Learning (predictive) risk scores in the presence of censoring due to interventions

By Kirill Dyagilev, Suchi Saria. 2015

39 citations recorded by the source corpus.

A large and diverse set of measurements are regularly collected during a patient’s hospital stay to monitor their health status. Tools for integrating these measurements into severity scores, that accurately track changes in illness severity, can improve clinicians’ ability to provide timely interventions. Existing approaches for creating such scores either (1) rely on experts to fully specify the severity score, (2) infer a score using detailed models of disease progression, or (3) train a predictive score, using supervised learning, by regressing against a surrogate marker of severity such as the presence of downstream adverse events. The first approach does not extend to diseases where an accurate score cannot be elicited from experts. The second assumes that the progression of disease can be accurately modeled, limiting its application to populations with simple, well-understood disease dynamics. The third approach, also most commonly used, often produces scores that suffer from bias due to treatment-related censoring (Paxton et al. in AMIA annual symposium proceedings, American Medical Informatics Association, p 1109, 2013). Specifically, since the downstream outcomes used for their training are observed only noisily and are influenced by treatment administration patterns, these scores do not generalize well when treatment administration patterns change. We propose a novel ranking based framework for disease severity score learning (DSSL). DSSL exploits the following key observation: while it is challenging for experts to quantify the disease severity at any given time, it is often easy to compare the disease severity at two different times. Extending existing ranking algorithms, DSSL learns a function that maps a vector of patient’s measurements to a scalar severity score subject to two constraints. First, the resulting score should be consistent with the expert’s ranking of the disease severity state. Second, changes in score between consecutive periods should be smooth. We apply DSSL to the problem of learning a sepsis severity score using a large, real-world electronic health record dataset. The learned scores significantly outperform state-of-the-art clinical scores in ranking patient states by severity and in early detection of downstream adverse events. We also show that the learned disease severity trajectories are consistent with clinical expectations of disease evolution. Further, we simulate datasets containing different treatment administration patterns and show that DSSL shows better generalization performance to changes in treatment patterns compared to the above approaches.

Subfields: Artificial Intelligence, Epidemiology, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Epidemiology

In Statistics and Probability

Citations in the corpus

Counterfactual Normalization: Proactively Addressing Dataset Shift and Improving Reliability Using Causal Mechanisms (2018, background): “When this assumption does not hold, training with classical frameworks can yield unreliable models and, in the case of safety-critical applications like medicine, dangerous predictions (Dyagilev and Saria, 2015; Caruana et al., 2015; Schulam and Saria, 2017).”
Explainable machine learning predictions to help anesthesiologists prevent hypoxemia during surgery (2017, background): “that models can learn when an anesthesiologist is likely to intervene and hence lower the risk of an otherwise highrisk patient (26).”
What-If Reasoning with Counterfactual Gaussian Processes (2017, background): “19 to 20), and are therefore sensitive to small changes in treatment policy, which compromises their reliability (Dyagilev and Saria, 2016).”
The fused lasso penalty for learning interpretable medical scoring systems (2017, background): “Among interesting but not very related to this contribution papers, since our setting is not one with time series, we would like to mention [5] where risk scores (disease severity score learning, or DSSL) are learned from time series data to model progression of disease.”
A targeted real-time early warning score (TREWScore) for septic shock (2015, background): “Methods that assume that these patients are negative and do not account for the uncertainty in the outcome due to censoring can yield scores that underestimate the probability of a positive outcome (38, 39).”
Reliable Decision Support using Counterfactual Models (2017, methodology): “rk proposed here is increasingly pertinent. Others have noted this issue and studied the impact that action policies in the training data have on models ﬁt using supervised learning objectives (e.g., Dyagilev and Saria 2016). Counterfactual GPs (and counterfactual models more broadly) make predictio”
Clinical artificial intelligence quality improvement: towards continual monitoring and updating of AI algorithms in healthcare (2022, background): “Although confounding occurs in the absence of AI-based predictions 62,63 , the CMIs becomes much more severe when clinicians utilize AI algorithms in their decision-making process 64 – 66 .”