This is a Symposium-2023 project organised in our college ITER, SOA University.
Hospital-acquired infections (HAIs) affect millions worldwide, with 10% of patients in impoverished countries and 7% in affluent nations contracting healthcare-related infections. In the US alone, HAIs cause 1.7 million infections and 99,000 deaths annually, with an economic burden of $28 billion to $45 billion per year. The most common HAIs include bloodstream infections, pneumonia, urinary tract infections, and surgical site infections. This research aims to develop a machine-learning model using patient and hospital data to predict HAI risk accurately. By utilizing advanced algorithms like Random Forest, the model can identify factors increasing infection likelihood and generate personalized risk scores, enabling targeted prevention and early interventions to improve patient safety and reduce HAIs in hospitals.
Developed a machine-learning model using patient and hospital data to predict HAI risk accurately by utilizing advanced algorithms like Random Forest, the model can identify factors increasing infection likelihood and generate personalized risk scores, enabling targeted prevention and early interventions to improve patient safety and reduce HAIs in hospitals.
Filling the required field.
Output showing on the web page!