You will get a Knowledge-based Clinical Decision Support System utilizing ML techniques
Project details
A Clinical Decision Support System (CDSS) is able improve patient’s safety by minimizing medical errors. The objective of model is to improve the accuracy of heart disease and other disease prediction and diagnosis.
The technique uses 10-fold cross validation to train the individual classifiers and ensemble vote schemes. Standard 10-fold cross validation has been used to divide the data into training and testing sets. The approach uses five different majority voting based ensemble schemes and their performances are analyzed.
The technique has the following important steps:
-- First step is to generate the classification decisions of independent classifiers for each heart disease dataset. -- Second step involves computation of the average results of individual classifiers and select the top 3 on the
basis of average accuracy.
-- In third step, top-3 individual classifiers are combined in ensemble voting schemes and their results are
evaluated. The performance of the selected ensemble schemes for all the heart disease dataset is noted.
-- Finally, in the fourth step, the average results of ensemble vote schemes, across all dataset, are computed and
compared
The technique uses 10-fold cross validation to train the individual classifiers and ensemble vote schemes. Standard 10-fold cross validation has been used to divide the data into training and testing sets. The approach uses five different majority voting based ensemble schemes and their performances are analyzed.
The technique has the following important steps:
-- First step is to generate the classification decisions of independent classifiers for each heart disease dataset. -- Second step involves computation of the average results of individual classifiers and select the top 3 on the
basis of average accuracy.
-- In third step, top-3 individual classifiers are combined in ensemble voting schemes and their results are
evaluated. The performance of the selected ensemble schemes for all the heart disease dataset is noted.
-- Finally, in the fourth step, the average results of ensemble vote schemes, across all dataset, are computed and
compared
What's included
| Service Tiers |
Starter
$120
|
Standard
$150
|
Advanced
$200
|
|---|---|---|---|
| Delivery Time | 9 days | 7 days | 3 days |
Number of Revisions | 0 | 1 | 2 |
Model Validation/Testing | - | - | |
Model Documentation | |||
Data Source Connectivity | - | ||
Source Code |
About Muhammad
Machine Learning Specialist | Data Scientist
Rawalpindi, Pakistan - 8:11 am local time
- Data analysis - Ability in feature engineering, identify business issues and applying analytical techniques. Ability to deliver insights and implement action-oriented solutions to complex business problems.
- Machine learning - Professional in Deep learning, Statistical model, Supervised/Unsupervised learning, Reinforcement learning.
- Natural language processing - Expert in Chatbot, Sentiment analysis, Text summarization, Recommendation system, Entity extraction, Text classification, Tagging, Text generation
- Computer vision - Semantic segmentation, Object detection, OCR
- Time series analysis - Experienced in time series prediction, quantitative analysis and state space model
- Coding - Fluent in Python, Strong background in machine learning platforms: PyTorch, Tensorflow, Keras, Scikit-learn, lightGBM. Familiar with restful api using flask, django. Skilled in different data visualization tools
- Big Data - Strong experience in Spark, Hadoop, Docker, Kubernetes, AWS, Google Cloud.
Steps for completing your project
After purchasing the project, send requirements so Muhammad can start the project.
Delivery time starts when Muhammad receives requirements from you.
Muhammad works on your project following the steps below.
Revisions may occur after the delivery date.
Edit Model
Fine tuning of the provided model