Learning Normal Representations for Blood Biomarkers

TL;DR

This paper introduces NORMA, a transformer-based model that improves blood biomarker interpretation by combining individual history with population data, leading to better prediction of clinical outcomes.

Contribution

The study presents NORMA, a novel framework that generates personalized reference intervals using both patient history and population data, outperforming existing methods.

Findings

Purely personalized intervals overfit, classifying up to 68% of measurements as abnormal.

NORMA-derived intervals better predict mortality, kidney injury, and chronic disease.

Population-level priors improve individual biomarker interpretation over over-personalization.

Abstract

Blood-based biomarkers underpin clinical diagnosis and management, yet their interpretation relies largely on fixed population reference intervals that ignore stable, intra-patient variability. As such, population-based interpretation can mask meaningful deviation from an individual's baseline, risking delayed disease detection. To remedy this, there have been increasing efforts to personalize blood biomarker interpretation using individual testing histories. However, these methods may overfit to sparse data, inflating false-positive rates and unnecessary follow-up, and can also unwittingly include unrecognized or subclinical disease. Here, we leverage nearly 2 billion longitudinal laboratory measurements from over 1.6 million individuals across North America, the Middle East, and East Asia, to show that while laboratory values are highly individual, purely personalized intervals routinely overfit, classifying up to 68% of measurements as abnormal, without corresponding associations with adverse clinical outcomes. We then introduce NORMA, a conditional transformer-based framework that generates reference intervals by conditioning on both a patient's history and population-level data about "normal" variation. NORMA-derived intervals achieve higher precision for predicting outcomes, including mortality, acute kidney injury, and chronic disease. These findings caution against over-personalization in laboratory medicine and demonstrate that anchoring individual trajectories to population-level priors outperforms either approach alone. To promote transparency, we publicly release the model, code, and an interactive user interface for accessible, individualized laboratory interpretation.