Clinicians Prepare for a Possible Shift to Misoprostol-Only Care as Mifepristone Case Looms

 As federal courts weigh the future of mifepristone access, some clinicians are preparing for a scenario many hoped was behind them: relying on misoprostol-only regimens for both abortion and early pregnancy loss care.

A recent ruling from the U.S. Court of Appeals for the Fifth Circuit would reinstate in-person dispensing requirements for mifepristone, which would curtail telehealth prescribing and mail distribution. The U.S. Supreme Court has temporarily paused those restrictions, but a final decision is still pending, leaving providers planning for multiple scenarios. 

“At Planned Parenthood, we’ve actually been preparing for this moment for some time,” said Colleen McNicholas, DO, chief clinical transformation officer at Planned Parenthood Great Northwest, Hawai‘i, Alaska, Indiana, Kentucky. “We knew that mifepristone was going to be a target.” 

If restrictions take effect, many providers would shift toward misoprostol-only protocols, which are supported by global evidence but differ in efficacy, dosing, and side effect profiles, said Eve Espey, MD, MPH, distinguished professor in the Department of Obstetrics and Gynecology at the University of New Mexico. 

“The misoprostol-only regimen is a safe and effective alternative to the combination of mifepristone and misoprostol for medication management of early abortion and miscarriage,” Espey said.

Espey said the primary differences are “effectiveness and side effects.” While safe and effective, she said, misoprostol-only regimens are less effective and less predictable than the combined regimen, resulting in higher rates of ongoing pregnancy and more prolonged or irregular bleeding in some patients.

Indeed, McNicholas said that the combined regimen has efficacy “somewhere around 95%,” while misoprostol alone is “about 85%-95% effective,” depending on gestational age and regimen adherence.

Misoprostol-only regimens also require repeated dosing over a shorter interval and may increase the need for patient counseling around timing, expectations, and symptom management.

“The timing is a little bit different,” McNicholas said, adding that patients take multiple doses within hours rather than spacing medications over 24 to 48 hours. 

According to Espey, because patients generally require more doses of misoprostol than in the combined regimen, clinicians should expect increased rates of nausea, chills, diarrhea, and temperature elevation, as well as potentially more unscheduled clinic or emergency department visits related to bleeding concerns or side effects.

Expanded Implications for Pregnancy Loss 

The implications extend beyond abortion care. Because the same medications are used in miscarriage management, any restriction on mifepristone could have broader clinical consequences. 

“Abortion doesn’t happen in a silo,” McNicholas said. “It is one pregnancy outcome of many, and we do use these medications routinely for other aspects of pregnancy care, most commonly for miscarriage management.”

She warned that challenges to the drug’s safety or availability could spill over into those settings.

“Attacking the sort of safety or the efficacy of the medication used in the indication of abortion absolutely will spill over into miscarriage management,” she said. 

The Supreme Court’s temporary administrative stay preserving telehealth prescribing and mail distribution of mifepristone has been extended to May 14. 

Even if the Court issues a longer-term stay, clinicians and health systems are likely to continue contingency planning as the broader legal challenge proceeds through the courts. And regardless of the outcome, maintaining clarity on the safety and effectiveness of abortion care is critical, McNicholas said. 

“Any time abortion is in the media, people get confused,” McNicholas said. “Medication abortion by mail will still be available, it will still be safe. It might just look a little bit different.”

https://www.medscape.com/viewarticle/clinicians-prepare-possible-shift-misoprostol-only-care-2026a1000fit

Is ChatGPT Health Ready for Emergency Triage?

 ChatGPT Health was launched in January 2026 as OpenAI’s consumer health tool and has reached millions of users. A study evaluating its reliability in clinical practice has raised concerns. Published recently in Nature Medicine, the study found that the system struggled to distinguish emergency situations from routine clinical cases reliably.

Researchers conducted a structured stress test of triage recommendations using 60 clinician-authored vignettes across 21 clinical domains under 16 factorial conditions, yielding a total of 960 responses.

Although ChatGPT performed reasonably well in moderately severe cases, its accuracy declined in clinically extreme scenarios. Among the clinical extremes, only 48% were correctly classified with recommendations for immediate emergency care. Classic emergencies, such as stroke and anaphylaxis, were appropriately identified. However, in the remaining 52% of emergency cases, the system underestimated the severity of the condition. Patients with diabetic ketoacidosis or impending respiratory failure were advised to seek evaluation within 24-48 hours instead of going directly to the emergency department.

The model also overestimated severity in nonurgent situations. In 65% of cases that physicians considered appropriate for home management, the system instead recommended an in-person medical evaluation.

Researchers have found that the system’s handling of possible suicidal ideation is particularly concerning. Recommendations for contact crisis intervention services, including the Suicide and Crisis Lifeline, were triggered unpredictably and did not consistently reflect the severity of the situation.

Training Limitations

The authors suggested that clinical extremes, including both true emergencies and low- acuity “code white” cases, may be underrepresented in the datasets used to train the AI model. Instead, the system appears to be optimized for more “average” clinical presentations.

However, ChatGPT Health may be flawed for another fundamental reason: it lacks true reasoning ability, much like its predecessor, ChatGPT. The training data may differ for each case. ChatGPT Health draws on scientific articles, educational resources, licensed datasets, databases, and data provided by experts to reinforce learning, while ChatGPT was trained on books and vast amounts of internet content. However, the underlying mechanisms remain the same. Both systems generate responses by identifying statistical patterns in a language rather than through genuine reasoning. In practice, ChatGPT Health generates answers based on the likelihood that certain words and phrases logically “fit well” together.

A recent study published in JAMA Network Open supports this concern. Researchers evaluated 21 generative AI models, including OpenAI’s ChatGPT, Anthropic’s Claude, Google’s Gemini, and xAI’s Grok, using 29 clinical cases obtained from widely used medical textbooks. The models were assessed across various stages of the clinical decision-making process, including differential diagnosis, test selection, final diagnosis, and treatment management.

The most significant weaknesses emerged during the early stages of the reasoning process, particularly differential diagnosis, where error rates exceeded 80% across all models. Accuracy improved once the systems were given the full clinical picture, and final diagnoses were sufficiently accurate.

The findings suggest that these models tend to reach diagnostic conclusions too quickly, without adequately addressing uncertainty or before considering a comprehensive differential diagnosis. This differs substantially from the traditional clinical methodology used by clinicians, which relies on stepwise hypothesis testing and systematic exclusion of alternative explanations.

The problem is compounded by what some experts describe as an epistemological illusion: Generative AI can produce text that appears fluent, coherent, and authoritative, even when the underlying reasoning is incomplete or incorrect. The smooth flow and narrative consistency of these responses can create an impression of knowledge without guaranteeing factual accuracy.

Taken together, the evidence suggests that despite rapid advances and the emergence of models optimized for reasoning, generative AI systems, including those designed specifically for healthcare, still fall short of the level of clinical intelligence required for safe implementation. However, their ability to perform advanced clinical reasoning remains limited.

Therefore, what can be done beyond approaching these tools with caution? First, greater transparency is needed. The datasets used to train these systems should be made publicly available to independent experts so that they can assess what information was included, whether biases were addressed or could persist, and how well the data represent real patient populations. In addition, tools such as ChatGPT Health should undergo rigorous scientific validation and comply with medical device regulations before being adopted in clinical settings.

Most importantly, prospective validation is required before AI-based triage systems are deployed on a large scale, a standard that should apply to any technology in medicine. These evaluations should more closely reflect real-world clinical practice rather than relying on multiple-choice style testing, which cannot fully capture the complexity of diagnostic reasoning and clinical decision-making.

Clinicians should avoid relying on these tools whenever possible or restrict their use to the most straightforward clinical scenarios. Even in lower-risk situations, the results generated by these systems should be reviewed carefully and independently verified before being used in clinical decision-making.

Eugenio Santoro is a digital health researcher at the Mario Negri Institute for Pharmacological Research IRCCS in Milan, Italy, where he works in the Laboratory of Medical Informatics and conducts research focused on digital health and digital therapeutics. 

https://www.medscape.com/viewarticle/chatgpt-health-ready-emergency-triage-2026a1000ffi

BeOne accelerated approval for BEQALZI, first BCL2 inhibitor for relapsed, refractory mantle cell lymphoma

 

BeOne Medicines gets U.S. FDA accelerated approval for BEQALZI, first BCL2 inhibitor for relapsed or refractory mantle cell lymphoma after BTK therapy

• BEQALZI (sonrotoclax) is approved for adult mantle cell lymphoma patients who have previously been treated with a BTK inhibitor.

https://finviz.com/quote?t=ONC&p=d

Amdocs guides to flat Q/Q Q3 revenue

 

Amdocs modestly tops fiscal Q2 2026 expectations and guides fiscal Q3 non-GAAP EPS $1.81–$1.87, revenue $1.16–$1.20B

Fiscal Q2 2026 revenue was $1.17B and non-GAAP EPS $1.78, modestly topping expectations. Amdocs expands Lumen billing engagement on Microsoft Azure, extending its Lumen billing engagement.

https://finviz.com/quote?t=DOX&p=d

STAAR beats, returns to profitability

 

STAAR Surgical beats Q1 expectations with adjusted EPS $0.38 on revenue of $93.5 million

• Analyst expectations were $0.13 per share adjusted EPS, compared with reported $0.38 per share.
• Q1 2026 net sales were $93.5 million and EPS was $0.10.
• The company returned to profitability in Q1 2026 while topping consensus expectations.

https://finviz.com/quote?t=STAA&p=d

Tango advances vopimetostat toward pivotal MTAP-deleted pancreatic cancer development

 

Tango Therapeutics advances vopimetostat toward pivotal MTAP-deleted pancreatic cancer development as it posts Q1 2026 $45.5M net loss

• Company disclosed changes to its board of directors in a new SEC filing today.

https://finviz.com/quote?t=TNGX&p=d

Iran Claims 80% Of Bombed-Out Areas Of Tehran Restored, Amid $270B War Loss Compensation Demand

 Iran has been seeking to prove its unity and defiance to the world in the aftermath of the 38-days of heavy US-Israeli bombing it endured throughout the Trump-ordered Operation Epic Fury.

Along with fast seeking to rearm and recover its missile capability after the bombardment which heavily targeted above and below-ground missile silos, it is also rapidly rebuilding bombed-out parts of the capital city Tehran.

Getty Images

In what sounds like a surprising and perhaps high estimate, about 80% of war-damaged sites in Iran's capital have been repaired, the state Islamic Republic of Iran Broadcasting (IRIB) reports.

"More than 60,000 residential and commercial units in Tehran province were hit by American-Zionist attacks during the third imposed war," Deputy Governor of Tehran Seyyed Kamaleddin Mirjafarian was quoted in the report as saying.

The 80% claim might be met with a lot of scrutiny and doubt, given that many neighborhoods and buildings seemed to suffer damage so immense in scale, that it should take at least months if not years to rebuild.

But there has been some clear evidence that Iranian construction teams and engineers have worked around the clock to repair and replace vital infrastructure, like bridges for example.

The US and Israel had struck bridges and rail lines to cripple Iran's national transport network. Israel especially adopted attacks against key civilian infrastructure as a battle tactic, in hopes that eventually there would be a groundswell of anti-Tehran anger domestically, leading to government overthrow.

Also, "ports and railway networks, universities and research centers, and several power plants and water desalination plants were directly hit, while a large number of hospitals, schools and civilian homes were also damaged or destroyed," Al Jazeera describes.

By mid-April, Iran had put a price on the damage, while demanding compensation from Washington:

Iran has also raised the idea of compensation for damages to come through a Strait of Hormuz protocol, which would include a tax on ships passing through the waterway.

An early estimate indicates that Iran has suffered about $270bn in direct and indirect damages since the start of the US-Israel war on February 28, Iranian government spokeswoman Fatemeh Mohajerani said during an interview with Russia’s RIA Novosti news agency, published on Tuesday.

She did not provide further information, such as a breakdown of the damages, but said the issue of compensation was discussed in last week’s negotiations between Tehran and Washington in Pakistan, and will be raised in any potential future talks with the US and mediators.

President Trump himself repeatedly threatening to bomb bridges, power plants, and other infrastructure to send Iran "back to the Stone Age." He's reportedly mulling the resumption of full military operations, amid stalled or non-existent peace talks.

While vital infrastructure and even energy sites have indeed in many cases been obliterated, the lights are still on across the country, save for the persisting government-imposed internet blackout. The internet blackout is now approaching 80 days.

https://www.zerohedge.com/geopolitical/iran-claims-80-bombed-out-areas-tehran-restored-amid-270bn-war-loss-compensation