Pharyngeal diseases, also known as throat diseases, are rampant- owing to pollution, allergies, and pathogens. The current practice to detect such diseases, i.e., the Throat Culture or the Strep Test, is invasive and depends entirely on the bacterial growth from the swab samples, which is a time taking process. We aim to develop a patient-friendly mechanism for easy and efficient detection of throat diseases, reducing the time taken for diagnosis.
VADDOT describes a voice-based disease identification system that utilizes machine learning algorithms to detect diseases based on vocal parameters. The model aims to provide an alternative and non-invasive way for early detection of various diseases. The system consists of a Data Collection Module (DCM), Feature Extraction Module (FEM), and a Machine Learning Model(ML Model). The DCM records the patient's voice sample, and the FCM extracts relevant characteristics from the vocal sample. The extracted features are then fed into the machine learning model to classify the disease.
Research in this field has shown promising results on various diseases such as Parkinson's, Alzheimer's, and COVID-19. With further development and testing, the system has the potential to be widely used in healthcare facilities, enabling early detection and treatment of diseases, ultimately leading to better patient outcomes.
Since the research is relatively new, datasets available to train the machine learning model are limited, causing difficulties in widening the spectrum of diseases that can be successfully detected through VADDOT.
Research on VADDOT is of great value since it is non-invasive, affordable, easy to use and reduces the diagnosis time. The system is simple and requires minimal training, making it an accessible tool for healthcare providers. The system is also cost-effective compared to prevailing disease detection methods and aims to have a significant impact on the environment, because of the medical wastage that can be prevented, in the long run.