An Agentic System for Automated Data Curation and Analysis in Large-Scale Biobanks

Chang-Uk Jeong, Jaesik Kim, Jaehyun Joo, Byounghan Lee, Yang-Gyun Kim, Dokyoon Kim
Proceedings of the Fifth Machine Learning for Health Symposium, PMLR 297:1141-1158, 2026.

Abstract

The translation of clinical and lifestyle concepts into computable phenotypes is a critical yet manually intensive bottleneck in leveraging large-scale biomedical datasets like the {UK} Biobank. This process is slow, requires deep domain expertise, and suffers from a lack of scalability and reproducibility, especially for clinicians unfamiliar with large-scale data analysis. We propose and develop an autonomous, dual-component agentic system designed to automate the research workflow from hypothesis to report. The first component, the large language model ({LLM})-based data preprocessing framework, systematically searches the {UK} Biobank’s public data dictionary, translating high-level clinical and lifestyle concepts into machine-readable rules. The second component, the Analysis Agent, autonomously executes the statistical analysis plan and synthesizes the findings. The framework is further validated by successfully phenotyping and analyzing several clinical and lifestyle screeners. This work demonstrates a viable end-to-end system that enhances scalability and democratizes complex data analysis with transparency, representing a foundational step toward a new paradigm of {AI}-driven scientific discovery.

Cite this Paper

BibTeX
@InProceedings{pmlr-v297-jeong26a, title = {An Agentic System for Automated Data Curation and Analysis in Large-Scale Biobanks}, author = {Jeong, Chang-Uk and Kim, Jaesik and Joo, Jaehyun and Lee, Byounghan and Kim, Yang-Gyun and Kim, Dokyoon}, booktitle = {Proceedings of the Fifth Machine Learning for Health Symposium}, pages = {1141--1158}, year = {2026}, editor = {Argaw, Peniel and Zhang, Haoran and Jabbour, Sarah and Chandak, Payal and Ji, Jerry and Mukherjee, Sumit and Salaudeen, Olawale and Chang, Trenton and Healey, Elizabeth and Gröger, Fabian and Adibi, Amin and Hegselmann, Stefan and Wild, Benjamin and Noori, Ayush}, volume = {297}, series = {Proceedings of Machine Learning Research}, month = {13--14 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v297/main/assets/jeong26a/jeong26a.pdf}, url = {https://proceedings.mlr.press/v297/jeong26a.html}, abstract = {The translation of clinical and lifestyle concepts into computable phenotypes is a critical yet manually intensive bottleneck in leveraging large-scale biomedical datasets like the {UK} Biobank. This process is slow, requires deep domain expertise, and suffers from a lack of scalability and reproducibility, especially for clinicians unfamiliar with large-scale data analysis. We propose and develop an autonomous, dual-component agentic system designed to automate the research workflow from hypothesis to report. The first component, the large language model ({LLM})-based data preprocessing framework, systematically searches the {UK} Biobank’s public data dictionary, translating high-level clinical and lifestyle concepts into machine-readable rules. The second component, the Analysis Agent, autonomously executes the statistical analysis plan and synthesizes the findings. The framework is further validated by successfully phenotyping and analyzing several clinical and lifestyle screeners. This work demonstrates a viable end-to-end system that enhances scalability and democratizes complex data analysis with transparency, representing a foundational step toward a new paradigm of {AI}-driven scientific discovery.} }
Endnote
%0 Conference Paper %T An Agentic System for Automated Data Curation and Analysis in Large-Scale Biobanks %A Chang-Uk Jeong %A Jaesik Kim %A Jaehyun Joo %A Byounghan Lee %A Yang-Gyun Kim %A Dokyoon Kim %B Proceedings of the Fifth Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2026 %E Peniel Argaw %E Haoran Zhang %E Sarah Jabbour %E Payal Chandak %E Jerry Ji %E Sumit Mukherjee %E Olawale Salaudeen %E Trenton Chang %E Elizabeth Healey %E Fabian Gröger %E Amin Adibi %E Stefan Hegselmann %E Benjamin Wild %E Ayush Noori %F pmlr-v297-jeong26a %I PMLR %P 1141--1158 %U https://proceedings.mlr.press/v297/jeong26a.html %V 297 %X The translation of clinical and lifestyle concepts into computable phenotypes is a critical yet manually intensive bottleneck in leveraging large-scale biomedical datasets like the {UK} Biobank. This process is slow, requires deep domain expertise, and suffers from a lack of scalability and reproducibility, especially for clinicians unfamiliar with large-scale data analysis. We propose and develop an autonomous, dual-component agentic system designed to automate the research workflow from hypothesis to report. The first component, the large language model ({LLM})-based data preprocessing framework, systematically searches the {UK} Biobank’s public data dictionary, translating high-level clinical and lifestyle concepts into machine-readable rules. The second component, the Analysis Agent, autonomously executes the statistical analysis plan and synthesizes the findings. The framework is further validated by successfully phenotyping and analyzing several clinical and lifestyle screeners. This work demonstrates a viable end-to-end system that enhances scalability and democratizes complex data analysis with transparency, representing a foundational step toward a new paradigm of {AI}-driven scientific discovery.
APA
Jeong, C., Kim, J., Joo, J., Lee, B., Kim, Y. & Kim, D.. (2026). An Agentic System for Automated Data Curation and Analysis in Large-Scale Biobanks. Proceedings of the Fifth Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 297:1141-1158 Available from https://proceedings.mlr.press/v297/jeong26a.html.

Related Material