IJSDIP | International Journal of System Design & Info Processing

AWS Comprehend for Clinical Text Analysis: A Study of Natural Language Processing in Healthcare

Paper ID:

IJSDIP_2024_VOLUME 12_ISSUE 4_127-134

Author's Name:

Sagar Kukkamudi, Divyasri Nalimela

Volume:

Issue:

Issue 4

Year:

2024

Pages:

127-134

Abstract

Natural language Processing (NLP). has become a critical part of automatic derivation of clinical information on the basis of unstructured healthcare text data. In this paper, the author explores how AWS Comprehend Medical, which is an Amazon Web Services (AWS) controlled NLP service, can be used to facilitate the process of text analysis in clinical settings through tasks like entity recognition, extraction of medical conditions, identification of medicines, and classification of relationships in electronic health records (EHRs). Our results will be based on the accuracy, efficiency, and domain flexibility of AWS Comprehend Medical using a dataset (anonymized clinical notes) across various healthcare domains. Findings show that AWS Comprehend Medical is able to detect key clinical entities and relationship with a high precision and recall and greatly minimizes the workload on manual annotation. Nonetheless, there are still some difficulties with dealing with vague clinical terminology, situation-semantics, and syntactic domain variability. The paper ends with the description of practical limitations and the future research directions that concentrate on the hybrid NLP structures, fine-tuning of custom models, and their integration with the decision support systems to enhance their clinical utility.

Keywords

Clinical Text Analysis, AWS Comprehend Medical, Electronic Health Records (EHR), Medical Entity Recognition, Clinical Decision Support Systems.

References

[1] Ali, W., Zuo, W., Ali, R., Zuo, X., & Rahman, G. (2021). Causality mining in Natural Languages using machine and Deep learning techniques: a survey. Applied Sciences, 11(21), 10064. https://doi.org/10.3390/app112110064 [2] Atherley, L. T. (2023). Intelligent risk management: natural language processing real-time triage of police calls for service. Police Practice and Research, 26(6), 654–672. https://doi.org/10.1080/15614263.2024.2388210 [3] Cho, H., Yoo, S., Kim, B., Jang, S., Sunwoo, L., Kim, S., Lee, D., Kim, S., Nam, S., & Chung, J. (2023). Extracting lung cancer staging descriptors from pathology reports: A generative language model approach. Journal of Biomedical Informatics, 157, 104720. https://doi.org/10.1016/j.jbi.2024.104720 [4] Deborah, R. N., Rajiv, S. A., Vinora, A., Soundarya, M., Arif, G. S. M., &Arif, S. M. (2022). Efficient information Retrieval: AWS Textract in action. In Lecture notes in networks and systems (pp. 95–105). https://doi.org/10.1007/978-981-97-7423-4_8 [5] Feng, Y., & Chen, H. (2022). Leveraging Artificial Intelligence to Analyze Consumer Sentiments within Their Context: A Case Study of Always #LikeAGirl Campaign. Journal of Interactive Advertising, 22(3), 336–348. https://doi.org/10.1080/15252019.2022.2126337 [6] Guzman, B., Metzger, I., Aphinyanaphongs, Y., D, M., D, P., Grover, H., & D, P. (2020). Assessment of Amazon comprehend medical: medication information extraction. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2002.00481 [7] K, H., Rodriguez, R. V., Subramaniam, U., &Balas, V. E. (2023). Artificial intelligence and knowledge processing. https://doi.org/10.1201/9781003328414 [8] Kocaman, V., Gul, Y., Kaya, M. A., Haq, H. U., Butgul, M., Celik, C., &Talby, D. (2023). Beyond Negation Detection: Comprehensive Assertion Detection Models for Clinical NLP. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2503.17425 [9] Kruuser, K., Bossenko, I., Lohk, A., Piho, G., & Ross, P. (2020). Application of artificial intelligence in the analysis of Estonian unstructured clinical text. In Lecture notes in networks and systems (pp. 483–500). https://doi.org/10.1007/978-3-032-00071-2_30 [10] Pal, S., Chang, M., &Iriarte, M. F. (2022). Summary generation using natural language processing techniques and cosine similarity. In Lecture notes in networks and systems (pp. 508–517). https://doi.org/10.1007/978-3-030-96308-8_47 [11] Tamla, P., Hartmann, B., Nguyen, N., Kramer, C., Freund, F., &Hemmje, M. (2023). CIE: a Cloud-Based information extraction system for named entity recognition in AWS, azure, and medical domain. In Communications in computer and information science (pp. 127–148). https://doi.org/10.1007/978-3-031-43471-6_6 [12] Tan, T. H. B., Lim, S., Qiu, Y., & Miao, C. (2022). A comparison of web services for sentiment analysis in digital mental health interventions. In Lecture notes in computer science (pp. 389–407). https://doi.org/10.1007/978-3-031-05061-9_28 [13] Tyagi, N., &Bhushan, B. (2023). Demystifying the role of Natural Language Processing (NLP) in Smart City Applications: background, motivation, recent advances, and future research directions. Wireless Personal Communications, 130(2), 857–908. https://doi.org/10.1007/s11277-023-10312-8 Wolff, B. (2020). [14] Artificial intelligence and natural language processing in modern clinical neuropsychology: A narrative review. The Clinical Neuropsychologist, 1–25, 2020. [15] Young, J., Bishop, S., Humphrey, C., &Pavlacic, J. M. (2023). A review of natural language processing in the identification of suicidal behavior. Journal of Affective Disorders Reports, 12, 100507. https://doi.org/10.1016/j.jadr.2023.100507

DOI: https://doi.org/10.64971/j.cph.ijsdip.v12.i4.1.2024