Artificial Scientific Intelligence for Measurement-burden-aware Modelling and Interpretation of Multi-site Bone Mineral Density
Xiang, S.; He, H.; Xie, Z.; Cheng, C.-Y.; Li, H.; Liu, D.
Show abstract
Agentic workflows can coordinate modelling, but balancing predictive performance, measurement burden and reproducibility is unclear. We developed DXA Agent, an agentic workflow for dual-energy X-ray absorptiometry (DXA) outcomes integrating planning, feature-model refinement, tools, provenance and hypothesis-generating interpretation. Models were independently developed and tested in UK Biobank (5,318 participants) and the National Health and Nutrition Examination Survey (NHANES; 3,777 participants), using cost-efficient and no-limit strategies. Across 20 UK Biobank and three NHANES bone mineral density sites, cost-efficient models achieved lower RMSE and higher R2 than the best conventional comparator, with median relative RMSE reductions of 10.9% and 9.9%, respectively. Classification was task dependent: UK Biobank osteoporosis averaged AUROC 0.839 and PR-AUC 0.182, whereas NHANES performance was comparable with conventional models. Higher-burden features did not consistently improve prediction. These retrospective, cohort-internal findings position DXA Agent as an inspectable, measurement-burden-aware research workflow requiring independent prospective validation.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Covid-19 prevalence estimation by random sampling in the wider population - Optimal sample pooling under varying assumptions about true prevalence 90%
- Quantitative bias analysis in practice: Review of software for regression with unmeasured confounding 89%
- Advancing data science in drug development through an innovative computational framework for data sharing and statistical analysis 88%
Similar papers in this journal
- Combined physical and pharmaceutical anabolic osteoporosis therapies synergistically increase bone response and local mechanoregulation 89%
- Selecting causal risk factors from high-throughput experiments using multivariable Mendelian randomization 88%
- Osteocyte Transcriptome Mapping Identifies a Molecular Landscape Controlling Skeletal Homeostasis and Susceptibility to Skeletal Disease 88%
Similar papers in this journal
- Comparing DXA and MRI body composition measurements in cross-sectional and longitudinal cohorts 91%
- Achieving Inclusive Healthcare through Integrating Education and Research with AI and Personalized Curricula 90%
- Extraction of Crohn's Disease Clinical Phenotypes from Clinical Text Using Natural Language Processing 88%
Similar papers in this journal
- Machine Learning Approaches for the Prediction Bone Mineral Density by using genomic and phenotypic data of 5,130 older Men 92%
- Machine learning approach to dynamic risk modeling of mortality in COVID-19: a UK Biobank study 90%
- Clinical Observation of Diminished Bone Quality and Quantity through Longitudinal HR-pQCT-derived Remodeling and Mechanoregulation 90%
Similar papers in this journal
- Digital health technologies and machine learning augment patient reported outcomes to remotely characterise rheumatoid arthritis 90%
- Large language models improve transferability of electronic health record-based predictions across countries and coding systems 89%
- Development and assessment of a machine learning tool for predicting emergency admission in Scotland 89%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.