Universal Laboratory Model: prognosis of abnormal clinical outcomes based on routine tests

TL;DR

This paper introduces a novel method for predicting abnormal clinical test outcomes using routine laboratory data, effectively handling missing values and improving prediction accuracy for key biomarkers.

Contribution

It formulates a set translation approach that bridges large language models with tabular clinical data, enabling accurate predictions without imputing missing values.

Findings

Achieved up to 8% AUC improvement in predicting abnormal test results.

Effectively handles missing data without explicit imputation.

Bridges LLM techniques with clinical tabular data analysis.

Abstract

Clinical laboratory results are ubiquitous in any diagnosis making. Predicting abnormal values of not prescribed tests based on the results of performed tests looks intriguing, as it would be possible to make early diagnosis available to everyone. The special place is taken by the Common Blood Count (CBC) test, as it is the most widely used clinical procedure. Combining routine biochemical panels with CBC presents a set of test-value pairs that varies from patient to patient, or, in common settings, a table with missing values. Here we formulate a tabular modeling problem as a set translation problem where the source set comprises pairs of GPT-like label column embedding and its corresponding value while the target set consists of the same type embeddings only. The proposed approach can effectively deal with missing values without implicitly estimating them and bridges the world of LLM with the tabular domain. Applying this method to clinical laboratory data, we achieve an improvement up to 8% AUC for joint predictions of high uric acid, glucose, cholesterol, and low ferritin levels.