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.

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.

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.

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.

Data flow in clinical laboratories: could metadata and peridata bridge the gap to new AI-based applications?

In the last decades, clinical laboratories have significantly advanced their technological capabilities, through the use of interconnected systems and advanced software. Laboratory Information Systems (LIS), introduced in the 1970s, have transformed into sophisticated information technology (IT) components that integrate with various digital tools, enhancing data retrieval and exchange. However, the current capabilities of LIS are not sufficient to rapidly save the extensive data, generated during the total testing process (TTP), beyond just test results. This opinion paper discusses qualitative types of TTP data, proposing how to divide laboratory-generated information into two categories, namely metadata and peridata. Being both metadata and peridata information derived from the testing process, it is proposed that the first is useful to describe the characteristics of data, while the second is for interpretation of test results. Together with standardizing preanalytical coding, the subdivision of laboratory-generated information into metadata or peridata might enhance ML studies, also by facilitating the adherence of laboratory-derived data to the Findability, Accessibility, Interoperability, and Reusability (FAIR) principles. Finally, integrating metadata and peridata into LIS can improve data usability, support clinical utility, and advance AI model development in healthcare, emphasizing the need for standardized data management practices.

A comprehensive survey of artificial intelligence adoption in European laboratory medicine: current utilization and prospects.

BACKGROUND: As the healthcare sector evolves, Artificial Intelligence's (AI's) potential to enhance laboratory medicine is increasingly recognized. However, the adoption rates and attitudes towards AI across European laboratories have not been comprehensively analyzed. This study aims to fill this gap by surveying European laboratory professionals to assess their current use of AI, the digital infrastructure available, and their attitudes towards future implementations. METHODS: We conducted a methodical survey during October 2023, distributed via EFLM mailing lists. The survey explored six key areas: general characteristics, digital equipment, access to health data, data management, AI advancements, and personal perspectives. We analyzed responses to quantify AI integration and identify barriers to its adoption. RESULTS: From 426 initial responses, 195 were considered after excluding incomplete and non-European entries. The findings revealed limited AI engagement, with significant gaps in necessary digital infrastructure and training. Only 25.6 % of laboratories reported ongoing AI projects. Major barriers included inadequate digital tools, restricted access to comprehensive data, and a lack of AI-related skills among personnel. Notably, a substantial interest in AI training was expressed, indicating a demand for educational initiatives. CONCLUSIONS: Despite the recognized potential of AI to revolutionize laboratory medicine by enhancing diagnostic accuracy and efficiency, European laboratories face substantial challenges. This survey highlights a critical need for strategic investments in educational programs and infrastructure improvements to support AI integration in laboratory medicine across Europe. Future efforts should focus on enhancing data accessibility, upgrading technological tools, and expanding AI training and literacy among professionals. In response, our working group plans to develop and make available online training materials to meet this growing educational demand.

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.

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.

A vision to the future: value-based laboratory medicine.

The ultimate goal of value-based laboratory medicine is maximizing the effectiveness of laboratory tests in improving patient outcomes, optimizing resources and minimizing unnecessary costs. This approach abandons the oversimplified notion of test volume and cost, in favor of emphasizing the clinical utility and quality of diagnostic tests in the clinical decision-making. Several key elements characterize value-based laboratory medicine, which can be summarized in some basic concepts, such as organization of in vitro diagnostics (including appropriateness, integrated diagnostics, networking, remote patient monitoring, disruptive innovations), translation of laboratory data into clinical information and measurable outcomes, sustainability, reimbursement, ethics (e.g., patient empowerment and safety, data protection, analysis of big data, scientific publishing). Education and training are also crucial, along with considerations for the future of the profession, which will be largely influenced by advances in automation, information technology, artificial intelligence, and regulations concerning in vitro diagnostics. This collective opinion paper, composed of summaries from presentations given at the two-day European Federation of Laboratory Medicine (EFLM) Strategic Conference "A vision to the future: value-based laboratory medicine" (Padova, Italy; September 23-24, 2024), aims to provide a comprehensive overview of value-based laboratory medicine, projecting the profession into a more clinically effective and sustainable future.

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.

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.

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.

Where is laboratory medicine headed in the next decade? Partnership model for efficient integration and adoption of artificial intelligence into medical laboratories.

OBJECTIVES: The field of artificial intelligence (AI) has grown in the past 10 years. Despite the crucial role of laboratory diagnostics in clinical decision-making, we found that the majority of AI studies focus on surgery, radiology, and oncology, and there is little attention given to AI integration into laboratory medicine. METHODS: We dedicated a session at the 3rd annual European Federation of Clinical Chemistry and Laboratory Medicine (EFLM) strategic conference in 2022 to the topic of AI in the laboratory of the future. The speakers collaborated on generating a concise summary of the content that is presented in this paper. RESULTS: The five key messages are (1) Laboratory specialists and technicians will continue to improve the analytical portfolio, diagnostic quality and laboratory turnaround times; (2) The modularized nature of laboratory processes is amenable to AI solutions; (3) Laboratory sub-specialization continues and from test selection to interpretation, tasks increase in complexity; (4) Expertise in AI implementation and partnerships with industry will emerge as a professional competency and require novel educational strategies for broad implementation; and (5) regulatory frameworks and guidances have to be adopted to new computational paradigms. CONCLUSIONS: In summary, the speakers opine that the ability to convert the value-proposition of AI in the laboratory will rely heavily on hands-on expertise and well designed quality improvement initiative from within laboratory for improved patient care.

Biological variation: recent development and future challenges.

Biological variation (BV) data have many applications in laboratory medicine. However, these depend on the availability of relevant and robust BV data fit for purpose. BV data can be obtained through different study designs, both by experimental studies and studies utilizing previously analysed routine results derived from laboratory databases. The different BV applications include using BV data for setting analytical performance specifications, to calculate reference change values, to define the index of individuality and to establish personalized reference intervals. In this review, major achievements in the area of BV from last decade will be presented and discussed. These range from new models and approaches to derive BV data, the delivery of high-quality BV data by the highly powered European Biological Variation Study (EuBIVAS), the Biological Variation Data Critical Appraisal Checklist (BIVAC) and other standards for deriving and reporting BV data, the EFLM Biological Variation Database and new applications of BV data including personalized reference intervals and measurement uncertainty.

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.

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.

A survey on Artificial Intelligence and Big Data utilisation in Italian clinical laboratories.

OBJECTIVES: The Italian Society of Clinical Biochemistry and Clinical Molecular Biology (SIBioC) Big Data and Artificial Intelligence (BAI) Working Group promoted a survey to frame the knowledge, skills and technological predisposition in clinical laboratories. METHODS: A questionnaire, focussing on digitization, information technology (IT) infrastructures, data accessibility, and BAI projects underway was sent to 1,351 SIBioC participants. The responses were evaluated using SurveyMonkey software and Google Sheets. RESULTS: The 227 respondents (17%) from all over Italy (47% of 484 labs), mainly biologists, laboratory physicians and managers, mostly from laboratories of public hospitals, revealed lack of hardware, software and corporate Wi-Fi, and dearth of PCs. Only 25% work daily on clouds, while 65%-including Laboratory Directors-cannot acquire health data from sources other than laboratories. Only 50% of those with access can review a clinical patient's health record, while the other access only to laboratory information. The integration of laboratory data with other health data is mostly incomplete, which limits BAI-type analysis. Many are unaware of integration platforms. Over 90% report pulling data from the Laboratory Information System, with varying degrees of autonomy. Very few have already undertaken BAI projects, frequently relying on IT partnerships. The majority consider BAI as crucial in helping professional judgements, indicating a growing interest. CONCLUSIONS: The questionnaire received relevant feedback from SIBioC participants. It highlighted the level of expertise and interest in BAI applications. None of the obstacles stands out more than the others, emphasising the need to all-around work: IT infrastructures, data warehouses, BAI analysis software acquisition, data accessibility and training.

How is test laboratory data used and characterised by machine learning models? A systematic review of diagnostic and prognostic models developed for COVID-19 patients using only laboratory data.

The current gold standard for COVID-19 diagnosis, the rRT-PCR test, is hampered by long turnaround times, probable reagent shortages, high false-negative rates and high prices. As a result, machine learning (ML) methods have recently piqued interest, particularly when applied to digital imagery (X-rays and CT scans). In this review, the literature on ML-based diagnostic and prognostic studies grounded on hematochemical parameters has been considered. By doing so, a gap in the current literature was addressed concerning the application of machine learning to laboratory medicine. Sixty-eight articles have been included that were extracted from the Scopus and PubMed indexes. These studies were marked by a great deal of heterogeneity in terms of the examined laboratory test and clinical parameters, sample size, reference populations, ML algorithms, and validation approaches. The majority of research was found to be hampered by reporting and replicability issues: only four of the surveyed studies provided complete information on analytic procedures (units of measure, analyzing equipment), while 29 provided no information at all. Only 16 studies included independent external validation. In light of these findings, we discuss the importance of closer collaboration between data scientists and medical laboratory professionals in order to correctly characterise the relevant population, select the most appropriate statistical and analytical methods, ensure reproducibility, enable the proper interpretation of the results, and gain actual utility by using machine learning methods in clinical practice.

The multicenter European Biological Variation Study (EuBIVAS): a new glance provided by the Principal Component Analysis (PCA), a machine learning unsupervised algorithms, based on the basic metabolic panel linked measurands.

OBJECTIVES: The European Biological Variation Study (EuBIVAS), which includes 91 healthy volunteers from five European countries, estimated high-quality biological variation (BV) data for several measurands. Previous EuBIVAS papers reported no significant differences among laboratories/population; however, they were focused on specific set of measurands, without a comprehensive general look. The aim of this paper is to evaluate the homogeneity of EuBIVAS data considering multivariate information applying the Principal Component Analysis (PCA), a machine learning unsupervised algorithm. METHODS: The EuBIVAS data for 13 basic metabolic panel linked measurands (glucose, albumin, total protein, electrolytes, urea, total bilirubin, creatinine, phosphatase alkaline, aminotransferases), age, sex, menopause, body mass index (BMI), country, alcohol, smoking habits, and physical activity, have been used to generate three databases developed using the traditional univariate and the multivariate Elliptic Envelope approaches to detect outliers, and different missing-value imputations. Two matrix of data for each database, reporting both mean values, and "within-person BV" (CVP) values for any measurand/subject, were analyzed using PCA. RESULTS: A clear clustering between males and females mean values has been identified, where the menopausal females are closer to the males. Data interpretations for the three databases are similar. No significant differences for both mean and CVPs values, for countries, alcohol, smoking habits, BMI and physical activity, have been found. CONCLUSIONS: The absence of meaningful differences among countries confirms the EuBIVAS sample homogeneity and that the obtained data are widely applicable to deliver APS. Our data suggest that the use of PCA and the multivariate approach may be used to detect outliers, although further studies are required.