Learning from heterogeneous temporal data in electronic health records
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
Electronic health records contain large amounts of longitudinal data that are valuable for biomedical informatics research. The application of machine learning is a promising alternative to manual analysis of such data. However, the complex structure of the data, which includes clinical events that are unevenly distributed over time, poses a challenge for standard learning algorithms. Some approaches to modeling temporal data rely on extracting single values from time series; however, this leads to the loss of potentially valuable sequential information. How to better account for the temporality of clinical data, hence, remains an important research question. In this study, novel representations of temporal data in electronic health records are explored. These representations retain the sequential information, and are directly compatible with standard machine learning algorithms. The explored methods are based on symbolic sequence representations of time series data, which are utilized in a number of different ways. An empirical investigation, using 19 datasets comprising clinical measurements observed over time from a real database of electronic health records, shows that using a distance measure to random subsequences leads to substantial improvements in predictive performance compared to using the original sequences or clustering the sequences. Evidence is moreover provided on the quality of the symbolic sequence representation by comparing it to sequences that are generated using domain knowledge by clinical experts. The proposed method creates representations that better account for the temporality of clinical events, which is often key to prediction tasks in the biomedical domain.
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
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
The use of the area under the ROC curve in the evaluation of machine learning algorithms
Bradley, A. P. (1997) · Pattern Recognition · doi:10.1016/s0031-3203(96)00142-2 · Cited by 7,217 · cited 12×
“In general, α of 2 is slightly in favor 17 AUC AUPRC 0 .0 0 .6 D611 2 3 5 0 .0 0 .6 D642 2 3 5 0 .0 0 .6 D695 2 3 5 0 .0 0 .6 E273 2 3 5 0 .0 0 .6 G620 2 3 5 0 .0 0 .6 I952 2 3 5 0 .0 0 .6 L270 2 3 5 0 .0 0 .6 L271 2 3 5 0 .0 0 .6 M804 2 3 5 0 .0 0 .6 M814 2 3 5 0 .0 0 .6 O355 2 3 5 0 .0 0 .6 R502 2 3 5 0 .0 0 .6 T782…”
MethodInfluentialThe relationship between Precision-Recall and ROC curves
Davis, J., & Goadrich, M. (2006) · Proceedings of the 23rd international conference on Machine learning - ICML '06 · doi:10.1145/1143844.1143874 · Cited by 6,559
Mining electronic health records: towards better research applications and clinical care
Jensen, P. B., Jensen, L. J., & Brunak, S. (2012) · Nature Reviews Genetics · doi:10.1038/nrg3208 · Cited by 1,680 · cited 1×
“Currently, the analysis of EHR data falls mainly into four categories: comorbidity, patient clustering, machine learning, and cohort querying [9].”
Experiencing SAX: A novel symbolic representation of time series
Lin, J., Keogh, E., Wei, L., & Lonardi, S. (2007) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-007-0064-z · Cited by 1,618 · cited 2×
“The resulting discrete sequence representation is called the Symbolic Aggregate approXimation (SAX) [19, 20].”
BackgroundMethodA Framework for Knowledge-Based Temporal Abstraction
Shahar, Y. (1997) · Artificial Intelligence · doi:10.1016/s0004-3702(96)00025-2 · Cited by 461 · cited 1×
“Some of them [26, 27, 28] build on temporal abstraction [33] or temporal logic [34] to de ne patterns that can describe temporal relationships among multiple time series.”
BackgroundDefining and measuring completeness of electronic health records for secondary use
Weiskopf, N. G., Hripcsak, G., Swaminathan, S., & Weng, C. (2013) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2013.06.010 · Cited by 367 · cited 1×
“The widespread adoption of EHRs has triggered an increased interest in clinical researchers for the secondary use of clinical data [2].”
BackgroundA Bag-of-Features Framework to Classify Time Series
Baydogan, M. G., Runger, G., & Tuv, E. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.72 · Cited by 361
Wei, W.-Q., Teixeira, P. L., Mo, H., Cronin, R. M., Warner, J. L., & Denny, J. C. (2016) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocv130 · Cited by 230
Singh, A., Nadkarni, G., Gottesman, O., Ellis, S. B., Bottinger, E. P., & Guttag, J. V. (2015) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2014.11.005 · Cited by 136
Cited by
Predicting healthcare trajectories from medical records: a deep learning approach
Pham, T., Tran, T., Phung, D., & Venkatesh, S. (2017) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2017.04.001 · Cited by 447
Influential Usage of Big Data and Artificial Intelligence in Healthcare
Yang, Y. C., Islam, S. U., Noor, A., Khan, S., Afsar, W., & Nazir, S. (2021) · Computational and Mathematical Methods in Medicine · doi:10.1155/2021/5812499 · Cited by 68
“[33] have determined the illustration of temporal data in electronic health record (EHR); there were several methods based on symbolic sequence representation of time series data, which can be used in several ways, while several evidence relies on the standard of symbolic sequence representation by comparing it to par…”
MethodRetractedModeling asynchronous event sequences with RNNs
Wu, S., Liu, S., Sohn, S., Moon, S., Wi, C.-I., Juhn, Y., & Liu, H. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2018.05.016 · Cited by 45
Performing an Informatics Consult: Methods and Challenges
Schuler, A., Callahan, A., Jung, K., & Shah, N. H. (2018) · Journal of the American College of Radiology · doi:10.1016/j.jacr.2017.12.023 · Cited by 37
High-throughput phenotyping with temporal sequences
Estiri, H., Strasser, Z. H., & Murphy, S. N. (2021) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaa288 · Cited by 26
Metadata
- Authors
- Zhao, J., Papapetrou, P., Asker, L., & Boström, H.
- Venue
- Journal of Biomedical Informatics
- Publisher
- Elsevier BV
- Published
- 2017-01
- Volume
- 65
- Pages
- 105-119
- ISSN
- 1532-0464 (ISSN-L)
- OpenAlex
- W2559646245
- Cited by
- 97
- References
- 10
- FWCI
- 8.30
- Type
- journal article
- Language
- en
- Open access
- hybrid
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 from heterogeneous temporal data in electronic health records. https://app.cochat.ai/papers/10.1016/j.jbi.2016.11.006
- The paper
- Zhao, J., Papapetrou, P., Asker, L., & Boström, H. (2017). Learning from heterogeneous temporal data in electronic health records. Journal of Biomedical Informatics. https://doi.org/10.1016/j.jbi.2016.11.006
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.