Python

Heart Disease Detection Using Python And Machine Learning



►Mayoclinic Information On Cardiovascular/Heart Disease:

⭐Please Subscribe !⭐

⭐Support the channel and/or get the code by becoming a supporter on Patreon:

⭐Websites:

⭐Helpful Programming Books
► Python (Hands-Machine-Learning-Scikit-Learn-TensorFlow):

► Learning…

Similar Posts

35 thoughts on “Heart Disease Detection Using Python And Machine Learning
  1. I thought having this disease was as a result of my old age, while I was diagnosed of heart disease Dec. 19 2020, I used series of medication but I was still having the severe pain, until I used an herbal mixture from Dr. Gbenga which I saw on YouTube and I was completely cured, I appreciate Dr. Gbenga for his help

  2. For 6 years I have been battling with cardiovascular disease which almost took my life, but when I came across Dr. Gbenga, I decided to give a try to his herbal mixture, which I used for sometime  but today am completely cured and strong, thank you Dr. Gbenga for your help.

  3. A healthy life will always find life meaningful, being finally cured from this heart disease using an herbal medicine from Dr. Gbenga was my greatest Adventure in life, all thanks to Dr. Gbenga for his help.

  4. Correct me if I'm wrong. if you are using random forest you have to use the 'max_features ' property to tune the model. When the select the 'max_features' value should me square root of the features for classifications and regression it should be a log base 2 of features. I got the random forest for 90.1% accuracy for random forest while splitting the data set to 80:20. Is there any reason behind you did split data 75:25?
    I am really interested in your videos. they are so interesting to watch. Keep it up.

  5. forest = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 1)
    forest.fit(X_train, Y_train)

    ValueError: Unknown label type: 'continuous-multioutput'

    Any solution for this issue ?

  6. this dataset has no support from any univerity. someone just put it on kaggle. however it is useful for training but not to have on account for research. can you do the same with cleveland dataset with 303 instance? i have tried but the accuracy is less than 84%

  7. Since we have done feature scaling to 0-1 range for X. After this if we want to predict for new values how do we enter values? Do we need to scale the values as well?

Leave a Reply

Your email address will not be published. Required fields are marked *