Using Machine Learning to Predict Laboratory Test Results

2016/06/01 by Yuan Luo, Peter Szolovits, Anand S Dighe +3 · 171 citations
Medicine · #Artificial intelligence #Biology #Clinical Laboratory Practices and Quality Control #Computer science #Hemoglobinopathies and Related Disorders #Iron Metabolism and Disorders #Machine learning #Test (biology)

paper · pdf · doi:10.1093/ajcp/aqw064

published in American Journal of Clinical Pathology 145(6), 778-788 (Oxford University Press)

openalex publication_date 2016/06/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/25

Abstract

OBJECTIVES: While clinical laboratories report most test results as individual numbers, findings, or observations, clinical diagnosis usually relies on the results of multiple tests. Clinical decision support that integrates multiple elements of laboratory data could be highly useful in enhancing laboratory diagnosis. METHODS: Using the analyte ferritin in a proof of concept, we extracted clinical laboratory data from patient testing and applied a variety of machine-learning algorithms to predict ferritin test results using the results from other tests. We compared predicted with measured results and reviewed selected cases to assess the clinical value of predicted ferritin. RESULTS: We show that patient demographics and results of other laboratory tests can discriminate normal from abnormal ferritin results with a high degree of accuracy (area under the curve as high as 0.97, held-out test data). Case review indicated that predicted ferritin results may sometimes better reflect underlying iron status than measured ferritin. CONCLUSIONS: These findings highlight the substantial informational redundancy present in patient test results and offer a potential foundation for a novel type of clinical decision support aimed at integrating, interpreting, and enhancing the diagnostic value of multianalyte sets of clinical laboratory test results.

Cited by

• Early Prediction of Mortality in Critical Care Setting in Sepsis Patients Using Structured Features and Unstructured Clinical Notes
• Integrating Hypertension Phenotype and Genotype with Hybrid Non-negative Matrix Factorization
• Unsupervised Learning to Subphenotype Delirium Patients from Electronic Health Records
• Are My EHRs Private Enough? -Event-level Privacy Protection
• An Optimal Policy for Patient Laboratory Tests in Intensive Care Units
• Machine Learning and Visualization in Clinical Decision Support: Current State and Future Directions
• Universal Laboratory Model: prognosis of abnormal clinical outcomes based on routine tests
• Natural Language Processing for EHR-Based Computational Phenotyping
• 3D-MICE: integration of cross-sectional and longitudinal imputation for multi-analyte longitudinal clinical data. [europepmc]
• An application of machine learning to haematological diagnosis. [europepmc]
• Estimating summary statistics for electronic health record laboratory data for use in high-throughput phenotyping algorithms. [europepmc]
• Natural Language Processing for EHR-Based Computational Phenotyping. [europepmc]
• Early prediction of acute kidney injury following ICU admission using a multivariate panel of physiological measurements. [europepmc]
• Prevalence and Predictability of Low-Yield Inpatient Laboratory Diagnostic Tests. [europepmc]
• Suggestions for designing studies investigating diagnostic accuracy of biomarkers. [europepmc]
• Predictive modeling of bacterial infections and antibiotic therapy needs in critically ill adults. [europepmc]
• Development of a prognostic model for mortality in COVID-19 infection using machine learning. [europepmc]
• Development and External Validation of a Machine Learning Tool to Rule Out COVID-19 Among Adults in the Emergency Department Using Routine Blood Tests: A Large, Multicenter, Real-World Study. [europepmc]
• Predicting Missing Values in Medical Data via XGBoost Regression. [europepmc]
• Deep into Laboratory: An Artificial Intelligence Approach to Recommend Laboratory Tests. [europepmc]
• Rise of the Machines: The Inevitable Evolution of Medicine and Medical Laboratories Intertwining with Artificial Intelligence-A Narrative Review. [europepmc]
• Machine Learning Applications in the Diagnosis of Benign and Malignant Hematological Diseases. [europepmc]
• Imputation of missing values for electronic health record laboratory data. [europepmc]
• Evaluating the state of the art in missing data imputation for clinical data. [europepmc]
• Beyond the In-Practice CBC: The Research CBC Parameters-Driven Machine Learning Predictive Modeling for Early Differentiation among Leukemias. [europepmc]
• MedGCN: Medication recommendation and lab test imputation via graph convolutional networks. [europepmc]
• Applications of machine learning in routine laboratory medicine: Current state and future directions. [europepmc]
• Machine Learning in Causal Inference: Application in Pharmacovigilance. [europepmc]
• Deep learning on time series laboratory test results from electronic health records for early detection of pancreatic cancer. [europepmc]
• Building the Model. [europepmc]
• Multimodal machine learning in precision health: A scoping review. [europepmc]
• Targeting repetitive laboratory testing with electronic health records-embedded predictive decision support: A pre-implementation study. [europepmc]
• Response accuracy of ChatGPT 3.5 Copilot and Gemini in interpreting biochemical laboratory data a pilot study. [europepmc]

Related

• Using Machine Learning to Develop Smart Reflex Testing Protocols
• Machine Learning in Laboratory Medicine: Recommendations of the IFCC Working Group
• Validating, Implementing, and Monitoring Machine Learning Solutions in the Clinical Laboratory Safely and Effectively
• Universal Laboratory Model: prognosis of abnormal clinical outcomes based on routine tests
• Medical Diagnosis From Laboratory Tests by Combining Generative and Discriminative Learning