Regardless of whether you think the COVID-19 pandemic is over, we need to be prepared for the global health challenges to come. Our resources will always be limited and treatments will always require the most effective management. This is where artificial intelligence (AI) can be extremely useful, according to scientists from the University of Waterloo.
Artificial intelligence can help control resources during crises as profound as the COVID-19 pandemic. Image credit: Tiia Monto qua Wikimedia (CC BY-SA 4.0)
Scientists at the University of Waterloo have developed sophisticated new computer software that can identify the most vulnerable patients by learning from previous COVID-19 patient cases with results known clinical results. This information can help healthcare facilities assign more care, medications, and general interest to patients who might benefit most. This isn’t the first time scientists have tried to capitalize on the strengths of AI, such as its ability to analyze huge amounts of data quickly and efficiently, during this COVID-19 pandemic. But this new software is part of an open source project called COVID-Net.
These new AI model-driven analyzes take into account information such as serum ferritin levels, therapeutic heparin use, heart rate, and blood pressure. It then compares those biomarkers with patterns it learns by looking at hundreds of similar cases. The system is based on so-called interpretable AI technology, which allows the model to interpret the metrics it relies on to make predictions. This removes some doubt from the system and helps medical professionals make the final decision with the software if needed.
Alexander Wong, one of the study’s authors, said: “AI models not only provide predictions but also the rationale behind predictions that can significantly improve trust and application. widely used to assist physicians in their decision making along the entire workflow. It is the power of AI that can be explained.”
The reason why the world needs such systems is because the COVID-19 pandemic is not over yet. Hospitals are already overwhelmed because of this same pandemic. Resources are limited and physicians need to make quick and rational decisions about which patients should be prioritized. This AI-based model predicts which COVID-19 patients are most at risk of dying or developing kidney injuries during hospitalization. Ultimately, it can help prevent many adverse outcomes.
Even with the COVID-19 pandemic coming to an end, we need these systems in place to prepare for what the future may have in store for us. There will be other pandemics and we will be overwhelmed again. Our resources are limited, and AI can help use them in the most efficient way possible. It is also good for doctors, as it makes the decision-making process easier and allows to focus on the treatment of the patient.
The source: University of Waterloo
