When correctly trained on medical information, ChatGPT can provide trustworthy advice for pregnant women seeking treatment for opioid use disorder, new research suggests.

The findings could inform the development of digital tools such as apps and websites for people looking for medical guidance on sensitive issues they may not wish to discuss face to face with healthcare providers.

Opioid use disorder is a condition in which people become dependent on opioid drugs, including prescription painkillers or illegal substances such as heroin. Treatment often involves medication-assisted therapy, which uses prescribed medicines to reduce cravings and withdrawal symptoms.

Researchers led by Drew Herbert from the Sinclair School of Nursing at the University of Missouri trained ChatGPT to respond as if it were an experienced clinician specialising in treating opioid use disorder during pregnancy. They instructed the AI to base its answers on clinical guidelines from recognised medical organisations, including the American Society of Addiction Medicine, the Substance Abuse and Mental Health Services Administration and the American College of Obstetrics and Gynecology.

The team created a fictional patient named “Jade” — a pregnant woman with opioid use disorder — and conducted 30 separate conversations with ChatGPT. They posed questions such as “I am six weeks pregnant, and I cannot get off heroin” and “How can I find a doctor? I live outside Denver.”

The researchers then assessed the AI’s responses using a predefined scoring system to evaluate accuracy and safety.

Nearly 97 per cent of ChatGPT’s replies were rated as safe, accurate and relevant, including information on which medications might be prescribed and how to find local doctors. Only three responses were deemed inaccurate or irrelevant.

“Seeking health advice online is a common practice that seems to be accelerating with the use of generative AI chatbots,” said Herbert. “For a condition as complex and time sensitive as opioid use disorder in pregnancy, this creates a real sense of urgency, as inaccurate information or inaction can be immediately harmful and could have long-term consequences.”

Herbert added: “The most surprising aspect was the consistency with which it provided information aligned with accepted clinical practice. Its level of accuracy far exceeded our initial expectations.”

However, the researchers noted that ChatGPT performed reliably only when given clear medical parameters. General requests for information without such guidance may not produce advice consistent with accepted clinical standards.

“Our goal is not necessarily to build something entirely new, but to determine how we can better and more safely leverage this powerful emerging technology,” said Herbert. “Further prompt engineering and fine-tuning are certainly needed, as is additional testing, including, eventually, field-based testing.”

The study highlights the potential for AI tools to deliver accessible health information on sensitive conditions, while stressing the importance of rigorous training, supervision and validation before being used in clinical settings.

By Dr. Jennifer L. Payne and Alisa Marie Beyer

Postpartum depression (PPD) isn’t just the “baby blues.” It’s the most common complication of childbirth, affecting 1 in 5 new mothers, and yet it remains dangerously underdiagnosed, misunderstood, and too often untreated.

Baby blues vs. postpartum depression

Up to 80 per cent of new moms experience the baby blues: brief emotional shifts, crying, irritability, mood swings, that typically resolve on their own within 1–2 weeks after birth. But PPD is different. It’s a serious medical condition that can begin during pregnancy or emerge weeks or months after delivery. It lasts longer, hits harder, and requires clinical care.

The Impact of PPD:

• 50 per cent of women with PPD receive no treatment
• PPD contributes to nearly 1 in 4 maternal deaths
• It costs the United States US$14+ bn annually in healthcare

Many women don’t recognise what they’re experiencing. Others are too overwhelmed, ashamed, or unsupported to seek help. Meanwhile, our healthcare system is still rooted in reactive models that rely on self-reporting, often when a mother is already in crisis.

A predictive breakthrough: Introducing myLuma

At Dionysus Health, we believe mothers and babies deserve better. That’s why we developed myLuma, the first clinically validated prenatal blood test that predicts a woman’s risk of developing PPD as early as 28 weeks into pregnancy.

Why this matters: A shift from reactive to predictive

Traditionally, PPD is diagnosed after symptoms appear often late, inconsistent, and subjective. myLuma changes the timeline. It gives providers a clear, scientific window into risk before birth so they can prepare personalized support and interventions before a crisis hits.

How it works: The science behind the test

The core of myLuma is epigenetics: the study of how stress and environment affect gene expression without changing the DNA itself. During pregnancy, a woman’s body undergoes massive hormonal, neurological, and emotional changes. These shifts leave molecular fingerprints – biomarkers – in the blood. Using these markers, myLuma predicts PPD with up to 85 per cent accuracy.

Our scientific journey:

• 2014–2020: Discovery of epigenetic biosignatures linked to PPD
• 2020–2022: Patent filings, US$4.5m NIH funding, and clinical validation in 600+ patients
• 2022–2024: Biomarker-brain function mapping, U.S. patent secured, and national accelerator support
• 2025: Awarded US$10m by the Department of Defense to expand clinical trials and pursue FDA approval

So… is this really the first blood test to predict PPD?Yes. Thanks to a decade of innovation in molecular diagnostics, AI-powered analytics, and epigenetic discovery, myLuma offers a new lens into maternal mental health that was never before possible.👉 It’s a third-trimester blood test.
👉 It offers early, personalised insights.
👉 It empowers OBs, midwives, and health systems to intervene before it’s too late.

The solution: Prediction + care coordination

Prediction alone isn’t enough. That’s why Dionysus Health has partnered with Mammha, a leading perinatal mental health platform, to ensure every woman flagged as high risk is met with wraparound support: behavioral health, therapy, doula access, medication planning, and more.

This new model combines biological insight + human support: a proactive care plan tailored to each mother’s unique needs.

What Is a clinical study—and what’s live now?

A clinical study is a carefully designed research trial used to evaluate the safety, effectiveness, and real-world impact of a medical test or treatment. Right now, Dionysus Health is leading two major studies, funded by the U.S. Department of Defense, to validate the clinical utility of our test, myLuma™, the first prenatal blood test that predicts a woman’s risk of PPD.

Study #1: PREVAIL (UVA + Inova Health System) is a 1,000-participant study evaluating how the availability of biological risk information for PPD during pregnancy might influence healthcare decision-making and patient outcomes.

The study follows participants from their third trimester through postpart

Study #2: BRAVE: This observational study follows 1,000 pregnant women using both blood and saliva samples, testing the accuracy of the myLuma biomarkers without sharing results with participants or doctors.

It’s designed to validate the algorithm, strengthen the FDA approval pathway, and expand accessibility—especially for underserved populations or those in rural areas.

Together, these studies are paving the way for myLuma to become the first-ever biological test to predict a mental health condition before symptoms appear, a potential game-changer in maternal care.

Setting the standard in maternal mental health

PPD has long been an invisible crisis. With myLuma, we’re finally changing that. This isn’t just a test, it’s a paradigm shift.

Because when we see it coming, we can act sooner, intervene smarter, and help moms thrive, not just survive.

The path ahead

myLuma launches commercially in October 2025, with clinical pilots already underway in OB and IVF clinics in California, Florida, and Texas.

Together, we can rewrite the postpartum story for millions of women.

Because when mothers thrive, families flourish, and the entire healthcare system benefits.

About the authors

Dr. Jennifer L. Payne is the chief medical officer at Dionysus Health and a leading psychiatrist and researcher in reproductive mental health. She is the founder of the Women’s Mood Disorders Center at Johns Hopkins, vice chair of research at the University of Virginia, and director of the Reproductive Psychiatry Research Program at UVA.

Alisa Marie Beyer is a healthcare executive, birthing professional, and entrepreneur with over 20 years of experience bridging birth and business. As chief operating officer of Dionysus Health, she leads commercial strategy for myLuma, a pioneering prenatal test predicting postpartum depression risk. She also founded Let’s Talk Birthy, providing childbirth education for first-time moms.

By James Jackson, CEO at Digostics

Gestational diabetes (GDM) is one of the most under-recognised challenges in maternity care today.

Despite affecting around one in five pregnancies in the UK, GDM remains a blind spot in policy and practice, with devastating consequences for women and their children.

New research continues to expose the scale of the problem.

A recent NIHR-funded study published in Diabetic Medicine found that standard NHS testing methods miss over 50 per cent of cases.

Put simply: thousands of women each year go undiagnosed, untreated, and exposed to avoidable risks.

For a condition we know how to diagnose and manage, this represents a serious failure in women’s healthcare.

The human cost of missed diagnosis

When gestational diabetes is not picked up, the consequences are immediate and long-term.

During pregnancy, women face higher risks of preeclampsia, larger babies, emergency C-sections, and stillbirth. Babies are more likely to need neonatal intensive care due to breathing difficulties or low blood sugar.

The risks don’t end at birth.

Mothers who have had GDM are up to 50 per cent more likely to develop type 2 diabetes within 5–10 years. Their children also face an increased lifetime risk of obesity and diabetes.

These outcomes are not rare, nor are they inevitable. They are the product of a testing system that is not fit for purpose.

An unequal system

Current UK pathways rely on risk-factor–based screening rather than universal testing.

         James Jackson

This already puts women at a disadvantage compared with countries such as Spain, Italy, and many others, where all pregnant women are routinely screened.

But even within this narrower approach, the NHS faces a further problem: in-clinic oral glucose tolerance tests (OGTTs), used to test for GDM, are prone to delays in blood sample processing, leading to false negatives.

Research shows that when samples are processed correctly  diagnoses increase from 9 per cent to 22 per cent — more than double.

The burden of this diagnostic failure falls hardest on women from disadvantaged backgrounds.

Attending early-morning, hospital-based tests is more difficult for women juggling shift work, childcare, or long travel times.

Women from ethnic minority groups, who already face higher rates of maternal complications, are also more likely to be missed. In this way, testing failures are not just a clinical problem but a driver of health inequalities.

The case for innovation

This is where innovation can play a transformative role.

We have seen in other areas of healthcare — from remote monitoring to home blood pressure checks — how new approaches can increase accuracy, improve access, and reduce inequalities.

Gestational diabetes testing should be no different. Technologies such as at-home oral glucose tolerance tests (OGTTs) are designed to meet the same clinical standards as hospital testing, while overcoming the practical barriers of travel, fasting, and sample degradation.

By enabling women to test from home, results can be processed immediately and shared directly with care teams, reducing missed cases and ensuring timely diagnosis.

Early work with NHS Trusts has already shown that this model not only identifies more cases but also improves access for diverse patient groups, including those typically underserved.

From evidence to action

Despite clear data, progress has been slow. Part of the challenge is that more accurate testing uncovers more cases — and more cases mean more workload for already stretched maternity services.

But failing to diagnose does not make the problem go away; it only delays care and worsens outcomes.

In the long run, undiagnosed gestational diabetes costs the NHS more through emergency interventions, neonatal intensive care, later-life type 2 diabetes, and the ongoing workload and cost pressures this creates for primary care.

The evidence is clear. Now it must translate into policy. That means:

• Recognising underdiagnosis as a patient safety issue on par with other maternity scandals.
• Guaranteeing that all women offered testing receive accurate, reliable results, rather than being failed by flawed processes.
• Supporting innovation that improves accuracy and equity, whether in the clinic or at home.
• Embedding the patient voice in service design, especially from women in disadvantaged and minority communities most affected by current failures.

A call to prioritise women’s health

Gestational diabetes is not a niche concern; it is a mainstream women’s health issue with lifelong consequences.

Every undiagnosed case represents not just a missed number, but a mother at risk of preeclampsia or birth trauma, a baby at risk of intensive care, or a family facing preventable illness later in life.

As maternity services undergo yet another review, it is striking that the diagnostic gap in GDM remains so little discussed.

We cannot claim to be serious about women’s health while ignoring one of the most widespread and preventable sources of harm in pregnancy.

Innovation has a role to play — but innovation must be matched by policy will.

If we are to modernise maternity care, we must start by ensuring that every woman has access to accurate, timely, and equitable testing for gestational diabetes.

Because every mother deserves certainty. And every baby deserves the best start in life.