Article Impact Level: HIGH Data Quality: STRONG Summary of International Breastfeeding Journal, 20(1), 59. https://doi.org/10.1186/s13006-025-00756-y Dr. Rachel Pilgrim et al.
Points
- A significant percentage of women discontinue breastfeeding due to medication, with rates ranging from 2% to 58% depending on the population and maternal health conditions.
- The majority of medications implicated in breastfeeding cessation, excluding lithium, have post-marketing data indicating they are safe, suggesting that much of this discontinuation may be avoidable.
- Healthcare professionals provide inconsistent guidance, with some encouraging unnecessary cessation while others help reduce it, highlighting a critical gap between evidence and standard clinical practice.
- Identified risk factors for discontinuation include lower education, Caesarean delivery, chronic health conditions, pre-pregnancy smoking, and less prior experience with breastfeeding, indicating vulnerable populations.
- Further research is needed to address systemic barriers and inform interventions that support women’s decision-making, especially among diverse and underrepresented groups, to improve maternal and infant outcomes.
Summary
A recent study published in npj Digital Medicine evaluated the clinical reliability of three generative large language models (LLMs)—GPT-4o, Claude 3 Sonnet, and Gemini Ultra 1.0—across the stroke care continuum. Researchers from National Taiwan University and Harvard T.H. Chan School of Public Health tested the models on realistic patient inquiries spanning four stages: prevention, diagnosis, treatment, and rehabilitation. Three prompt engineering techniques were utilized: Zero-Shot Learning (ZSL), Chain of Thought (COT), and Talking Out Your Thoughts (TOT). The study did not include confidence intervals or hazard ratios, as it was based on qualitative scoring rather than clinical trial outcomes.
Outputs were assessed by four blinded senior stroke specialists across five domains: accuracy, hallucinations, specificity, empathy, and actionability. A clinical competency benchmark was established at a score of 60/100, aligning with the standards of Taiwan’s medical qualification exam. Overall performance was suboptimal, with average scores ranging between 48 and 56. No single model or prompt combination consistently passed the competency threshold. The models struggled most significantly with acute treatment inquiries, where scores were lowest.
While the LLMs showed inconsistent performance, specific prompt engineering techniques demonstrated distinct advantages. TOT prompts improved scores for empathy and actionability, occasionally allowing models to meet or exceed the 60/100 benchmark in prevention and rehabilitation scenarios. ZSL was most effective at reducing hallucinations and providing concise, accurate responses, particularly in the treatment stage. The authors conclude that despite their potential, current general-purpose LLMs are unreliable for independent use in high-risk medical situations like stroke and necessitate robust human oversight and AI-clinician collaboration for safe deployment.
Link to the article: https://internationalbreastfeedingjournal.biomedcentral.com/articles/10.1186/s13006-025-00756-y
References Pilgrim, R., Kwok, M., May, A., Chapman, S., & Jones, M. D. (2025). The effect of medication use on breastfeeding continuation: A systematic review with narrative synthesis. International Breastfeeding Journal, 20(1), 59. https://doi.org/10.1186/s13006-025-00756-y
