Biyomedikal literatürden solunum yolu hastalıkları ve semptom ilişkilerinin çıkarılması için semantik benzerlik temelli bir yaklaşım

Yıl 2025, Cilt: 40 Sayı: 1, 121 - 134, 16.08.2024

Azer Çelikten , Hasan Bulut , Aytuğ Onan

https://doi.org/10.17341/gazimmfd.1354324

Öz

Biyomedikal alandaki artan makale sayısıyla birlikte, hastalıklar ve semptomlar hakkında keşfedilen değerli bilgiler akademik literatürde gizli kalmaktadır. Biyomedikal metinleri işlemek ve doğal dil işleme ve metin madenciliği yöntemlerini kullanarak bu bilgileri çıkarmak, erken teşhis, klinik karar destek sistemleri geliştirmek ve biyomedikal bilgi grafikleri ve ontolojileri oluşturmak için kritik öneme sahiptir. Solunum yolu hastalıklarının ateş, öksürük, nefes darlığı gibi birçok ortak semptomları olduğundan, hastalıkları semptomlara göre ayırt etmek, hastalığın erken evrelerinde doğru teşhis için son derece önemlidir, Bu çalışmada, sağlık kaynaklarında belirtilmeyen ancak hastalıkla ilişkili nadir semptomları tespit etmek ve hastalıkların semptomlarla ilişki derecesini tespit etmek için bir hastalık-semptom ilişkisi çıkarma yöntemi önerilmiştir. İlk olarak, tıbbi metinlerdeki hastalıkları ve semptomları tanımlamak için önceden eğitilmiş bir dil modeli ve tıbbi ontolojiden oluşan hibrit bir varlık ismi tanıma yöntemi önerilmiştir. İkinci olarak, elde edilen hastalık ve semptomlar normalize edilmiştir. Sonraki adımda, semantik benzerliğe dayalı yöntemler kullanılarak semptomların hastalıklarla ilişki dereceleri elde edilen benzerlik skorlarına göre sıralanmıştır. Önerilen yöntem solunum yolu hastalıklarından oluşan özgün bir veriseti üzerinde değerlendirilmiştir. Bu veriseti, astım, bronşit, pulmoner emboli ve koronavirüs hastalıklarına ait akademik makale özetlerinden oluşmaktadır. Sonuç olarak, karakteristik semptomlara ek olarak, sağlık kaynaklarında bahsedilmeyen ancak hastalıkla ilişkilendirilebilecek nadir semptomlar keşfedilmiştir. Önerilen yöntem ile hastalıkların semptomları arasındaki ilişkilerin tespitinde nokta çarpımı benzerlik yönteminin daha başarılı olduğu görülmüştür. Nadir semptomların ise literatür değerlendirmesi yapılarak hastalıklar ile ilişkisi ortaya çıkarılmıştır.

Anahtar Kelimeler

Biyomedikal Varlık İsmi Tanıma, Biyomedikal İlişki Çıkarımı, Metin Madenciliği, Bilgi Çıkarma, Solunum Yolu Hastalıkları

Kaynakça

• 1. Eurostat Statistics Explained, Respiratory diseases statistics, https://ec.europa.eu/eurostat/statistics-explained/index.php?title=Respiratory_diseases_statistics&oldid=541149#Deaths_from_diseases_of_the_respiratory_system,Erişim Tarihi Mart 10 2023.
• 2. Brosnahan, S. B., Jonkman, A. H., Kugler, M. C., Munger, J. S., & Kaufman, D. A. (COVID-19 and Respiratory System Disorders: Current Knowledge, Future Clinical and Translational Research Questions. Arteriosclerosis, Thrombosis, and Vascular Biology, 40 (11), 2586-2597, 2020.
• 3. PUBMED, pubmed.gov.tr. Erişim Tarihi Aralık 10 2023.
• 4. PubMed Overview ,https://pubmed.ncbi.nlm.nih.gov/about/#:~:text=PubMed%20Overview,health%E2%80%93both%20globally%20and%20personally, Erişim Tarihi Aralık 10 2023.
• 5. MEDLINE PubMed Production Statistics, https://www.nlm.nih.gov/bsd/medline_pubmed_production_stats.html, Erişim Tarihi Aralık 10 2023.
• 6. Sun, C., Yang, Z., Wang, L., Zhang, Y., Lin, H., & Wang, J. Attention guided capsule networks for chemical-protein interaction extraction. Journal of Biomedical Informatics, 103, 103392, 2020.
• 7. Peng, Y., Rios, A., Kavuluru, R., & Lu, Z. Extracting chemical–protein relations with ensembles of SVM and deep learning models. Database, 2018.
• 8. Zhou, H., Liu, Z., Ning, S., Lang, C., Lin, Y., & Du, L. Knowledge-aware attention network for protein-protein interaction extraction. Journal of Biomedical Informatics, 96, 103234, 2019.
• 9. Zhou, H., Li, X., Yao, W., Liu, Z., Ning, S., Lang, C., & Du, L. Improving neural protein-protein interaction extraction with knowledge selection. Computational Biology and Chemistry, 83, 107146., 2019.
• 10. Onye, S. C., Akkeleş, A., & Dimililer, N. RelSCAN–a system for extracting chemical-induced disease relation from biomedical literature. Journal of Biomedical Informatics, 87, 79-87, 2018.
• 11. Deng, Y., Xu, X., Qiu, Y., Xia, J., Zhang, W., & Liu, S. A multimodal deep learning framework for predicting drug–drug interaction events. Bioinformatics, 36 (15), 4316-4322, 2020.
• 12. Feng, Y. H., Zhang, S. W., & Shi, J. Y. DPDDI: a deep predictor for drug-drug interactions. BMC bioinformatics, 21 (1), 1-15, 2020.
• 13. Machado, J., Rodrigues, C., Sousa, R., & Gomes, L. M. Drug–drug interaction extraction-based system: An natural language processing approach. Expert Systems, e13303, 2023.
• 14. Li, J., Sun, A., Han, J., & Li, C. A survey on deep learning for named entity recognition. IEEE Transactions on Knowledge and Data Engineering, 34 (1), 50-70, 2020.
• 15. Yang Z, Lin H, Li Y. Exploiting the performance of dictionary-based bio-entity name recognition in biomedical literature. Comput Biol Chem, 32 (4), 287–91, 2008.
• 16. AR Aronson. Effective mapping of biomedical text to the UMLS metathesaurus: the metamap program. In: Proceedings of the AMIA Symposium, p. 17. American Medical Informatics Association, 2001.
• 17. N Kang, B Singh, Z Afzal, et al. Using rule-based natural language processing to improve disease normalization in biomedical text. J Am Med Inform Assoc. 20 (5), 876–81, 2013.
• 18. Fukuda, K. I., Tsunoda, T., Tamura, A., & Takagi, T. Toward information extraction: identifying protein names from biological papers. In Pac symp biocomput, 707 (18), 707-718, 1998.
• 19. İlgün E.G., Samet R., Increasing the performance of intrusion detection models developed using machine learning method with preprocessing applied to the dataset Journal of the Faculty of Engineering and Architecture of Gazi University, 39 (2), 679-692, 2024.
• 20. Morwal, S., Jahan, N., & Chopra, D. Named entity recognition using hidden Markov model (HMM). International Journal on Natural Language Computing (IJNLC), 1, 2012.
• 21. Xie, X. Y. A Review on Support Vector Machines for Biomedical NER. Data Science for NLP, 1, 06, 2020.
• 22. Cho, M., Ha, J., Park, C., & Park, S. Combinatorial feature embedding based on CNN and LSTM for biomedical named entity recognition. Journal of biomedical informatics, 103, 103381, 2020.
• 23. Zhu, Q., Li, X., Conesa, A., & Pereira, C. GRAM-CNN: a deep learning approach with local context for named entity recognition in biomedical text. Bioinformatics, 34 (9), 1547-1554, 2018.
• 24. Jackson RG, Patel R, Jayatilleke N, et al Natural language processing to extract symptoms of severe mental illness from clinical text: the Clinical Record Interactive Search Comprehensive Data Extraction (CRIS-CODE) Project BMJ Open;7:e012012. doi: 10.1136/bmjopen-2016-012012, 2017.
• 25. Wu, C. S., Kuo, C. J., Su, C. H., Wang, S. H., & Dai, H. J. Using text mining to extract depressive symptoms and to validate the diagnosis of major depressive disorder from electronic health records. Journal of affective disorders, 260, 617-623, 2020.
• 26. Uddin, M. Z., Dysthe, K. K., Følstad, A., & Brandtzaeg, P. B. Deep learning for prediction of depressive symptoms in a large textual dataset. Neural Computing and Applications, 34 (1), 721-744., 2022.
• 27. Eisman, A. S., Shah, N. R., Eickhoff, C., Zerveas, G., Chen, E. S., Wu, W. C., & Sarkar, I. N., Extracting angina symptoms from clinical notes using pre-trained transformer architectures. In AMIA Annual Symposium Proceedings, 2020, 412, American Medical Informatics Association., 2020.
• 28. Leiter, R. E., Santus, E., Jin, Z., Lee, K. C., Yusufov, M., Chien, I., ... & Lindvall, C. Deep natural language processing to identify symptom documentation in clinical notes for patients with heart failure undergoing cardiac resynchronization therapy. Journal of Pain and Symptom Management, 60 (5), 948-958., 2020.
• 29. Wang, J., Abu-el-Rub, N., Gray, J., Pham, H. A., Zhou, Y., Manion, F. J., ... & Zhang, Y. COVID-19 SignSym: a fast adaptation of a general clinical NLP tool to identify and normalize COVID-19 signs and symptoms to OMOP common data model. Journal of the American Medical Informatics Association, 28 (6), 1275-1283, 2021.
• 30. Lybarger, K., Ostendorf, M., Thompson, M., & Yetisgen, M., Extracting COVID-19 diagnoses and symptoms from clinical text: A new annotated corpus and neural event extraction framework. Journal of Biomedical Informatics, 117, 103761, 2021.
• 31. Du, N., Chen, K., Kannan, A., Tran, L., Chen, Y., & Shafran, I., Extracting symptoms and their status from clinical conversations. arXiv preprint arXiv:1906.02239, 2019.
• 32. Alshuwaier, F., Areshey, A., & Poon, J. A comparative study of the current technologies and approaches of relation extraction in biomedical literature using text mining. In 2017 4th IEEE International Conference on Engineering Technologies and Applied Sciences (ICETAS), 1-13, IEEE, 2017.
• 33. Zhou X, Menche J, Barabási A-L, et al. Human symptoms–disease network. Nat Commun. 5, 4212, 2014.
• 34. Hassan, M., Makkaoui, O., Coulet, A., & Toussaint, Y. Extracting disease-symptom relationships by learning syntactic patterns from dependency graphs. In BioNLP 15, 184, 2015.
• 35. Abulaish, M., & Parwez, M. A. DiseaSE: A biomedical text analytics system for disease symptom extraction and characterization. Journal of Biomedical Informatics, 100, 103324, 2019.
• 36. Zlabinger, M., Hofstätter, S., Rekabsaz, N., & Hanbury, A. DSR: A Collection for the Evaluation of Graded Disease-Symptom Relations. In European Conference on Information Retrieval, Springer, Cham, 433-440, 2020.
• 37. Wada, S., Iida, R., Torisawa, K., Takeda, T., Manabe, S., & Matsumura, Y. Symptom Extraction and Disease-Symptom Relation Recognition from Web Texts with Multi-Column Convolutional Neural Networks, 2018.
• 38. Ma X., Conrad T., Alchikh M., Reiche J., Schweiger B., Rath B.. Can we distinguish respiratory viral infections based on clinical features? A prospective pediatric cohort compared to systematic literature review. Reviews in Medical Virology, 28 (5), e1997, 2018.
• 39. Van der Sar IG., Wijsenbeek MS., Braunstahl GJ., Loekabino JO., Dingemans AC., In 't Veen JCCM, Moor CC. Differentiating interstitial lung diseases from other respiratory diseases using electronic nose technology. Respir Res. 24 (1), 271, 2023.
• 40. Neumann, M., King, D., Beltagy, I., & Ammar, W. ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing. ArXiv, abs/1902.07669., 2019.
• 41. The Open Biological and Biomedical Ontology (OBO) Foundry, “Symptom Ontology”, https://obofoundry.org/ontology/symp.html, Erişim 03.12.2021.
• 42. Jiao L., Yueping S., Robin J., Daniela S., Chih-Hsuan W., Robert L, Allan P.D., Carolyn J.M., Thomas C.W., and Zhiyong L., BioCreative V CDR task corpus: a resource for chemical disease relation extraction, Database: the journal of biological databases and curation, 2016.
• 43. Rao, D., McNamee, P., & Dredze, M. Entity linking: Finding extracted entities in a knowledge base, Multi-source, multilingual information extraction and summarization, Theory and Applications of Natural Language Processing. Springer, Berlin, Heidelberg 93-115, 2013.
• 44. Ahmed M., Roy S., Iktidar MA., Chowdhury S., Akhter S., Khairul Islam AM., Hawlader MDH. Post-COVID-19 Memory Complaints: Prevalence and Associated Factors, Neurologia. PMID: 35469238; PMCID: PMC9020525, 2022.
• 45. Shah PL., Orton C. Epithelial Resurfacing: The Bronchial Skin Peel. American Journal of Respiratory and Critical Care Medicine, 202 (5), 641-642, 2020.
• 46. Lehrer, P. M., Isenberg, S., & Hochron, S. M. Asthma and emotion: a review. Journal of Asthma, 30 (1), 5-21, 1993.