Thanks to new computer technology treating and preventing heart disease can now be more personalized instead of a one-size-fits-all. Researchers have developed a powerful new risk assessment tool for predicting outcomes in individuals with heart failure and that is just one of many new tools changing the practice of medicine.
The new tool for heart failure harnesses the power of machine learning (ML) and artificial intelligence (AI) to determine patient-specific risks of developing unfavorable outcomes. “Heart failure is a progressive condition that affects not only quality of life but quantity as well. All heart failure patients are not the same. Each patient is on a spectrum along the continuum of risk of suffering adverse outcomes,” said researcher Dr. Sula Mazimba, who is a heart failure expert and an associate professor of medicine at the University of Virginia (UVA) in Charlottesville, Virginia.
Heart failure occurs when the heart is unable to pump enough blood for the body’s needs. This can lead to fatigue, weakness, swollen legs and feet and, ultimately, death. Heart failure is a progressive condition, so it is extremely important to be able to identify patients at risk of adverse outcomes. Further, heart failure is a growing problem. More than 6 million Americans already have heart failure, and that number is expected to increase to more than 8 million by 2030.
The UVA researchers developed a new model they call CARNA to improve care. The model uses data drawn from thousands of patients enrolled in heart failure clinical trials. It was able to outperform existing predictors for determining how a broad spectrum of patients would fare in areas such as the need for heart surgery or transplant, the risk of rehospitalization and the risk of death.
“This model presents a breakthrough because it ingests complex sets of data and can make decisions even among missing and conflicting factors,” said researcher Josephine Lamp with UVA’s School of Engineering’s Department of Computer Science. “It is really exciting because the model intelligently presents and summarizes risk factors reducing decision burden so clinicians can quickly make treatment decisions.”
By using the model, doctors will be better equipped to personalize care to individual patients, helping them live longer, healthier lives, the researchers hope. The team has made the tool publicly available for free to clinicians.
Augmented Intelligence May Greatly Enhance Breast Cancer Detection
It is not just heart disease being treated in a new way, but also many types of cancer. Augmented reality and augmented intelligence offer promise for improving breast cancer care.Beilinson Hospital, one of the largest medical centers in Israel, recently completed a pilot program utilizing AI technologies to review more than 15,000 mammography scans. The technology identified previously undetected tumors, significantly enhanced diagnostic capabilities, and significantly increased the chances for early detection of breast cancer in women 40 and older. It also helped in the development of informed screening plans for women at risk of developing breast cancer.
“By utilizing better tools like artificial intelligence to aid radiologists in these scans, we are able to increase the reliability of the scans and the cases of early detection, thus saving lives,” said Head of Beilinson’s Mammography Department Dr. Ahuva Grubstein.
This program is widely available and is already approved by the United States Food and Drug Administration (FDA). In addition to its ability to benchmark a woman’s level of risk of developing a cancerous tumor in the next two years, the program’s ability to “see” through dense tissue increases the chances of early detection. Similar programs are now being developed for detecting prostate cancer and many other types of cancer, eliminating the one-size-fits-all approach for prevention and treatment.
Augmented Intelligence May Greatly Benefit Those with Mental Health Issues
AI may also help speed up diagnoses in the mental health arena, according to Andy Beam, who is an assistant professor of epidemiology and deputy at Harvard University, Boston, Massachusetts. “A person with type 1 bipolar disorder, on average, is undiagnosed for 7 years. That can be a very rocky 7-year period. It can manifest to the person’s family as something like substance abuse, and there’s no clear indication of what’s going on.”
Access to AI may lead to a quicker diagnosis and improve quality of the life for an individual with this condition. Beam said one of his top concerns about the use of AI in healthcare is misinformation. “We now have open-source AI models that are as powerful as GPT-4. It is the model behind ChatGPT and the most well-known AI system. There are essentially no safeguards that would stop a bad actor from using that to spread misinformation,” he said.
Beam and other experts in this field are recommending new ways to ensure that AI is used safely and responsibly in healthcare, such as closely evaluating AI models. They would also like to see the Food and Drug Administration (FDA) regulate the models as medical devices. Further, there should be training programs in the AI realm on how to use it for social good.
For Beam, the best-case scenario for AI in healthcare would be that eventually it operates in the background “so that my life and my interactions with the healthcare system are more seamless, they’re quicker, they’re cheaper, and they’re better,” said Beam.
John Schieszer is an award-winning national journalist and radio and podcast broadcaster of The Medical Minute. He can be reached at medicalminutes@gmail.com.
