# Leveraging Implicit Expert Knowledge for Non-Circular Machine Learning in Sepsis Prediction

arXiv: https://arxiv.org/abs/1909.09557 · HTML: https://mlsanity.com/paper/1909.09557/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2019.

## Built on by (most cited first, 5 of 5)

- [What Makes An Expert? Reviewing How ML Researchers Define "Expert"](https://mlsanity.com/paper/2411.00179/) (2024)
- [Ensembling Neural Networks for Improved Prediction and Privacy in Early Diagnosis of Sepsis](https://mlsanity.com/paper/2209.00439/) (2022)
- [Early Prediction of Causes (not Effects) in Healthcare by Long-Term Clinical Time Series Forecasting](https://mlsanity.com/paper/2408.03816/) (2024)
- [The Consequences of the Framing of Machine Learning Risk Prediction Models: Evaluation of Sepsis in General Wards](https://mlsanity.com/paper/2101.10790/) (2021)
- [False perfection in machine prediction: Detecting and assessing circularity problems in machine learning](https://mlsanity.com/paper/2106.12417/) (2021)

## Abstract (arXiv)

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.