DEV Community: Madhankumar Anandan

DermaScribe AI: AI-Powered Backend for Dermatology Workflows

Madhankumar Anandan — Fri, 04 Jul 2025 14:26:02 +0000

*Using Spring Boot, JWT, and OpenAI to enhance medical transcription*

🩺 Introduction

In clinical settings, dermatologists often spend a significant amount of time transcribing session notes and summarizing case details. What if AI could assist with this routine work—helping doctors focus more on diagnosis and treatment?

DermaScribe AI is a backend service built with Spring Boot that integrates AI models (like OpenAI) to support dermatologists through automated transcription and analysis. This system securely handles session data, processes it intelligently, and exposes clean REST APIs for seamless integration with frontend or mobile apps.

🔍 Why DermaScribe AI?

Medical transcription is time-consuming, repetitive, and prone to inconsistency. By integrating AI into clinical backend systems, we can:

Automate session summarization
Provide intelligent suggestions for diagnosis
Offer structured session storage and easy retrieval

🧱 System Architecture

The project is built using a layered architecture, making it modular and extendable:

✅ Core Features:

JWT Authentication & Authorization using Spring Security
AI-Powered Analysis via OpenAI's API
RESTful APIs for session management
Modular Design for maintainability and scalability

🗂 Layered Breakdown:

Security Layer
Handles authentication/authorization with SecurityConfig, JwtTokenProvider, and a customizable CustomUserDetailsService.
Controller Layer

AuthController: Manages user login and token generation
SessionController: Exposes endpoints to create and retrieve dermatology sessions

Service Layer

AIProcessorService: Central logic to call and process AI output
OpenAIService: Makes requests to OpenAI and parses responses

Data Layer

JPA repositories and domain models to persist dermatology sessions

🧪 Running the Project

🔧 Prerequisites:

Java 17+
Maven 3.6+
OpenAI API Key
Git

📦 Clone the Repository:

git clone https://github.com/amkumar072/DermaScribe-AI
cd derma_scribe_ai_springboot

⚙️ Setup Configuration:

Update application.properties with:

OpenAI API key
JWT secrets
Database settings (or use in-memory H2 for dev)

🔨 Build and Run:

mvn clean install
mvn spring-boot:run

By default, the server will run on http://localhost:8080.

🧪 API Testing:

Use Postman or Swagger UI to test:

/auth/login
/api/sessions/create
/api/sessions/{id}
/api/{id}/upload

Sample credentials (dev mode):

Username: dermatologist
Password: password

📌 What’s Next?

Some ideas for future enhancements:

NLP fine-tuning for more specialized medical suggestions
Audit logging and analytics dashboard
Frontend (React or Android) to consume APIs

🚀 Conclusion

DermaScribe AI is a step toward smarter, AI-assisted healthcare. It’s modular, secure, and designed for real-world extensibility. If you're a developer, clinician, or AI enthusiast, I’d love your feedback or collaboration!

🔗 GitHub: https://github.com/amkumar072/DermaScribe-AI

AI #HealthcareAI #SpringBoot #Java #OpenSource #MedicalTranscription #BackendDevelopment #RESTAPI #TechForGood #ClinicalAI #Dermatology #OpenAI #ProjectShowcase

Build an AI-Powered SQL Generator Using OpenAI and Spring Boot

Madhankumar Anandan — Mon, 16 Jun 2025 17:20:07 +0000

Ever wished you could just ask for the SQL query you need instead of writing it? In this project, I built a Java-based backend that lets you do exactly that.

🔗 Project Repo

Check out the full code on GitHub:
👉 github.com/amkumar072/AI-SQL-Generator

🧩 What Is It?

AI-SQL Generator is a backend application that transforms natural language prompts into SQL queries using OpenAI's GPT API. It’s perfect for:

Developers building analytics dashboards
Business users who aren’t fluent in SQL
Teams needing AI-driven query interfaces

🚀 How It Works

You send a POST request with:

A natural language prompt
The table schema (as a SQL CREATE TABLE string)

And you get back a GPT-generated SQL query that's ready to use.

📦 Sample Request

POST /query
Content-Type: application/json

{
  "question": "Which seller has delivered the most orders to customers in Rio de Janeiro"
}

✅ Sample Response

{
  "sql": "SELECT * FROM Employee ORDER BY salary DESC LIMIT 5;"
}

🔧 Tech Stack

Layer	Tech Used
Language	Java 17
Framework	Spring Boot
API	OpenAI GPT (via HTTPS)
Config	dotenv-java for secrets
Build Tool	Maven
Testing	Postman / curl

⚙️ Setup Instructions

Clone the repo:

git clone https://github.com/amkumar072/AI-SQL-Generator.git
cd AI-SQL-Generator

Add your OpenAI key to a .env file:

OPENAI_API_KEY=your_openai_api_key

Run the Spring Boot app:

mvn spring-boot:run

📈 Example Use Cases

🔍 Internal tools for data analysts
🧠 Chatbot assistants that answer data questions
🖥️ AI dashboards for business users
🛠️ Dev platforms embedding auto-SQL features

📌 What’s Next?

Here are a few potential enhancements:

UI frontend with React or Angular
Support for SQL dialects (MySQL, PostgreSQL, etc.)
Real-time database validation for generated SQL

🧠 Why I Built This

The idea came from a common pain point: not everyone can write SQL, but everyone needs data. Tools like ChatGPT already understand data requests well—why not bring that power into a dedicated backend app?

This project combines the reliability of Java/Spring Boot with the intelligence of OpenAI GPT to deliver something actually useful for devs and data teams alike.

📬 Let’s Connect

If you liked this or have ideas to improve it, feel free to:

⭐ Star the repo
Drop a comment below
Connect with me on LinkedIn or GitHub

#java #springboot #openai #sql #gpt #api #backend #ai #devtools #projectshowcase

Deploy Application to Firebase

Madhankumar Anandan — Tue, 02 Feb 2021 20:55:23 +0000

Deploy the ionic application in firebase

Installation

Make sure you have installed the firebase-tools. If not, please find the following command to install

npm install -g firebase-tools

Login & Test the connection

firebase login:ci

Check the list of projects available. It displays the list of projects available.

firebase projects:list

Initialize a project

Initialize the project with the following command.

firebase init

Follow as per instructions and pick the Hosting and then select the project.
Post selection set of question will pop up

What do you want to use as your public directory? - Mention your build folder (e.g www).
Configure as a single-page app (rewrite all URLs to /index.html)? - No
Set up automatic builds and deploys with GitHub? - Y

It requests you to authorize the GitHub by CLI URL.

For which GitHub repository would you like to set up a GitHub workflow? (format: user/repository) - Updated the user and repository (e.g amkumar072/firebase-deploy-sample)

It will set up an account FIREBASE_SERVICE_ACCOUNT for your project.

Set up the workflow to run a build script before every deploy? (y/N) - Select depend upon your request. I have selected YES, then the next question will appear.
What script should be run before every deploy? (npm ci && npm run build) - Provide the build script/commands or else press enter to take the default.
Set up automatic deployment to your site's live channel when a PR is merged? (Y/n) - Select depend upon your request. I have selected NO.

Initialization is completed. By the time you would able to see the 3 files are created

.firebaserc
firebase.json
firebase-hosting-pull-request.yml

Deploy to Firebase

Now we are in the final part of the process. Deploy your project with the following commands.

note: Make sure the project is already built (npm run build)

firebase deploy

Changes will deploy into Firebase and the URL will be displayed in Console.

Please find the source code in Github

Happy Deployment :)

How to Create a Firebase Project

Madhankumar Anandan — Mon, 01 Feb 2021 19:54:08 +0000

Firebase

Firebase is a platform developed by Google for creating mobile and web applications. It provides the services such as

Authentication
Hosting
Storage
DB
Analytics etc...

Project Creation

Login to Firebase console
Click on Add Project.
Enter the Project Name and click Continue.
Continue on the Google Analytics section. !
Select a Default Account else to create a new one and click Create Project.
Few seconds to create. Once created you would able to see the project.
Successfully Project is created.