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, they have various constraints. Although structured, laboratory data often contain unstandardized terminology or missing information. The major challenge lies in the lack of standardization of test results in terms of metrology, which complicates comparisons across laboratories. In this review, we delve into the essential components necessary for integrating real-world laboratory data into high-quality big data, including the standardization of terminology, data formats, equations, and the harmonization and standardization of results. Moreover, we address the transference and adjustment of laboratory results, along with the certification for quality of laboratory data. By discussing these critical aspects, we seek to shed light on the challenges and opportunities inherent to utilizing real-world laboratory data within the framework of healthcare big data and artificial intelligence.

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 on ML applications in laboratory medicine published between February 2014 and March 2024. A PubMed search using a search string yielded 779 articles on the topic, among which 144 articles were selected for this review. These articles were analyzed to extract and categorize related fields within laboratory medicine, research objectives, specimen types, data types, ML models, evaluation metrics, and sample sizes. Sankey diagrams and pie charts were used to illustrate the relationships between categories and the proportions within each category. We found that most studies involving the application of ML in laboratory medicine were designed to improve efficiency through automation or expand the roles of clinical laboratories. The most common ML models used are convolutional neural networks, multilayer perceptrons, and tree-based models, which are primarily selected based on the type of input data. Our findings suggest that, as the technology evolves, ML will rise in prominence in laboratory medicine as a tool for expanding research activities. Nonetheless, expertise in ML applications should be improved to effectively utilize this technology.

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 large sets of healthcare data for training. Embedded bias introduced into AI and ML models not only has disastrous consequences for quality of care but also may perpetuate and exacerbate health disparities.The lack of test harmonization, which is defined as the ability to produce comparable results and the same interpretation irrespective of the method or instrument platform used to produce the result, may introduce aggregation bias into algorithms with potential adverse outcomes for patients. Limited interoperability of laboratory results at the technical, syntactic, semantic, and organizational levels is a source of embedded bias that limits the accuracy and generalizability of algorithmic models. Population-specific issues, such as inadequate representation in clinical trials and inaccurate race attribution, not only affect the interpretation of laboratory results but also may perpetuate erroneous conclusions based on AI and ML models in the healthcare literature.

Vancomycin, a vital antibiotic for treating gram-positive bacterial infections, requires therapeutic drug monitoring (TDM) because of its substantial pharmacokinetic variability. While traditional TDM relies on steady-state trough concentrations, recent guidelines advocate the area under the concentration–time curve (AUC) as the target index. However, detailed protocols for AUC estimation are lacking, leading to potential discrepancies among institutions. We surveyed medical institutions in Korea regarding vancomycin TDM, including AUC estimation. Nineteen participants responded to the TDM case challenge under three patient scenarios. For an ordinary patient in Case 1, the overall CV for AUC values was 0.4% when both trough and peak concentrations were included in the AUC calculation and 1.9% when utilizing only the trough concentration. For Case 2, an older patient with obesity, the corresponding CV was 6.6%. For Case 3 with multiple trough concentrations, the CV was 15.6%, reflecting variations in the selective use of data. Although the agreements in Case 1 were good, significant variability in AUC estimation was noted in cases involving atypical patient characteristics or old TDM data. Our study provides insight into the current status of vancomycin TDM in Korea and underscores the need for standardized operational protocols for AUC estimation.

Background: NUP98 rearrangements (NUP98r), associated with various hematologic malignancies, involve more than 30 partner genes. Despite their clinical significance, reports on the clinicopathological characteristics of rare NUP98r remain limited. We investigated the characteristics of patients with myeloid neoplasms harboring NUP98r among those identified as having 11p15 translocation in chromosomal analysis. Methods: We retrospectively reviewed results from bone marrow chromosomal analyses conducted between 2011 and 2023 and identified 15 patients with 11p15 translocation.Subsequently, NUP98r were evaluated using FISH and/or reverse transcription PCR, and clinical and laboratory data of the patients were analyzed. Results: NUP98r were identified in 11 patients initially diagnosed as having AML (N = 8), myelodysplastic syndrome (N = 2), or chronic myelomonocytic leukemia (N = 1), with a median age of 44 yrs (range, 4–77 yrs). Three patients had a history of chemotherapy. In total, five NUP98 fusions were identified: NUP98::DDX10 (N = 3), NUP98::HOXA9 (N = 2), NUP98::PSIP1 (N = 2), NUP98::PRRX1 (N = 1), and NUP98::HOXC11 (N = 1). Patients with NUP98r exhibited a poor prognosis, with a median overall survival of 12.0 months (95% confidence interval [CI], 3.4–29.6 months) and a 5-yr overall survival rate of 18.2% (95% CI, 5.2%–63.7%). Conclusions Our study revealed the clinical and genetic characteristics of patients with myeloid neoplasms harboring rare and non-cryptic NUP98r. Given its association with poor prognosis, a comprehensive evaluation is crucial for identifying previously underdiagnosed NUP98r in patients with myeloid neoplasms.

Background: In 2022, the WHO and International Consensus Classification (ICC) published diagnostic criteria for myelodysplastic neoplasms (MDSs). We examined the influence of the revised diagnostic criteria on classifying MDSs in a large population. Methods: We retrieved an open-source pre-existing dataset from cBioPortal and included 2,454 patients with MDS in this study. Patients were reclassified based on the new diagnostic 2022 WHO and ICC criteria. Survival analysis was performed using Cox regression to validate the new criteria and to assess risk factors. Results: Based on the 2022 WHO criteria, 1.4% of patients were reclassified as having AML. The 2022 WHO criteria provide a superior prognostic/diagnostic model to the 2017WHO criteria (Akaike information criterion, 14,152 vs. 14,516; concordance index, 0.705vs. 0.681). For classifying MDS with low blast counts and SF3B1 mutation, a variant allele frequency cut-off of 5% (2022 WHO criteria) and the absence of RUNX1 co-mutation (2022 ICC criteria) are diagnostically relevant. For classifying MDSs with mutated TP53, a blast count cut-off of 10% (2022 ICC criteria) and multi-hit TP53 (2022 WHO criteria) areindependent risk factors in cases with ≥ 10% blasts. Conclusions Our findings support the refinements of the new WHO criteria. We recommend the complementary use of the new WHO and ICC criteria in classifying SF3B1 - and TP53-mutated MDSs for better survival prediction.