LymeML: Providing effective and immediate medical diagnosis

Navigating Through the App

When the app is opened:

1. Navigate to the "Upload File" button.
2. On either a mobile or computer device, select the image of the rash you would like to upload.
3. After uploading the image, the button is automatically selected to give consent for the model to use the image of your rash to run a clinical diagnosis on.
4. Once you have uploaded the image, select ALL the symptoms you are currently facing. The model works simultaneously on the symptoms and image to generate an output.
5. Ensure that you have selected the correct image, given consent, and selected all symptoms.
6. Click the submit button and read the output generated by the model.
7. If POSITIVE - Read full CDC guidelines through the link that is generated. Seek immediate medical action and consult with a medical professional before symptoms worsen.
8. If NEGATIVE - Still seek a doctor to find out more about your symptoms and understand that it is not certain that you are not facing symptoms generated by Lyme disease.

Inspiration and Problem

Research suggests that over 14% of the world's population has been affected or is currently being affected by Lyme disease, a consequential illness that requires an extensive diagnosis and the need for access to a doctor. However, with billions of individuals living in remote areas without access to a medical professional, it seems that little can be done to provide clinical assistance. But, with the use of novel machine learning algorithms that implement convolutional neural networks, an effective clinical diagnosis is available to all. It is important to effectively diagnose Lyme disease since a timely and accurate response is needed to prevent complications in the brain and heart infections. With LymeML, countless people will have access to an effective telemedicine solution.

Addressing the Problem

Due to the extensive amount of time that is required to diagnose and treat Lyme disease, it has become one of the largest problems that society faces today. But with the help of machine learning algorithms to classify this disease and send immediate solutions, countless lives can be saved. The app requires users to input an image that runs through a convolutional neural network to diagnose Lyme disease. Next, a symptoms checker is required to ensure that the user is undergoing the symptoms of this illness. By simultaneously using data from both the image classification algorithm and symptoms checker, this application returns an effective clinical diagnosis. With LymeML, millions of individuals who do not have access to health care will receive medical attention.

How the App was Built

This app was created in MecSimCalc by utilizing novel machine learning techniques (such as CNNs), Python libraries (NumPy, Tensorflow, etc.), and conditional algorithms. Once the user opens the app, an Upload File button is displayed to input an image through either a mobile or computer device. This image will be sent immediately to the model to diagnose once the submit button is clicked. A checkbox is displayed underneath the Upload File button to ensure that the user has given us consent to use the image in the model. Please note that this image will not be sent to any human but is only seen by you and the model. We used Python and machine learning to diagnose the disease and return an effective result instantly to the user. Not only have we included a machine learning aspect, yet included a self-check symptoms diagnosis to simultaneously ensure that the model outputs an accurate diagnosis. These sophisticated algorithms open doors to diagnosing several more diseases for individuals without access to medical professionals.

The Future for Medical Diagnosis

In the future, we want to publicize LymeML so it is well-known and accessible to countless more people. Through the help of MecSimCalc, this revolutionary technology is available to the public to diagnose if they have been affected with Lyme disease. Additionally, LymeML will include a more accurate machine learning model and more symptoms will be evaluated to diagnose Lyme disease in the future. We will improve the user interface of this app to make it more appealing and likely, in the future, provide machine learning solutions to other diseases that many face in remote conditions. We would also like to make this app available on iOS or Google Play for others to test out. Please spread the word about LymeML and test out the app for yourself.

--------------------------------------------------------

Built by Soham Jain using MecSimCalc.