Leveraging Deep Representations of Radiology Reports in Survival Analysis for Predicting Heart Failure Patient Mortality
Open accessAbstract
Utilizing clinical texts in survival analysis is difficult because they are largely unstructured. Current automatic extraction models fail to capture textual information comprehensively since their labels are limited in scope. Furthermore, they typically require a large amount of data and high-quality expert annotations for training. In this work, we present a novel method of using BERT-based hidden layer representations of clinical texts as covariates for proportional hazards models to predict patient survival outcomes. We show that hidden layers yield notably more accurate predictions than predefined features, outperforming the previous baseline model by 5.7% on average across C-index and time-dependent AUC. We make our work publicly available at https://github.com/bionlplab/heart_failure_mortality.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
A prior work found that CheXbert model embeddings led to better prediction performance than the features of 14 observations extracted by CheXpert for heart failure patient mortality prediction.
“In their experiments, they also found that these hidden features led to better prediction performance than the features of 14 observations extracted by CheXpert.”
From Evaluating progress in automatic chest X-ray radiology report generation (2023) · cites this paper as [41]
The Results & Discussions section says CheXbert’s hidden representations yielded more accurate mortality predictions than predefined features. The Methods > Model section identifies the comparator as 14 findings defined by CheXpert, but says those features were extracted using CheXbert—not CheXpert. Page numbers are unavailable in our copy. (LLM, conf=0.88)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Regression Models and Life-Tables
Cox, D. R. (1972) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1972.tb00899.x · Cited by 39,793 · see citing works
Regression Models and Life-Tables
Cox, D. R. (1992) · Springer Series in Statistics · doi:10.1007/978-1-4612-4380-9_37 · Cited by 26,297 · see citing works
Nishimura, R., Osako, T., Nishiyama, Y., Tashima, R., Nakano, M., Fujisue, M., Toyozumi, Y., & Arima, N. (2013) · Oncology · doi:10.1159/000353099 · Cited by 13,239 · see citing works
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218 · see citing works
Evaluating the Yield of Medical Tests
Harrell, F. E. (1982) · JAMA: The Journal of the American Medical Association · doi:10.1001/jama.1982.03320430047030 · Cited by 3,490 · see citing works
Katzman, J. L., Shaham, U., Cloninger, A., Bates, J., Jiang, T., & Kluger, Y. (2018) · BMC Medical Research Methodology · doi:10.1186/s12874-018-0482-1 · Cited by 1,995 · see citing works
Alsentzer, E., Murphy, J., Boag, W., Weng, W.-H., Jindi, D., Naumann, T., & McDermott, M. (2019) · Proceedings of the 2nd Clinical Natural Language Processing Workshop · doi:10.18653/v1/w19-1909 · Cited by 1,736 · see citing works
Uno, H., Cai, T., Pencina, M. J., D'Agostino, R. B., & Wei, L. J. (2011) · Statistics in Medicine · doi:10.1002/sim.4154 · Cited by 1,535 · see citing works
Survival Model Predictive Accuracy and ROC Curves
Heagerty, P. J., & Zheng, Y. (2005) · Biometrics · doi:10.1111/j.0006-341x.2005.030814.x · Cited by 1,471 · see citing works
Pencina, M. J., & D’Agostino, R. B. (2004) · Statistics in Medicine · doi:10.1002/sim.1802 · Cited by 1,446 · see citing works
A Simple Algorithm for Identifying Negated Findings and Diseases in Discharge Summaries
Chapman, W. W., Bridewell, W. B., Hanbury, P., Cooper, G. F., & Buchanan, B. G. (2001) · Journal of Biomedical Informatics · doi:10.1006/jbin.2001.1029 · Cited by 1,121 · see citing works
Peng, Y., Yan, S., & Lu, Z. (2019) · Proceedings of the 18th BioNLP Workshop and Shared Task · doi:10.18653/v1/w19-5006 · Cited by 899 · see citing works
Self-citationTime-dependent ROC curve analysis in medical research: current methods and applications
Kamarudin, A. N., Cox, T. F., & Kolamunnage‐Dona, R. (2017) · BMC Medical Research Methodology · doi:10.1186/s12874-017-0332-6 · Cited by 839 · see citing works
DeepHit: A Deep Learning Approach to Survival Analysis With Competing Risks
Lee, C., Zame, W. R., Yoon, J., & van der Schaar, M. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11842 · Cited by 651 · see citing works
A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme
Lao, J., Chen, Y., Li, Z.-C., Li, Q., Zhang, J., Liu, J., & Zhai, G. (2017) · Scientific Reports · doi:10.1038/s41598-017-10649-8 · Cited by 630 · see citing works
CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison
Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R., Shpanskaya, K., et al. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.3301590 · Cited by 392 · see citing works
Time-to-Event Prediction with Neural Networks and Cox RegressionPreprint
Kvamme, H., Borgan, Ø., & Scheel, I. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.00825 · Cited by 224 · see citing works
NegBio: a high-performance tool for negation and uncertainty detection in radiology reports
Peng, Y., Wang, X., Lu, L., Bagheri, M., Summers, R., & Lu, Z. (2017) · arXiv · doi:10.48550/arxiv.1712.05898 · Cited by 175 · see citing works
Self-citationSprung, C. L., Joynt, G. M., Christian, M. D., Truog, R. D., Rello, J., & Nates, J. L. (2020) · Critical Care Medicine · doi:10.1097/ccm.0000000000004410 · Cited by 158 · see citing works
Deep Survival AnalysisPreprint
Ranganath, R., Perotte, A., Elhadad, N., & Blei, D. M. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.02158 · Cited by 124 · see citing works
Deep Recurrent Survival Analysis
Ren, K., Qin, J., Zheng, L., Yang, Z., Zhang, W., Qiu, L., & Yu, Y. H. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33014798 · Cited by 117 · see citing works
Nielsen, A. B., Thorsen‐Meyer, H., Belling, K., Nielsen, A. P., Thomas, C. E., Chmura, P. J., Lademann, M., Moseley, P. L., Heimann, M., Dybdahl, L., et al. (2019) · The Lancet Digital Health · doi:10.1016/s2589-7500(19)30024-x · Cited by 109 · see citing works
Smit, A., Jain, S., Rajpurkar, P., Pareek, A., Ng, A. Y., & Lungren, M. P. (2020) · arXiv · doi:10.48550/arxiv.2004.09167 · Cited by 103 · see citing works
RNN-SURV: A Deep Recurrent Model for Survival Analysis
Giunchiglia, E., Nemchenko, A., & van der Schaar, M. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-01424-7_3 · Cited by 90 · see citing works
Time-to-Event Prediction with Neural Networks and Cox Regression
Kvamme, H., Borgan, Ø., & Scheel, I. (2019) · NORA - Norwegian Open Research Archives · Cited by 63 · see citing works
Pandey, M. K., Xu, Z., Sholle, E., Maliakal, G., Singh, G., Fatima, Z., Larine, D., Lee, B. C., Wang, J., van Rosendael, A. R., et al. (2020) · PLoS ONE · doi:10.1371/journal.pone.0236827 · Cited by 27 · see citing works
Self-citationMcDermott, M. B. A., Hsu, T. M. H., Weng, W.-H., Ghassemi, M., & Szolovits, P. (2020) · arXiv · doi:10.48550/arxiv.2006.15229 · Cited by 22 · see citing works
Various Approaches for Predicting Stroke Prognosis using Magnetic Resonance Imaging Text Records
Heo, T.-S., Kim, C., Choi, J.-M., Jeong, Y.-S., & Kim, Y.-S. (2020) · Clinical Natural Language Processing Workshop (ClinicalNLP) · doi:10.18653/v1/2020.clinicalnlp-1.1 · Cited by 3 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Evaluating progress in automatic chest X-ray radiology report generation
Yu, F., Endo, M., Krishnan, R., Pan, I., Tsai, A., Reis, E. P., Fonseca, E. K. U. N., Lee, H. M. H., Abad, Z. S. H., Ng, A. Y., et al. (2023) · Patterns · doi:10.1016/j.patter.2023.100802 · Cited by 200 · see citing works
“for heart failure patient mortality prediction.(41) In their experiments, they also found that these hidden features led to better prediction performance than the features of 14 observations extracted by CheXpert.”
Self-citationSurvival prediction of heart failure patients using motion-based analysis method
Guo, S., Zhang, H., Gao, Y., Wang, H., Xu, L., Gao, Z., Guzzo, A., & Fortino, G. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107547 · Cited by 24 · see citing works
Quality Management of Pulmonary Nodule Radiology Reports Based on Natural Language Processing
Fei, X., Chen, P., Wei, L., Huang, Y. M., Xin, Y., & Li, J. (2022) · Bioengineering · doi:10.3390/bioengineering9060244 · Cited by 12 · see citing works
Ando, K., Okumura, T., Komachi, M., Horiguchi, H., & Matsumoto, Y. (2022) · PLOS Digital Health · doi:10.1371/journal.pdig.0000099 · Cited by 7 · see citing works
Yu, Y., Wang, J., Liu, W., Mien, I. H., Krishnaswamy, P., Yang, X., & Cheng, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130018 · Cited by 5 · see citing works
Rui, S., Su, H., Xiang, J., Wu, L., & Wang, X. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461484 · Cited by 1 · see citing works
Multimodal Graph Convolutional Networks for Patient Survival Analysis
Guo, W., & Li, J. (2025) · International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) · doi:10.1109/icnc-fskd67701.2025.11198055
- Authors
- Lee, H. G., Sholle, E., Beecy, A., Al’Aref, S., & Peng, Y.
- Affiliations
- Weill Cornell Medicine (US)
- Venue
- Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Published
- 2021
- Volume
- 2021
- Pages
- 4533-4538
- PMC
- PMC9034454
- OpenAlex
- W3172818317
- Cited by
- 7
- References
- 29
- Citations by year
- 2026: 1 · 2025: 2 · 2023: 2 · 2022: 2
- FWCI
- 0.46
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- National Institutes of Health (UL1TR002384)
- Weill Cornell Medical College (UL1TR002384)
- National Heart, Lung, and Blood Institute
- U.S. National Library of Medicine (R00LM013001)
- National Center for Advancing Translational Sciences
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiomics and Machine Learning in Medical Imaging
- Keywords
- heart failure mortality, radiology reports, proportional hazards model, survival prediction, deep representations, clinical text
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
