Artificial intelligence (AI) is rapidly transforming laboratory medicine, impacting medical devices and healthcare practices. Despite these advancements, AI-based medical device software (MDSW) introduces a new layer of complexity in regulatory compliance. This paper outlines the regulatory landscape for MDSW and AI-driven MDSW, clarifying the responsibilities of laboratory professionals and manufacturers under the In Vitro Diagnostic Regulation (IVDR), ISO 15189:2022, and the Artificial Intelligence Act. An analysis of 89 MDSWs approved under the IVDR, derived from the European Database on Medical Devices (EUDAMED) reveals a diverse landscape of applications, ranging from digital pathology and molecular diagnostics to laboratory automation and clinical decision support. While Germany currently dominates the EU market for these devices, and the majority of approved MDSW remain non-AI driven and classified as low-risk, the increasing presence of AI-powered Class C devices underscores the growing potential of software in complex diagnostic scenarios. However, realizing the full potential of AI in laboratory medicine requires careful navigation of the evolving regulatory landscape. Key challenges persist, including defining intended use, ensuring robust clinical evidence, mitigating data bias, and establishing rigorous post-market surveillance. Balancing regulatory oversight with innovation is critical to fostering the development of trustworthy AI systems without stifling progress. As regulatory frameworks continue to evolve, establishing clear validation methodologies and transparent compliance pathways will be essential to unlocking the full potential of AI in laboratory medicine while ensuring the highest standards of safety and clinical effectiveness.

Objectives: According to ISO 15189:2022, analytical performance specifications (APS) should relate to intended clinical use and impact on patient care. Therefore, we aimed to develop a web application for laboratory professionals to calculate APS based on a simulation of the impact of measurement uncertainty (MU) on the outcome using the chosen decision limits, agreement thresholds, and data of the population of interest. Methods: We developed the “APS Calculator” allowing users to upload and select data of concern, specify decision limits and agreement thresholds, and conduct simulations to determine APS for MU. The simulation involved categorizing original measurand concentrations, generating measured (simulated) results by introducing different degrees of MU, and recategorizing measured concentrations based on clinical decision limits and acceptable clinical misclassification rates. The agreements between original and simulated result categories were assessed, and values that met or exceeded user-specified agreement thresholds that set goals for the between-category agreement were considered acceptable. The application generates contour plots of agreement rates and corresponding MU values. We tested the application using National Health and Nutrition Examination Survey data, with decision limits from relevant guidelines. Results: We determined APS for MU of six measurands (blood total hemoglobin, plasma fasting glucose, serum total and high-density lipoprotein cholesterol, triglycerides, and total folate) to demonstrate the potential of the application to generate APS. Conclusions: The developed data-driven web application offers a flexible tool for laboratory professionals to calculate APS for MU using their chosen decision limits and agreement thresholds, and the data of the population of interest.

Background: Multiple sclerosis (MS) is characterized by inflammation, demyelination and axonal degeneration. Oxidative stress (OS) plays a significant role in the pathogenesis of the disease. The aim of the study was to examine the association between OS and smoking on the MS development. Methods: The study included 175 patients with relapsing-remitting multiple sclerosis (RRMS) (76 males, 99 females) and 254 healthy subjects (81 males and 173 females). Oxidative stress biomarkers in serum, Total Antioxidant Status (TAS) and Total Oxidative Status (TOS) were determined spectrophotometrically. Oxidative Stress Index (OSI) was calculated as the ratio of TOS and TAS. Urinary 8-oxo7,8-dihydro-2'-deoxyguanosine were determined by HPLC-MS/MS and expressed as 8-oxodG/creatinine. Results: In females with RRMS were higher TOS, OSI and 8-oxodG/creatinine than in females in control group. The group of males with RRMS had lower level of TAS than the males in control group. Higher levels of 8-oxodG/creatinine was obtained in active, passive and former smokers with RRMS than in control group with the same exposition to tobacco smoke. Independent predictors of MS are passive smoking, increased OSI and increased levels of urinary 8-oxodG/creatinine. Conclusions: Our results demonstrate that the OS parameters should be included in the assessment of the risk for MS development. Due to the more sensitivity to oxidative stress, females may be at higher risk of MS development. This data indicates the importance of introducing the antioxidant therapy as a complementary treatment in patients with RRMS.

Several studies report the important role of an altered gut microbiota in the development of obesity, highlighting the potential use of probiotics in the treatment of obesity. The aim of this study is to investigate the effect of a novel probiotic approach on the expression of specific miRNAs and mRNAs associated with obesity in combination with the hypocholesterolemic octacosanol. Twenty overweight/obese women participated in a randomized, placebo-controlled, double-blind study and were randomly divided into two groups: the intervention group (daily one capsule containing Lactobacillus plantarum 299v (DSM9843), Saccharomyces cerevisiae var. boulardii, and 40 mg octacosanol; N = 12) and the placebo group (N = 8). Changes in lipid parameters and expression of miRNAs and mRNAs were assessed before (T0) and after the 12-week intervention (T1). After the intervention, the expression of miR-155-5p (9.38 ± 0.85 vs. 8.38 ± 1.06, p = 0.05) and miR-24-3p (3.42 ± 0.38 vs. 2.71 ± 0.97, p = 0.031) showed significant decreases in the intervention group when compared to the control group. At T1, the expression of miR-155-5p (8.69 ± 1.31 vs. 9.3 ± 0.85, p = 0.04), miR-125b-5p (5.41 ± 1.18 vs. 5.99 ± 1.36, p = 0.049), and TNF-α (10.24 ± 1.66 vs. 11.36 ± 1.12, p = 0.009) were significantly decreased in the intervention group. No changes in lipids and anthropometric parameters were observed. The novel probiotic approach had a positive effect on regulating the expression of certain miRNAs and mRNAs important for regulating inflammation and adipogenesis, which are essential for obesity onset and control.

Background. Influence of TMPRSS6 A736V and HFE (C282Y and H63D) polymorphisms on serum hepcidin-25 levels and iron status parameters in end-stage renal disease (ESRD) patients stratified according to gender has not been previously investigated. In addition, we aimed to evaluate the diagnostic accuracy of the parameters to separate iron-deficiency anemia (IDA) from anemia of chronic disease. Materials and Methods. Iron status parameters and genetic analysis were performed in 126 ESRD patients and in 31 IDA patients as the control group. Results. ESRD patients had significantly higher ferritin and hepcidin-25 (<0.001) relative to IDA patients. Cut-off values with the best diagnostic accuracy were found for hepcidin ≥9.32 ng/mL, ferritin ≥48.2 μg/L, transferrin saturation ≥16.8%, and MCV ≥81 fL. Interaction between gender and HFE haplotypes for the hepcidin-25 and ferritin levels in ESRD patients (p=0.005, partial eta squared=0.09; p=0.027, partial eta squared=0.06, respectively) was found. Serum transferrin was influenced by the combined effect of gender and TMPRSS6 A736V polymorphism in ESRD patients (p=0.002, partial eta squared=0.07). Conclusion. Our findings could contribute to the further investigation of mechanisms involved in the pathophysiology and important gender-related involvement of the TMPRSS6 and HFE polymorphisms on anemia in ESRD patients.