The Golden Opportunity or the Cutting Room Floor? Quantifying and Characterizing the Loss and Addition of Social Determinants of Health during Clinician Editing of Ambient AI Documentation
Kim, S.; Guo, Y.; Sutari, S.; Chow, E.; Tam, S.; Perret, D.; Pandita, D.; Zheng, K.
Show abstract
Social determinants of health (SDoH) are important for clinical care, but it remains unclear how much AI-captured social context is preserved after clinician editing in ambient documentation workflows. We retrospectively analyzed 75,133 paired ambient AI-drafted and clinician-finalized note sections from ambulatory care at a large academic health system. Using a rule-based NLP pipeline, we extracted 21 SDoH categories and quantified retention, deletion, and addition. SDoH appeared in 25.2% of AI drafts versus 17.2% of final notes. At the mention level, AI captured 29,991 SDoH mentions, of which 45.1% were deleted, 54.9% were retained with clinicians adding 3,583 new mentions. Insurance and marital status were most often deleted, whereas substance use and physical activity were more often retained. Deletion patterns also varied by specialty, supporting the need for specialty-aware ambient AI systems.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Natural Language Word-Embeddings as a glimpse into healthcare at the End Of Life 93%
- User Testing of a Diagnostic Decision Support System with Machine-assisted Chart Review to Facilitate Clinical Genomic Diagnosis 92%
- Connecting Artificial Intelligence and Primary Care Challenges: Findings from a Multi-Stakeholder Collaborative Consultation 92%
Similar papers in this journal
- Low adherence to existing model reporting guidelines by commonly used clinical prediction models 92%
- Characterizing Potential Conflicts of Interest Among UpToDate and DynaMed Content Contributors 90%
- Electronic Health Record Documentation of Psychiatric Assessments in Massachusetts Emergency Department and Outpatient Settings During the COVID-19 Pandemic 90%
Similar papers in this journal
- Interventions To Improve Patient Safety During The COVID-19 Pandemic: A Systematic Review 91%
- An electronic application to improve management of infections in low-income neonatal units: pilot implementation of the NeoTree Beta App in a public sector hospital in Zimbabwe. 90%
- National statutory reporting: not even ticking the boxes? The quality of ‘Learning from Deaths’ reporting in Quality Accounts within the NHS in England 2017-2020 89%
Similar papers in this journal
- Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale 93%
- Evaluating Anti-LGBTQIA+ Medical Bias in Large Language Models 92%
- A proposed de-identification framework for a cohort of children presenting at a health facility in Uganda 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.