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.

Current figures show that around one in six pregnant women worldwide are affected by a special form of diabetes known as gestational diabetes. According to the Robert Koch Institute, 63,000 women in Germany were affected by the disease in 2021, and the trend is increasing. These numbers are alarming because excessively high blood sugar levels during pregnancy are associated with negative consequences for mother and child. This increases the risk of affected women developing type 2 diabetes later on and their children have a higher risk of developing metabolic disorders and being overweight.

Long-Term Effect of Metformin on Offspring is Unclear

For several years, the placenta-crossing oral antidiabetic agent metformin has been increasingly gaining importance as an alternative to insulin administration when lifestyle changes show no success during the treatment of gestational diabetes. However, there are currently only a few studies on the long-term effects of metformin on the health of offspring. It is known that metformin has an impact on the AMPK signaling pathway, which regulates the networking of nerve cells during brain development.

The interdisciplinary team of DIfE researchers led by Junior Research Group Leader Dr. Rachel Lippert therefore grappled with two central questions: Is metformin treatment only beneficial for the mother or also the child? And does metformin treatment lead to long-term negative physiological changes in the offspring, especially in connection with the development of neuronal circuits in the hypothalamus, a critical region in the regulation of energy homeostasis?

Mouse Models Shed some Light

To answer the key questions, the researchers used two mouse models to represent the main causes of gestational diabetes:

severe obesity of the mother before pregnancy and excessive weight gain during pregnancy. These metabolic states were achieved by means of different feeding patterns, with the mice receiving either a high-fat or control diet. The antidiabetic treatment of female mice and their offspring took place during the lactation period as this corresponds to the third trimester of a human pregnancy in terms of brain development.

Treatment involved insulin, metformin, or a placebo, whereby the dosage was based on standard human treatments. The research team collected data on the body weight of the mice, analyzed various metabolic parameters and hormones, and examined molecular signaling pathways in the hypothalamus.

Maternal Metabolic State is Crucial

“As a result of antidiabetic treatment in the early postnatal period, we were able to identify alterations in the weight gain and hormonal status of the offspring, which were critically dependent on the metabolic state of the mother,” explains Lippert. Furthermore, sex-specific changes in hypothalamic AMPK signaling in response to metformin exposure were also observed. Together with the metformin-induced shift in the examined hormone levels, the results indicate that the maternal metabolic state must be taken into account before starting the treatment of gestational diabetes.

Focusing on Prevention

According to Rachel Lippert, treatment of gestational diabetes in future could entail developing a medication that is available for all and does not cross the placenta. “Given the increasing prevalence, education about gestational diabetes and preventive measures are of vital importance. If we can find a way to manage lifestyle and diet more proactively, we are in a better position to exploit the potential of gestational diabetes treatment,” says Lippert.