Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915450920632320 |
|---|---|
| author | Wong, Cliff Preston, Sam Liu, Qianchu Gero, Zelalem Bagga, Jaspreet Zhang, Sheng Jain, Shrey Zhao, Theodore Gu, Yu Xu, Yanbo Kiblawi, Sid Yegnasubramanian, Srinivasan Botsis, Taxiarchis Borja, Marvin Ahumada, Luis M. Murray, Joseph C. Gan, Guo Hui Weerasinghe, Roshanthi Young, Kristina Leidner, Rom Piening, Brian Bifulco, Carlo Naumann, Tristan Wei, Mu Poon, Hoifung |
| author_facet | Wong, Cliff Preston, Sam Liu, Qianchu Gero, Zelalem Bagga, Jaspreet Zhang, Sheng Jain, Shrey Zhao, Theodore Gu, Yu Xu, Yanbo Kiblawi, Sid Yegnasubramanian, Srinivasan Botsis, Taxiarchis Borja, Marvin Ahumada, Luis M. Murray, Joseph C. Gan, Guo Hui Weerasinghe, Roshanthi Young, Kristina Leidner, Rom Piening, Brian Bifulco, Carlo Naumann, Tristan Wei, Mu Poon, Hoifung |
| contents | A significant fraction of real-world patient information resides in unstructured clinical text. Medical abstraction extracts and normalizes key structured attributes from free-text clinical notes, which is the prerequisite for a variety of important downstream applications, including registry curation, clinical trial operations, and real-world evidence generation. Prior medical abstraction methods typically resort to building attribute-specific models, each of which requires extensive manual effort such as rule creation or supervised label annotation for the individual attribute, thus limiting scalability. In this paper, we show that existing frontier models already possess the universal abstraction capability for scaling medical abstraction to a wide range of clinical attributes. We present UniMedAbstractor (UMA), a unifying framework for zero-shot medical abstraction with a modular, customizable prompt template and the selection of any frontier large language models. Given a new attribute for abstraction, users only need to conduct lightweight prompt adaptation in UMA to adjust the specification in natural languages. Compared to traditional methods, UMA eliminates the need for attribute-specific training labels or handcrafted rules, thus substantially reducing the development time and cost. We conducted a comprehensive evaluation of UMA in oncology using a wide range of marquee attributes representing the cancer patient journey. These include relatively simple attributes typically specified within a single clinical note (e.g. performance status), as well as complex attributes requiring sophisticated reasoning across multiple notes at various time points (e.g. tumor staging). Based on a single frontier model such as GPT-4o, UMA matched or even exceeded the performance of state-of-the-art attribute-specific methods, each of which was tailored to the individual attribute. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_00943 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale Wong, Cliff Preston, Sam Liu, Qianchu Gero, Zelalem Bagga, Jaspreet Zhang, Sheng Jain, Shrey Zhao, Theodore Gu, Yu Xu, Yanbo Kiblawi, Sid Yegnasubramanian, Srinivasan Botsis, Taxiarchis Borja, Marvin Ahumada, Luis M. Murray, Joseph C. Gan, Guo Hui Weerasinghe, Roshanthi Young, Kristina Leidner, Rom Piening, Brian Bifulco, Carlo Naumann, Tristan Wei, Mu Poon, Hoifung Computation and Language A significant fraction of real-world patient information resides in unstructured clinical text. Medical abstraction extracts and normalizes key structured attributes from free-text clinical notes, which is the prerequisite for a variety of important downstream applications, including registry curation, clinical trial operations, and real-world evidence generation. Prior medical abstraction methods typically resort to building attribute-specific models, each of which requires extensive manual effort such as rule creation or supervised label annotation for the individual attribute, thus limiting scalability. In this paper, we show that existing frontier models already possess the universal abstraction capability for scaling medical abstraction to a wide range of clinical attributes. We present UniMedAbstractor (UMA), a unifying framework for zero-shot medical abstraction with a modular, customizable prompt template and the selection of any frontier large language models. Given a new attribute for abstraction, users only need to conduct lightweight prompt adaptation in UMA to adjust the specification in natural languages. Compared to traditional methods, UMA eliminates the need for attribute-specific training labels or handcrafted rules, thus substantially reducing the development time and cost. We conducted a comprehensive evaluation of UMA in oncology using a wide range of marquee attributes representing the cancer patient journey. These include relatively simple attributes typically specified within a single clinical note (e.g. performance status), as well as complex attributes requiring sophisticated reasoning across multiple notes at various time points (e.g. tumor staging). Based on a single frontier model such as GPT-4o, UMA matched or even exceeded the performance of state-of-the-art attribute-specific methods, each of which was tailored to the individual attribute. |
| title | Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.00943 |