Validation of Prediction Models for Critical Care Outcomes Using Natural Language Processing of Electronic Health Record Data
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Importance: Accurate prediction of outcomes among patients in intensive care units (ICUs) is important for clinical research and monitoring care quality. Most existing prediction models do not take full advantage of the electronic health record, using only the single worst value of laboratory tests and vital signs and largely ignoring information present in free-text notes. Whether capturing more of the available data and applying machine learning and natural language processing (NLP) can improve and automate the prediction of outcomes among patients in the ICU remains unknown. Objectives: To evaluate the change in power for a mortality prediction model among patients in the ICU achieved by incorporating measures of clinical trajectory together with NLP of clinical text and to assess the generalizability of this approach. Design, Setting, and Participants: This retrospective cohort study included 101 196 patients with a first-time admission to the ICU and a length of stay of at least 4 hours. Twenty ICUs at 2 academic medical centers (University of California, San Francisco [UCSF], and Beth Israel Deaconess Medical Center [BIDMC], Boston, Massachusetts) and 1 community hospital (Mills-Peninsula Medical Center [MPMC], Burlingame, California) contributed data from January 1, 2001, through June 1, 2017. Data were analyzed from July 1, 2017, through August 1, 2018. Main Outcomes and Measures: In-hospital mortality and model discrimination as assessed by the area under the receiver operating characteristic curve (AUC) and model calibration as assessed by the modified Hosmer-Lemeshow statistic. Results: Among 101 196 patients included in the analysis, 51.3% (n = 51 899) were male, with a mean (SD) age of 61.3 (17.1) years; their in-hospital mortality rate was 10.4% (n = 10 505). A baseline model using only the highest and lowest observed values for each laboratory test result or vital sign achieved a cross-validated AUC of 0.831 (95% CI, 0.830-0.832). In contrast, that model augmented with measures of clinical trajectory achieved an AUC of 0.899 (95% CI, 0.896-0.902; P < .001 for AUC difference). Further augmenting this model with NLP-derived terms associated with mortality further increased the AUC to 0.922 (95% CI, 0.916-0.924; P < .001). These NLP-derived terms were associated with improved model performance even when applied across sites (AUC difference for UCSF: 0.077 to 0.021; AUC difference for MPMC: 0.071 to 0.051; AUC difference for BIDMC: 0.035 to 0.043; P < .001) when augmenting with NLP at each site. Conclusions and Relevance: Intensive care unit mortality prediction models incorporating measures of clinical trajectory and NLP-derived terms yielded excellent predictive performance and generalized well in this sample of hospitals. The role of these automated algorithms, particularly those using unstructured data from notes and other sources, in clinical research and quality improvement seems to merit additional investigation.
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
Hosmer, D. W., Lemeshow, S., & Sturdivant, R. X. (2013) · Wiley Series in Probability and Statistics · doi:10.1002/9781118548387 · Cited by 13,861
Introduction to information retrieval
(2009) · Choice Reviews Online · doi:10.5860/choice.46-2715 · Cited by 12,278
Introduction to Information Retrieval
Manning, C. D., Raghavan, P., & Schütze, H. (2008) · doi:10.1017/cbo9780511809071 · Cited by 11,288
Le Gall, J.-R. (1993) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.270.24.2957 · Cited by 7,773
Saito, T., & Rehmsmeier, M. (2015) · PLOS ONE · doi:10.1371/journal.pone.0118432 · Cited by 5,309
A few useful things to know about machine learning
Domingos, P. (2012) · Communications of the ACM · doi:10.1145/2347736.2347755 · Cited by 3,326
Scalable and accurate deep learning with electronic health records
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., Liu, P. J., Liu, X., Marcus, J., Sun, M., et al. (2018) · npj Digital Medicine · doi:10.1038/s41746-018-0029-1 · Cited by 2,648
Bias in error estimation when using cross-validation for model selection
Varma, S., & Simon, R. (2006) · BMC Bioinformatics · doi:10.1186/1471-2105-7-91 · Cited by 2,485
Zimmerman, J. E., Kramer, A. A., McNair, D. S., & Malila, F. M. (2006) · Critical Care Medicine · doi:10.1097/01.ccm.0000215112.84523.f0 · Cited by 1,764 · cited 1×
“19,20 Overall, our approach thus differs from existing models in the following 2 ways: (1) by using information present across all observations of each laboratory test or vital sign to build measures of clinical trajectory; and (2) by adding variables derived via NLP.”
MethodKramer, A. A., & Zimmerman, J. E. (2007) · Critical Care Medicine · doi:10.1097/01.ccm.0000275267.64078.b0 · Cited by 886
Cited by
Giannini, H. M., Ginestra, J. C., Chivers, C., Draugelis, M., Hanish, A., Schweickert, W. D., Fuchs, B. D., Meadows, L., Lynch, M., Donnelly, P. J., et al. (2019) · Critical Care Medicine · doi:10.1097/ccm.0000000000003891 · Cited by 269
Sarkar, R., Martin, C., Mattie, H., Gichoya, J. W., Stone, D. J., & Celi, L. A. (2021) · The Lancet Digital Health · doi:10.1016/s2589-7500(21)00022-4 · Cited by 85
Mao, C., Xu, J., Rasmussen, L., Li, Y., Adekkanattu, P., Pacheco, J., Bonakdarpour, B., Vassar, R., Shen, L., Jiang, G., et al. (2023) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2023.104442 · Cited by 67
Metadata
- Authors
- Marafino, B. J., Park, M., Davies, J. M., Thombley, R., Luft, H. S., Sing, D. C., Kazi, D. S., DeJong, C., Boscardin, W. J., Dean, M. L., & Dudley, R. A.
- Venue
- JAMA Network Open
- Publisher
- American Medical Association (AMA)
- Published
- 2018-12-21
- Volume
- 1
- Issue
- 8
- Pages
- e185097
- ISSN
- 2574-3805 (ISSN-L)
- OpenAlex
- W2906103632
- Cited by
- 118
- References
- 12
- FWCI
- 5.38
- Type
- journal article
- Language
- en
- Open access
- gold
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
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.