A standard to report biological variation data studies - based on an expert opinion.

There is a need for standards for generation and reporting of Biological Variation (BV) reference data. The absence of standards affects the quality and transportability of BV data, compromising important clinical applications. To address this issue, international expert groups under the European Federation of Clinical Chemistry and Laboratory Medicine (EFLM) have developed an online resource (https://tinyurl.com/bvmindmap) in the form of an interactive mind map that serves as a guideline for researchers planning, performing and reporting BV studies. The mind map addresses study design, data analysis, and reporting criteria, providing embedded links to relevant references and resources. It also incorporates a checklist approach, identifying a Minimum Data Set (MDS) to enable the transportability of BV data and incorporates the Biological Variation Data Critical Appraisal Checklist (BIVAC) to assess study quality. The mind map is open to access and is disseminated through the EFLM BV Database website, promoting accessibility and compliance to a reporting standard, thereby providing a tool to be used to ensure data quality, consistency, and comparability of BV data. Thus, comparable to the STARD initiative for diagnostic accuracy studies, the mind map introduces a Standard for Reporting Biological Variation Data Studies (STARBIV), which can enhance the reporting quality of BV studies, foster user confidence, provide better decision support, and be used as a tool for critical appraisal. Ongoing refinement is expected to adapt to emerging methodologies, ensuring a positive trajectory toward improving the validity and applicability of BV data in clinical practice.

The biological variation of insulin resistance markers: data from the European Biological Variation Study (EuBIVAS).

OBJECTIVES: An insulin resistant state is characteristic of patients with type 2 diabetes, polycystic ovary syndrome, and metabolic syndrome. Identification of insulin resistance (IR) is most readily achievable using formulae combining plasma insulin and glucose results. In this study, we have used data from the European Biological Variation Study (EuBIVAS) to examine the biological variability (BV) of IR using the Homeostasis Model Assessment for Insulin Resistance (HOMA-IR) and the Quantitative Insulin sensitivity Check Index (QUICKI). METHODS: Ninety EuBIVAS non-diabetic subjects (52F, 38M) from five countries had fasting HOMA-IR and QUICKI calculated from plasma glucose and insulin samples collected concurrently on 10 weekly occasions. The within-subject (CVI) and between-subject (CVG) BV estimates with 95 % CIs were obtained by CV-ANOVA after analysis of trends, variance homogeneity and outlier removal. RESULTS: The CVI of HOMA-IR was 26.7 % (95 % CI 25.5-28.3), driven largely by variability in plasma insulin and the CVI for QUICKI was 4.1 % (95 % CI 3.9-4.3), reflecting this formula's logarithmic transformation of glucose and insulin values. No differences in values or BV components were observed between subgroups of men or women below and above 50 years. CONCLUSIONS: The EuBIVAS, by utilising a rigorous experimental protocol, has produced robust BV estimates for two of the most commonly used markers of insulin resistance in non-diabetic subjects. This has shown that HOMA-IR, in particular, is highly variable in the same individual which limits the value of single measurements.

C-Reactive Protein and Brain Natriuretic Peptides Harmonization.

The harmonization of laboratory biomarkers is pivotal in ensuring consistent and reliable diagnostic outcomes across different clinical settings. This systematic review examines the harmonization of C-Reactive Protein (CRP) and N-Terminal Prohormone of Brain Natriuretic Peptide (NT-proBNP) measurements, both of which are jointly utilized in the diagnosis and management of cardiovascular diseases. To identify relevant studies, we searched the PubMed electronic database using specific medical subject headings and keywords such as C-Reactive Protein, CRP, high sensitivity C-Reactive Protein (hs-CRP), N-terminal pro B-type natriuretic peptide, and NT-proBNP, focusing on publications from June 1 to September 26, 2021. The query filtered studies to include only those in English involving human subjects. From our search, 97 articles met the inclusion criteria and were included for in-depth analysis. Despite their widespread use, significant variability remains in the measurements of CRP and NT-proBNP due to a lack of standardized pre-analytical, analytical, and post-analytical practices. This review highlights the consequences of this variability on clinical decision-making and patient outcomes and emphasizes the need for international standards and guidelines to achieve better harmonization. Our findings advocate for the establishment of universal protocols to enhance the reliability of these biomarker measurements across different clinical environments, ensuring improved healthcare delivery.

A New Concept for Reference Change Values-Regression to the Population Mean.

BACKGROUND: Reference change values (RCV) are used to indicate a change in analyte concentration that is unlikely to be due to random variation in the patient or the measurement. Current theory describes RCV relative to a first measurement result (X1). We investigate an alternative view predicting the starting point for RCV calculations from X1 and its location in the reference interval. METHODS: Data for serum sodium, calcium, and total protein from the European Biological Variation study and from routine clinical collections were analyzed for the effect of the position of X1 within the reference interval on the following result from the same patient. A model to describe the effect was determined, and an equation to predict the RCV for a sample in a population was developed. RESULTS: For all data sets, the midpoints of the RCVs were dependent on the position of X1 in the population. Values for X1 below the population mean were more likely to be followed by a higher result, and X1 results above the mean were more likely to be followed by lower results. A model using population mean, reference interval dispersion, and result diagnostic variation provided a good fit with the data sets, and the derived equation predicted the changes seen. CONCLUSIONS: We have demonstrated that the position of X1 within the reference interval creates an asymmetrical RCV. This can be described as a regression to the population mean. Adding this concept to the theory of RCVs will be an important consideration in many cases.

Biological Variation Estimates for Plasma Copeptin and Clinical Implications.

BACKGROUND: Plasma copeptin measurement is useful for the differential diagnoses of polyuria-polydipsia syndrome. It has also been proposed as a prognostic marker for cardiovascular diseases. However, limited information is available about the within- (CVI) and between-subject (CVG) biological variation (BV). This study presents BV estimates for copeptin in healthy individuals. METHODS: Samples were collected weekly from 41 healthy subjects over 5 weeks and analyzed using the BRAHMS Copeptin proAVP KRYPTOR assay after at least 8 h of food and fluid abstinence. Outlier detection, variance homogeneity, and trend analysis were performed followed by CV-ANOVA for BV and analytical variation (CVA) estimation with 95% confidence intervals. Reference change values (RCVs), index of individuality (II), and analytical performance specification (APS) were also calculated. RESULTS: The analysis included 178 results from 20 males and 202 values from 21 females. Copeptin concentrations were significantly higher in males than in females (mean 8.5 vs 5.2 pmol/L, P < 0.0001). CVI estimates were 18.0% (95% CI, 15.4%-21.6%) and 19.0% (95% CI, 16.4%-22.6%), for males and females, respectively; RCVs were -35% (decreasing value) and 54% (increasing value). There was marked individuality for copeptin. No result exceeded the diagnostic threshold (>21.4 pmol/L) for arginine vasopressin resistance. CONCLUSIONS: The availability of BV data allows for refined APS and associated II, and RCVs applicable as aids in the serial monitoring of patients with specific diseases such as heart failure. The BV estimates are only applicable in subjects who abstained from oral intake due to the rapid and marked effects of fluids on copeptin physiology.

Analytical performance specifications based on biological variation data - considerations, strengths and limitations.

Analytical performance specifications (APS) are typically established through one of three models: (i) outcome studies, (ii) biological variation (BV), or (iii) state-of-the-art. Presently, The APS can, for most measurands that have a stable concentration, be based on BV. BV based APS, defined for imprecision, bias, total allowable error and allowable measurement uncertainty, are applied to many different processes in the laboratory. When calculating APS, it is important to consider the different APS formulae, for what setting they are to be applied and if they are suitable for the intended purpose. In this opinion paper, we elucidate the background, limitations, strengths, and potential intended applications of the different BV based APS formulas. When using BV data to set APS, it is important to consider that all formulae are contingent on accurate and relevant BV estimates. During the last decade, efficient procedures have been established to obtain reliable BV estimates that are presented in the EFLM biological variation database. The database publishes detailed BV data for numerous measurands, global BV estimates derived from meta-analysis of quality-assured studies of similar study design and automatic calculation of BV based APS.

The European biological variation study (EuBIVAS): Biological variation data for testosterone, follicle stimulating hormone, prolactin, luteinizing hormone and dehydroepiandrosterone sulfate in men.

BACKGROUND: Knowledge of biological variation (BV) of hormones is essential for interpretation of laboratory tests and for diagnostics of endocrinological and reproductive diseases. There is a lack of robust BV data for many hormones in men. METHODS: We used serum samples collected weekly over 10 weeks from the European Biological Variation Study (EuBIVAS) to determine BV of testosterone, follicle-stimulating hormone (FSH), prolactin, luteinizing hormone (LH) and dehydroepiandrosterone sulfate (DHEA-S) in 38 men. We derived within-subject (CVI) and between-subject (CVG) BV estimates by CV-ANOVA after trend, outlier, and homogeneity analysis and calculated reference change values, index of individuality (II), and analytical performance specifications. RESULTS: The CVI estimates were 10 % for testosterone, 8 % for FSH, 13 % for prolactin, 22 % for LH, and 9 % for DHEA-S, respectively. The IIs ranged between 0.14 for FSH to 0.66 for LH, indicating high individuality. CONCLUSIONS: In this study, we have used samples from the highly powered EuBIVAS study to derive BV estimates for testosterone, FSH, prolactin, LH and DHEA-S in men. Our data confirm previously published BV estimates of testosterone, FSH and LH. For prolactin and DHEA-S BV data for men are reported for the first time.

Biological variation of inflammatory and iron metabolism markers in high-endurance recreational athletes; are these markers useful for athlete monitoring?

OBJECTIVES: To deliver biological variation (BV) data for serum hepcidin, soluble transferrin receptor (sTfR), erythropoietin (EPO) and interleukin 6 (IL-6) in a population of well-characterized high-endurance athletes, and to evaluate the potential influence of exercise and health-related factors on the BV. METHODS: Thirty triathletes (15 females) were sampled monthly (11 months). All samples were analyzed in duplicate and BV estimates were delivered by Bayesian and ANOVA methods. A linear mixed model was applied to study the effect of factors related to exercise, health, and sampling intervals on the BV estimates. RESULTS: Within-subject BV estimates (CVI) were for hepcidin 51.9 % (95 % credibility interval 46.9-58.1), sTfR 10.3 % (8.8-12) and EPO 27.3 % (24.8-30.3). The mean concentrations were significantly different between sex, but CVI estimates were similar and not influenced by exercise, health-related factors, or sampling intervals. The data were homogeneously distributed for EPO but not for hepcidin or sTfR. IL-6 results were mostly below the limit of detection. Factors related to exercise, health, and sampling intervals did not influence the BV estimates. CONCLUSIONS: This study provides, for the first time, BV data for EPO, derived from a cohort of well-characterized endurance athletes and indicates that EPO is a good candidate for athlete follow-up. The application of the Bayesian method to deliver BV data illustrates that for hepcidin and sTfR, BV data are heterogeneously distributed and using a mean BV estimate may not be appropriate when using BV data for laboratory and clinical applications.

Sex-related differences in within-subject biological variation estimates for 22 essential and non-essential amino acids.

BACKGROUND: Measurement of serum amino acid (AA) concentrations is important in particular for the diagnosis and monitoring of inborn errors of AA metabolism. To ensure optimal clinical interpretation of AAs, reliable biological variation (BV) data are essential. In the present study, we derived BV data for 22 non-essential, conditionally essential, and essential AAs and assessed differences in BV of AAs related to sex. METHODS: Morning blood samples were drawn from 66 subjects (31 males and 35 females) once a week for 10 consecutive weeks. All samples were analyzed in duplicate using liquid chromatography-tandem mass-spectrometry. The data were assessed for outliers, trends, normality and variance homogeneity analysis prior to estimating within-subject (CVI) and between-subject (CVG) BV. RESULTS: CVI estimates ranged from 9.0 % for histidine (male) to 33.0 % for taurine (male). CVI estimates in males and females were significantly different for all AAs except for aspartic acid, citrulline and phenylalanine, in most cases higher in females than in males. Apart from for arginine, CVG estimates in males and females were similar. CONCLUSIONS: In this highly powered BV study, we provide updated BV estimates for 22 AAs and demonstrate that for most AAs, CVI estimates differ between males and females, with implications for interpretation and use of AAs in clinical practice.

Biological variation estimates of Alzheimer's disease plasma biomarkers in healthy individuals.

INTRODUCTION: Blood biomarkers have proven useful in Alzheimer's disease (AD) research. However, little is known about their biological variation (BV), which improves the interpretation of individual-level data. METHODS: We measured plasma amyloid beta (Aß42, Aß40), phosphorylated tau (p-tau181, p-tau217, p-tau231), glial fibrillary acidic protein (GFAP), and neurofilament light chain (NfL) in plasma samples collected weekly over 10 weeks from 20 participants aged 40 to 60 years from the European Biological Variation Study. We estimated within- (CVI ) and between-subject (CVG ) BV, analytical variation, and reference change values (RCV). RESULTS: Biomarkers presented considerable variability in CVI and CVG . Aß42/Aß40 had the lowest CVI (≈ 3%) and p-tau181 the highest (≈ 16%), while others ranged from 6% to 10%. Most RCVs ranged from 20% to 30% (decrease) and 25% to 40% (increase). DISCUSSION: BV estimates for AD plasma biomarkers can potentially refine their clinical and research interpretation. RCVs might be useful for detecting significant changes between serial measurements when monitoring early disease progression or interventions. Highlights Plasma amyloid beta (Aß42/Aß40) presents the lowest between- and within-subject biological variation, but also changes the least in Alzheimer's disease (AD) patients versus controls. Plasma phosphorylated tau variants significantly vary in their within-subject biological variation, but their substantial fold-changes in AD likely limits the impact of their variability. Plasma neurofilament light chain and glial fibrillary acidic protein demonstrate high between-subject variation, the impact of which will depend on clinical context. Reference change values can potentially be useful in monitoring early disease progression and the safety/efficacy of interventions on an individual level. Serial sampling revealed that unexpectedly high values in heathy individuals can be observed, which urges caution when interpreting AD plasma biomarkers based on a single test result.

Rising adoption of artificial intelligence in scientific publishing: evaluating the role, risks, and ethical implications in paper drafting and review process.

BACKGROUND: In the rapid evolving landscape of artificial intelligence (AI), scientific publishing is experiencing significant transformations. AI tools, while offering unparalleled efficiencies in paper drafting and peer review, also introduce notable ethical concerns. CONTENT: This study delineates AI's dual role in scientific publishing: as a co-creator in the writing and review of scientific papers and as an ethical challenge. We first explore the potential of AI as an enhancer of efficiency, efficacy, and quality in creating scientific papers. A critical assessment follows, evaluating the risks vs. rewards for researchers, especially those early in their careers, emphasizing the need to maintain a balance between AI's capabilities and fostering independent reasoning and creativity. Subsequently, we delve into the ethical dilemmas of AI's involvement, particularly concerning originality, plagiarism, and preserving the genuine essence of scientific discourse. The evolving dynamics further highlight an overlooked aspect: the inadequate recognition of human reviewers in the academic community. With the increasing volume of scientific literature, tangible metrics and incentives for reviewers are proposed as essential to ensure a balanced academic environment. SUMMARY: AI's incorporation in scientific publishing is promising yet comes with significant ethical and operational challenges. The role of human reviewers is accentuated, ensuring authenticity in an AI-influenced environment. OUTLOOK: As the scientific community treads the path of AI integration, a balanced symbiosis between AI's efficiency and human discernment is pivotal. Emphasizing human expertise, while exploit artificial intelligence responsibly, will determine the trajectory of an ethically sound and efficient AI-augmented future in scientific publishing.

Machine learning algorithms in sepsis.

Sepsis remains a significant global health challenge due to its high mortality and morbidity, compounded by the difficulty of early detection given its variable clinical manifestations. The integration of machine learning (ML) into laboratory medicine for timely sepsis identification and outcome forecasting is an emerging field of interest. This comprehensive review assesses the current body of research on ML applications for sepsis within the realm of laboratory diagnostics, detailing both their strengths and shortcomings. An extensive literature search was performed by two independent investigators across PubMed and Scopus databases, employing the keywords "Sepsis," "Machine Learning," and "Laboratory" without publication date limitations, culminating in January 2023. Each selected study was meticulously evaluated for various aspects, including its design, intent (diagnostic or prognostic), clinical environment, demographics, sepsis criteria, data gathering period, and the scope and nature of features, in addition to the ML methodologies and their validation procedures. Out of 135 articles reviewed, 39 fulfilled the criteria for inclusion. Among these, the majority (30 studies) were focused on devising ML algorithms for diagnosis, fewer (8 studies) on prognosis, and one study addressed both aspects. The dissemination of these studies across an array of journals reflects the interdisciplinary engagement in the development of ML algorithms for sepsis. This analysis highlights the promising role of ML in the early diagnosis of sepsis while drawing attention to the need for uniformity in validating models and defining features, crucial steps for ensuring the reliability and practicality of ML in clinical setting.

Biological variation estimates for serum neurofilament light chain in healthy subjects.

OBJECTIVES: Neurofilament light chain (NfL) is an emerging biomarker of neurodegeneration disorders. Knowledge of the biological variation (BV) can facilitate proper interpretation between serial measurements. Here BV estimates for serum NfL (sNfL) are provided. METHODS: Serum samples were collected weekly from 24 apparently healthy subjects for 10 consecutive weeks and analyzed in duplicate using the Siemens Healthineers sNfL assay on the Atellica® IM Analyzer. Outlier detection, variance homogeneity analyses, and trend analysis were performed followed by CV-ANOVA to determine BV and analytical variation (CVA) estimates with 95%CI and the associated reference change values (RCV) and analytical performance specifications (APS). RESULTS: Despite observed differences in sNfL concentrations between males and females, BV estimates remained consistent across genders. Both within-subject BV (CVI) for males (10.7%, 95%CI; 9.2-12.6) and females (9.1%, 95%CI; 7.8-10.9) and between-subject BV (CVG) for males (26.1%, 95%CI; 18.0-45.6) and females (30.2%, 95%CI; 20.9-53.5) were comparable. An index of individuality value of 0.33 highlights significant individuality, indicating the potential efficacy of personalized reference intervals in patient monitoring. CONCLUSIONS: The established BV estimates for sNfL underscore its potential as a valuable biomarker for monitoring neurodegenerative diseases, offering a foundation for improved decision-making in clinical settings.

Review on adherence of the literature to official recommendations on albuminuria harmonization and standardization.

Albuminuria standardization is a key issue to produce reliable and equivalent results between laboratories. We investigated whether official recommendations on albuminuria harmonization are followed in the literature. The PubMed database was searched from June 1 to September 26, 2021. The search terms included urine albumin, urine albumin-to-creatinine ratio (uACR), and albuminuria. A total of 159 articles were considered eligible; 50.9 % reported the type of urine collection. Specifically, 58.1 % collected a random spot urine specimen, 21 % collected a first morning void, and 6.2 % collected a 24-h specimen. Overall, 15 % of articles reported data on sample shipping, storage, and centrifugation and 13.3 % mentioned the preanalytical phase without any data on albuminuria. The method for albuminuria was properly described in 31.4 % of articles; of these, 54.9 % used immunological methods, and 8.9 % contained errors or missing data. Most articles (76.7 %) expressed test results as albuminuria-to-creatininuria ratio. Different decision levels were utilized in 130 articles; of these, 36 % used a decision level of ≤30 mg/g creatininuria and 23.7 % used three decision levels (≤30, 30-300, and ≥300 mg/g). The failure to follow guidelines on albuminuria harmonization was mainly found in the preanalytical phase. The poor awareness of the importance of preanalytical steps on test result may be a possible explanation.

Potentials and pitfalls of ChatGPT and natural-language artificial intelligence models for the understanding of laboratory medicine test results. An assessment by the European Federation of Clinical Chemistry and Laboratory Medicine (EFLM) Working Group on Artificial Intelligence (WG-AI).

OBJECTIVES: ChatGPT, a tool based on natural language processing (NLP), is on everyone's mind, and several potential applications in healthcare have been already proposed. However, since the ability of this tool to interpret laboratory test results has not yet been tested, the EFLM Working group on Artificial Intelligence (WG-AI) has set itself the task of closing this gap with a systematic approach. METHODS: WG-AI members generated 10 simulated laboratory reports of common parameters, which were then passed to ChatGPT for interpretation, according to reference intervals (RI) and units, using an optimized prompt. The results were subsequently evaluated independently by all WG-AI members with respect to relevance, correctness, helpfulness and safety. RESULTS: ChatGPT recognized all laboratory tests, it could detect if they deviated from the RI and gave a test-by-test as well as an overall interpretation. The interpretations were rather superficial, not always correct, and, only in some cases, judged coherently. The magnitude of the deviation from the RI seldom plays a role in the interpretation of laboratory tests, and artificial intelligence (AI) did not make any meaningful suggestion regarding follow-up diagnostics or further procedures in general. CONCLUSIONS: ChatGPT in its current form, being not specifically trained on medical data or laboratory data in particular, may only be considered a tool capable of interpreting a laboratory report on a test-by-test basis at best, but not on the interpretation of an overall diagnostic picture. Future generations of similar AIs with medical ground truth training data might surely revolutionize current processes in healthcare, despite this implementation is not ready yet.

Analytical performance specifications for the measurement uncertainty of 24,25-dihydroxyvitamin D examinations.

OBJECTIVES: The exploration of the metabolites in the degradation pathways of vitamin D (VTD) has gained importance in recent years and simultaneous quantitation of twenty-five-hydroxy vitamin D (25(OH)D) mass concentration together with 24,25-dihydroxyvitamin D (24,25(OH)2D) has been proposed as a newer approach to define VTD deficiency. Yet, no data are available on 24,25(OH)2D biological variation (BV). In this study, we evaluated 24,25(OH)2D's BV on the European Biological Variation Study (EuBIVAS) cohort samples to determine if analytical performance specifications (APS) for 24,25(OH)2D could be generated. METHODS: Six European laboratories recruited 91 healthy participants. 25(OH)D and 24,25(OH)2D concentrations in K3-EDTA plasma were examined weekly for up to 10 weeks in duplicate with a validated LC-MS/MS method. The Vitamin D Metabolite Ratio (24,25(OH)2D divided by 25(OH)D × 100) was also calculated at each time point. RESULTS: Linear regression of the mean 24,25(OH)2D concentrations at each blood collection showed participants were not in steady state. Variations of 24,25(OH)2D over time were significantly positively associated with the slopes of 25(OH)D concentrations over time and the concentration of 25(OH)D of the participant at inclusion, and negatively associated with body mass index (BMI), but not with age, gender, or location of the participant. The variation of the 24,25(OH)2D concentration in participants over a 10 weeks period was 34.6%. Methods that would detect a significant change linked to the natural production of 24,25(OH)2D over this period at p<0.05 would need a relative measurement uncertainty (u%)<14.9% while at p<0.01, relative measurement uncertainty should be <10.5%. CONCLUSIONS: We have defined for the first time APS for 24,25(OH)2D examinations. According to the growing interest in this metabolite, several laboratories and manufacturers might aim to develop specific methods for its determination. The results presented in this paper are thus necessary prerequisites for the validation of such methods.

The European Register of Specialists in Clinical Chemistry and Laboratory Medicine: code of conduct, version 3 - 2023.

Whilst version 2 focussed on the professional conduct expected of a Specialist in Laboratory Medicine, version 3 builds on the responsibilities for ethical conduct from point of planning to point of care. Particular responsibilities that are outlined include: - The need for evidence when planning a new service, providing assurance that a new test does not do harm - Maintaining respect for patient confidentiality, their religious/ethnic beliefs, the need for informed consent to test, agreement on retrospective use of samples as part of governance envelopes in the pre-analytical phase - Ensuring respect for patient autonomy in the response to untoward results generated in the analytical phase - Supporting the safety of patients in the post-analytical phase through knowledge-based interpretation and presentation of results - The duty of candour to disclose and respond to error across the total testing process - Leading initiatives to harmonise and standardise pre-analytical, analytical and post-analytical phases to ensure more consistent clinical decision making with utilisation of demand management to ensure more equitable access to scarce resources - Working with emerging healthcare providers beyond the laboratory to ensure consistent application of high standards of clinical care In identifying opportunities for wider contributions to resolving ethical challenges across healthcare the need is also highlighted for more external quality assurance schemes and ethics-based quality indicators that span the total testing process.

Diagnostic quality model (DQM): an integrated framework for the assessment of diagnostic quality when using AI/ML.

BACKGROUND: Laboratory medicine has reached the era where promises of artificial intelligence and machine learning (AI/ML) seem palpable. Currently, the primary responsibility for risk-benefit assessment in clinical practice resides with the medical director. Unfortunately, there is no tool or concept that enables diagnostic quality assessment for the various potential AI/ML applications. Specifically, we noted that an operational definition of laboratory diagnostic quality - for the specific purpose of assessing AI/ML improvements - is currently missing. METHODS: A session at the 3rd Strategic Conference of the European Federation of Laboratory Medicine in 2022 on "AI in the Laboratory of the Future" prompted an expert roundtable discussion. Here we present a conceptual diagnostic quality framework for the specific purpose of assessing AI/ML implementations. RESULTS: The presented framework is termed diagnostic quality model (DQM) and distinguishes AI/ML improvements at the test, procedure, laboratory, or healthcare ecosystem level. The operational definition illustrates the nested relationship among these levels. The model can help to define relevant objectives for implementation and how levels come together to form coherent diagnostics. The affected levels are referred to as scope and we provide a rubric to quantify AI/ML improvements while complying with existing, mandated regulatory standards. We present 4 relevant clinical scenarios including multi-modal diagnostics and compare the model to existing quality management systems. CONCLUSIONS: A diagnostic quality model is essential to navigate the complexities of clinical AI/ML implementations. The presented diagnostic quality framework can help to specify and communicate the key implications of AI/ML solutions in laboratory diagnostics.