How bdeekshith066/neuro-well works
Project Type and Purpose
• Neuro-Well is a full-stack health-tech application aimed at streamlining stroke diagnosis and neurorehabilitation. It integrates multi-modal assessments – including cognitive, speech, and motor tests – into a comprehensive, data-driven platform. This is evident from the README, which details how the platform leverages computer vision, AI, and even hardware sensor integration (e.g., flex sensors, hand gloves with servo motors) to provide real-time evaluations.
• The project also includes research papers and presentations, indicating it might be partially exploratory, with a clear focus on clinical decision making and rehabilitation strategies.
File Structure
• Top-level files:
– Research papers (in “Referred Research Papers”) suggest that this project is heavily grounded in academic and clinical research insights.
– “about_Project.txt”, “NeuroWell Report.pdf”, and “NueroWell PPT.pptx” provide additional context and documentation.
• Project Code Directory (“nuerowell code”):
– Contains multiple Python files (app.py, community.py, home.py, game.py, physio.py, etc.), which likely stand for distinct functional modules (e.g., application startup, community interactions, patient home page, rehabilitation games, etc.).
– A CSV file (patients_data.csv) indicates that local data storage is in play, even though the README mentions Google Sheets for score storage.
– Subfolders for “images” hold static assets, demonstrating how user interfaces incorporate graphics.
README for Architectural Insights
• The README reveals the use of:
– Streamlit for the interactive web interface.
– Various external APIs & libraries: Google Sheets, Speech Recognition Model, Google Translate, OpenCV, MediaPipe, CVZone, and Matplotlib.
• It also describes multiple user interface components – Home page, Nurse Dashboard, Speech Test, and several game elements – signifying that the system is modular with distinct functions.
• Hardware integration is highlighted, showing that the application isn’t purely digital but is augmented with sensor-based devices (flex sensors, hand gloves, LED displays).
a. Main Components:
• Frontend: Streamlit-based web interface that provides multiple pages (Home Page, Nurse Dashboard, and various assessment/game modules).
• Backend Application Logic: Consists of individual Python modules (app.py, community.py, home.py, game.py, etc.) that handle business logic, game mechanics, and module-specific processes (e.g., speech analysis, physiotherapy tests).
• Data Storage: Incorporates both a local CSV (patients_data.csv) and remote storage via Google Sheets for storing patient scores and assessment data.
• External Services & APIs: External integrations like Google Translate, Speech Recognition service, and third-party libraries (OpenCV, MediaPipe, CVZone, Matplotlib) involved in image processing, hand tracking, and graphical representations.
• Hardware Interface/Integration: Represents the actual hardware components (flex sensors, hand gloves with servo motors, LED display) that relay sensor data back into the system for real-time evaluation and feedback.
b. Relationships and Interactions:
• The Frontend interacts with the Backend logic through function calls and event driven responses.
• The Backend communicates with the Data Storage system and external APIs to fetch, process, and store patient data.
• Real-time sensor data from hardware integration devices flows into the Backend, possibly via a dedicated module (such as “hand.py” or “physio.py”) for processing.
• External libraries (OpenCV, MediaPipe, etc.) are integrated within these modules to process images or video streams, and their processing results are channeled towards the UI for display.
• Data flows from user interactions (e.g., taking a speech test) through the corresponding module to external services (like speech recognition) and back, with results visualized using Matplotlib or directly within the Streamlit interface.
c. Important Architectural Patterns and Design Principles:
• Modular Design: Each test or assessment function is modularized into separate Python files (e.g., game.py, rehab.py, home.py) for clarity and ease of updates.
• Separation of Concerns: The system clearly distinguishes between the user interface (Streamlit frontend), business logic (Python modules), and data/integration layers (external APIs, hardware interfaces).
• Extensibility: With separate modules for community features, games, and patient management, the architecture is designed to accommodate new tests or hardware components in the future.
d. Relevant Technologies, Frameworks, or Libraries:
• Streamlit for the UI layer.
• Python for backend module implementations with libraries such as OpenCV, MediaPipe, CVZone, and Matplotlib.
• Google Sheets for cloud-based patient data management.
• External APIs for speech recognition and Google Translate.
• CSV file as a local fallback for patient data.
• Hardware components controlled by embedded code (potentially interfaced with Python modules).
Specific Elements
• Use clear labels for each component:
• "Streamlit Frontend", "Backend Logic (app.py, community.py, etc.)", "Data Storage (Google Sheets, patients_data.csv)", "External APIs (Google Translate, Speech Recognition)", and "Hardware Interface (Flex Sensors, Hand Gloves, LED Display)".
• Hardware data flow from "Sensors" to "Backend Processing".
• And another for hardware components.