Abstract
Electronic medical records (EMR) provide valuable insights into patients’ medical history, symptoms, and treatments. Similar EMRs can help clinicians make an accurate diagnosis and develop an appropriate treatment plan for their patients, which makes the EMR recommendation a hot topic. However, searching for similar cases in a database containing many EMRs would be labor-intensive, while a recommendation system can return results quickly. In order to improve the recommendation accuracy and reduce the time-consuming at the same time, a similar EMR recommendation framework is proposed, which consists of three parts: Data Preprocessing, Prefetching, and Similarity Assessment. In the preprocessing module, named entities are extracted by a Named Entity Recognition (NER) tool and sliced by a particular rule. In the prefetching module, a pretrained deep learning model is fine-tuned on a classification task and generates embeddings for EMRs to avoid redundant calculations and filter candidate samples by computing cosine similarity. Furthermore, Weight-DSC is proposed to assess the similarity of EMR pairs, which is calculated by entity frequency and outperforms other entity-based methods. Experiments on real data show that this framework demonstrates superior recommendation performance compared to previous approaches across all metrics and saves 2/3 of the query time, notably achieving a 2.89% increase in Mean Reciprocal Rank (MRR).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bissoyi, S., Patra, M.R.: A similarity matrix based approach for building patient centric social networks. Int. J. Inf. Technol. 13(4), 1449–1455 (2021). https://doi.org/10.1007/s41870-021-00692-0, https://link.springer.com/10.1007/s41870-021-00692-0
Darabi, S., Kachuee, M., Fazeli, S., Sarrafzadeh, M.: TAPER: time-aware patient EHR representation. IEEE J. Biomed. Health Inform. 24(11), 3268–3275 (2020). https://doi.org/10.1109/JBHI.2020.2984931, https://ieeexplore.ieee.org/document/9056492/
Dhayne, H., Kilany, R., Haque, R., Taher, Y.: EMR2vec: bridging the gap between patient data and clinical trial. Comput. Ind. Eng. 156, 107236 (2021). https://doi.org/10.1016/j.cie.2021.107236, https://linkinghub.elsevier.com/retrieve/pii/S0360835221001406
Gupta, V., Sachdeva, S., Bhalla, S.: A novel deep similarity learning approach to electronic health records data. IEEE Access 8, 209278–209295 (2020). https://doi.org/10.1109/ACCESS.2020.3037710, https://ieeexplore.ieee.org/document/9257424/
Johnson, A.E., et al.: MIMIC-III, a freely accessible critical care database. Sci. Data 3(1), 160035 (2016). https://doi.org/10.1038/sdata.2016.35, https://www.nature.com/articles/sdata201635
Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach (2019). http://arxiv.org/abs/1907.11692, arXiv:1907.11692 [cs]
Memarzadeh, H., Ghadiri, N., Shahreza, M.L., Pokharel, S.: Heterogeneous electronic medical record representation for similarity computing. CoRR abs/2104.14229 (2021). https://arxiv.org/abs/2104.14229
Neumann, M., King, D., Beltagy, I., Ammar, W.: ScispaCy: fast and robust models for biomedical natural language processing. In: Proceedings of the 18th BioNLP Workshop and Shared Task, pp. 319–327 (2019). https://doi.org/10.18653/v1/W19-5034, http://arxiv.org/abs/1902.07669, arXiv:1902.07669 [cs]
Pokharel, S., Li, X., Zhao, X., Adhikari, A., Li, Y.: Similarity computing on electronic health records. In: Hirano, M., Myers, M.D., Kijima, K., Tanabu, M., Senoo, D. (eds.) 22nd Pacific Asia Conference on Information Systems, PACIS 2018, Yokohama, Japan, 26–30 June 2018, p. 198 (2018). https://aisel.aisnet.org/pacis2018/198
Salton, G., Buckley, C.: Term-weighting approaches in automatic text retrieval. Inf. Process. Manag. 24(5), 513–523 (1988). https://doi.org/10.1016/0306-4573(88)90021-0, https://linkinghub.elsevier.com/retrieve/pii/0306457388900210
Vaswani, A., et al.: Attention is all you need (2017). http://arxiv.org/abs/1706.03762, number: arXiv:1706.03762 [cs]
Wang, Y., Chen, W., Li, B., Boots, R.: Learning fine-grained patient similarity with dynamic Bayesian network embedded RNNs. In: Li, G., Yang, J., Gama, J., Natwichai, J., Tong, Y. (eds.) DASFAA 2019. LNCS, vol. 11446, pp. 587–603. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-18576-3_35
Wu, Y., Mukunoki, M., Funatomi, T., Minoh, M., Lao, S.: Optimizing mean reciprocal rank for person re-identification. In: 2011 8th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS), pp. 408–413 (2011). https://doi.org/10.1109/AVSS.2011.6027363
Zhao, Z., Jin, Q., Chen, F., Peng, T., Yu, S.: PMC-patients: a large-scale dataset of patient summaries and relations for benchmarking retrieval-based clinical decision support systems. arXiv e-prints arXiv-2202 (2022)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zheng, Y., Yan, X., Cao, X., Ai, C. (2023). Electronic Medical Record Recommendation System Based on Deep Embedding Learning with Named Entity Recognition. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14260. Springer, Cham. https://doi.org/10.1007/978-3-031-44195-0_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-44195-0_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44194-3
Online ISBN: 978-3-031-44195-0
eBook Packages: Computer ScienceComputer Science (R0)