I am a medical doctor working in a consultant-led vascular surgery service, with extensive hands-on experience in venous intervention and vascular ultrasound.

My research interest is at the intersection of:

Medicine × Vascular Science × Artificial Intelligence × Biomedical Engineering × IoT

I am particularly interested in developing intelligent, patient-centred biomedical systems that combine clinical data, medical imaging, physiological sensing and AI to improve diagnosis, treatment selection and longitudinal monitoring.

• AI-assisted vascular medicine
• Personalised vascular intervention
• Medical image analysis
• Duplex ultrasound and vascular imaging
• Clinical machine learning
• Biomedical IoT (IoMT)
• Wearable physiological sensing
• Digital twins in healthcare
• Clinical decision-support systems
• Autonomous biomedical experimentation
• Healthcare interoperability and HL7 FHIR
• Translational medical technology

AI-enabled personalised vascular intervention and intelligent vascular monitoring

A long-term goal is to develop systems that connect:

Clinical data
      ↓
Medical imaging
      ↓
Physiological sensing
      ↓
IoT / Edge devices
      ↓
AI / Machine Learning
      ↓
Patient-specific modelling
      ↓
Clinical decision support
      ↓
Continuous monitoring

I work in a vascular surgery environment with substantial experience in venous disease and vascular assessment.

• 1,000+ EVLA procedures
• Hundreds of foam sclerotherapy procedures
• Hundreds of phlebectomies
• Hundreds of vascular duplex ultrasound examinations

These clinical experiences have motivated my interest in understanding how AI, sensing and computational modelling can be translated into practical vascular care.

• Python
• R
• Machine Learning
• Statistical modelling
• Logistic regression
• Generalized Linear Models
• Mixed-effects modelling
• Predictive modelling
• Time-series analysis
• Explainable AI
• Clinical decision-support systems

• ESP32 / embedded systems
• Biomedical sensors
• IoT / IoMT
• BLE / Wi-Fi
• MQTT
• Physiological signal processing
• PPG / ECG
• HL7 FHIR
• Healthcare interoperability
• Edge computing

• Python
• TypeScript
• JavaScript
• React
• Next.js
• Django
• FastAPI
• PostgreSQL
• MySQL
• REST APIs
• Linux
• Docker
• Git / GitHub

An end-to-end clinical prediction and statistical modelling project demonstrating reproducible machine-learning and statistical workflows for medical research.

Focus:

• Clinical predictive modelling
• Logistic regression
• Machine learning
• Statistical validation
• R/Python integration
• Reproducible research

View repository →

A prototype healthcare IoT architecture connecting physiological sensing, edge computing, clinical telemetry and HL7 FHIR-based interoperability.

Physiological Sensor
        ↓
ESP32 / Edge Device
        ↓
Signal Processing
        ↓
Telemetry
        ↓
FHIR
        ↓
Healthcare System

Focus:

• Biomedical IoT
• PPG signal processing
• Heart-rate estimation
• SpO₂ estimation
• Edge computing
• HL7 FHIR
• Clinical interoperability

View repository →

Development of machine-learning systems using:

duplex ultrasound + clinical data + venous anatomy + treatment parameters

to predict:

• treatment success
• recurrence
• recanalisation
• complications
• patient outcomes

A future clinical decision-support platform for personalised selection of venous interventions such as:

EVLA | foam sclerotherapy | phlebectomy | other endovenous treatments

Development of patient-specific computational models combining:

ultrasound + anatomy + haemodynamics + clinical data

to simulate and predict treatment outcomes.

Combining:

wearable sensors + IoT + physiological signals + AI

for longitudinal monitoring after vascular intervention.

I am interested in research that moves beyond prediction toward real-world clinical translation.

My long-term vision is:

        Clinical Problem
               ↓
          Hypothesis
               ↓
       AI / Computational Model
               ↓
        Biomedical Prototype
               ↓
       IoT / Sensor Data
               ↓
        Clinical Validation
               ↓
        Real-world Translation

I believe the future of biomedical research will increasingly combine clinical expertise, artificial intelligence, engineering and autonomous experimentation.

To develop internationally relevant research in:

Intelligent Vascular Biomedical Engineering

with applications in vascular disease, personalised intervention, medical imaging, physiological sensing and AI-enabled clinical decision support.

I am particularly interested in collaborating with researchers in:

vascular surgery • biomedical engineering • medical imaging • artificial intelligence • digital health • computational modelling • medical devices

I am continuously developing skills in:

• Advanced clinical statistics
• Machine learning
• Deep learning
• Medical image analysis
• Signal processing
• Biomedical engineering
• Embedded systems
• Digital twins
• Causal inference
• Clinical research methodology

I am interested in research collaborations involving:

• Clinical AI
• Vascular imaging
• AI-assisted intervention
• Biomedical sensors
• Healthcare IoT
• Digital twins
• Medical-device development
• Translational biomedical engineering

Open to collaboration with clinicians, engineers, data scientists, biomedical researchers and research institutions.

GitHub:
https://github.com/neranjandissanayake

I am interested in connecting with researchers working at the intersection of vascular medicine, AI, biomedical engineering and intelligent healthcare systems.