AI Assistance For Healthcare Using NLP, Machine Learning
DOI:
https://doi.org/10.63665/nhzwrc51Keywords:
NLP, Machine Learning, KNN, Medical Chatbot, Disease PredictionAbstract
This study presents an AI-based medical chatbot that utilizes Natural Language Processing (NLP) and Machine
Learning (ML) to provide preliminary disease diagnosis from user-reported symptoms. The system employs a multistage
symptom matching approach, including syntactic similarity (Jaccard), semantic similarity (WordNet WUP), and
synonym mapping, to interpret natural language inputs effectively. A K-Nearest Neighbors (KNN) classifier trained
on 4,920 records with 132 symptom features predicts diseases across 41 conditions. The chatbot is implemented using
a Flask-based conversational interface that collects user inputs, performs disease prediction, and provides relevant
descriptions and precautions. Experimental results demonstrate the effectiveness of combining NLP techniques with
ML models for accessible and efficient healthcare support systems.
Downloads
References
[1] L. Laranjo et al., “Conversational agents in
healthcare: A systematic review,” J. Am. Med. Inform.
Assoc., vol. 25, no. 9, pp. 1248–1258, 2018.
[2] S. Bird, E. Klein, and E. Loper, Natural Language
Processing with Python. O’Reilly Media, 2009.
[3] T. Cover and P. Hart, “Nearest neighbor pattern
classification,” IEEE Trans. Inf. Theory, vol. 13, no. 1,
pp. 21–27, 1967.
[4] E. Topol, Deep Medicine: How Artificial
Intelligence Can Make Healthcare Human Again.
Basic Books, 2019.
[5] D. Jurafsky and J. Martin, Speech and Language
Processing, 3rd ed., 2020.
[6] G. A. Miller, “WordNet: A lexical database for
English,” Commun. ACM, vol. 38, no. 11, pp. 39–41,
1995.
[7] Z. Wu and M. Palmer, “Verb semantics and lexical
selection,” ACL, 1994.
[8] I. Kononenko, “Machine learning for medical
diagnosis,” AI in Medicine, vol. 23, no. 1, pp. 89–109,
2001.
[9] L. Breiman, “Random forests,” Machine Learning,
vol. 45, pp. 5–32, 2001.
[10] M. Grinberg, Flask Web Development. O’Reilly
Media, 2018.
[11] D. Merkel, “Docker: Lightweight Linux
containers,” Linux Journal, 2014.
