About me

Hi!, I’m Kavishwa, a PhD researcher at the University of Oulu, specializing in Medical AI and mHealth software solutions. With a strong background in software engineering and a master’s degree in Information Systems, I have extensive experience in developing innovative software systems for the medical industry, focusing on AI-driven applications that improve healthcare outcomes. My research interests include leveraging AI to enhance mobile health applications, real-time monitoring, and personalized healthcare solutions. I am also skilled in full-stack software development, enabling me to design and implement complex systems that integrate seamlessly into medical workflows.
Throughout my academic and professional journey, I have worked on various projects, including the development of AI-based tools, patient monitoring systems, prescription management systems, and healthcare management platforms. My work is driven by a passion for creating impactful technology that addresses critical challenges in healthcare.
Let’s Connect!
Revised Research Title
Self-Adaptive AI Systems for Enhancing Pediatric Brain Health: A Secure and Privacy-Focused Framework for Real-Time, Personalized Interventions
Research Questions
RQ1) What are the key components and design principles needed to create an AI-driven adaptive system for delivering personalized, real-time interventions in pediatric brain health care?
RQ2) How can a self-adaptive AI system be designed to ensure real-time personalization of care while maintaining scalability, data privacy, and security for pediatric patients?
RQ3) How effective is the proposed AI framework in maintaining performance, scalability, and data integrity while delivering real-time personalized interventions in simulated pediatric healthcare environments?
Research Objectives
1) Propose a theoretical Framework for AI-driven adaptive Systems in Pediatric Brain Health Care. The first objective focuses on developing a software engineering framework that outlines the architecture and design principles for AI-driven systems that provide personalized, real-time interventions. The framework will specify how AI can support adaptive decision-making and dynamic intervention generation, focusing on how software systems can process real-time patient data to optimize user experience, system responsiveness, and personalized care in pediatric brain health.
2) Design a Self-adaptive, Security and Privacy-Focused AI Framework for Pediatric Care with Personalized Recommendations. This objective involves creating a conceptual model for a self-adaptive AI system capable of continuous learning and real-time data processing. The AI model will be designed to analyze incoming data streams, adapt its recommendations, and optimize its decision-making algorithms (Wang et al., 2023). The model will focus on software engineering aspects such as scalability, system adaptability, and data privacy, with applications for managing real-time adjustments for personalized user support.
3) Evaluate the Performance and Scalability of the AI Framework Through Simulated or Clinical Scenarios. This objective aims to validate the proposed AI-driven framework by evaluating its performance, scalability, and system responsiveness in simulated environments. The evaluation will assess how effectively the framework processes real-time data, adapts to changing user inputs, and delivers optimized recommendations. The focus will be on the technical aspects of system efficiency, data integrity, and maintaining user privacy in software-driven healthcare solutions.
Research Methodology

Recent Projects
MentalEEG
Prescription Management System(Ray PMS)
SurveyFlow
FamilySpend
Publications
Coming Soon!
