John Itodo*

School of Computer, University of Hull, United Kingdom

*Corresponding Author: John Itodo, School of Computer, University of Hull, United Kingdom.

Received: February 02, 2024; Published: April 30, 2024

Abstract

The influence of Artificial Intelligence (AI) has left an indelible mark on diverse aspects of human existence, offering profound automation in a daily activities. This paper undertakes a focused exploration of the applications of AI in healthcare services, a domain where its impact has been transformative. Within healthcare, AI applications have ushered in revolutionary advancements encompassing disease diagnosis, medical record management, treatment protocols, and medical administration.
This paper centers on developing a healthcare chatbot An AI-driven application designed to interact with users, providing valuable medical information and assistance. The motivation for the focus on the chatbot technology is to understand how AI chatbots are able to generate their responses when a prompt is given. Other uses of chatbots for medical applications include medical diagnosis, appointment scheduling, and medication-related inquiries. The chatbot was trained on an extensive Kaggle dataset from The Devastator, [1], comprising 47,603 rows of medical-related questions and corresponding answers. Dataset is the foundational knowledge base for AI models (chatbot's responses) [2].
Before the development of the model, several critical operations were conducted on the dataset to ensure its efficacy. Data cleaning procedures were implemented to rectify inconsistencies and inaccuracies, bolstering the dataset's integrity. Comprehensive data analysis unveiled insights crucial for understanding the dataset, while feature-engineering techniques were employed to enhance the dataset's suitability for training. Python, its libraries, and dependencies were the primary toolkit for executing these operations and building the model.
This paper showcased a versatile approach by incorporating various models; the paper achieved a well-rounded analysis by integrating modern deep learning methods and conventional machine learning approaches' architectures spanning from cluster models such as random forest to advanced neural networks like RNN and LSTM. This diverse model selection facilitated a more comprehensive exploration of the dataset, harnessing the strengths of each model type for a nuanced and effective solution.

Keywords: Artificial Intelligence; Healthcare; Chatbot; Natural Language Processing; Machine Learning

References

1. The devastator. “Comprehensive medical Q&A dataset” (2023).
2. Subbaswamy A and Saria S. “From development to deployment: dataset shift, causality, and shift-stable models in health AI”. Biostatistics (2019).
3. Tecuci G. “Artificial Intelligence”. Researchgate, Research gate (2012).
4. Poola I and Božić V. “How artificial intelligence in impacting real life every day”. Researchgate, research gate (2017).
5. Bohr A and Memarzadeh K. “The rise of Artificial Intelligence in healthcare applications”. Artificial Intelligence in Healthcare. Edited by A. Bohr and K. Memarzadeh (2023).
6. Sri YL., et al. “Conversational AI chatbot for healthcare”. (2023).
7. Saddique AA. “Integrated Delivery Systems (IDSs) as a Means of Reducing Costs and Improving Healthcare Delivery”. Journal of Healthcare Communications1 (2017).
8. Kelly-Cirino CD., et al. “Importance of diagnostics in epidemic and pandemic preparedness”. BMJ Global Health (2019).
9. Ogamba I and Nwaberiegwu C. “Persistent challenges to healthcare systems and the role of strategic”. (2020).
10. Aljaber T and Gordon N. “A guidance and evaluation approach for mHealth education applications”. In Learning and Collaboration Technologies. Technology in Education: 4th International Conference, LCT 2017, Held as Part of HCI International 2017, Vancouver, BC, Canada, July 9-14, 2017, Proceedings, Part II 4 (2017): 330-340.
11. Aljaber T and Gordon N. “A Hybrid Evaluation Approach and Guidance for mHealth Education Applications”. In Advances in Usability and User Experience: Proceedings of the AHFE 2017 International Conference on Usability and User Experience, July 17-21, 2017, The Westin Bonaventure Hotel, Los Angeles, California, USA 8 (2018): 282-290.
12. Mc Carthy J. “What is Artificial Intelligence, McCarthy, J, what is artificial intelligence”. Stanford University (2007).
13. Brooks R. “Artificial Intelligence and its impact on Everyday Life, University of York”. (2023).
14. Shaheen MY. “Artificial Intelligence in healthcare - executives for Health Innovation” (2021).
15. Gopal NN and Karnan M. “Diagnose brain tumor through MRI using image processing”. IEEE Xplore (2010).
16. Uslu BÇ., et al. “Analysis of factors affecting IoT-based smart hospital design”. Journal of Cloud Computing 1 (2020).
17. Haleem A., et al. “Current status and applications of Artificial Intelligence (AI) in medical field: An overview”. Current Medicine Research and Practice (2019).
18. Johnson KB., et al. “Precision Medicine, AI, and the Future of Personalized Health Care”. Wiley.com (2020).
19. King MR. “The future of AI in medicine: A perspective from a chatbot - annals of biomedical engineering”. SpringerLink (2022).
20. Fan X., et al. “Utilization of self-diagnosis health chatbots in real-world settings: Case study”. Journal of Medical Internet Research (2021).
21. Mesko B. “The top 10 healthcare chatbots”. The Medical Futurist (2023).
22. Bharti U., et al. “Medbot: Conversational Artificial Intelligence powered”. IEEE xplore (2020).
23. Kusner MJ., et al. “From word embeddings to document distances - proceedings of machine”. (2015).
24. Zhao R and Mao K. “Fuzzy Bag-of-words model for document representation”. IEEE journals (2017).
25. Abu-Rasheed H., et al. “Supporting Student Decisions on Learning Recommendations: An LLM-Based Chatbot with Knowledge Graph Contextualization for Conversational Explainability and Mentoring”. (2024).
26. Provos F., et al. “Automatic classification of endogenous seismic sources within a landslide
27. body using random forest algorithm”. (2016).
28. Grossberg S. “Recurrent neural networks”. Scholarpedia (2023).
29. Sutskever I. “By Ilya Sutskever - Department of Computer Science, University of Toronto”. (2023).
30. Houdt GV., et al. “A Review on the Long Short-Term Memory Model”. researchgate.net. (2020).

Citation

Citation: John Itodo. “AI Application in Health Care (Chatbot)".Acta Scientific Computer Sciences 6.4 (2024): 31-39.

Copyright

Copyright: © 2024 John Itodo. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.