Github Link: Website:


Today, in the US alone, there are over 5,800,000 American citizens over the age of 65 living with Alzheimer's. On an annual basis, Alzheimer's costs the US roughly $305 Billion dollars, and by 2050, estimates project this figure to increase to as much as $1.1 Trillion per year. Most patients with Alzheimer's today are diagnosed at the mild dementia stage, only after they have already begun to experience significant memory and thinking issues. However, if the aggregate amount of all Americans alive today who will develop Alzheimer's were to be diagnosed earlier, when they have a mild cognitive impairment, it would save the US $7.9 trillion. Although there is no cure for Alzheimer's, early diagnosis for Alzheimer's results in many benefits for the healthcare system, patients, and their families. In addition to the cost savings for patients and the government, early diagnosis enables patients to access treatment options earlier, allowing them to have a greater chance of benefiting from new treatments, and the possibility of enrolling in clinical trials for new therapies. Additionally, with a diagnosis, patients can choose to adjust their lifestyle habits to slow cognitive decline and maximize the time they spend with their friends and family. Thus, we decided that there needed to be a solution for aging individuals (those most susceptible to AD & dementia) to enable them to have their cognitive health screened & monitored in an innovative fashion, so HCP's can use this information to inform diagnostic decisions.

What it does

Syne is a screening and data processing platform for cognitive impairment monitoring. Syne helps HCP's screen for changes in cognitive impairment as aging patients routinely get tested over time. The Syne testing process is two-fold, Part A is an MMSE test created using a Wordpress website along with a form, where HCP's can enter patient test results which can then be related to an estimated level of cognitive impairment. Part B involves an EEG test which has become more and more established within academia as a screening method for Alzheimer's. The EEG data is gathered using an OpenBCI and is then processed by a signal processing algorithm on Google Colab, and can then be compared to literature values within the form (that can be accessed from the webite) to generate insights for HCP's.

How we built it

The creation of Syne involved both hardware and software components which involved the usage of an OpenBCI device, Google Collab, and WordPress to create a more comprehensive screening and data analysis platform. Initially, we ordered a Cyton board headset from OpenBCI which is a headset that contains 16 electrodes for EEG streaming of data across the scalp, and a 3-axis accelerometer. Once we ordered the product, it required assembling of the given computer chips, wires, and electrodes, and installation of the GUI. Afterward EEG data from the scalp was streamed, recorded, and then exported as a CSV file, and as a BDF file to our Google Colab platform. Our developed Python-based script then sorted the files received and then converted them into a RAW file for processing using the MNE library. The time-series data was converted to the frequency domain and then used to compute the coherence of each pair of the electrode, final average coherence, total spectral power, and average theta power using logical loops and conditional statements. Finally, the resulting arrays of data were IIR Bandpass filtered using a Butterworth filter into each of the alpha, beta, theta, delta sub-bands of interest and were also plotted to provide a graphical interpretation of the brain waves. Of course, this entire procedure has a user interface in the form of a wesbite that was developed using WordPress. The recorded cognitive assessment answers and computations will be stored on a database for each user over time. Submissions are then compared for the user over time for further medical analysis .

Challenges we ran into

Since our problem space was situated in the disease screening niche of neuroscience, our primary challenges were obtaining several sources of academic literature to support our proposed solution. After extensive searching and discussion with experienced specialists, our next challenge occurred with the implementation of the openBCI which was a tool that none of us were familiar with. Finally, the last challenge we ran into was when we were creating the Python script which required a lot of troubleshooting. This is because the computations we ran were complex, and the signal processing aspect needed to be accurate to ensure that the data was being properly filtered. To ensure that our calculations were correct, we also used other websites and handwritten calculations of sample data to verify our code.

Accomplishments that we're proud of

We are very proud of integrating both hardware and software components into our final product. Additionally, we're excited at the success observed in computing our metrics which required a lot of software debugging and research. Finally, we're proud that our product is lightweight, computationally fast, and visually appealing and intuitive for the user.

What we learned

We learned hands-on skills related to hardware in terms of assembling circuit boards together, installing necessary drivers and software development kits, working with electrodes and wires. Software skills learned included Python which entailed new libraries like MNE and Scipy which we were initially unaware of. Additionally, we learned more about Alzheimer's disease, other studies, the idea behind our proposed metrics. Finally, a very important skill of researching scientific literature, properly analyzing sources, reviewing procedure methodologically, and proper data collection protocols were also learned.

What's next for Syne - Alzheimer's Detection Assistant

Future features for Syne include privacy & security features, EHRintegrations, EEG Training Modules for HCP's and ML-Driven Data Analysis which would generate even more meaningful insights, especially as more and more data is gathered and processed. Our market strategy for Syne would be to first focus on partnerships with small scale-AD focused providers in the US, where our platform could be used to routinely monitor aging patients for cognitive impairment, which will improve patient outcomes and will allow us to improve our data analysis methods. Once our model and techniques have been successfully developed to screen for cognitive impairment with extremely high reliability, we could scale across the US being more readily adopted by traditional providers, before attempting to enter international markets which abide by a myriad of rules and regulations.

Built With

+ 22 more
Share this project: