Lending a Helping Machine
For most patients who succumbed to COVID-19, the ultimate cause of death was pneumonia, a condition in which inflammation and fluid buildup make it difficult to breathe. Severe pneumonia often requires lengthy hospital stays in intensive care units and assisted breathing from mechanical ventilators.
To quickly detect pneumonia — sometimes before a COVID-19 diagnosis — UC San Diego Health clinicians used artificial intelligence to augment lung-imaging analysis, part of a clinical research study.
— Albert Hsiao, MD, PhD
“Pneumonia can be subtle, especially if it’s not your average bacterial pneumonia. If we could identify those patients early, before you can even detect it with a stethoscope, we might be better positioned to treat those at highest risk for severe disease and death,” said Albert Hsiao, MD, PhD, associate professor of radiology at UC San Diego School of Medicine and a radiologist at UC San Diego Health.
Hsaio’s team developed a machine-learning algorithm that made earlier detection possible.
The images show chest X-rays from a patient with COVID-19 pneumonia. At top is the X-ray with the AI algorithm applied, indicating pneumonia. Below is the original X-ray. This particular patient also happened to have a pacemaker device and an enlarged heart, indicators that, while a subject may have significant underlying health issues, the algorithm was still able to do its job.