Priyanka Ahimaz | PubMed Health

PubMed2026

Hard to Halt: Automation Bias in Agent-Driven Sequencing Prior Authorization Workflows.

PURPOSE: Prior authorization (PA) for exome or genome sequencing is a time-consuming process that impedes timely rare disease diagnosis. Large language model-based browser agents offer potential for automating these workflows, but their clinical reliability remain uncharacterized. METHODS: We developed a sandbox compromising a simulated ES/GS PA submission payer portal and a synthetic EHR containing 836 patient records spanning compliant profiles and deficient profiles with different types of issues. Gemini 3 Pro, Gemini 3 Flash, and Claude Opus 4.5 were evaluated on task completion rate, form completion accuracy, and appropriate withholding for deficient profiles. RESULTS: Larger models achieved much higher task completion rates (Gemini 3 Pro 95.45%, Claude Opus 4.5 93.67%) compared to Gemini 3 Flash (56.05%), but nearly universally failed to withhold submission for deficient profiles whereas Gemini 3 Flash ironically demonstrated superior withholding performance (17.33%). In a non-agentic setting, Gemini 3 Pro correctly identified 91% of the issues in deficient profiles, indicating that withholding failure is attributable to the browser interaction rather than the model's reasoning limitations. CONCLUSION: Current LLM-based browser agents exhibit a systematic bias towards form submission that poses risks in PA workflows. A modular, multi-agent architecture with human supervision is necessary for a safe clinical deployment.

Journal Article↗

PubMed2026

Are we Prepared? Genetic Counseling for Stillbirth in the Sequencing Era.

Stillbirth affects approximately 1 in 175 pregnancies annually in the United States. Although the American College of Obstetricians and Gynecologists recommends genetic testing as part of the stillbirth evaluation, families often face barriers to obtaining a complete evaluation. Expansion of the diagnostic evaluation of stillbirth is expected to include exome/genome sequencing, with preliminary studies demonstrating its diagnostic utility. Consequently, genetic counselors (GCs) are expected to play an expanding role in post-stillbirth care. This study explored current genetic counseling practices for stillbirth and GCs' preparedness to support patients in this setting. A cross-sectional survey was distributed across four channels. Eligible participants included GCs in the United States and Canada with at least 1 year of prenatal experience. The survey assessed GC frequency and timing in stillbirth counseling, genetic testing practices, comfort addressing psychosocial needs, and perceived barriers to care. Responses were analyzed using descriptive statistics. Group comparisons were performed using Chi-square and Fisher's exact tests. Open-ended responses were coded for themes. Seventy-one responses were analyzed. Approximately half of respondents (49.3%, n = 36) reported "never/very rarely/rarely" counseling patients postpartum, despite this being the optimal time to offer genetic testing. Delivering providers (46.5%, n = 33) were often responsible for informing patients about testing and obtaining consent, compared to GCs (11.3%, n = 8). Although chromosomal microarray (CMA) is recommended as the standard of care (SOC), 12.7% (n = 9) of GCs reported not offering CMA for anomalous and non-anomalous stillbirths. Perceived barriers to SOC testing included reported lack of obstetrician awareness (91.5%, n = 65) and challenges coordinating specimen collection (90.1%, n = 64). These findings highlight barriers to SOC genetic evaluation and underscore the need to strengthen institutional protocols, enhance provider education, and develop stillbirth-specific genetic counseling guidelines. GC involvement in these efforts will be essential to promoting equitable access to comprehensive post-stillbirth care as sequencing becomes integrated into practice.

Humans↗