Skip to Main Content

An official website of the United States government

Government Funding Lapse

Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted. The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit  cc.nih.gov. Updates regarding government operating status and resumption of normal operations can be found at OPM.gov.

Principal Investigator
Name
Jyoti Bhadana
Degrees
PhD
Institution
University of Alberta
Position Title
PIMS Postdoctoral Fellow
Email
About this CDAS Project
Study
NLST (Learn more about this study)
Project ID
NLST-1224
Initial CDAS Request Approval
Apr 2, 2024
Title
Probabilistic Analysis of NLST data and prediction
Summary
Data analysis concerns describing, condensing, and evaluating data through statistical and logical techniques. Researchers generally analyze patterns in observations throughout the entire dataset and often employ an ongoing process where data is collected and analyzed iteratively. There are usually still subtle statistical signs hidden within all the data. Neural networks have proven to be excellent tools in pattern-recognition-type applications (such as classification of images, handwriting analysis, and stock market prediction). We have proposed new algorithms that are performing very well so far. We are keen to use these algorithms to detect anomalies in scans in the early stages of diseases and aid in diagnosing issues quickly with better accuracy than existing models. These methods can deliver quick and accurate estimates. Once this work is completed, we can ensure that the overall model adapts correctly to both the original and simulated data. We aim to contribute to healthcare research.
Aims

1. To learn and understand the need for early prediction of diseases using our model.
2. To introduce a new method for training wide neural networks and calibrating models to real data to achieve the desired level of accuracy.
3. To compare the results with existing neural network algorithms.

Collaborators

Dr. Michael Kouritzin, Professor, Department of Mathematical and Statistical Sciences, University of Alberta, Canada