The findings boost AI-driven medical diagnostics and bring health care professionals closer to being able to quickly diagnose patients with COVID-19 and other pulmonary diseases with algorithms that comb through ultrasound images to identify signs of disease.

The findings, newly published in Communications Medicine, culminate an effort that started early in the pandemic when clinicians needed tools to rapidly assess legions of patients in overwhelmed emergency rooms.

“We developed this automated detection tool to help doctors in emergency settings with high caseloads of patients who need to be diagnosed quickly and accurately, such as in the earlier stages of the pandemic,” said senior author Muyinatu Bell, the John C. Malone Associate Professor of Electrical and Computer Engineering, Biomedical Engineering, and Computer Science at Johns Hopkins University. “Potentially, we want to have wireless devices that patients can use at home to monitor progression of COVID-19, too.”

The tool also holds potential for developing wearables that track such illnesses as congestive heart failure, which can lead to fluid overload in patients’ lungs, not unlike COVID-19, said co-author Tiffany Fong, an assistant professor of emergency medicine at Johns Hopkins Medicine.

“What we are doing here with AI tools is the next big frontier for point of care,” Fong said. “An ideal use case would be wearable ultrasound patches that monitor fluid buildup and let patients know when they need a medication adjustment or when they need to see a doctor.”

The AI analyzes ultrasound lung images to spot features known as B-lines, which appear as bright, vertical abnormalities and indicate inflammation in patients with pulmonary complications. It combines computer-generated images with real ultrasounds of patients — including some who sought care at Johns Hopkins.

“We had to model the physics of ultrasound and acoustic wave propagation well enough in order to get believable simulated images,” Bell said. “Then we had to take it a step further to train our computer models to use these simulated data to reliably interpret real scans from patients with affected lungs.”

Early in the pandemic, scientists struggled to use artificial intelligence to assess COVID-19 indicators in lung ultrasound images because of a lack of patient data and because they were only beginning to understand how the disease manifests in the body, Bell said.

Her team developed software that can learn from a mix of real and simulated data and then discern abnormalities in ultrasound scans that indicate a person has contracted COVID-19. The tool is a deep neural network, a type of AI designed to behave like the interconnected neurons that enable the brain to recognize patterns, understand speech, and achieve other complex tasks.

“Early in the pandemic, we didn’t have enough ultrasound images of COVID-19 patients to develop and test our algorithms, and as a result our deep neural networks never reached peak performance,” said first author Lingyi Zhao, who developed the software while a postdoctoral fellow in Bell’s lab and is now working at Novateur Research Solutions. “Now, we are proving that with computer-generated datasets we still can achieve a high degree of accuracy in evaluating and detecting these COVID-19 features.”

The team’s code and data are publicly available here: https://gitlab.com/pulselab/covid19

Scientists have long known that COVID-19 increases the risk of heart attack, stroke, and Long COVID, and prior imaging research has shown that over 50% of people who get COVID-19 experience some inflammation or damage to the heart. What scientists did not know is whether the damage occurs because the virus infects the heart tissue itself, or because of systemic inflammation triggered by the body’s well-known immune response to the virus.

“This was a critical question and finding the answer opens up a whole new understanding of the link between this serious lung injury and the kind of inflammation that can lead to cardiovascular complications,” said Michelle Olive, Ph.D., associate director of the Basic and Early Translational Research Program at the National Heart, Lung, and Blood Institute (NHLBI), part of NIH. “The research also suggests that suppressing the inflammation through treatments might help minimize these complications.”

To reach their findings, the researchers focused on immune cells known as cardiac macrophages, which normally perform a critical role in keeping the tissue healthy but can turn inflammatory in response to injury such as heart attack or heart failure. The researchers analyzed heart tissue specimens from 21 patients who died from SARS-CoV-2-associated ARDS and compared them with specimens from 33 patients who died from non-COVID-19 causes. They also infected mice with SARS-CoV-2 to follow what happened to the macrophages after infection.

In both humans and mice, they found the SARS-CoV-2 infection increased the total number of cardiac macrophages and also caused them to shift from their normal routine and become inflammatory.

When macrophages are no longer doing their normal jobs, which includes sustaining the metabolism of the heart and clearing out harmful bacteria or other foreign agents, they weaken the heart and the rest of the body, said Matthias Nahrendorf, M.D., Ph.D., professor of Radiology at Harvard Medical School and senior author on the study.

The researchers then designed a study in mice to test whether the response they observed happened because SARS-CoV-2 was infecting the heart directly, or because the SARS-CoV-2 infection in the lungs was severe enough to render the heart macrophages more inflammatory. This study mimicked the lung inflammation signals, but without the presence of the actual virus. The result: even in the absence of a virus, the mice showed immune responses strong enough to produce the same heart macrophage shift the researchers observed both in the patients who died of COVID-19 and the mice infected with SARS-CoV-2 infection.

“What this study shows is that after a COVID infection, the immune system can inflict remote damage on other organs by triggering serious inflammation throughout the body — and this is in addition to damage the virus itself has directly inflicted on the lung tissue,” said Nahrendorf. “These findings can also be applied more generally, as our results suggest that any severe infection can send shockwaves through the whole body.”

The research team also found that blocking the immune response with a neutralizing antibody in the mice stopped the flow of inflammatory cardiac macrophages and preserved cardiac function. While they have yet to test this in humans, Nahrendorf said a treatment like this could be used as a preventive measure to help COVID-19 patients with pre-existing conditions, or people who are likely to have more severe outcomes from SARS-CoV-2 associated ARDS.

Study: Grune J, Bajpai G, Ocak PT, et al. Virus-induced ARDS causes cardiomyopathy through eliciting inflammatory responses in the heart. Circulation. 2024. doi:10.1161/CIRCULATIONAHA.123.066433.

Funding: This study was supported by NHLBI grants: HL139598, HL142494, HL155097, and HL149647.