
New Tool IDs Women at High Risk for Postpartum Depression
LOS ANGELES — Researchers have developed and externally validated a simple, machine learning model that can help identify women at a high risk for postpartum depression (PPD) immediately after childbirth, even before they leave the hospital.
Untreated PPD is a significant contributor to maternal morbidity and mortality. It's estimated to play a role in up to 10% of maternal deaths by suicide.
Earlier identification will improve the health of patients as they won't have to wait to begin treatment for 6 or 8 weeks after delivery, when symptoms might become much more severe, lead investigator Mark A. Clapp, MD, maternal-fetal medicine specialist at Massachusetts General Hospital and assistant professor in the Department of Obstetrics and Gynecology, Harvard Medical School, both in Boston, told Medscape Medical News .
'It's an opportunity for collaboration between obstetricians and psychiatrists to ensure high-risk patients are seen promptly,' said Clapp.
The findings were presented on May 19 at American Psychiatric Association (APA) 2025 Annual Meeting and simultaneously published online in The American Journal of Psychiatry.
A Common Problem
PPD, which can affect up to 15% of women after childbirth, is linked to an increased risk for suicide and self-harm. The condition has a profound impact on a woman's physical and mental health, ability to function, and relationships with her newborn and family.
Until 2023, the American College of Obstetricians and Gynecologists (ACOG) recommended first PPD screening at the postpartum visit. ACOG now recommends screening at the initial prenatal visit, later in pregnancy, and at the postpartum visit. The Edinburgh Postnatal Depression Scale (EPDS) has traditionally been used to screen for the condition.
Clapp noted only an estimated 60% of women appear at their postpartum visit, 'so about 4 in 10 patients are actually not presenting for postpartum care,' he said.
The study included 29,168 women (media age, 33 years; 70% White) with available EPDS scores and no recent history of a depressive disorder, who gave birth at two large academic hospitals (Brigham and Women's Hospital and Massachusetts General Hospital), and six surrounding community-based hospitals sharing a common electronic health record (EHR) system.
A PPD risk stratification model based on EHRs of women having a baby in a hospital makes sense given the widespread use of EHRs in healthcare facilities, where over 98% of pregnant women deliver, said Clapp.
Researchers divided participants into a model development group (15,018 participants delivering at five hospitals) and a model validation group (14,150 participants delivering at three hospitals).
All information for the model was readily available through EHRs, including maternal medical history, medication use, pregnancy history, and demographic factors. Researchers also incorporated other factors known or hypothesized to influence the risk for PPD such as maternal age; education level; marital status; primary language; public or private insurance; and pregnancy factors such as gestational age, mode of delivery, number of prenatal visits, and length of hospital stay.
The primary outcome was PPD, defined as the presence of a mood disorder, an antidepressant prescription, or a positive screen on the EPDS (score ≥ 13) within 6 months of delivery.
For both the training and testing sets, researchers assessed model discrimination by the area under the receiver operating characteristic curve (AUROC), as well as positive predictive value (PPV) and negative predictive value (NPV) using a screen-positive threshold and a set specificity of 90%.
High Specificity
Of the total number of participants, 9.2% met at least one criterion for PPD within 6 months of delivering their baby. Top factors contributing to the risk for PPD included anxiety/fear-related disorders, antiemetic use, headache disorders, gastrointestinal disorders, and prenatal EPDS score.
For the primary model, the AUROC was 0.750 (95% CI, 0.721-0.778), indicating the model had good discrimination. The Brier score was 0.073 (95% CI, 0.067-0.080), indicating the model was well calibrated. At the set threshold of 90% specificity, the PPV was 24.4% (95% CI, 21.3%-27.6%) and the NPV was 94.7% (95% CI, 93.9%-95.5%).
In the external validity cohort, the AUROC was 0.721 (95% CI, 0.709-0.736) and the Brier score was 0.087 (95% CI, 0.083-0.091). At a specificity of 90%, the PPV was 28.8% (95% CI, 26.7%-30.8%) and the NPV was 92.2% (95% CI, 91.8%-92.7%).
'Using the predefined specificity, we were able to identify about 30% of individuals who were predicted to be at high risk where the diagnosis of postpartum depression occurred,' said Clapp. 'Remember, the overall population risk was about 10%, but of those that we flagged as high risk, the rate of postpartum depression was 30% — or three times the population rate.'
In addition to distinguishing between higher- and lower-risk populations, the model performed similarly across patient subgroups by race, ethnicity, age, and hospital type, suggesting the model could be applied equitably in diverse populations, said Clapp.
The researchers hope to pair the model with tailored interventions, which in some cases could merely involve a phone call during the postpartum period, said Clapp.
'People at high risk for postpartum depression benefit from a simple phone call, so having a nurse or doctor call them to say, 'Hey, how are you doing?'' can make a big difference, he noted.
A limitation of the study is that it only reflects practice patterns in eastern Massachusetts and southern New Hampshire in a single health system. Other limitations were that most patients were White, college-educated, and privately insured, and misclassification may have occurred, as is the case with any study using diagnostic codes.
'We're working to integrate this model into our electronic health record to facilitate real-time predictions' of high PPD risk, said Clapp. The team is also investigating how the model can be used to reduce the incidence, severity, and consequences of PPD.
Clinically Important Tool
Commenting for Medscape Medical News , reproductive psychiatrist Misty Richards, MD, associate clinical professor, Department of Psychiatry and OB-GYN, University of California at Los Angeles, noted that PPD is the most common complication of childbirth, highlighting the need for better diagnostics.
'We're talking about 1 in 5 women', many of whom, especially those with no history of depression, 'don't tend to get diagnosed,' said Richards, who was not part of the research.
'We try to catch people with postpartum depression before it becomes a forest fire' but 'oftentimes we miss it,' she said. 'Having predictive tools like thisis very, very important clinically, so we can catch things early.'
Only one medication — zuranolone, a GABA A receptor–positive allosteric modulator — is approved by the US Food and Drug Administration for PPD, said Richards.
Ned Kalin, MD, professor and chair, Department of Psychiatry, and director of the HealthEmotions Research Institute, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, who was not part of the study, highlighted in a press briefing that patients in the study who developed PPD didn't have a history of depression.
'These are people that otherwise would probably go completely undetected, so this is really a critical advance in that regard.'
Hashtags

Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles


Associated Press
14 hours ago
- Associated Press
New Study: Wildfires Cause Months-Long Delays in Medical Care for At-Risk Californians
SANTA BARBARA, Calif., June 9, 2025 /3BL/ - A new study reveals how wildfires are particularly dangerous for Californians with significant health conditions, with one in five respondents reporting harm to their health from delays in medical care after the Oak Fire. Led by researchers from Harvard Medical School-affiliated Beth Israel Deaconess Medical Center, Direct Relief, and Mariposa County Health and Human Services Agency, the study focuses on the 2022 Oak Fire in rural Mariposa County—but its findings resonate statewide, as wildfires, evacuations, and public safety power shutoffs increase in frequency. 'Interruptions to health care access during and in the aftermath of disasters impact health long after the initial insult,' the authors write. The study appears in the journal Disaster Medicine and Public Health Preparedness (Cambridge University Press) and is available at The study 'underscores the worrisome disruptions in health care access faced by medically vulnerable populations across the US during disaster,' the paper says. 'That 1/5 missed routine appointments, and that the vast majority could not re-establish care for weeks or months deserves urgent attention.' Researchers surveyed Mariposa County residents who were enrolled in the Support and Aid For Everyone (SAFE) program - a county program that assists those with self-identified special needs during emergencies, and comprises largely older adults and those with chronic medical conditions and mobility needs. Among the respondents – with a median age of 78 years old, nearly ¾ of whom had mobility issues, and nearly half of whom needed help with activities of daily living – the study found major gaps in emergency readiness, access to information, and continued medical care: With over 230,000 Medicare beneficiaries in California relying on powered medical devices, the study raises red flags far beyond Mariposa County—from seniors in Fresno to immunocompromised residents in Los Angeles. Asked to identify the most trusted sources of reliable information about evacuations and fires, 77% pointed to county officials, compared to 57% for state officials and 23% for TV news. The Oak Fire information they found most useful was fire location and progress, road closures, risks to the household, shelter locations, and evacuation routes. As California enters another active fire season, the authors make the case that wildfire response must include protecting access to care for those who can't go without it. 'Preparedness must focus not only on response to disasters, but on preempting health care disruptions at home—through improved outreach and communication, access to back-up power and supplies, and pathways to efficiently reinstate health services,' they write. Media Contacts: Beth Israel Deaconess Medical Center: Katie Brace, [email protected] Direct Relief: Paul Sherer, [email protected] Mariposa County Health and Human Services Agency: Kazzy Cunningham, [email protected]


Boston Globe
15 hours ago
- Boston Globe
Ozempic, the internet, GPS: Here are 5 things New England researchers helped develop with federal funding
Here are some of the most impactful, federally-funded scientific breakthroughs that have come out of New England. Advertisement Weight loss drugs Often referred to by the well-known brand names In the 1980s, Joel Habener and Svetlana Mojsov, both at Massachusetts General Hospital at the time, were among the first to Advertisement 'When they were discovering these things, I'm sure they didn't realize that if we fast forwarded 45 to 50 years, these would be the most talked about [medications],' said Dr. Fatima Cody Stanford, obesity specialist and associate professor of medicine and pediatrics at Harvard Medical School. The US Food and Drug Administration 'What happened here in the '70s and '80s is translating into what we're seeing in 2025,' Stanford said. 'They were developed within the academic setting with The internet Researchers at the Massachusetts Institute of Technology played a significant role in the creation of the internet through a project called John Guttag, a professor of computer science and electrical engineering at MIT, emphasized that while the internet itself was not invented in a single place, 'MIT's fingerprints were all over it.' 'A lot of it was also done by MIT graduates in other places,' he said. 'There were a lot of things that didn't happen at MIT but were clearly influenced by people from MIT.' ARPAnet, which stands for Advanced Research Projects Agency Network, was the direct precursor to and is the basis of today's internet, said Guttag. A computer scientist affiliated with MIT and later Harvard, J.C.R. Licklider, was key in the internet's development. In 1960, he authored a paper outlining his vision of using computer networks for communication, laying the groundwork for ARPAnet, which was first used in 1969. Advertisement 'The Defense Department, immensely wisely, picked a few targets and funded them to do something pretty dramatic over a long period of time,' Guttag said. Pacemakers and defibrillators Defibrillators, medical devices that deliver an electric shock to the heart to restore a normal heart rhythm, are near universally found in malls, offices, and schools these days, saving countless lives. Between 1950 and 1960, Dr. Paul Zoll, a cardiologist at Beth Israel Hospital and professor at Harvard Medical School, Cohen said the development of the external defibrillator was a 'pioneering' discovery 'to help humanity.' 'That's the whole purpose of medical investigation, medical research — it's always ongoing and improving," Cohen said. Black hole imaging In New England, a researcher built one of the algorithms to piece together the first image of a black hole. That image was The Advertisement In 2022, a team led by scientists at the These images are helping scientists discover crucial details about astrophysics, including the ability to test theories about how gas behaves around black holes. 'Black holes are natural laboratories where we can test Einstein's theory of gravity in ways we can't anywhere else in the cosmos,' said Doelman. 'We can see black holes for the first time in ways we would have not thought possible even a decade ago.' Navigation systems During World War II, MIT researchers helped develop the first widely-used electronic navigation system, known as 'It was a very important moment in both MIT's history and the history of federal funding of science and technology,' said David Mindell, professor of aeronautics and astronautics and the history of engineering and manufacturing at MIT. He said the system played a Many researchers who worked on the project went on to become key to GPS development, Mindell said. 'Federal funding for these ecosystems has been enormously important over a long time period,' he said, adding that GPS alone probably 'generated more economic value' over a 40-year period than the entire budgets of the government agencies that helped launch the navigational system. Advertisement Emily Spatz can be reached at


Indianapolis Star
a day ago
- Indianapolis Star
Caitlin Clark injury update: When will Fever star return? 'We're gonna play the long game'
INDIANAPOLIS – Caitlin Clark will not play in Tuesday's game at Atlanta, Fever coach Stephanie White said on Monday. Clark's status for the game, which come just over two weeks after she suffered a quad strain, was previously up in the air. Clark didn't rule out playing in the game in her availability on June 3, but said she would need to be re-evaluated and left it up to the Fever's medical staff to make the final decision. Now, that question has been answered. "Not for tomorrow, no," White said Monday when asked if Clark would be available on Tuesday. Personal touches, secret messages: Behind the scenes of making Caitlin Clark's new Wilson basketballs Clark suffered a quad strain sometime during the Fever's game against the New York Liberty on May 24, though she couldn't pinpoint the specific play it happened. She reported some pain after the game and got an MRI, which showed a strain in her left quad. 'Obviously, adrenaline covers up a lot of stuff when you're in the heat of battle,' Clark said during her media availability on June 3. 'And after the game, I had some pain, and then we got an MRI, and that kind of gave me the result that I didn't want to see. But, you know, those types of things don't lie.' Clark's original timeline was that she would be out for two weeks before she would be re-evaluated, setting her re-evaluation date at June 8. She was evaluated this weekend and allowed to begin some aspects of practice again, White said, but not necessarily cleared for basketball activities at the highest level. "I don't know if cleared is the right word, I mean, she's ready to start ramping back up," White said. "But it's completely different when you're just doing 1-on-1 workouts, and when you're out there in 5-on-5, getting up and down the floor, moving laterally. So she's been allowed to do some practicing, not everything. And we're gonna be smart, and we're gonna be cautious, and we're gonna play the long game." Clark participated in the portion of practice open to media Monday afternoon, which were shooting drills from midrange and 3-point range. They went around the arc as a team, making shots from each corner, each wing and the top of the key. Clark didn't seem limited in that portion of practice, running for rebounds and shooting as normal. But shooting drills are much different than actual practice — both in the amount of contact and the intricacies of it. "It's one thing to do some shooting drills," White said. "It's another thing to get out there on the floor, get back into movement patterns, rhythm, timing, and so that's what part of, you know, picking and choosing things that they can be in in practice, so that we can see their progression." White did not provide a specific timeline for Clark's return to the court. The Fever play at Atlanta on Tuesday, then return to Indianapolis and a have a few days off before playing the New York Liberty on Saturday. No, the Fever star will miss her fifth straight game as she recovers from a quad injury. Coach Stephanie White confirmed Monday that Clark would not play on Tuesday.