A machine learning and blockchain based secure and cost-effective framework for minor medical consultations

Area of Science:

• Health Informatics
• Blockchain Technology
• Artificial Intelligence

Background:

• Growing health awareness increases doctor visits.
• COVID-19 pandemic accelerated adoption of home-based consultations.
• Current online models face challenges with privacy and professional engagement.

Purpose of the Study:

• To present an advanced, protected blockchain-based consultation model for minor medical conditions.
• To address privacy concerns and enhance professional participation in online consultations.
• To develop an incentivized system for accessible and cost-effective healthcare.

Main Methods:

• Utilized a blockchain-based framework for secure consultations.
• Incorporated a machine learning model for professional scoring.
• Employed word2vec, TF-IDF, and cosine similarity for question classification and analysis.

Main Results:

• The proposed model ensures user privacy during online consultations.
• A smart contract was developed to predict professional scores based on parameters.
• An incentivized mechanism rewards professionals and charges patients based on consultation scores.

Conclusions:

• The blockchain-based model enhances privacy and security in telehealth.
• Machine learning integration optimizes professional matching and incentivization.
• This approach promotes more accessible and affordable healthcare solutions for minor conditions.