Learning (predictive) risk scores in the presence of censoring due to interventions
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Unbiased Recursive Partitioning: A Conditional Inference Framework
Hothorn, T., Hornik, K., & Zeileis, A. (2006) · Journal of Computational and Graphical Statistics · doi:10.1198/106186006x133933 · Cited by 4,021 · cited 1×
“The per-iteration computational complexity of this approach is equivalent to the computational complexity of building a single regression tree, which is | T | log | T | (Hothorn et al, 2006), where | T | is the number of unique tuples in the set O ∪ S of tuple pairs.”
BackgroundLearning to rank using gradient descent
Burges, C., Shaked, T., Renshaw, E., Lazier, A., Deeds, M., Hamilton, N., & Hullender, G. (2005) · Proceedings of the 22nd international conference on Machine learning - ICML '05 · doi:10.1145/1102351.1102363 · Cited by 2,836
Saeed, M., Villarroel, M., Reisner, A. T., Clifford, G., Lehman, L.-W., Moody, G., Heldt, T., Kyaw, T. H., Moody, B., & Mark, R. G. (2011) · Critical Care Medicine · doi:10.1097/ccm.0b013e31820a92c6 · Cited by 1,162
(2006) · doi:10.7551/mitpress/7503.003.0029 · Cited by 753
A targeted real-time early warning score (TREWScore) for septic shock.
Henry, K. E., Hager, D. N., Pronovost, P. J., & Saria, S. (2015) · Science Translational Medicine · doi:10.1126/scitranslmed.aab3719 · Cited by 598 · cited 1×
“Prior Art: Historically, severity scores have been designed in a number of different ways (Ghanem-Zoubi et al, 2011).”
BackgroundSelf-citationPirracchio, R., Petersen, M. L., Carone, M., Rigon, M. R., Chevret, S., & van der Laan, M. J. (2015) · The Lancet Respiratory Medicine · doi:10.1016/s2213-2600(14)70239-5 · Cited by 374 · cited 1×
“Others have similarly used downstream adverse events such as the development of Clostridium difficile infection (Wiens et al, 2012), septic shock (Ho et al, 2012), morbidity (Saria et al, 2010b), and mortality (Pirracchio et al, 2015) as surrogate sources of supervision for training severity scores.”
Method
Cited by
Explainable machine-learning predictions for the prevention of hypoxaemia during surgery
Lundberg, S. M., Nair, B., Vavilala, M. S., Horibe, M., Eisses, M. J., Adams, T., Liston, D. E., Low, D. K.-W., Newman, S.-F., Kim, J., et al. (2018) · Nature Biomedical Engineering · doi:10.1038/s41551-018-0304-0 · Cited by 1,967
A targeted real-time early warning score (TREWScore) for septic shock.
Henry, K. E., Hager, D. N., Pronovost, P. J., & Saria, S. (2015) · Science Translational Medicine · doi:10.1126/scitranslmed.aab3719 · Cited by 598
“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).”
BackgroundSelf-citationFeng, J., Phillips, R. V., Malenica, I., Bishara, A., Hubbard, A. E., Celi, L. A., & Pirracchio, R. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00611-y · Cited by 423
“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 .”
BackgroundShimabukuro, D. W., Barton, C. W., Feldman, M. D., Mataraso, S. J., & Das, R. (2017) · BMJ Open Respiratory Research · doi:10.1136/bmjresp-2017-000234 · Cited by 382
Zhan, A., Mohan, S., Tarolli, C., Schneider, R. B., Adams, J. L., Sharma, S., Elson, M. J., Spear, K. L., Glidden, A. M., Little, M. A., et al. (2018) · JAMA Neurology · doi:10.1001/jamaneurol.2018.0809 · Cited by 381
Self-citation
Metadata
- Authors
- Dyagilev, K., & Saria, S.
- Venue
- Machine Learning
- Published
- 2015-10-20
- Volume
- 102
- Issue
- 3
- Pages
- 323-348
- ISSN
- 0885-6125 (ISSN-L)
- 1573-0565
- OpenAlex
- W985756785
- Cited by
- 36
- References
- 6
- FWCI
- 4.69
- Type
- journal article
- Language
- en
- Open access
- bronze
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning (predictive) risk scores in the presence of censoring due to interventions. https://app.cochat.ai/papers/10.1007/s10994-015-5527-7
- The paper
- Dyagilev, K., & Saria, S. (2016). Learning (predictive) risk scores in the presence of censoring due to interventions. Machine Learning. https://doi.org/10.1007/s10994-015-5527-7
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.