Arnav Gupta 2021236
Karan Gupta 2021258
Shivesh Gulati 2021286
Vishal Singh 2021575
A timely and correct diagnosis of cardiovascular diseases helps provide a better prognosis and improve the quality of patient care. A diagnosis often involves multiple parameters some of which, the doctors might neglect or whose effects are not yet explored. Machine learning applications can identify complex patterns in the data and give much better, timely and accurate diagnoses.The idea for this topic came up due to the large number of cardiovascular-related mortalities during the COVID pandemic which were often caused due to negligence of subtle signs and symptoms. This prompted us to come up with a machine-learning model for diagnosing cardiovascular diseases.
leaning techniques This study develops a model to predict cardiovascular diseases and reduce related fatalities. Dif- ferent models like random forest (RF), decision tree (DT), multilayer perceptron (MP), and XGBoost (XGB) were em- ployed. Parameters were optimized using GridSearchCV. The research concludes that cross-validated multilayer perceptron outperformed other algorithms, achieving 87.28% accuracy. [1]
Associated Fatty Liver Disease This study aims to establish a relationship between (MAFLD) . To identify the MAFLD pa- tients with the highest risk of CVD, this paper uses techniques such as multiple logistic regression and PCA on the dataset.The paper concluded that people showing various symptoms of MAFLD had an increased chance of CVD. MAFLD is closely linked with symptoms like high lipid profile due to metabolic dysfunction, whichismainlycausedduetohighcholesterol.[2]
new findings from advance. This research paper is aimed at finding out the importance of Blood Pressure indices such as Systolic Blood Pressure (SBP), Diastolic Blood Pres- sure (DBP), Pulse Pressure (PP) (defined as (mean(SBP)- mean(DBP)) and Mean Arterial Pressure (MAP) defined as (DBP+1(PP)) in predicting the risk of cardiovascular diseases in a patient, using well-established ML Models such as Cox proportional hazard regression models.[3]
Week 1-2 : Data Cleaning
Week 3 : Pre-processing and Data Visualization.
Week 4 : Feature Extraction and Analysis.
Week 5 : Feature Analysis, Selection, Correlation, Heat-Maps.
Week 6 : Logistic Regression, Support Vector Machines.
Week 7 : Decision Trees, Random Forest.
Week 8 : K- Nearest Neighbours, K- Shortest Path.
Week 9 : Analysis and performance of models.
Week10: Hyper-parameterTuning, CheckformodelforOver- fittingand Under-fitting.
Week 11 : Report Generation.
Week 12 : Buffer.
| Week | Tasks | Team Members |
|---|---|---|
| 1-2 | Data Cleaning and Pre-Processing | Vishal, Karan |
| 1-2 | Research Paper Review | Vishal,Shivesh |
| 3 | Outlier Detection | Shivesh,Arnav,Vishal |
| 3 | Data Visualization | Arnav, Shivesh |
| 4 | Feature Extraction | Vishal, Arnav |
| 5 | Analysis of Features (Selection, correlation, etc.) | Karan,Shivesh |
| 6 | Logistic Regression and Naive Bayes | Shivesh,Karan |
| 6 | SVM | Arnav, Vishal |
| 7 | Report | Shivesh,Karan |
| 7 | Presentation | All Members |
| 7 | ----------Midsem Finish------------------- | |
| 8 | Decision Trees and Random Forest | Arnav, Karan |
| 9 | K-Modes + Xgboost in particular | Vishal |
| 10 | Multi-Layer Perceptron | Shivesh |
| 10 | Hyperparameter Tuning | All Members (for their respective models) |
| 11+12 | Final Report Writing + Final Presentation | All Members |
The model is expected to achieve an accuracy of atleast 80% onthetestdataset. ThisprojectaimstocreateaMachineLearn- ing model with a high accuracy of predicting whether a person has cardiovascular disease or not. The project would use clas- sical machine learning algorithms to find a pattern in the data of patients , thereby developing a model whose data could be easily visualized and improved upon to get much better predic- tions.
- Chintan M Bhatt, Parth Patel, Tarang Ghetia, and Pier Luigi Mazzeo. Effective heart disease prediction using machine learning techniques. Algorithms, 16(2):88, 2023.
- KarolinaDrozd˙ z,˙ KatarzynaNabrdalik, HannaKwiendacz, Mirela Hendel, Anna Olejarz, Andrzej Tomasik, Wojciech Bartman, Jakub Nalepa, Janusz Gumprecht, and Gregory YH Lip. Risk factors for cardiovascular disease in patients with metabolic- associated fatty liver disease: a machine learning approach. Car- diovascular Diabetology, 21(1):240, 2022.
- Andre-Pascal Kengne, Sebastien´ Czernichow, Rachel Huxley, Diederick Grobbee, Mark Woodward, Bruce Neal, Sophia Zoun- gas, Mark Cooper, Paul Glasziou, Pavel Hamet, et al. Blood pres- surevariablesandcardiovascularrisk: newfindingsfromadvance. Hypertension, 54(2):399–404, 2009.