Machine Learning to Identify Point-of-Care Ultrasound and Evaluate Standardized Documentation: Retrospective Operational Cohort Study.
Standardized templates lowered odds of missed point-of-care ultrasound billing charges.
Machine Learning to Identify Point-of-Care Ultrasound and Evaluate Standardized Documentation: Retrospective Operational Cohort Study.
Point-of-care ultrasound (point-of-care ultrasound) is integral to obstetrics and gynecology (obstetrics and gynecology), offering bedside diagnostic and therapeutic advantages.
This study leveraged machine learning (machine learning) to automatically identify point-of-care ultrasound procedures within clinical notes and assessed the effect of implementing standardized procedure documentation (procedure documentation) templates on billing capture accuracy and efficiency.
We conducted a multipart retrospective cohort study at a large academic medical center using EHRs from January 2018 to August 2024 across 11 obstetrics and gynecology clinic sites.
auto-capture cut the odds of missed billing charges
The BioClinBERT model (accuracy 0.97; F1-score 0.55-0.63) demonstrated a robust ability to identify documented and missed procedures in free-text clinical notes.
Procedure documentation adoption reached 75.1% within 12 months, supported by comprehensive staff education.
Most postintervention Current Procedural Terminology codes (1812/2404, 75.4%) originated from procedure documentation templates, confirming improved workflow efficiency and reduced manual audit burden.
Model analysis and billing metrics demonstrated that improvements were associated with workflow changes and not an increase in procedure frequency.
Machine learning modeling proved effective for extracting point-of-care ultrasound procedures from clinical documentation and serving as an evaluation tool for workflow interventions.
Standardized documentation with procedure documentation significantly enhanced charge capture accuracy and reduced dependence on manual chart reviews and billing reconciliation.
This approach highlights the use of machine learning as a retrospective auditing and evaluation tool for assessing clinical workflow interventions.