There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | Sebastian Langan |
| Institution: | University of Maryland, College Park |
| Department: | Fischell Department of Bioengineering |
| Country: | |
| Proposed Analysis: | I would like access to your database so that I can find EEG data from Alzheimer's patients and age-matched controls to build a Machine Learning-driven program, written in Python, that can provide AD diagnoses based on the most accurate results from a number of classification algorithms. These algorithms are to include: K-Nearest Neighbors, SVM, and Feed-Forward Neural Networks; the algorithm used in the final application will be that which achieved the highest classification accuracy with the pre-labeled data I am able to obtain. The expected functionality of this GUI-based (GUI written with the PyQT5 library) program is to read .csv or MATLAB data files, perform typical EEG signal processing on said data with the Fast-Fourier Transform technique, apply the highest-performing classification algorithm from the above list to produce diagnoses, and then output these diagnoses to the user. I would like this program to function as a proof-of-concept that open-source software that uses EEG or other biological data from AD patients can be used as an assistive diagnostic tool in a clinical setting, specifically to enhance the accuracy of traditional diagnostic criteria in the final diagnosis of this disease. My goal is to complete this project by July 21st of this year. Thank you, Sebastian Langan https://www.linkedin.com/in/sebastian-langan/ |
| Additional Investigators |
