Papers
Topics
Authors
Recent
2000 character limit reached

Prediction of COVID-19 Patients' Emergency Room Revisit using Multi-Source Transfer Learning

Published 29 Jun 2023 in cs.LG, cs.AI, and cs.CL | (2306.17257v1)

Abstract: The coronavirus disease 2019 (COVID-19) has led to a global pandemic of significant severity. In addition to its high level of contagiousness, COVID-19 can have a heterogeneous clinical course, ranging from asymptomatic carriers to severe and potentially life-threatening health complications. Many patients have to revisit the emergency room (ER) within a short time after discharge, which significantly increases the workload for medical staff. Early identification of such patients is crucial for helping physicians focus on treating life-threatening cases. In this study, we obtained Electronic Health Records (EHRs) of 3,210 encounters from 13 affiliated ERs within the University of Pittsburgh Medical Center between March 2020 and January 2021. We leveraged a Natural Language Processing technique, ScispaCy, to extract clinical concepts and used the 1001 most frequent concepts to develop 7-day revisit models for COVID-19 patients in ERs. The research data we collected from 13 ERs may have distributional differences that could affect the model development. To address this issue, we employed a classic deep transfer learning method called the Domain Adversarial Neural Network (DANN) and evaluated different modeling strategies, including the Multi-DANN algorithm, the Single-DANN algorithm, and three baseline methods. Results showed that the Multi-DANN models outperformed the Single-DANN models and baseline models in predicting revisits of COVID-19 patients to the ER within 7 days after discharge. Notably, the Multi-DANN strategy effectively addressed the heterogeneity among multiple source domains and improved the adaptation of source data to the target domain. Moreover, the high performance of Multi-DANN models indicates that EHRs are informative for developing a prediction model to identify COVID-19 patients who are very likely to revisit an ER within 7 days after discharge.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. B. Oberfeld, A. Achanta, K. Carpenter, P. Chen, N. M. Gilette, P. Langat, J. T. Said, A. E. Schiff, A. S. Zhou, A. K. Barczak et al., “SnapShot: covid-19,” Cell, vol. 181, no. 4, pp. 954–954, 2020.
  2. V. A. Rodriguez, S. Bhave, R. Chen, C. Pang, G. Hripcsak, S. Sengupta, N. Elhadad, R. Green, J. Adelman, K. S. Metitiri et al., “Development and validation of prediction models for mechanical ventilation, renal replacement therapy, and readmission in COVID-19 patients,” Journal of the American Medical Informatics Association, vol. 28, no. 7, pp. 1480–1488, 2021.
  3. S. Peiris, J. L. Nates, J. Toledo, Y.-L. Ho, O. Sosa, V. Stanford, S. Aldighieri, and L. Reveiz, “Hospital readmissions and emergency department re-presentation of COVID-19 patients: a systematic review,” Rev Panam Salud Publica; 46, oct. 2022, 2022.
  4. S. J. Pan and Q. Yang, “A survey on transfer learning,” IEEE Transactions on knowledge and data engineering, vol. 22, no. 10, pp. 1345–1359, 2010.
  5. S. Zhao, X. Yue, S. Zhang, B. Li, H. Zhao, B. Wu, R. Krishna, J. E. Gonzalez, A. L. Sangiovanni-Vincentelli, S. A. Seshia et al., “A review of single-source deep unsupervised visual domain adaptation,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 2, pp. 473–493, 2020.
  6. S. Ruder, M. E. Peters, S. Swayamdipta, and T. Wolf, “Transfer learning in natural language processing,” in Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: Tutorials, 2019, pp. 15–18.
  7. N. Balachandar, K. Chang, J. Kalpathy-Cramer, and D. L. Rubin, “Accounting for data variability in multi-institutional distributed deep learning for medical imaging,” Journal of the American Medical Informatics Association, vol. 27, no. 5, pp. 700–708, 2020.
  8. K. Muhammad, S. Khan, J. Del Ser, and V. H. C. De Albuquerque, “Deep learning for multigrade brain tumor classification in smart healthcare systems: A prospective survey,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 2, pp. 507–522, 2020.
  9. M. Alzubaidi, H. D. Zubaydi, A. A. Bin-Salem, A. A. Abd-Alrazaq, A. Ahmed, and M. Househ, “Role of deep learning in early detection of COVID-19: Scoping review,” Computer methods and programs in biomedicine update, vol. 1, p. 100025, 2021.
  10. Z. Zhao, J. Qin, Z. Gou, Y. Zhang, and Y. Yang, “Multi-task learning models for predicting active compounds,” Journal of Biomedical Informatics, vol. 108, p. 103484, 2020.
  11. Y. Kim, S. Zheng, J. Tang, W. Jim Zheng, Z. Li, and X. Jiang, “Anticancer drug synergy prediction in understudied tissues using transfer learning,” Journal of the American Medical Informatics Association, vol. 28, no. 1, pp. 42–51, 2021.
  12. D. S. Sachan, P. Xie, M. Sachan, and E. P. Xing, “Effective use of bidirectional language modeling for transfer learning in biomedical named entity recognition,” in Machine learning for healthcare conference.   PMLR, 2018, pp. 383–402.
  13. C. Lin, S. Bethard, D. Dligach, F. Sadeque, G. Savova, and T. A. Miller, “Does BERT need domain adaptation for clinical negation detection?” Journal of the American Medical Informatics Association, vol. 27, no. 4, pp. 584–591, 2020.
  14. D. Dana, S. V. Gadhiya, L. G. St. Surin, D. Li, F. Naaz, Q. Ali, L. Paka, M. A. Yamin, M. Narayan, I. D. Goldberg et al., “Deep learning in drug discovery and medicine; scratching the surface,” Molecules, vol. 23, no. 9, p. 2384, 2018.
  15. R. Saeedi, K. Sasani, and A. H. Gebremedhin, “Collaborative multi-expert active learning for mobile health monitoring: architecture, algorithms, and evaluation,” Sensors, vol. 20, no. 7, p. 1932, 2020.
  16. Y. Ganin, E. Ustinova, H. Ajakan, P. Germain, H. Larochelle, F. Laviolette, M. Marchand, and V. Lempitsky, “Domain-adversarial training of neural networks,” The journal of machine learning research, vol. 17, no. 1, pp. 2096–2030, 2016.
  17. E. Brion, J. Léger, A. M. Barragán-Montero, N. Meert, J. A. Lee, and B. Macq, “Domain adversarial networks and intensity-based data augmentation for male pelvic organ segmentation in cone beam CT,” Computers in Biology and Medicine, vol. 131, p. 104269, 2021.
  18. M. W. Lafarge, J. P. Pluim, K. A. Eppenhof, P. Moeskops, and M. Veta, “Domain-adversarial neural networks to address the appearance variability of histopathology images,” in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: Third International Workshop, DLMIA 2017, and 7th International Workshop, ML-CDS 2017, Held in Conjunction with MICCAI 2017, Québec City, QC, Canada, September 14, Proceedings 3.   Springer, 2017, pp. 83–91.
  19. Y. Ye and A. Gu, “Deep transfer learning for infectious disease case detection using electronic medical records,” arXiv preprint arXiv:2103.06710, 2021.
  20. S. Visweswaran, B. McLay, N. Cappella, M. Morris, J. T. Milnes, S. E. Reis, J. C. Silverstein, and M. J. Becich, “An atomic approach to the design and implementation of a research data warehouse,” Journal of the American Medical Informatics Association, vol. 29, no. 4, pp. 601–608, 2022.
  21. M. Neumann, D. King, I. Beltagy, and W. Ammar, “ScispaCy: Fast and robust models for biomedical natural language processing,” in Proceedings of the 18th BioNLP Workshop and Shared Task.   Association for Computational Linguistics, 2019, pp. 319–327.
  22. O. Day and T. M. Khoshgoftaar, “A survey on heterogeneous transfer learning,” Journal of Big Data, vol. 4, pp. 1–42, 2017.
  23. F. Zhuang, Z. Qi, K. Duan, D. Xi, Y. Zhu, H. Zhu, H. Xiong, and Q. He, “A comprehensive survey on transfer learning,” Proceedings of the IEEE, vol. 109, no. 1, pp. 43–76, 2020.
  24. J. Jiang, Y. Shu, J. Wang, and M. Long, “Transferability in deep learning: A survey,” arXiv preprint arXiv:2201.05867, 2022.
  25. S. Sun, H. Shi, and Y. Wu, “A survey of multi-source domain adaptation,” Information Fusion, vol. 24, pp. 84–92, 2015.
  26. K. Li, J. Lu, H. Zuo, and G. Zhang, “Multi-source contribution learning for domain adaptation,” IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 10, pp. 5293–5307, 2021.
  27. S. Christodoulidis, M. Anthimopoulos, L. Ebner, A. Christe, and S. Mougiakakou, “Multisource transfer learning with convolutional neural networks for lung pattern analysis,” IEEE journal of biomedical and health informatics, vol. 21, no. 1, pp. 76–84, 2016.
  28. Y. Bengio, A. Courville, and P. Vincent, “Representation learning: A review and new perspectives,” IEEE transactions on pattern analysis and machine intelligence, vol. 35, no. 8, pp. 1798–1828, 2013.
  29. J. X. Dou, M. Jia, N. Zaslavsky, M. Ebeid, R. Bao, S. Zhang, K. Ni, P. P. Liang, H. Mao, and Z.-H. Mao, “Learning more effective cell representations efficiently,” in NeurIPS 2022 Workshop on Learning Meaningful Representations of Life, 2022.
  30. J. X. Dou, A. Q. Pan, R. Bao, H. H. Mao, and L. Luo, “Sampling through the lens of sequential decision making,” arXiv preprint arXiv:2208.08056, 2022.
  31. E. Alsentzer, J. R. Murphy, W. Boag, W.-H. Weng, D. Jin, T. Naumann, and M. McDermott, “Publicly available clinical BERT embeddings,” arXiv preprint arXiv:1904.03323, 2019.
  32. R. Luo, L. Sun, Y. Xia, T. Qin, S. Zhang, H. Poon, and T.-Y. Liu, “BioGPT: generative pre-trained transformer for biomedical text generation and mining,” Briefings in Bioinformatics, vol. 23, no. 6, 2022.
  33. OpenAI, “Introducing chatGPT.” [Online]. Available: https://openai.com/blog/chatgpt
  34. T. H. Kung, M. Cheatham, A. Medenilla, C. Sillos, L. De Leon, C. Elepaño, M. Madriaga, R. Aggabao, G. Diaz-Candido, J. Maningo et al., “Performance of chatGPT on USMLE: Potential for AI -assisted medical education using large language models,” PLoS digital health, vol. 2, no. 2, p. e0000198, 2023.
Citations (17)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now

Whiteboard

Paper to Video (Beta)

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up