STROKE PREDICTICN

• 

  LED RED :RISK & THINGSPEAK: LIVE UPDATE AND VISUALIZATION

• 

  LED YELLOW - Arrhythmia is a condition in which the heart beats in an irregular rhythm — too fast, too slow, or unevenly.

• 

  ITS COMPLETE DISPLAY OF MY WATCH MODEL LCD DISPLAY

• 

  LED GREEN : SAFE

Inspiration

StrokeRange – AI Powered Wearable for Real-Time Stroke Risk Prediction Inspiration

Stroke is one of the leading causes of death and long-term disability worldwide. Many stroke cases occur suddenly without early warning signs, and delayed medical response often leads to severe consequences. This inspired us to develop a smart healthcare solution capable of continuously monitoring patient health and predicting stroke risk before critical conditions occur.

We wanted to create a system that combines Artificial Intelligence, IoT, and cloud technologies to support preventive healthcare rather than reactive treatment. The idea was to design an intelligent wearable ecosystem that can monitor health parameters in real time, analyze data, and instantly alert caregivers during emergencies.

What it does

The project simulated wearable sensor data such as Heart Rate, SpO₂, and motion activity using the Wokwi platform. The collected data was transmitted to the ThingSpeak cloud platform for real-time monitoring and storage. A machine learning model analyzed the health parameters to identify abnormal patterns and estimate stroke risk conditions.

The processed data was visualized through a mobile dashboard, allowing continuous remote monitoring of patient health. Whenever critical conditions or high-risk situations were detected, the system automatically sent emergency alert notifications through Telegram to caregivers or healthcare providers.

The project successfully demonstrated the integration of IoT, cloud computing, machine learning, and smart communication technologies into a unified preventive healthcare solution.

How we built it

First, wearable healthcare sensor data such as Heart Rate, SpO₂, and motion activity were simulated using the Wokwi platform with ESP32. The simulated sensor values were continuously transmitted to the ThingSpeak cloud platform using IoT communication protocols.

The cloud platform stored and visualized the incoming patient health data in real time. A machine learning model was then used to analyze the collected health parameters and predict stroke risk based on abnormal patterns and predefined healthcare conditions.

To improve accessibility and monitoring, a mobile dashboard was used for live patient visualization. Additionally, Telegram API integration was implemented to automatically send emergency notifications whenever high-risk conditions were detected.

The complete workflow combined sensor simulation, cloud storage, AI analysis, mobile monitoring, and instant communication into one scalable smart healthcare solution.

Challenges we ran into

Building an integrated healthcare monitoring system involved several technical challenges:

Ensuring accurate simulation of real-time sensor values Managing reliable cloud communication between platforms Handling healthcare data preprocessing for AI analysis Reducing false prediction alerts in the system Designing a scalable and efficient monitoring workflow Integrating multiple technologies into one synchronized ecosystem

Despite these challenges, we successfully created a working prototype demonstrating real-time monitoring, AI-based analysis, and emergency alert functionality.

Accomplishments that we're proud of

Successfully developed an AI + IoT based healthcare monitoring system Integrated Wokwi simulation with ThingSpeak cloud platform Implemented real-time patient health monitoring and visualization Built a machine learning model for stroke risk prediction Created automated Telegram emergency alert functionality Combined cloud computing, AI, and wearable healthcare concepts into one ecosystem Designed a scalable and cost-effective preventive healthcare solution Demonstrated a working prototype capable of real-time data analysis and smart alerts

What we learned

Learned the integration of AI and IoT in healthcare applications Gained experience in real-time cloud data communication using ThingSpeak Understood wearable healthcare monitoring concepts and workflows Learned machine learning techniques for stroke risk prediction Explored sensor simulation using the Wokwi platform Improved knowledge of cloud-based visualization and remote monitoring Learned Telegram API integration for automated emergency alerts Developed problem-solving and system integration skills through project implementation

What's next for STROKE PREDICTICN

Integrate real wearable hardware sensors for live patient monitoring Develop a dedicated mobile application for healthcare tracking Improve prediction accuracy using advanced deep learning models Add ECG and arrhythmia detection for enhanced stroke analysis Integrate hospital and ambulance emergency support systems Enable cloud-based patient history and health analytics Expand the system to support multiple disease prediction modules Transform StrokeRange into a scalable smart healthcare platform for real-world deployment

Built With

• c++
• telegrambot
• thingspeak
• wokwi