Seheult, Jansen N

Context.— Generative artificial intelligence (GAI) technologies are likely to dramatically impact health care workflows in clinical pathology (CP). Applications in CP include education, data mining, decision support, result summaries, and patient trend assessments. Objective.— To review use cases of GAI in CP, with a particular focus on large language models. Specific examples are provided for the applications of GAI in the subspecialties of clinical chemistry, microbiology, hematopathology, and molecular diagnostics. Additionally, the review addresses potential pitfalls of GAI paradigms. Data Sources.— Current literature on GAI in health care was reviewed broadly. The use case scenarios for each CP subspecialty review common data sources generated in each subspecialty. The potential for utilization of CP data in the GAI context was subsequently assessed, focusing on issues such as future reporting paradigms, impact on quality metrics, and potential for translational research activities. Conclusions.— GAI is a powerful tool with the potential to revolutionize health care for patients and practitioners alike. However, GAI must be implemented with much caution considering various shortcomings of the technology such as biases, hallucinations, practical challenges of implementing GAI in existing CP workflows, and end-user acceptance. Human-in-the-loop models of GAI implementation have the potential to revolutionize CP by delivering deeper, meaningful insights into patient outcomes both at an individual and a population level.

Abstract Background Fibrinogen plays a critical role in hemostasis and is essential to clot formation. Changes in the quantity or activity of fibrinogen can lead to disorders affecting coagulation. Thus, it is essential to precisely quantify fibrinogen levels to differentiate between hyperfibrinogenemia in hypercoagulable disorders and dysfibrinogenemia, hypo/afibrinogenemia, and irregular bleeding. Current diagnostic tests that use antibodies to detect fibrinogen or activity-based measures are susceptible to interference from heparin contamination, hemolysis, and hyperbilirubinemia. Here, we evaluated the use of targeted proteomics for developing a quantitative assay for fibrinogen in plasma samples. Methods Four peptides each for alpha and gamma chains of fibrinogen were synthesized using FMOC chemistry on a Liberty Blue (CEM Corp) peptide synthesizer. A targeted multiple reaction monitoring (MRM) assay was developed and optimized using Dionex Ultimate 3000 HPLC connected to a TSQ Altis triple quadrupole mass spectrometer (Thermo Scientific). Evaluations were conducted using a range of standards, such as pure protein, WHO plasma and commercially available plasma with known fibrinogen amounts for the accurate quantitation of fibrinogen. Calibration curves were generated using different dilutions in various matrices. The repeatability and precision of the assay were evaluated across five different days. The plasma samples were processed and digested in a 96-well plate and subjected to C18 clean-up using a Bravo automated liquid handler (Agilent). All samples were spiked-in with corresponding heavy-labeled peptides prior to digestion with trypsin. Multiple reaction monitoring assays were performed on tryptic digests of plasma samples. Results Calibration curves using commercial plasma for all peptides showed linearity from 20 mg/dl to 1,308 mg/dl. This covers the entire clinical range including normal (200-350 mg/dl), deficient states (<100 mg/dl) and excess production (>350 mg/dl) that can be used for evaluation of bleeding disorders including consumption coagulopathy and hyperfibrinogenemia. Based on the overall performance in terms of linearity, limit of detection/quantitation, carryover and coefficient of variation (CV) across five different days, two peptides per chain were finally selected for developing the quantitative assay. The intra-assay variability was <5% and intra-day CV was ∼20%. This assay is currently being tested on a variety of clinical samples representing a range of fibrinogen levels. Conclusions Our study focused on assessing whether multiplexed MRM assay could be implemented to measure fibrinogen levels in plasma. Our data indicate the feasibility of MRM-based assays for determining fibrinogen levels as an alternative to existing non-mass spectrometry-based activity or antigen assays.

AbstractBackgroundUsing low titer group O whole blood (LTOWB) is increasingly popular for resuscitating trauma patients. LTOWB is often RhD‐positive, which might cause D‐alloimmunization and hemolytic disease of the fetus and newborn (HDFN) if transfused to RhD‐negative females of childbearing potential (FCP). This simulation determined the number of life years gained by the FCP and her future children if she was resuscitated with LTOWB compared with conventional component therapy (CCT).MethodsThe model simulated 500,000 injured FCPs of each age between 0 and 49 years with LTOWB mortality relative reductions (MRRs) compared with components between 0.1% and 25%. For each surviving FCP, number of life years gained was calculated using her age at injury and average life expectancy for American women. The number of expected future pregnancies for FCPs that did not survive was also based on her age at injury; each future child was assigned the maximum lifespan unless they suffered perinatal mortality or serious neurological events from HDFN.ResultsThe LTOWB group with an MRR 25% compared with CCT had the largest total life years gained. The point of equivalence for RhD‐positive LTOWB compared to CCT, where life years lost due to severe HDFN was equivalent to life years gained due to FCP survival/future childbearing, occurred at an MRR of approximately 0.1%.ConclusionIn this model, RhD‐positive LTOWB resulted in substantial gains in maternal and child life years compared with CCT. A >0.1% relative mortality reduction from LTOWB offset the life years lost to HDFN mortality and severe neurological events.

AbstractBackgroundClot based assays used for lupus anticoagulant (LAC) detection are typically interpreted in a qualitative fashion and may not reflect LAC potency. In this cross‐sectional study, we describe a method for quantifying the LAC titer using serial (dependent) two‐fold dilutions in normal pooled plasma.MethodsSerial dilutions of 51 residual plasma samples from 50 patients were tested using the Russell's viper venom screening time (DRVVT) and activated partial thromboplastin screening time (APTT) methodologies. The measured clotting times and the corresponding dilution factors were then used to derive a four‐parameter logistic model. The LAC titer for each patient was interpolated as the sample dilution that corresponds to the upper reference interval limit of the corresponding assay.ResultsCalculated APTT and DRVVT LAC titers displayed a strong linear correlation (R2 = 0.84) between each other, but not with the degree of prolongation of the APTT/DRVVT screening time in the neat undiluted samples. Using data driven partitioning, patients could be grouped into low (<10) or high (≥10) DRVVT LAC titer. There were no significant differences in anticardiolipin (aCL) or anti‐beta 2 glycoprotein 1 (aB2GPI) antibody levels or prevalence of thromboembolic events between low and high LAC titer groups. In contrast, antiphosphatidylserine/prothrombin (aPS/PT) IgM antibody levels, but not IgG, were significantly higher in the high LAC titer group.ConclusionsThe degree of prolongation of the APTT/DRVVT screening time is not correlated with the LAC titer. Only aPS/PT IgM antibodies levels were strongly correlated with the LAC titers. Additional studies are warranted to determine clinical implications of high LAC titers.

Abstract The diagnosis of leukemic T-cell malignancies is often challenging, due to overlapping features with reactive T-cells and limitations of currently available T-cell clonality assays. Recently developed therapeutic antibodies specific for the mutually exclusive T-cell receptor constant β chain (TRBC)1 and TRBC2 isoforms provide a unique opportunity to assess for TRBC-restriction as a surrogate of clonality in the flow cytometric analysis of T-cell neoplasms. To demonstrate the diagnostic utility of this approach, we studied 135 clinical specimens with (50) or without (85) T-cell neoplasia, in addition to 29 blood samples from healthy donors. Dual TRBC1 and TRBC2 expression was studied within a comprehensive T-cell panel, in a fashion similar to the routine evaluation of kappa and lambda immunoglobulin light chains for the detection of clonal B-cells. Polytypic TRBC expression was demonstrated on total, CD4+ and CD8+ T-cells from all healthy donors; and by intracellular staining on benign T-cell precursors. All neoplastic T-cells were TRBC-restricted, except for 5 cases (10%) lacking TRBC expression. T-cell clones of uncertain significance were identified in 15 samples without T-cell malignancy (13%), and accounted for smaller subsets than neoplastic clones (median: 4.7% vs. 73% of lymphocytes, p < 0.0001). Single staining for TRBC1 produced spurious TRBC1-dim subsets in 21 clinical specimens (16%), all of which resolved with dual TRBC1/2 staining. Assessment of TRBC restriction by flow cytometry provides a rapid diagnostic method to detect clonal T-cells, and to accurately determine the targetable TRBC isoform expressed by T-cell malignancies.

Context.— Machine learning applications in the pathology clinical domain are emerging rapidly. As decision support systems continue to mature, laboratories will increasingly need guidance to evaluate their performance in clinical practice. Currently there are no formal guidelines to assist pathology laboratories in verification and/or validation of such systems. These recommendations are being proposed for the evaluation of machine learning systems in the clinical practice of pathology. Objective.— To propose recommendations for performance evaluation of in vitro diagnostic tests on patient samples that incorporate machine learning as part of the preanalytical, analytical, or postanalytical phases of the laboratory workflow. Topics described include considerations for machine learning model evaluation including risk assessment, predeployment requirements, data sourcing and curation, verification and validation, change control management, human-computer interaction, practitioner training, and competency evaluation. Data Sources.— An expert panel performed a review of the literature, Clinical and Laboratory Standards Institute guidance, and laboratory and government regulatory frameworks. Conclusions.— Review of the literature and existing documents enabled the development of proposed recommendations. This white paper pertains to performance evaluation of machine learning systems intended to be implemented for clinical patient testing. Further studies with real-world clinical data are encouraged to support these proposed recommendations. Performance evaluation of machine learning models is critical to verification and/or validation of in vitro diagnostic tests using machine learning intended for clinical practice.

Background: Identification of minimal residual disease (MRD) in acute myeloid leukemia (AML) is essential for assessing risk of relapse and guiding therapeutic management. While molecular assays have streamlined AML MRD detection, flow cytometric immunophenotyping (FCI) remains the only available test modality for approximately 50% of patients lacking traceable molecular MRD targets. Unfortunately, due to the high level of expertise required, long manual analysis time and complexity of AML MRD FCI data, only a few reference laboratories offer this as an orderable test. Methods: To facilitate the analysis of AML MRD by FCI, we devised an unsupervised machine learning (ML) pipeline that intakes raw FCI data, eliminates acquisition errors (FlowCut), performs state-of-the-art clustering (PARC) and dimensionality reduction (UMAP), estimates how aberrant or different-from-normal each cluster is compared to a cohort of controls (15 donor and 15 reactive marrow aspirates), downsamples clusters with high event counts without significant loss of low-event clusters, and corrects for downsampling using an upsampling factor. This CCADDAS (Clinically-intended Clustering of All events, Dimensionality reduction, Downsampling and Aberrancy Scaling) pipeline was containerized, deployed in a cloud environment (Google Cloud Vertex AI), and used to process raw FCI files from 50 AML MRD FCI assays (3-tube/10-color panel) with 0.1% to &lt;5% leukemic subsets, and 20 assays with no detectable leukemic subsets by prior conventional analysis. Machine learning-enhanced data files were analyzed using a commercially available FCI analysis software (Kaluza v 2.1, Beckman Coulter). Results: Cluster-informed downsampling reduced the total number of events needed to be analyzed from 1 million cells to 179,531 cells per tube on average (82% data reduction), while preserving low event subsets (clusters smaller than 5000 cells) and allowing for accurate quantitative estimates for any gated population [# events x mean (upsampling factor)]. MRD was detected in all positive cases, and absent on all negative cases when analyzed using the enhanced downsampled data (100% correlation with original data), with accurate quantitative estimates (Spearman r = 0.85). Analysis time was dramatically reduced from 73 minutes to 8 minutes per case on average (89% reduction of manual analysis time). Dimensionality reduction parameters simplified gating of lineage- and maturation-defined subsets. Cluster comparison against control samples facilitated the rapid identification of MRD subsets, based on a calculated aberrancy scale parameter that helped distinguish MRD blasts (mean ± 2SD: 0.85 ± 0.3) from benign blasts (mean ± 2SD: 0.26 ± 0.3) (p&lt;0.0001). Conclusion: We introduce CCADDAS, an unsupervised containerized cloud ML pipeline that enhances raw AML-MRD FCI data with ML annotations, cluster-informed downsampling and comparison to normal controls to create markedly smaller and software-agnostic FCI files. CCADDAS simplifies and accelerates detection of AML-MRD in clinical diagnostics, reducing number of cells analyzed by 82% and manual analysis time by 89%, without impacting test performance. Moreover, CCADDAS can be deployed on any laboratory-developed AML-MRD assay, and its small-sized export is compatible with any clinical FCI software, computing platform and analysis strategy. Adoption of CCADDAS is likely to facilitate the implementation of AML MRD FCI analysis by more clinical laboratories.

Abstract Uncontrolled hemorrhage accounts for up to 40% of trauma related mortality, and approximately 30% of trauma related deaths occur in the hospital within the first 1-4 hours of injury. The Advanced Trauma Life Support (ATLS) guidelines still recommend initial resuscitation with crystalloid fluid as an integral part of maintaining or restoring hemodynamic stability, but are starting to recognize the role of early resuscitation with blood products in patients with evidence of Class III and IV hemorrhage, in line with recent clinical trial and observational data. Although there is a growing body of evidence that early transfusion with blood products may be associated with improved survival compared with crystalloid infusion, the optimal transfusion strategy still remains unclear and is being actively investigated in clinical trials. In silico models of resuscitation offer a means to evaluate the effectiveness and safety of resuscitation protocols, including effects on body fluid compartment volumes, tissue oxygenation, and hemostatic factors. Here we describe our work extending earlier deterministic models of trauma resuscitation to incorporate hemodynamic, hemostatic, resuscitation, biomarker, and tissue-oxygenation domains into a single comprehensive model. Additionally, this model expands upon previous deterministic models to create a stochastic computational model of hemostatic resuscitation that accounts for variations in blood component composition and temporal features of transfusion therapy. Using this stochastic model, an in silico trial was piloted to compare conventional component therapy, i.e. red cell, platelet and plasma components, to cold-stored whole blood using the following starting assumptions: patient weight of 81.3±21.8 kg, hematocrit of 41.8±4.3%, initial bleeding rate between 50 and 150 mL/min, systolic blood pressure of 125±18 mmHg, fibrinogen of 293±88 mg/dL, international normalized ratio of 1.0±0.1 and platelet count of 239±62x109/L, with blood component and whole blood constituent distributions based on laboratory quality control data. This in silico trial demonstrated that resuscitation with whole blood was associated with a 28-minute reduction in the time spent in the critical window defined by platelet count &lt;50x109/L, INR≥2, hemoglobin &lt;9 g/dL and fibrinogen &lt;150 mg/dL compared with conventional component resuscitation over the course of a 4 hour simulation (p&lt;0.001 based on median regression). We demonstrate how stochastic models of hemostatic resuscitation can be used to perform in silico trials of resuscitation strategies. Our work can guide inclusion and exclusion criteria for future clinical trials and facilitate identification of patient subgroups most likely to benefit from certain resuscitation strategies. This work was partially funded by the AABB Foundation (formerly the National Blood Foundation).

Abstract Objectives To determine the impact of residual platelets on dilute Russell’s viper venom time (DRVVT) assay in frozen-thawed plasma submitted for lupus anticoagulant (LAC) testing. Methods We measured platelet counts in frozen-thawed samples submitted for LAC testing and evaluated the association between platelet count and the DRVVT screening time and ratios. We also spiked platelets into a LAC-positive sample to observe the effect on the DRVVT. Results Progressive increase in platelet count resulted in a statistically significant shortening of the DRVVT assay results on plasma after 1 freeze-thaw cycle. A similar effect was noted on the LAC-positive sample. Conclusions Residual platelets in plasma samples result in shortening of DRVVT assay after 1 freeze-thaw cycle. This may result in a false-negative LAC test result.

PittUDT, a recursive partitioning decision tree algorithm for predicting urine culture (UC) positivity based on macroscopic and microscopic urinalysis (UA) parameters, was developed in support of a broader system-wide diagnostic stewardship initiative to increase appropriateness of UC testing. Reflex algorithm training utilized results from 19,511 paired UA and UC cases (26.8% UC positive); the average patient age was 57.4 years, and 70% of samples were from female patients.