Difference between revisions of "Watch me Build a Healthcare Startup"
(→Dr Source) |
|||
Line 44: | Line 44: | ||
* [[Natural Language Processing (NLP)]] | * [[Natural Language Processing (NLP)]] | ||
* [http://github.com/re-search/DocProduct DocProduct] | * [http://github.com/re-search/DocProduct DocProduct] | ||
− | * [http://github.com/dmis-lab/biobert BioBERT | DMIS-Lab - GitHub] a language representation model for biomedical domain, especially designed for biomedical text mining tasks such as biomedical named entity recognition, relation extraction, question answering, etc. | + | * AI Model(BioBERT , input question into retrained bioBERT to convert into an embedding. Input the embedding into a fully connected neural network, output an embedding for similarity lookup. Most similar Q&A's used by GPT-2 to generate an answer. ) |
− | ** [[Bidirectional Encoder Representations from Transformers (BERT)]] | + | ** [http://github.com/dmis-lab/biobert BioBERT | DMIS-Lab - GitHub] a language representation model for biomedical domain, especially designed for biomedical text mining tasks such as biomedical named entity recognition, relation extraction, question answering, etc. |
+ | *** [[Bidirectional Encoder Representations from Transformers (BERT)]] | ||
* [http://flutter.dev/ Flutter] is Google’s portable UI toolkit for building natively-compiled applications for mobile, web, and desktop from a single codebase. | * [http://flutter.dev/ Flutter] is Google’s portable UI toolkit for building natively-compiled applications for mobile, web, and desktop from a single codebase. | ||
** [http://flutter.dev/docs/development/ui/widgets Flutter Widget catalog] | ** [http://flutter.dev/docs/development/ui/widgets Flutter Widget catalog] |
Revision as of 18:37, 26 June 2019
YouTube search... ...Google search
- How do I leverage AI?
- Watch me Build a Marketing Startup | Siraj Raval
- Watch me Build a Finance Startup | Siraj Raval
- Watch me Build a Trading Bot | Siraj Raval
- Assistants
- Bot Framework
- Natural Language Processing (NLP)
- Bidirectional Encoder Representations from Transformers (BERT)
- AnyChart
- DialogFlow | Google
- Alpaca API lets you build and trade with real-time market data for free
- Plaid for users to connect their bank accounts to an app
- Word2Vec
- React Stripe Checkout for using Stripe Checkout as a React component]
- React CSV Reader React component that handles csv file input and its parsing
- Node.js - JavaScript runtime built on Chrome's V8 JavaScript engine
- React = JavaScript library for building user interfaces
- PostgreSQL Open Source Relational Database
- Knex.js SQL query builder
- GraphQL a query language for your API, and a server-side runtime for executing queries
- Relay a JavaScript framework for building data-driven React applications
- TensorFlow.js
- D3.js bring data to life using HTML, SVG, and CSS
- Google Analytics
- Clearbit marketing data engine
- Watchman a file watching service
Dr Source
I've built an open source app called Dr Source, your personal medical question answering service! It uses a model called BioBERT trained on over 700K Q&As from PubMed, HealthTap, and other health related websites. I used Flutter to build an app around it and present it to you as a more thought out idea. I was excited by what I saw possible with BioBERT's output in Python notebooks, and thought a cleaner interface could absolutely make it a viable business. There are millions of people in this world without access to healthcare, and while this app isn't perfect, an automated diagnosis is better than no diagnosis. I urge you to use this code and video as a starting point in your journey to generate value for the world, and build wealth while doing so. Enjoy! How to Build a Biomedical Startup | Siraj Raval
- Project Jupyter Notebook | Siraj Raval
- Natural Language Processing (NLP)
- DocProduct
- AI Model(BioBERT , input question into retrained bioBERT to convert into an embedding. Input the embedding into a fully connected neural network, output an embedding for similarity lookup. Most similar Q&A's used by GPT-2 to generate an answer. )
- BioBERT | DMIS-Lab - GitHub a language representation model for biomedical domain, especially designed for biomedical text mining tasks such as biomedical named entity recognition, relation extraction, question answering, etc.
- Flutter is Google’s portable UI toolkit for building natively-compiled applications for mobile, web, and desktop from a single codebase.
- Dart is a client-optimized language for fast apps on any platform
- Firebase | Google's storage service
Macy
I'm going to show you the entire process I used to conceive, design, and build the prototype for a healthcare startup business! This app is called "Macy", your personal Yoga Instructor. It uses a machine learning model called PoseNet to detect human poses and overlay a skeleton stick figure on top. I retrained posenet on labeled Yoga poses images so it could detect when a person correctly performs a certain pose, then i used speech generation to have the Flutter app guide your actions from pose to pose, just as a real Yoga instructor would do. The goal is to help a user reduce stress, anxiety, and depression through a series of guide meditative poses. I've integrated a subscription service and some interesting design schemes, but the app isn't finished! There is still more to do. The point is to give you the starting template to start your own profitable business. Enjoy! How to Build a Healthcare Startup | Siraj Raval - GitHub
- Project Jupyter Notebook | Siraj Raval
- Flutter is Google’s portable UI toolkit for building natively-compiled applications for mobile, web, and desktop from a single codebase.
- Dart is a client-optimized language for fast apps on any platform
- Firebase | Google's service & mobile development platform
- Paymenta
- TensorFlow
- TensorFlow Lite
- Transfer Learning
- PoseNet is a vision model that can be used to estimate the pose of a person in an image or video
- Using Transfer-Learning to Detect Yoga Poses | Nhoral - Medium
- YogAI is a responsive virtual yoga instructor using pose estimation to guide and correct a yogi
- tf-pose-estimation 'Openpose', human pose estimation algorithm, have been implemented using Tensorflow
- tf.image.non_max_suppression (NMS) algorithm
- Bipartite Graph | WolframMathWorld
- Line integral | Wikipedia
- MobileNetV2: Inverted Residuals and Linear Bottlenecks | M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. Chen
- Android Studio for building apps on Android devices
- Visual Studio Code
SmartMedScan
I'm going to build a medical imaging classification app called SmartMedScan! The potential customers for this app are medical professionals that need to scale and improve the accuracy of their diagnoses using AI. From ideation, to logo design, to integrating features like payments and AI into a single app, I'll show you my 10 step process. I hope that by seeing my thought process and getting familiar with the sequence of steps I'll demonstrate, you too will be as inspired as I am to use this technology to do something great for the world. Enjoy! "AI Startup Prototype" | Siraj Raval - GitHub
- Project Jupyter Notebook | Siraj Raval
- BrandMark create a unique, professional logo using NLP and generative network
- MailChimp landing page creator
- The Lean Startup | Eric Ries
- Flask a microframework for Python
- Flask boilerplate | Max Halford
- flaskSaaS | Max Halford starting point to build your SaaS in Flask & Python, with Stripe subscription billing
- flask-image-uploader | bboe
- Flask-Login for the user accounts
- Flask-SQLAlchemy interacting with the database
- Flask-WTF and WTForms for the form handling.
- Flask-Mail for sending mails.
- Flask-Bcrypt for generating secret user passwords.
- Flask-Admin for building an administration interface.
- Flask-Script for managing the app
- flask-stripe Stripe Checkout & user registration
- Stripe for subscription billing
- Flask-DebugToolBar for adding a performance toolbar in development
- TensorFlow
- Keras
- ImageNet: VGGNet, ResNet, Inception, and Xception with Keras
- itsdangerous for generating random tokens for the confirmation emails.
- structlog for logging.
- gunicorn for acting as a reverse-proxy for Nginx.
- Semantic UI for the global style. Very similar to Bootstrap
- Leaflet JS for the map, added for the sake of the example.