Bente Flatland

Background: Harmonization enables direct comparison of patient results from different analyzers and/or measurement techniques and the use of common reference intervals and decision thresholds. Point‐of‐care analyzers (POC) cannot be calibrated by the end user, so regression offers an opportunity for calculated harmonization. This approach has been used to harmonize (POC) with commercial laboratory analyzers (CL) with > 90 paired feline plasma samples. Objective: Our aims were to use 20 pairs of results to derive regression equations to harmonize the POC results with those of the CL. Harmonized results were assessed by recognized quality goals. Methods: Systematic sampling was used to choose the 20 samples used to calculate regression parameters (with three techniques). These were applied to the remainder of the original dataset to harmonize the POC results to those from the CL. POC results were assessed for bias and the number of results reaching quality goals before and after adjustment. Results: Regression from 20 paired samples was able to harmonize POC analyzer results to a commercial laboratory analyzer for 16 feline plasma biochemistry measurands. Conclusions: Most analytes could be harmonized by this approach. Reasons for harmonization failure were inadequate concentration range of patient results (AST, lipase, total bilirubin, GGT), potential non‐linear relationship (lipase), and no clinical performance goal (globulins). Additional studies using samples with clinically important values may overcome these limitations, and similar studies of other species and other types of point‐of‐care analyzers would be of interest.

Background: The majority of published reference intervals for hematology and clinical biochemistry in pigs are generated from a sample group that is demographically different from companion pigs, and as such may not be transferable. The goals of this study were to provide reference intervals generated from sexually mature companion pigs and to compare results based on age group, breed, and reproductive status. Reference intervals are ideally generated in the same laboratory in which patient samples are measured, since there is often bias in values generated from different instruments, but the cost and time commitment required to produce reference intervals may be prohibitive. If so, published reference intervals may be used cautiously as guidelines for interpretation. Methods: Complete blood count (CBC) and plasma biochemistry data were generated using the ADVIA 2120 hematology analyzer and Cobas c501 chemistry analyzer on blood samples collected from 94 sexually mature, clinically healthy companion pigs housed mostly in eastern Tennessee over a 5-year period. The majority (90/94) of samples were collected after sedation or general anesthesia. The age range of the reference sample group was 5 months to 11 years, including 2-years-old (n = 42). Reproductive status included intact females (n = 46), spayed females (n = 9), intact males (n = 15), and castrated males (n = 24). Breeds were predominantly Vietnamese potbellied mini pigs, American mini pigs, and mixed breed pigs. Results: Reference intervals are provided for routine CBC and plasma biochemistry values. The 1-year-old. These included red blood cell concentration, mean cell volume, mean cell hemoglobin, platelet count, mean platelet volume, lymphocyte concentrations by both automated and manual methods, and total protein by refractometry. Few significant differences were observed based on breed or reproductive status. Discussion: Age, breed, and reproductive status can affect some hematology and biochemistry results in companion pigs. If companion pig reference intervals are not available from the laboratory in which patient samples are measured, these published reference intervals may provide guidance for interpretation, although some methodologic variances are likely.

Artificial intelligence (AI) is emerging as a valuable diagnostic tool in veterinary medicine, offering affordable and accessible tests that can match or even exceed the performance of medical professionals in similar tasks. Despite the promising outcomes of using AI systems (AIS) as highly accurate diagnostic tools, the field of quality assurance in AIS is still in its early stages. Our Part I manuscript focused on the development and technical validation of an AIS. In Part II, we explore the next step in development: external validation (i.e., in silico testing). This phase is a critical quality assurance component for any AIS intended for medical use, ensuring that high‐quality diagnostics remain the standard in veterinary medicine. The quality assurance process for evaluating an AIS involves rigorous: (1) investigation of sources of bias, (2) application of calibration methods and prediction of uncertainty, (3) implementation of safety monitoring systems, and (4) assessment of repeatability and robustness. Testing with unseen data is an essential part of in silico testing, as it ensures the accuracy and precision of the AIS output.

Artificial intelligence (AI) has transformative potential in veterinary pathology in tasks ranging from cell enumeration and cancer detection to prognosis forecasting, virtual staining techniques, and individually tailored treatment plans. Preclinical testing and validation of AI systems (AIS) are critical to ensure diagnostic safety, efficacy, and dependability. In this two‐part series, challenges such as the AI chasm (ie, the discrepancy between the AIS model performance in research settings and real‐world applications) and ethical considerations (data privacy, algorithmic bias) are reviewed and underscore the importance of tailored quality assurance measures that address the nuances of AI in veterinary pathology. This review advocates for a multidisciplinary approach to AI development and implementation, focusing on image‐based tasks, highlighting the necessity for collaboration across veterinarians, computer scientists, and ethicists to successfully navigate the complex landscape of using AI in veterinary medicine. It calls for a concerted effort to bridge the AI chasm by addressing technical, ethical, and regulatory challenges, facilitating AI integration into veterinary pathology. The future of veterinary pathology must balance harnessing AI's potential while intentionally mitigating its risks, ensuring the welfare of animals and the integrity of the veterinary profession are safeguarded. Part I of this review focuses on considerations for model development, and Part II focuses on external validation of AI.

Background: Regression describes the relationship of results from two analyzers, and the generated equation can be used to harmonize results. Point‐of‐care (POC) analyzers cannot be calibrated by the end user, so regression offers an opportunity for calculated harmonization. Harmonization (uniformity) of laboratory results facilitates the use of common reference intervals and medical decision thresholds.Objective: Our aims were to characterize the relationship of results for multiple biochemistry analytes on a POC and a commercial laboratory analyzer (CL) with three regression techniques and to use regression equations to harmonize the POC results with those of the CL. Harmonized results were assessed by recognized quality goals. We used harmonized results to assess the regression techniques.Methods: After analyzer imprecision assessments, paired clinical samples were assessed with one dataset to calculate regression parameters that were applied to a second dataset. Three regression techniques were performed, and each was used to harmonize the POC results with those from the CL. POC results were assessed for bias and the number of results reaching quality goals before and after harmonization.Results: All regression techniques could be used to harmonize most analytes so that 95% of results were within ASVCP TEa guidelines. Harmonization could be further improved with alternate regression techniques or exclusions.Conclusions: Regression offers a means to harmonize POC and CL analyzers. Further work is needed to assess how few samples can reliably be used and to assess likely species differences. No regression technique reliably describes the relationship between methods when correlation is poor.

The theory and calculations underpinning Repeat Patient Testing-Quality Control (RPT-QC) have been presented in prior publications. This paper gives an example of the process used for implementing RPT-QC in a network of veterinary commercial reference laboratories and the stages associated with the transition to the sole use of RPT-QC. To employ RPT-QC in this commercial laboratory network, eight stages of implementation were identified: (1) education, (2) data collection, (3) calculations, (4) QC recording and documentation, (5) running RPT-QC in parallel with a commercially available quality control material (QCM), (6) development of a Standard Operating Procedure (SOP), (7) development of complementary aspects supporting RPT-QC, and (8) sole use of RPT-QC. Advantages of RPT-QC included cost savings for QCM and External Quality Assessment (EQA) participation and the ability to use commutable specimens with a veterinary matrix at a result level that is of clinical significance for the species. A disadvantage of RPT-QC using a single level of control was the inability to demonstrate stable performance over a range of results. Future avenues for investigation include ongoing refinement of control limits using a pooled standard deviation of the duplicates (SDdup), Sdup over time, investigation of blood samples from species other than the dog, and manipulation of specimens to produce "low abnormal" or "high abnormal" RPT-QC specimens.

Repeat‐patient testing quality control (RPT‐QC) is a version of statistical quality control (SQC) in which individual patient samples, rather than commercial control materials, are used. Whereas conventional SQC assumes control material stability and repeatedly measures the same lot of control material over time, RPT‐QC uses a unique patient sample for each QC event and exploits the labile nature of patient samples under prescribed storage conditions for QC purposes. Advantages of RPT‐QC include commutability, lower cost, and QC at concentrations of medical interest. Challenges include sample procurement and the establishment of control limits. The objective of this review is to compare and contrast the principles and procedures of RPT‐QC and conventional SQC and to provide an overview of RPT‐QC control limit establishment.

Background: The 2019 ASVCP Education Committee Forum for Discussion, presented at the annual ASVCP/ACVP meeting, identified a need to develop recommendations for teaching laboratory quality management principles in veterinary clinical pathology residency training programs.Objectives: To present a competency‐based framework for teaching laboratory quality management principles in veterinary clinical pathology residency training programs, including entrustable professional activities (EPAs), domains of competence, individual competencies, and learning outcomes.Methods: A joint subcommittee of the ASVCP Quality Assurance and Laboratory Standards (QALS) and Education Committees executed this project. A draft guideline version was reviewed by the ASVCP membership and shared with selected ACVP committees in early 2022, and a final version was voted upon by the full QALS and Education Committees in late 2022.Results: Eleven domains of competence with relevant individual competencies were identified. In addition, suggested learning outcomes and resource lists were developed. Domains and individual competencies were mapped to six EPAs.Conclusions: This guideline presents a framework for teaching principles of laboratory quality management in veterinary clinical pathology residency training programs and was designed to be comprehensive yet practical. Guidance on pedagogical terms and possible routes of implementation are included. Recommendations herein aim to improve and support resident training but may require gradual implementation, as programs phase in necessary expertise and resources. Future directions include the development of learning milestones and assessments and consideration of how recommendations intersect with the American College of Veterinary Pathologists training program accreditation and certifying examination.