An AI genetic test aims to detect postpartum depression before symptoms

Postpartum depression is a leading cause of maternal death, but its diagnosis and treatment are inconsistent at best and negligent at worst.

Today, San Diego-based startup Dionysus Digital Health offers a blood test to check for the disease, even before symptoms appear. The company says it has identified a gene that more closely links a person’s mood to hormonal changes. The test uses machine learning to compare epigenetics – the way genes are expressed – in your blood sample with benchmarks developed over a decade of research on pregnant women who did or did not develop postpartum depression. -partum.

Researchers from Dionysus’ academic partners, the Royal Institute of Mental Health Research and UVA Health, have published peer-reviewed articles confirming their findings, and the company is partnering with the Department of Defense and the National Institutes of Health for clinical trials, with the eventual goal of making the $250 test widely available and covered by insurance. But women’s health experts say better diagnosis of postpartum depression may not be helpful if mothers don’t have access to treatment and support.

One in seven mothers suffer from postpartum depression. When doctors screen for this condition, they typically use a questionnaire that asks patients how much they identify with statements such as “I looked forward to things as much as ever” and “I blamed myself unnecessarily when things have gone wrong.” .”

If diagnosed correctly, mothers rarely receive the care they need. In one widely cited study, only a third of pregnant patients with signs of mental disorders received treatment — which most often consisted of verbal “reassurance” from their providers.

“Our aspiration is that you can get treatment before you even experience a symptom,” Vivienne Ming, co-founder and chief scientist of Dionysus, said in an interview with The Washington Post. “Now we can show it’s not just in your head.”

Ming is one of many researchers using artificial intelligence to research new approaches to complex health problems. Delfi Diagnostics, based in Palo Alto, California, offers a test that uses artificial intelligence to detect signs of lung cancer. Researchers at Children’s National Hospital in Washington have built an AI tool to diagnose rheumatic heart disease in children.

But AI systems can easily exacerbate existing biases or inequities in healthcare. A 2019 study found that an algorithm making recommendations for C-sections falsely flagged Black women as being at high risk. Another algorithm, tasked with predicting health care needs for a large and diverse group of patients, consistently recommended less care for black patients, another study showed.

Ming acknowledged concerns about bias, cost and effectiveness. It would likely take years for Dionysus to gain approval from the Food and Drug Administration or for insurers and employers to agree to cover the cost of the test, Ming says. Meanwhile, the company says it received a $6 billion grant from the Department of Defense to validate its tests in more environments. The Defense Ministry did not respond to a request for comment.

Dionysus imagines a world in which providers administer a blood test between the second and third trimesters of pregnancy that detects women at higher risk for postpartum depression and other perinatal mood disorders. This, combined with other diagnostic methods, could allow health systems to refer vulnerable mothers for treatment – ​​or even preventive care.

The American College of Obstetricians and Gynecologists recommends that providers screen for postpartum depression several times during and after pregnancy, but that doesn’t always happen, said Elizabeth LaRusso, a psychiatrist specializing in women’s health. Some people make it through their prenatal and postnatal checkups without a provider ever mentioning depression. Low-income women and women of color are less likely to be screened than white mothers, according to LaRusso’s research.

LaRusso said she would welcome any tool that makes it easier to detect postpartum depression before it leads to hospitalizations, job loss or suicide. But identifying at-risk mothers is only the first step: More screening won’t make a difference if patients can’t access the care they need, like therapy or medication, she said. .

The impact of the Dionysus test will depend in part on its affordability and the willingness of insurance companies to cover the cost. Perinatal mood and anxiety disorders cost $14 billion in lost wages and additional expenses each year, researchers estimate. If reporting more cases of depression could reduce subsequent medical costs, insurers might have an incentive to pay for the test, Ming said.

But insurers may also view diagnosing depression as a way to increase medical costs as patients seek treatment they otherwise would not have pursued, said Wendell Potter, a former insurance executive who advocates in favor of reform of the sector. Ultimately, insurers and employers will decide individually which new medical technology to cover. If patients end up paying out of pocket for postpartum depression screening, tests like Dionysus’ could end up exacerbating existing inequities in maternal care, Potter said.

“I doubt the majority of Americans will be able to pay the cost (of the test) out of their own bank account,” he said.

Is this a safe use of AI?

As companies and researchers propose uses of AI in health care, checking these systems for bias will be critical, AI experts say. Because machine learning systems are trained to recognize patterns, it’s easy for them to regurgitate biases that appear in their training data, said Mark Sendak, a data scientist at the Duke Institute for Health Innovation (DIHI).

According to Sendak, an AI model’s training data should reflect the population it is intended to serve. Dionysus, for his part, says first validated its test in a cohort of largely white patients at Johns Hopkins Hospital in Baltimore. Its partnerships with Emory University Hospital and the Department of Defense will help it further validate its model with more diverse patient groups, Ming said.

Without recent advances in machine learning, Dionysus would never have been able to link a particular gene to postpartum depression, Ming said. Similar findings may follow closely as companies race to apply AI to medical challenges.

But the progress could have downsides, said Suresh Balu, program director at DIHI. If only people with disposable income could afford early detection and preventative care, existing inequalities in access to health care would worsen. Finding out you’re at risk for a disease you might never get could come with anxiety: Even people with a genetic predisposition to postpartum depression might never develop symptoms if that gene isn’t activated by environmental factors, according to Ming.

Ming said Dionysus’ ultimate goal is to sell the postpartum depression test directly to consumers, allowing them to assess their risk years before they even become pregnant. It could improve the lives of mothers and children, she said, if mothers could access the care they need.

News Source :
Gn Health

Back to top button