medical_records_processing · healthcare · workflow
Advent Health Partners uses active learning and model-assisted labeling to speed up medical record processing with Labelbox
Extracting entities from millions of multi-format medical records (PDFs, faxes, scans) from diverse providers with no consistent formatting was time-intensive and expensive, creating a bottleneck for training clinical ML models.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Medical records ingested
Medical records arrive from numerous providers, hospitals, and insurance companies in inconsistent formats including PDFs, faxes, and scans.
Tools used
LabelboxOCRNLP
Outcome
By adopting Labelbox's active learning and model-assisted labeling, AHP reduced the average time per label from 13 seconds to 8 seconds and cut 25 hours off each specific labeling task, while also achieving better model performance through semi-supervised class balancing.
Results
Time saved13 seconds
Volume8 seconds
Running sinceNov 2022
Grounding & classification
Source type: vendor customer story
30 fields verified against source quotes.
data extractiondocument classificationocrclinical notemedical recordhuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedhealthcareaccuracy improvementcycle time reductionemployee productivitytime savedvendor customer storydata entry opsmedical records processingquality assurancedocument to recordextract classify routehuman review queue