Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports

Yu Wang, Yingyun Li, Ying QIN, Haiyang Qian
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:2109-2130, 2026.

Abstract

This work addresses a cross-institution workflow in which patients present paper or scanned reports from prior visits because relevant records are not available in the receiving hospital’s EHR. This hinders not only electronic health record (EHR) integration and longitudinal review, but also downstream workflows that depend on more complete patient records, including cross-institution EHR back-fill, longitudinal follow-up for chronic disease and oncology, and report-derived clinical-trial eligibility screening. Although optical character recognition (OCR) can digitize such reports, reliable extraction remains challenging because clinical documents are heterogeneous, OCR text is noisy, and many healthcare settings require low-cost on-premise deployment. We formulate this problem as canonical key-conditioned extractive question answering and maintain a canonical inventory and alias mapping through iterative key mining, normalization, clustering, and incremental human verification. On the 849-report development set, inventory expansion increases end-to-end Exact recall from 0.3534 to 0.8042, with Exact F1 peaking at 0.8232 for Top-95. A supplementary gold-key-conditioned comparison shows that a compact 0.2B BERT–BiLSTM–CRF extractor runs substantially faster than LoRA-adapted Qwen3 models on the same GPU, with a modest trade-off in Exact F1. An independent downstream study found task-dependent effects of structured fields, including gains of 3.27 percentage points for histologic grade and 3.52 points for treatment response, but the effects were not uniformly positive across tasks; this study evaluates representation utility rather than the proposed extractor. Although the corpus is Chinese, the method is based on the language-agnostic key–value organization of semi-structured clinical reports and can be adapted to other settings with an appropriate canonical inventory and alias mapping.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-wang26a, title = {Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports}, author = {Wang, Yu and Li, Yingyun and QIN, Ying and Qian, Haiyang}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {2109--2130}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/wang26a/wang26a.pdf}, url = {https://proceedings.mlr.press/v340/wang26a.html}, abstract = {This work addresses a cross-institution workflow in which patients present paper or scanned reports from prior visits because relevant records are not available in the receiving hospital’s EHR. This hinders not only electronic health record (EHR) integration and longitudinal review, but also downstream workflows that depend on more complete patient records, including cross-institution EHR back-fill, longitudinal follow-up for chronic disease and oncology, and report-derived clinical-trial eligibility screening. Although optical character recognition (OCR) can digitize such reports, reliable extraction remains challenging because clinical documents are heterogeneous, OCR text is noisy, and many healthcare settings require low-cost on-premise deployment. We formulate this problem as canonical key-conditioned extractive question answering and maintain a canonical inventory and alias mapping through iterative key mining, normalization, clustering, and incremental human verification. On the 849-report development set, inventory expansion increases end-to-end Exact recall from 0.3534 to 0.8042, with Exact F1 peaking at 0.8232 for Top-95. A supplementary gold-key-conditioned comparison shows that a compact 0.2B BERT–BiLSTM–CRF extractor runs substantially faster than LoRA-adapted Qwen3 models on the same GPU, with a modest trade-off in Exact F1. An independent downstream study found task-dependent effects of structured fields, including gains of 3.27 percentage points for histologic grade and 3.52 points for treatment response, but the effects were not uniformly positive across tasks; this study evaluates representation utility rather than the proposed extractor. Although the corpus is Chinese, the method is based on the language-agnostic key–value organization of semi-structured clinical reports and can be adapted to other settings with an appropriate canonical inventory and alias mapping.} }
Endnote
%0 Conference Paper %T Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports %A Yu Wang %A Yingyun Li %A Ying QIN %A Haiyang Qian %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-wang26a %I PMLR %P 2109--2130 %U https://proceedings.mlr.press/v340/wang26a.html %V 340 %X This work addresses a cross-institution workflow in which patients present paper or scanned reports from prior visits because relevant records are not available in the receiving hospital’s EHR. This hinders not only electronic health record (EHR) integration and longitudinal review, but also downstream workflows that depend on more complete patient records, including cross-institution EHR back-fill, longitudinal follow-up for chronic disease and oncology, and report-derived clinical-trial eligibility screening. Although optical character recognition (OCR) can digitize such reports, reliable extraction remains challenging because clinical documents are heterogeneous, OCR text is noisy, and many healthcare settings require low-cost on-premise deployment. We formulate this problem as canonical key-conditioned extractive question answering and maintain a canonical inventory and alias mapping through iterative key mining, normalization, clustering, and incremental human verification. On the 849-report development set, inventory expansion increases end-to-end Exact recall from 0.3534 to 0.8042, with Exact F1 peaking at 0.8232 for Top-95. A supplementary gold-key-conditioned comparison shows that a compact 0.2B BERT–BiLSTM–CRF extractor runs substantially faster than LoRA-adapted Qwen3 models on the same GPU, with a modest trade-off in Exact F1. An independent downstream study found task-dependent effects of structured fields, including gains of 3.27 percentage points for histologic grade and 3.52 points for treatment response, but the effects were not uniformly positive across tasks; this study evaluates representation utility rather than the proposed extractor. Although the corpus is Chinese, the method is based on the language-agnostic key–value organization of semi-structured clinical reports and can be adapted to other settings with an appropriate canonical inventory and alias mapping.
APA
Wang, Y., Li, Y., QIN, Y. & Qian, H.. (2026). Key Coverage Matters: Semi-Structured Extraction of OCR Clinical Reports. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:2109-2130 Available from https://proceedings.mlr.press/v340/wang26a.html.

Related Material