ABSTRACT
Across the world, there are few universal scenarios, but the pain of losing a loved one to heart disease is an exception and a reality shared by millions every year. Heart disease is the greatest killer in society today, and one prevalent root of this issue is untimely diagnosis, often caused by unsustainable costs and lack of accessible healthcare for underserved populations. Recognizing these disparities, the goal of this project was to create an easily available application and interface for all that accurately indicates one's risk of heart disease. To address this, a machine learning model, Predict2Protect, was built in Python. An open-source dataset compiled of 1025 patients of diverse backgrounds was scaled, adjusted to include inquiries answerable by patients, and split into 75% for training, 15% for validation, and 25% for testing. Four models were tested with the hypothesis that if the RandomForestClassifier was used, it would have the highest validity. This was not supported, as the DecisionTree model had a 100% accuracy for training data and 95% for test data. Through the application software Streamlit, this program was processed into a web application that is now found in browser extensions. The application reports the risk of one having heart disease with a 95% accuracy and describes the risk percentage of developing heart disease within the next year. With a simple interface and high accuracy, Predict2Protect aims to provide a view into one's health with the goals of accessible heart disease prediction and early treatment for patients around the world.
ABSTRACT
A primary immune deficiency disorder is often suspected in children with recurrent deep seated and fungal infections and those admitted to pediatric intensive care units. Chronic granulomatous disease (CGD) is inherited disorder leading to infections caused due to defective superoxide production. Cases referred for testing for a primary immunodeficiency disorder were tested for Dihydrorhodamine 123 (DHR) assay by flow cytometry and nitroblue tetrazolium dye (NBT) slide test. The unstimulated and stimulated samples were tested for oxidative burst activity which gives bright fluorescence due to formation of Rhodamine 123 on flow cytometry and blue formazan pigment in NBT slide test. The test results were reported in real time. From a total of 330 patients screened for chronic granulomatous disease using DHR and NBT slide test, 17 patients (5.1%) were found to have CGD. These included 12 boys and 5 girls. They presented with deep seated infections, recurrent and multiple abscess, recurrent pneumonia and granulomatous lymphadenitis. The causative organisms were Mycobacteriae, Staphylococcus, Burkholderia cepacia, Pseudomonas, Aspergillus and Cytomegalovirus. In 6 out of 17 positive cases family studies were carried out. On follow up five children succumbed to disease, two patients underwent allogeneic bone marrow transplant, the chimerism status was demonstrated by repeat DHR assay at day 50 post-transplant. Rest are in follow up under prophylactic antibiotics and supportive care. As facilities for molecular testing are not easily available for primary immuno deficiency disorders, flow cytometry based clinical laboratories can help to screen for some of the frequently suspected disorders like chronic granulomatous disease. This has aided in paediatric care in our centre.
