Bias in Laboratory Medicine: The Dark Side of the Moon
Abdurrahman Coskun 
, M.D.
Review Article l 01 January 2025
Toward High-Quality Real-World Laboratory Data in the Era of Healthcare Big Data
Sollip Kim, M.D., Ph.D. and Won-Ki Min et al.
Ann Lab Med 2025; 45: 1-11
With Industry 4.0, big data and artificial intelligence have become paramount in the field of medicine. Electronic health records, the primary source of medical data, are not collected for research purposes but represent real-world data; therefore, t...
Keywords: Artificial intelligence, Big data, Data quality, Harmonization, Laboratory medicine, Real-world data, Standardization
Review Article l 01 January 2025
Laboratory Data as a Potential Source of Bias in Healthcare Artificial Intelligence and Machine Learning Models
Hung S. Luu, M.D.
Ann Lab Med 2025; 45: 12-21
Artificial intelligence (AI) and machine learning (ML) are anticipated to transform the practice of medicine. As one of the largest sources of digital data in healthcare, laboratory results can strongly influence AI and ML algorithms that require lar...
Keywords: Aggregation bias, Artificial intelligence, Clinical pathology, Diagnostic error, Health information interoperability, Logical Observation Identifiers Names and Codes, Machine learning, SNOMED CT
Review Article l 01 January 2025
Advancing Laboratory Medicine Practice With Machine Learning: Swift yet Exact
Jiwon You, M.S., Hyeon Seok Seok et al.
Ann Lab Med 2025; 45: 22-35
Machine learning (ML) is currently being widely studied and applied in data analysis and prediction in various fields, including laboratory medicine. To comprehensively evaluate the application of ML in laboratory medicine, we reviewed the literature...
Keywords: Artificial intelligence, Clinical laboratory tests, Laboratory medicine, Machine learning
Most Read
-
Review Article2024-01-01 Clinical Chemistry
Abstract : Physicians increasingly use laboratory-produced information for disease diagnosis, patient monitoring, treatment planning, and evaluations of treatment effectiveness. Bias is the systematic deviation of laboratory test results from the actual value, which can cause misdiagnosis or misestimation of disease prognosis and increase healthcare costs. Properly estimating and treating bias can help to reduce laboratory errors, improve patient safety, and considerably reduce healthcare costs. A bias that is statistically and medically significant should be eliminated or corrected. In this review, the theoretical aspects of bias based on metrological, statistical, laboratory, and biological variation principles are discussed. These principles are then applied to laboratory and diagnostic medicine for practical use from clinical perspectives.
-
Review Article2023-05-01 Clinical Chemistry
Biomarkers in Heart Failure: From Research to Clinical Practice
Alexander E. Berezin
Ann Lab Med 2023; 43(3): 225-236, M.D., Ph.D. and Alexander A. Berezin , M.D.Abstract : The aim of this narrative review is to summarize contemporary evidence on the use of circulating cardiac biomarkers of heart failure (HF) and to identify a promising biomarker model for clinical use in personalized point-of-care HF management. We discuss the reported biomarkers of HF classified into clusters, including myocardial stretch and biomechanical stress; cardiac myocyte injury; systemic, adipocyte tissue, and microvascular inflammation; cardiac fibrosis and matrix remodeling; neurohumoral activation and oxidative stress; impaired endothelial function and integrity; and renal and skeletal muscle dysfunction. We focus on the benefits and drawbacks of biomarker-guided assistance in daily clinical management of patients with HF. In addition, we provide clear information on the role of alternative biomarkers and future directions with the aim of improving the predictive ability and reproducibility of multiple biomarker models and advancing genomic, transcriptomic, proteomic, and metabolomic evaluations.
-
Review Article2024-03-01 Clinical Chemistry
Exploring Renal Function Assessment: Creatinine, Cystatin C, and Estimated Glomerular Filtration Rate Focused on the European Kidney Function Consortium Equation
Hans Pottel
Ann Lab Med 2024; 44(2): 135-143, Ph.D., Pierre Delanaye , M.D., Ph.D., and Etienne Cavalier , Ph.D.Abstract : Serum creatinine and serum cystatin C are the most widely used renal biomarkers for calculating the estimated glomerular filtration rate (eGFR), which is used to estimate the severity of kidney damage. In this review, we present the basic characteristics of these biomarkers, their advantages and disadvantages, some basic history, and current laboratory measurement practices with state-of-the-art methodology. Their clinical utility is described in terms of normal reference intervals, graphically presented with age-dependent reference intervals, and their use in eGFR equations.
-
Review Article2024-03-01 Clinical Chemistry
The Use of Bone-Turnover Markers in Asia-Pacific Populations
Samuel Vasikaran
Ann Lab Med 2024; 44(2): 126-134, M.D., Subashini C. Thambiah , M.Path., Rui Zhen Tan , Ph.D., and Tze Ping Loh , M.B., B.ch., B.A.O.; APFCB Harmonization of Reference Interval Working GroupAbstract : Bone-turnover marker (BTM) measurements in the blood or urine reflect the bone-remodeling rate and may be useful for studying and clinically managing metabolic bone diseases. Substantial evidence supporting the diagnostic use of BTMs has accumulated in recent years, together with the publication of several guidelines. Most clinical trials and observational and reference-interval studies have been performed in the Northern Hemisphere and have mainly involved Caucasian populations. This review focuses on the available data for populations from the Asia-Pacific region and offers guidance for using BTMs as diagnostic biomarkers in these populations. The procollagen I N-terminal propeptide and β-isomerized C-terminal telopeptide of type-I collagen (measured in plasma) are reference BTMs used for investigating osteoporosis in clinical settings. Premenopausal reference intervals (established for use with Asia-Pacific populations) and reference change values and treatment targets (used to monitor osteoporosis treatment) help guide the management of osteoporosis. Measuring BTMs that are not affected by renal failure, such as the bone-specific isoenzyme alkaline phosphatase and tartrate-resistant acid phosphatase 5b, may be advantageous for patients with advanced chronic kidney disease. Further studies of the use of BTMs in individuals with metabolic bone disease, coupled with the harmonization of commercial assays to provide equivalent results, will further enhance their clinical applications.
-
Brief Communication2023-09-01 Diagnostic Hematology
Implications of the 5th Edition of the World Health Organization Classification and International Consensus Classification of Myeloid Neoplasm in Myelodysplastic Syndrome With Excess Blasts and Acute Myeloid Leukemia
Cheonghwa Lee
Ann Lab Med 2023; 43(5): 503-507, M.D., Ha Nui Kim , M.D., Ph.D., Jung Ah Kwon , M.D., Ph.D., Soo-Young Yoon , M.D., Ph.D., Min Ji Jeon , M.D., Ph.D., Eun Sang Yu , M.D., Dae Sik Kim , M.D., Ph.D., Chul Won Choi , M.D., Ph.D., and Jung Yoon , M.D., Ph.D.Abstract : The fifth edition of the WHO classification (2022 WHO) and the International Consensus Classification (2022 ICC) of myeloid neoplasms have been recently published. We reviewed the changes in the diagnosis distribution in patients with MDS with excess blasts (MDS-EB) or AML using both classifications. Forty-seven patients previously diagnosed as having AML or MDS-EB with available mutation analysis data, including targeted next-generation and RNA-sequencing data, were included. We reclassified 15 (31.9%) and 27 (57.4%) patients based on the 2022 WHO and 2022 ICC, respectively. One patient was reclassified as having a translocation categorized as a rare recurring translocation in both classifications. Reclassification was mostly due to the addition of mutation-based diagnostic criteria (i.e., AML, myelodysplasia-related) or a new entity associated with TP53 mutation. In both classifications, MDS diagnosis required the confirmation of multi-hit TP53 alterations. Among 14 patients with TP53 mutations, 11 harbored multi-hit TP53 alterations, including four with TP53 mutations and loss of heterozygosity. Adverse prognosis was associated with multi-hit TP53 alterations (P=0.009) in patients with MDS-EB, emphasizing the importance of detecting the mutations at diagnosis. The implementation of these classifications may lead to the identification of different subtypes from previously heterogeneous diagnostic categories based on genetic characteristics.
-
Editorial2023-05-01
Apolipoprotein B, Non-HDL Cholesterol, and LDL Cholesterol as Markers for Atherosclerotic Cardiovascular Disease Risk Assessment
Yeo-Min Yun
Ann Lab Med 2023; 43(3): 221-222, M.D., Ph.D.
Full Text
PDF
Pubmed
PMC
Search for
Follow us
Editorial Office
