Development of Natural Language Dialogue System for Indian Language in Healthcare Domain
Keywords:
Dialogue system, Deep learning model, Healthcare, Natural Language Processing.Abstract
The healthcare dialogue system is developed using doctor-patient discussions. The doctor-patient conversations are used as input, and for every symptom, allopathic prescriptions are produced as the output. A total of 648 doctor-patient conversations were gathered for the dataset by going in-person to two rural hospitals. The use of local language for data collecting in the healthcare field is novelty in this study. Features are extracted from the words for further analysis. The linguistic model is constructed by feeding these features into a deep learning model. Using deep learning, the clinical dialogue system is developed. Evaluation result shows F1 score of 85.48%, recall of 85.31%, and precision of 85.65%. Following assessment, the ROC AUC value is 0.9233.
Downloads
References
Ramakrishnan, P., Dias, A., Rane, A., Shukla, A., Lakshmi, S., Ansari, B. K. M., ... & Koenig, H. G. (2014). Perspectives of Indian traditional and allopathic professionals on religion/spirituality and its role in medicine: basis for developing an integrative medicine program. Journal of Religion and Health, 53, 1161-1175.
Xu, Y. (2024). Boundaries and classification: the cultural logic of treating foreign medicine. Humanities and Social Sciences Communications, 11(1), 1-8.
Dowlagar, S., & Mamidi, R. (2023). A code-mixed task-oriented dialog dataset for medical domain. Computer Speech & Language, 78, 101449.
Maynard, D. W., & Heritage, J. (2005). Conversation analysis, doctor–patient interaction and medical communication. Medical education, 39(4), 428-435.
Sowmya, H. R., Ghani, S., Sreedaran, P., Sahu, M. K., Mysore, A., & Sharan, P. (2023). Cultural Expression of Anxiety Symptoms in Kannada Language: A Qualitative Study. Indian Journal of Psychological Medicine, 45(5), 496-502.
Yellapa, V., Devadasan, N., Krumeich, A., Pant Pai, N., Vadnais, C., Pai, M., & Engel, N. (2017). How patients navigate the diagnostic ecosystem in a fragmented health system: a qualitative study from India. Global Health Action, 10(1), 1350452.
Ramjee, P., Sachdeva, B., Golechha, S., Kulkarni, S., Fulari, G., Murali, K., & Jain, M. (2024). CataractBot: An LLM-Powered Expert-in-the-Loop Chatbot for Cataract Patients. arXiv preprint arXiv:2402.04620.
Abilkaiyrkyzy, A., Laamarti, F., Hamdi, M., & El Saddik, A. (2024). Dialogue System for Early Mental Illness Detection: Towards a Digital Twin Solution. IEEE Access.
Rani, S., & Jain, A. (2024). Optimizing healthcare system by amalgamation of text processing and deep learning: a systematic review. Multimedia Tools and Applications, 83(1), 279-303.
Samak, A. R., Bafna, P. B., & Saini, J. R. (2022). A Novel Marathi Speech-Based Question and Answer Chatbot for the Educational Domain. In ICT with Intelligent Applications: Proceedings of ICTIS 2022, Volume 1 (pp. 379-388). Singapore: Springer Nature Singapore.
Varshney, J. P., & Naresh, R. (2005). Comparative efficacy of homeopathic and allopathic systems of medicine in the management of clinical mastitis of Indian dairy cows. Homeopathy, 94(02), 81-85.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
