Kamorudeen Amuda

Graduate Trainee, Towson University

5 active projects

Duplicate of Heart disease

I am working on Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach. The specific scientific questions I intend to study are: 1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models? 2. What…

Scientific Questions Being Studied

I am working on Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach.
The specific scientific questions I intend to study are:
1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models?
2. What are the key factors that contribute to the model's performance when using diverse datasets from multiple sources?
3. Can we generate personalized health insights effectively without compromising patient data privacy?
These questions are important because cardiovascular disease is a leading cause of death worldwide. Improving detection methods can lead to early interventions and significantly impact public health. Federated learning is especially relevant as it allows the use of diverse, multi-institutional data while maintaining data privacy, and addressing major concerns in medical data sharing.

Project Purpose(s)

  • Disease Focused Research (heart disease)
  • Educational

Scientific Approaches

I will use diverse cardiovascular health datasets from multiple institutions, ensuring they include a wide range of patient demographics and medical histories.
Research Methods:
1. Implement a federated learning framework where models are trained locally on each institution's data, and only the model updates are shared and aggregated centrally. This maintains patient privacy while leveraging the diverse datasets.
2. Assess the models' accuracy, precision, recall, and F1-score to determine their effectiveness in detecting cardiovascular disease.
3. Employ differential privacy techniques to ensure that the data remains anonymous and secure throughout the process.
Tools:
I will use PyTorch and the Flower framework for federated learning implementation, along with libraries like NumPy and pandas for data preprocessing and analysis. Visualization tools such as Matplotlib and Seaborn will help in interpreting the results

Anticipated Findings

The anticipated findings from the study include:
1. Improved Model Accuracy
2. Privacy Preservation
These findings will contribute to the body of scientific knowledge by providing evidence that federated learning can be a powerful tool for personalized health applications. It will highlight the potential of federated learning to improve disease detection while safeguarding patient privacy, thus addressing major concerns in medical data sharing. This research could pave the way for broader adoption of federated learning in other healthcare domains, ultimately leading to better patient outcomes and enhanced public health strategies.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Registered Tier

Research Team

Owner:

Duplicate of Heart disease

I am working on "Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach." The specific scientific questions I intend to study are: 1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models? 2. What…

Scientific Questions Being Studied

I am working on "Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach."
The specific scientific questions I intend to study are:
1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models?
2. What are the key factors that contribute to the model's performance when using diverse datasets from multiple sources?
3. Can we generate personalized health insights effectively without compromising patient data privacy?
These questions are important because cardiovascular disease is a leading cause of death worldwide. Improving detection methods can lead to early interventions and significantly impact public health. Federated learning is especially relevant as it allows the use of diverse, multi-institutional data while maintaining data privacy, and addressing major concerns in medical data sharing.

Project Purpose(s)

  • Disease Focused Research (heart disease)
  • Educational

Scientific Approaches

I will use diverse cardiovascular health datasets from multiple institutions, ensuring they include a wide range of patient demographics and medical histories.
Research Methods:
1. Implement a federated learning framework where models are trained locally on each institution's data, and only the model updates are shared and aggregated centrally. This maintains patient privacy while leveraging the diverse datasets.
2. Assess the models' accuracy, precision, recall, and F1-score to determine their effectiveness in detecting cardiovascular disease.
3. Employ differential privacy techniques to ensure that the data remains anonymous and secure throughout the process.
Tools:
I will use PyTorch and the Flower framework for federated learning implementation, along with libraries like NumPy and pandas for data preprocessing and analysis. Visualization tools such as Matplotlib and Seaborn will help in interpreting the results

Anticipated Findings

The anticipated findings from the study include:
1. Improved Model Accuracy
2. Privacy Preservation
These findings will contribute to the body of scientific knowledge by providing evidence that federated learning can be a powerful tool for personalized health applications. It will highlight the potential of federated learning to improve disease detection while safeguarding patient privacy, thus addressing major concerns in medical data sharing. This research could pave the way for broader adoption of federated learning in other healthcare domains, ultimately leading to better patient outcomes and enhanced public health strategies.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Registered Tier

Research Team

Owner:

Cardiovasicular - EHR

I am working on "Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach." The specific scientific questions I intend to study are: 1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models? 2. What…

Scientific Questions Being Studied

I am working on "Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach."
The specific scientific questions I intend to study are:
1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models?
2. What are the key factors that contribute to the model's performance when using diverse datasets from multiple sources?
3. Can we generate personalized health insights effectively without compromising patient data privacy?
These questions are important because cardiovascular disease is a leading cause of death worldwide. Improving detection methods can lead to early interventions and significantly impact public health. Federated learning is especially relevant as it allows the use of diverse, multi-institutional data while maintaining data privacy, and addressing major concerns in medical data sharing.

Project Purpose(s)

  • Disease Focused Research (cardiovascular disease)
  • Educational

Scientific Approaches

I will use diverse cardiovascular health datasets from multiple institutions, ensuring they include a wide range of patient demographics and medical histories.
Research Methods:
1. Implement a federated learning framework where models are trained locally on each institution's data, and only the model updates are shared and aggregated centrally. This maintains patient privacy while leveraging the diverse datasets.
2. Assess the models' accuracy, precision, recall, and F1-score to determine their effectiveness in detecting cardiovascular disease.
3. Employ differential privacy techniques to ensure that the data remains anonymous and secure throughout the process.
Tools:
I will use PyTorch and the Flower framework for federated learning implementation, along with libraries like NumPy and pandas for data preprocessing and analysis. Visualization tools such as Matplotlib and Seaborn will help in interpreting the results

Anticipated Findings

The anticipated findings from the study include:
1. Improved Model Accuracy
2. Privacy Preservation
These findings will contribute to the body of scientific knowledge by providing evidence that federated learning can be a powerful tool for personalized health applications. It will highlight the potential of federated learning to improve disease detection while safeguarding patient privacy, thus addressing major concerns in medical data sharing. This research could pave the way for broader adoption of federated learning in other healthcare domains, ultimately leading to better patient outcomes and enhanced public health strategies.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Registered Tier

Research Team

Owner:

  • Ming Li - Early Career Tenure-track Researcher, Towson University
  • Kamorudeen Amuda - Graduate Trainee, Towson University

Heart disease

I am working on "Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach." The specific scientific questions I intend to study are: 1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models? 2. What…

Scientific Questions Being Studied

I am working on "Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach."
The specific scientific questions I intend to study are:
1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models?
2. What are the key factors that contribute to the model's performance when using diverse datasets from multiple sources?
3. Can we generate personalized health insights effectively without compromising patient data privacy?
These questions are important because cardiovascular disease is a leading cause of death worldwide. Improving detection methods can lead to early interventions and significantly impact public health. Federated learning is especially relevant as it allows the use of diverse, multi-institutional data while maintaining data privacy, and addressing major concerns in medical data sharing.

Project Purpose(s)

  • Disease Focused Research (heart disease)
  • Educational

Scientific Approaches

I will use diverse cardiovascular health datasets from multiple institutions, ensuring they include a wide range of patient demographics and medical histories.
Research Methods:
1. Implement a federated learning framework where models are trained locally on each institution's data, and only the model updates are shared and aggregated centrally. This maintains patient privacy while leveraging the diverse datasets.
2. Assess the models' accuracy, precision, recall, and F1-score to determine their effectiveness in detecting cardiovascular disease.
3. Employ differential privacy techniques to ensure that the data remains anonymous and secure throughout the process.
Tools:
I will use PyTorch and the Flower framework for federated learning implementation, along with libraries like NumPy and pandas for data preprocessing and analysis. Visualization tools such as Matplotlib and Seaborn will help in interpreting the results

Anticipated Findings

The anticipated findings from the study include:
1. Improved Model Accuracy
2. Privacy Preservation
These findings will contribute to the body of scientific knowledge by providing evidence that federated learning can be a powerful tool for personalized health applications. It will highlight the potential of federated learning to improve disease detection while safeguarding patient privacy, thus addressing major concerns in medical data sharing. This research could pave the way for broader adoption of federated learning in other healthcare domains, ultimately leading to better patient outcomes and enhanced public health strategies.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Registered Tier

Research Team

Owner:

Cardiovasicular

I am working on "Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach." The specific scientific questions I intend to study are: 1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models? 2. What…

Scientific Questions Being Studied

I am working on "Personalized Health: Cardiovascular Disease Detection Using a Federated Learning Approach."
The specific scientific questions I intend to study are:
1. How can federated learning improve the accuracy and privacy of cardiovascular disease detection models?
2. What are the key factors that contribute to the model's performance when using diverse datasets from multiple sources?
3. Can we generate personalized health insights effectively without compromising patient data privacy?
These questions are important because cardiovascular disease is a leading cause of death worldwide. Improving detection methods can lead to early interventions and significantly impact public health. Federated learning is especially relevant as it allows the use of diverse, multi-institutional data while maintaining data privacy, and addressing major concerns in medical data sharing.

Project Purpose(s)

  • Disease Focused Research (arteriosclerotic cardiovascular disease)
  • Educational

Scientific Approaches

I will use diverse cardiovascular health datasets from multiple institutions, ensuring they include a wide range of patient demographics and medical histories.
Research Methods:
1. Implement a federated learning framework where models are trained locally on each institution's data, and only the model updates are shared and aggregated centrally. This maintains patient privacy while leveraging the diverse datasets.
2. Assess the models' accuracy, precision, recall, and F1-score to determine their effectiveness in detecting cardiovascular disease.
3. Employ differential privacy techniques to ensure that the data remains anonymous and secure throughout the process.
Tools:
I will use PyTorch and the Flower framework for federated learning implementation, along with libraries like NumPy and pandas for data preprocessing and analysis. Visualization tools such as Matplotlib and Seaborn will help in interpreting the results

Anticipated Findings

The anticipated findings from the study include:
1. Improved Model Accuracy
2. Privacy Preservation
These findings will contribute to the body of scientific knowledge by providing evidence that federated learning can be a powerful tool for personalized health applications. It will highlight the potential of federated learning to improve disease detection while safeguarding patient privacy, thus addressing major concerns in medical data sharing. This research could pave the way for broader adoption of federated learning in other healthcare domains, ultimately leading to better patient outcomes and enhanced public health strategies.

Demographic Categories of Interest

This study will not center on underrepresented populations.

Data Set Used

Registered Tier

Research Team

Owner:

  • Ming Li - Early Career Tenure-track Researcher, Towson University
  • Kamorudeen Amuda - Graduate Trainee, Towson University
1 - 5 of 5
<
>
Request a Review of this Research Project

You can request that the All of Us Resource Access Board (RAB) review a research purpose description if you have concerns that this research project may stigmatize All of Us participants or violate the Data User Code of Conduct in some other way. To request a review, you must fill in a form, which you can access by selecting ‘request a review’ below.