{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":791239200,"defaultBranch":"main","name":"Heart-Failure-Prediction-Model","ownerLogin":"DDILLOUD","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2024-04-24T10:56:47.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/167950449?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1713956642.0","currentOid":""},"activityList":{"items":[{"before":"69aefe131dcbeaf7bcffcc1d0080c9a7c1c5fcf4","after":"0078fadf39044275203bb906def816436ebe0756","ref":"refs/heads/main","pushedAt":"2024-06-13T20:38:17.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"Update README.md","shortMessageHtmlLink":"Update README.md"}},{"before":"18fce99903691fd98cdacc3ae7e2b4c33cc735ad","after":"69aefe131dcbeaf7bcffcc1d0080c9a7c1c5fcf4","ref":"refs/heads/main","pushedAt":"2024-04-24T11:44:45.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"evaluate.py\n\nThis script contains functions for calculating various evaluation metrics and generating evaluation reports to assess the model's performance.","shortMessageHtmlLink":"evaluate.py"}},{"before":"b42a51ccd0228965ae95c35c63f1490cdbbc035d","after":"18fce99903691fd98cdacc3ae7e2b4c33cc735ad","ref":"refs/heads/main","pushedAt":"2024-04-24T11:38:35.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"utils.py\n\n This script contains various utility functions that assist in data preprocessing, feature engineering","shortMessageHtmlLink":"utils.py"}},{"before":"6d936321f05cb88d274e09bdd7ec2ae256646ad5","after":"b42a51ccd0228965ae95c35c63f1490cdbbc035d","ref":"refs/heads/main","pushedAt":"2024-04-24T11:35:02.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"predict.py\n\nTo make predictions with the trained machine learning model (Heart-Failure-Prediction-Model), you can use the predict.py script.","shortMessageHtmlLink":"predict.py"}},{"before":"d6aa4a9c3c63cae59910cf72f75924e418c40480","after":"6d936321f05cb88d274e09bdd7ec2ae256646ad5","ref":"refs/heads/main","pushedAt":"2024-04-24T11:31:59.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"Create train.py\n\nThe script that we use to train our Heart-Failure-Prediction-Model","shortMessageHtmlLink":"Create train.py"}},{"before":"de8cc65c2c0ed28fadba2ba7ea39ec8a28bf9e9d","after":"d6aa4a9c3c63cae59910cf72f75924e418c40480","ref":"refs/heads/main","pushedAt":"2024-04-24T11:24:14.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"Dataset for model training and testing.\n\nPeople with cardiovascular disease or who are at high cardiovascular risk (due to the presence of one or more risk factors such as hypertension, diabetes, hyperlipidemia or already established disease) need early detection and management wherein a machine learning model can be of great help.\r\n\r\nAttribute Information\r\nAge: age of the patient [years]\r\nSex: sex of the patient [M: Male, F: Female]\r\nChestPainType: chest pain type [TA: Typical Angina, ATA: Atypical Angina, NAP: Non-Anginal Pain, ASY: Asymptomatic]\r\nRestingBP: resting blood pressure [mm Hg]\r\nCholesterol: serum cholesterol [mm/dl]\r\nFastingBS: fasting blood sugar [1: if FastingBS > 120 mg/dl, 0: otherwise]\r\nRestingECG: resting electrocardiogram results [Normal: Normal, ST: having ST-T wave abnormality (T wave inversions and/or ST elevation or depression of > 0.05 mV), LVH: showing probable or definite left ventricular hypertrophy by Estes' criteria]\r\nMaxHR: maximum heart rate achieved [Numeric value between 60 and 202]\r\nExerciseAngina: exercise-induced angina [Y: Yes, N: No]\r\nOldpeak: oldpeak = ST [Numeric value measured in depression]\r\nST_Slope: the slope of the peak exercise ST segment [Up: upsloping, Flat: flat, Down: downsloping]\r\nHeartDisease: output class [1: heart disease, 0: Normal]\r\nSource\r\nThis dataset was created by combining different datasets already available independently but not combined before. In this dataset, 5 heart datasets are combined over 11 common features which makes it the largest heart disease dataset available so far for research purposes. The five datasets used for its curation are:\r\n\r\nCleveland: 303 observations\r\nHungarian: 294 observations\r\nSwitzerland: 123 observations\r\nLong Beach VA: 200 observations\r\nStalog (Heart) Data Set: 270 observations\r\nTotal: 1190 observations Duplicated: 272 observations\r\n\r\nFinal dataset: 918 observations\r\n\r\nEvery dataset used can be found under the Index of heart disease datasets from UCI Machine Learning Repository on the following link: https://archive.ics.uci.edu/ml/machine-learning-databases/heart-disease/\r\n\r\nCitation\r\nfedesoriano. (September 2021). Heart Failure Prediction Dataset. Retrieved [Date Retrieved] from https://www.kaggle.com/fedesoriano/heart-failure-prediction.\r\n\r\nAcknowledgments\r\nCreators:\r\n\r\nHungarian Institute of Cardiology. Budapest: Andras Janosi, M.D.\r\nUniversity Hospital, Zurich, Switzerland: William Steinbrunn, M.D.\r\nUniversity Hospital, Basel, Switzerland: Matthias Pfisterer, M.D.\r\nV.A. Medical Center, Long Beach and Cleveland Clinic Foundation: Robert Detrano, M.D., Ph.D.","shortMessageHtmlLink":"Dataset for model training and testing."}},{"before":"5f5e85f00673c89e788ee7dda1f04025c579ebe7","after":"de8cc65c2c0ed28fadba2ba7ea39ec8a28bf9e9d","ref":"refs/heads/main","pushedAt":"2024-04-24T11:16:37.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":".gitignore","shortMessageHtmlLink":".gitignore"}},{"before":"6297ee46dba20468c8e1d800142c83af6d41cb0b","after":"5f5e85f00673c89e788ee7dda1f04025c579ebe7","ref":"refs/heads/main","pushedAt":"2024-04-24T11:10:15.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"Add files via upload\n\nHeart Failure Prediction Model Building Steps\r\n1. Data Preparation and Exploration\r\nLoad the dataset (Heart.csv) containing clinical data related to heart health.\r\nExplore the dataset to understand its structure, features, and target variable.\r\nCheck for missing values and handle them appropriately (e.g., imputation or removal).\r\nEncode categorical variables into numerical values using techniques like one-hot encoding or label encoding.\r\nSplit the dataset into features (X) and the target variable (y).\r\n2. Data Preprocessing\r\nNormalize numerical features to ensure uniform scale across different variables.\r\nPerform feature scaling to standardize the range of features and improve model performance.\r\nHandle any remaining preprocessing steps specific to the dataset, such as handling outliers or feature engineering.\r\n3. Model Selection and Training\r\nChoose an appropriate machine learning algorithm for the task, such as the Random Forest Classifier.\r\nSplit the preprocessed data into training and testing sets to evaluate the model's performance.\r\nTrain the selected model on the training data using appropriate hyperparameters.\r\nValidate the trained model on the testing data to assess its performance.\r\n4. Model Evaluation and Fine-Tuning\r\nEvaluate the model's performance using metrics like accuracy, precision, recall, and F1-score.\r\nUse techniques like cross-validation or grid search to fine-tune the model's hyperparameters for improved performance.\r\nExperiment with different feature engineering techniques or algorithms to enhance model accuracy and generalization.\r\n5. Results Analysis and Interpretation\r\nAnalyze the model's predictions and evaluate its strengths and weaknesses.\r\nInterpret the importance of different features in predicting heart failure using techniques like feature importance plots.\r\nDiscuss any insights gained from the model and its implications for clinical practic","shortMessageHtmlLink":"Add files via upload"}},{"before":"97a0550deda8844e5e3308ab7fd5110a9fd86bda","after":"6297ee46dba20468c8e1d800142c83af6d41cb0b","ref":"refs/heads/main","pushedAt":"2024-04-24T11:07:12.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"Add files via upload\n\nThe Heart Failure Prediction Model utilizes the Random Forest Classifier algorithm, a powerful ensemble learning method, to predict the probability of heart failure in patients. This model analyzes a range of clinical features, including age, sex, chest pain type, resting blood pressure, cholesterol levels, fasting blood sugar, electrocardiogram results, maximum heart rate achieved, exercise-induced angina, old peak value, and the slope of the peak exercise ST segment.","shortMessageHtmlLink":"Add files via upload"}},{"before":"ab01f8b8949fb9690258011473b98c179b65b035","after":"97a0550deda8844e5e3308ab7fd5110a9fd86bda","ref":"refs/heads/main","pushedAt":"2024-04-24T11:05:08.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"Requirements.txt","shortMessageHtmlLink":"Requirements.txt"}},{"before":null,"after":"ab01f8b8949fb9690258011473b98c179b65b035","ref":"refs/heads/main","pushedAt":"2024-04-24T11:04:02.000Z","pushType":"branch_creation","commitsCount":0,"pusher":{"login":"DDILLOUD","name":"Devendra Dilloud","path":"/DDILLOUD","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/167950449?s=80&v=4"},"commit":{"message":"README.md","shortMessageHtmlLink":"README.md"}}],"hasNextPage":false,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"Y3Vyc29yOnYyOpK7MjAyNC0wNi0xM1QyMDozODoxNy4wMDAwMDBazwAAAARk1O86","startCursor":"Y3Vyc29yOnYyOpK7MjAyNC0wNi0xM1QyMDozODoxNy4wMDAwMDBazwAAAARk1O86","endCursor":"Y3Vyc29yOnYyOpK7MjAyNC0wNC0yNFQxMTowNDowMi4wMDAwMDBazwAAAAQ5B8oW"}},"title":"Activity · DDILLOUD/Heart-Failure-Prediction-Model"}