by learning from electronic health records where sepsis labels were defined automatically following established clinical criteria. We argue that the practice of incorporating the clinical criteria that are used to automatically define ground truth sepsis labels as features of severity scoring models is inherently circular and compromises the validity of the proposed approaches. We propose to create an independent ground truth for sepsis research by exploiting implicit knowledge of clinical practitioners via an electronic questionnaire which records attending physicians’ daily judgements of patients’ sepsis status. We show that despite its small size, our dataset allows to achieve state-of-the-art AUROC scores. An inspection of learned weights for standardized features of the linear model lets us infer potentially surprising feature contributions and allows to interpret seemingly counterintuitive findings. |
|---|---|
| Item Description: | Gesehen am 25.11.2019 |
| Physical Description: | Online Resource |
| ISSN: | 1873-2860 |
| DOI: | 10.1016/j.artmed.2019.101725 |