Predict Heart Disease With F# And ML.NET Machine Learning
In this article, I am going to build an F# app with ML.NET and NET Core that reads medical data and predicts if a patient has a risk of heart disease. I will show you how to do this with only 120 lines of code.
ML.NET is Microsoft’s new machine learning library. It can run linear regression, logistic classification, clustering, deep learning, and many other machine learning algorithms.
NET Core is the Microsoft multi-platform NET Framework that runs on Windows, OS/X, and Linux. It’s the future of cross-platform NET development.
And F# is a perfect language for machine learning. It’s a 100% pure functional programming language based on OCaml and inspired by Python, Haskell, Scala, and Erlang. It has a powerful syntax and lots of built-in classes and functions for processing data.
The first thing I need for my app is a data file with patients, their medical info, and their heart disease risk assessment. I will use the famous UCI Heart Disease Dataset which has real-life data from 303 patients.
The training data file looks like this:
It’s a CSV file with 14 columns of information:
- Sex: 1 = male, 0 = female
- Chest Pain Type: 1 = typical angina, 2 = atypical angina , 3 = non-anginal pain, 4 = asymptomatic
- Resting blood pressure in mm Hg on admission to the hospital
- Serum cholesterol in mg/dl
- Fasting blood sugar > 120 mg/dl: 1 = true; 0 = false
- Resting EKG results: 0 = normal, 1 = having ST-T wave abnormality, 2 = showing probable or definite left ventricular hypertrophy by Estes’ criteria
- Maximum heart rate achieved
- Exercise induced angina: 1 = yes; 0 = no
- ST depression induced by exercise relative to rest
- Slope of the peak exercise ST segment: 1 = up-sloping, 2 = flat, 3 = down-sloping
- Number of major vessels (0–3) colored by fluoroscopy
- Thallium heart scan results: 3 = normal, 6 = fixed defect, 7 = reversible defect
- Diagnosis of heart disease: 0 =…