Seheult, Jansen N

Abstract Background The lupus anticoagulant (LAC) is an important laboratory criterion in the diagnosis of antiphospholipid antibody syndrome. LAC testing at the Mayo Clinic Special Coagulation Laboratory includes up to 13 tests, which are interpreted by trained physicians to identify the presence of LAC and rule out anticoagulant interferences. This feasibility study explored the use of two deep neural network (DNN) architectures for multilabel classification of LAC profiles as a first step toward automating interpretation. Methods Seven thousand two hundred and two retrospective cases were randomly split (64:16:20) for training, validation, and test, respectively. LAC positivity by dilute Russell's viper venom time (LAC-DRVVT) and activated partial thromboplastin time (LAC-APTT) and the presence of warfarin (WAR) and heparin (HEP) were adjudicated by one expert. DNN architectures included: single-output DNNs using domain-knowledge input feature selection and a single-column multioutput DNN using all 13 inputs. Results Domain-knowledge-naïve multioutput DNN achieved similar or improved performance for all 4 label prediction tasks compared with domain knowledge optimized DNNs: F1 scores of 0.977 vs 0.968 for LAC-DRVVT, 0.954 vs 0.945 for LAC-APTT, 0.961 vs 0.957 for HEP, and 0.995 vs 0.977 for WAR, respectively. Conclusions The comparable performance of the 4 domain knowledge optimized DNNs and the multioutput DNN using all 13 input features suggests that the DNN may learn feature importance or mapping to a task without explicit input selection. Given its relative simplicity and versatility, the multioutput DNN is the preferred choice for implementation in a clinical laboratory to standardize LAC diagnosis.

ABSTRACTIntroductionVon Willebrand factor (VWF) multimer analysis is essential for diagnosing and classifying von Willebrand disease (VWD) but requires expert interpretation and is subject to inter‐rater variability. We developed an automated image analysis pipeline using deep learning to improve the reproducibility and efficiency of VWF multimer pattern classification.MethodsWe trained a YOLOv8 deep learning model on 514 gel images (6168 labeled instances) to classify VWF multimer patterns into 12 classes. The model was validated on 192 images (2304 instances) and tested on an independent set of 94 images (1128 instances). Images underwent preprocessing, including histogram equalization, contrast enhancement, and gamma correction. Two expert raters provided ground truth classifications.ResultsThe model achieved 91% accuracy compared to Expert 1 (macro‐averaged precision = 0.851, recall = 0.757, F1‐score = 0.786) and 87% accuracy compared to Expert 2 (macro‐averaged precision = 0.653, recall = 0.653, F1‐score = 0.641). Inter‐rater agreement was very high between experts (κ = 0.883), with strong agreement between the model and Expert 1 (κ = 0.845) and good agreement with Expert 2 (κ = 0.773). The model performed exceptionally well on common patterns (F1 > 0.93) but showed lower performance on rare subtypes.ConclusionAutomated VWF multimer analysis using deep learning demonstrates high accuracy in pattern classification and could standardize the interpretation of VWF multimer patterns. While not replacing expert analysis, this approach could improve the efficiency of expert human review, potentially streamlining laboratory workflow and expanding access to VWF multimer testing.

AbstractBackgroundAs low titer group O whole blood (LTOWB) increases in popularity, blood centers are finding innovative ways of maintaining the supply. One potential way is collecting LTOWB from parous female donors without testing for HLA antibodies. This in silico simulation predicted the risk of an LTOWB unit containing an HLA antibody and the subsequent risk for an HLA‐incompatible transfusion.MethodsAn LTOWB blood bank with 1 million units was simulated consisting of male, nulliparous, and parous female donors. The proportion of each donor type was modeled after the sex distribution at US blood centers. The parity of female donors was calculated based on the average number of live births per female depending on her age. HLA‐alloimmunization risk was determined by her parity status. The HLA haplotypes of the simulated recipients were derived from the 100 most common HLA haplotypes in the US National Marrow Registry Program database. The proportion of different race/ethnic groups in the US was used to simulate 100,000 LTOWB recipients to whom between 1 and 10 units were administered.ResultsOverall, the risk of an LTOWB unit containing at least one HLA antibody was 12.2% and the rate of receiving an HLA‐incompatible unit was 21.3%. The risk of receiving an HLA‐incompatible unit rose from 4.8% after receipt of one unit to 36.5% after 10 units.ConclusionBlood collectors and hospitals should evaluate the potential TRALI risk against the benefit of a potentially expanded inventory of LTOWB before collecting plasma‐containing products from non‐HLA‐tested parous female donors.

Abstract Background and Objectives Artificial intelligence (AI) has been gaining increasing interest in healthcare. During the 2024 International Society of Blood Transfusion (ISBT) Congress, the Clinical Transfusion Working Party (CTWP) conducted a session to explore the exciting intersection of AI in transfusion medicine (TM) practice, education and research. We report here the potential applications and the session outcome. Materials and Methods A pre‐workshop survey explored the participants' demographics and areas of use of AI and whether they have had any AI‐specific training or education. The workshop included presentations on the regulatory aspects of AI use and its application in TM practice, education and research. These were followed by round‐table discussions to explore participants' experience and concerns. Results The workshop had 72 attendees, with 38% falling in the 36–45‐year age group. A total of 70% indicated the use of AI, but only 12% reported having specific training or education. Participants expressed interest in different potential applications but also shared concerns on over‐reliance, potential loss of skills, the accuracy of provided information and content plagiarism. Conclusion The findings of the workshop highlight the need for training, educational resources, standards and regulatory frameworks to guide the use of AI tools in the field of TM.

Abstract Objectives Fluorescence resonance energy transfer (FRET)–based ADAMTS13 activity assays are critical for the diagnosis of thrombotic thrombocytopenic purpura. However, these assays are susceptible to interference. As iodide has been suggested to interfere in laboratory testing via fluorophore quenching or promotion, we aimed to determine whether iodinated contrast (Omnipaque) interferes with the ATS-13 ADAMTS13 Activity Assay 2.0. Methods We evaluated the excitation, emission, and absorbance spectrum of Omnipaque alone and spiked in patient plasma with known ADAMTS13 activity and ADAMTS13 activity on Omnipaque alone, an abnormal control of patient plasma previously observed to display elevated baseline relative fluorescent units, and variable concentrations of patient plasma with known ADAMTS13 activity spiked with Omnipaque. Results No atypical fluorescent peaks were observed on any sample (Omnipaque alone or spiked in plasma) between 250 and 700 nm. There was no difference in the mean ADAMTS13 activity among the various concentrations of plasma spiked with Omnipaque or plasma spiked with saline. Conclusions Iodinated contrast does not appear to interfere—either via spectral overlap of the fluorophore or through physiologic inhibition of the ADAMTS13 enzyme—with ADAMTS13 activity FRET-based assays based on the findings from this in vitro analysis. Delaying sample collection for ADAMTS13 activity testing from suspected patients with thrombotic thrombocytopenic purpura following administration of iodinated radiocontrast agents is not necessary, and recent contrast administration should not yield erroneous ADAMTS13 activity results.

Background: Flow cytometry (FC) is widely utilized for the identification of minimal residual disease (MRD) in B acute lymphoblastic leukemia (BALL), providing an essential laboratory indicator for prognostic assessment and therapeutic management. Unfortunately, the high level of expertise required, long manual analysis time, and complexity of FC data files limit the offering of this testing to selected reference laboratories. Methods: We developed an artificial intelligence (AI) pipeline to automatically enhance unaltered FC files, minimizing the expertise and manual analysis time needed to detect BALL-MRD on a single-tube 10-color panel (CD10, CD19, CD20, CD22, CD24, CD34, CD38, CD45, CD58, CD66c). Raw FC files corresponding to peripheral blood or bone marrow specimens from 171 BALL MRD positive cases (MRD < 5%, median = 0.11%, 107 patients), and 89 MRD-negative cases (63 patients) were processed through our CCADDAS (Clustering and Classification of All events, Dimensionality reduction, Downsampling and Aberrancy Scaling) pipeline on a cloud environment (Google Vertex AI). Automated processing steps included elimination of acquisition errors (FlowCut), state-of-the-art clustering (PARC), dimensionality reduction (UMAP), cluster-based anomaly detection compared to negative controls (24 bone marrow aspirates and 7 peripheral bloods), and cluster-informed downsampling with preservation of low-event subsets. In addition, a deep neural network (DNN) trained on expert-defined subpopulations from negative controls was included for automatic gating of normal subsets (Tensorflow v2). AI-enhanced data files were analyzed using a general purpose flow cytometry analysis software (Kaluza v 3.5, Beckman Coulter), and %MRD estimates compared to reported results based on expert analysis of original FC files. Results: Cluster-informed downsampling reduced the number of cells per case to be manually analyzed from 1.2 million to 155,884 cells on average (87% cellularity reduction); resulting in a smaller FC data file (from 64.5 MB to 13.7 MB; 79% data reduction). Importantly, low-level MRD events were adequately preserved after downsampling (median 100% retention for both MRD<0.01% and MRD 0.01-1%). True number of events were accurately estimated on gated subsets using an “upsampling factor” parameter [observed # events x mean (upsampling factor)]. Gating of normal subsets was completely automated using a DNN classifier parameter. Identification of MRD was aided by an AI-generated “aberrancy scale” parameter that discriminated BALL (median: 991) from both benign mononuclear cells (median: 486, p < 0.0001) and background B-lymphoid cells (median: 379, p < 0.0001), with a performance (AUC: 0.98 and 0.94 for mononuclear and B-lymphoid cells, respectively) superior to CD20 (0.54 and 0.69), CD38 (0.60 and 0.81), CD45 (0.75 and 0.74), CD58 (0.52 and 0.89), CD66c (0.56 and 0.72) and all other antigens studied. The use of AI-enhanced files reduced manual analysis time from 14.16 minutes (SD = 3.7) to 1.05 minutes (SD = 0.6) per case, on average (p < 0.0001) (93% reduction). BALL MRD was detected in all positive cases above clinically relevant threshold (≥0.01%, as recommended by NCCN guidelines), and in 28 of 32 (88%) cases below this threshold, with excellent quantitative correlation with conventional analysis on original FC files (linear regression slope = 1.18, intercept = 0.04%, R squared = 0.92, P < 0.0001). Conclusion: We introduce a largely unsupervised AI pipeline that transforms raw BALL-MRD FC data into a markedly smaller, AI-annotated and software-agnostic FC file, including comparison to normal controls. This CCADDAS pipeline simplifies and accelerates detection of BALL-MRD in clinical diagnostics, reducing number of cells analyzed by 87% and manual analysis time by 93%, without impacting test performance. Moreover, CCADDAS can be utilized for any labroatory-developed BALL-MRD assay, and its small-sized export is compatible with any clinical FC software, computing platform and analysis strategy. Adoption of CCADDAS is likely to facilitate the implementation of BALL-MRD FC analysis by more clinical laboratories.

Introduction: Ticagrelor is a widely used reversible platelet adenosine 5'-diphosphate (ADP) P2Y12 receptor inhibitor used in patients with acute coronary syndrome and coronary interventions. Ticagrelor treated patients may be concomitantly exposed to heparin treatment for prophylaxis/treatment of thrombosis, and heparin induced thrombocytopenia (HIT), a thrombotic thrombocytopenic adverse event may be suspected in such patients. Objective: Here we describe the serological profile of a patient on ticagrelor treatment and strong clinical suspicion of HIT who presented with negative serotonin release assay (SRA) results. A follow up systematic study on the impact of ticagrelor on this gold standard HIT assay is presented. Methods: Remnants from 23 patient samples submitted for clinical SRA testing (5- SRA negative; 6- “low positive” [20-50%]; 5- “moderate positive” [>50 to <90%]; 7- “strong positive” [>90%]) were spiked with ticagrelor in concentrations of 100, 250, 500, and 1000 ng/mL before SRA re-testing. Testing was performed using heat inactivated serum, with low (0.1 units/mL) or high (100 units/mL) heparin and washed platelets (Leger, THSNA 2022). A positive SRA result was defined as ≥20% serotonin release with the low heparin condition and >50% inhibition of serotonin release with high concentration of heparin. A subset of SRA positive patient samples that tested falsely negative upon ticagrelor addition were subsequently incubated with activated charcoal and retested in the SRA to determine if ticagrelor interference was reversible using this methodology. Results: The index patient on ticagrelor had a high 4Ts score, ELISA optical density >1.0 but tested negative in the SRA. Re-testing of this patient with an activated charcoal treated sample demonstrated a striking change in SRA to a strong positive result (91% serotonin release). Upon testing of ticagrelor-spiked samples in the SRA negative patient cohort, as expected, the drug had no effect on results, with all 5 samples persistently staying SRA negative. Of the 6 patients that had low positive SRA results, all converted to SRA negative with ticagrelor concentrations >500 ng/mL. One of these patients became SRA negative at 100 ng/mL and 3 at 250 ng/mL. Of the 5 patients with moderately positive SRA results, 2 converted to SRA negative with ticagrelor concentrations >100 ng/mL, and 4 of 5 patients became negative with spiking at 500 ng/mL. Finally, of the 7 patients with strong positive SRA results, 1 became falsely negative in the SRA at a ticagrelor concentration of 1000 ng/mL. Activated charcoal was incubated with 6 samples that demonstrated negative SRA results with drug concentration of 500 ng/mL. Two samples reverted to SRA positive, while 4 samples remained persistently negative. Conclusion: In preliminary studies, ticagrelor has been shown to interfere with the heparin induced platelet activation (HIPA) assay but its impact on the SRA has been relatively unexplored. Here, we demonstrate that patients on ticagrelor may present with spuriously false HIT functional assay testing by the SRA, particularly if the HIT antibody is not strongly platelet activating. Activated charcoal treatment was only able to reverse drug interference in a subset of samples, even at drug concentrations below peak levels recorded in patients (approx. 800ng/mL). Given these findings, we recommend de-emphasizing the utility of the SRA in ticagrelor treated patients with reliance more on criteria such as pre-test probability of HIT (e.g. 4Ts score), and ELISA results in order to facilitate an accurate diagnosis of HIT.

Introduction: Laboratory identification of a lupus anticoagulant (LAC) requires evidence of: a) prolongation of a phospholipid-dependent screening test, usually a LAC-responsive dilute Russell's viper venom time (DRVVT) or activated partial thromboplastin time (APTT); b) inhibition on mixing with normal pooled plasma (NPP); c) confirmation of phospholipid-dependent inhibition by repeating the prolonged test with excess phospholipid. Despite decades of assay development and re-design and numerous attempts at standardization, diagnosis of a LAC remains challenging due to the heterogeneity of antiphospholipid antibodies, the marked variations in reagents, inconsistencies in post-analytic processes, and not least, the multitude of interferences, such as anticoagulant drugs, which influence test results. Guidelines recommend interruption of anticoagulation, if possible, prior to LAC testing to prevent obtaining false test results. While this is attempted in some instances for direct-acting anticoagulants, it is typically not considered for warfarin, and it is also not always possible. Our laboratory has observed a concerning pattern of potentially false-negative DRVVT screen/ confirm ratios in samples collected from patients on warfarin anticoagulation or with a factor deficiency (e.g. hypoprothrombinemia). The goal of this study is to replicate this observation using in vitro dilution experiments, mixing LAC-positive samples with either NPP or warfarin plasma. Methods: DRVVT Screen, Mix and Confirm assays (Precision Biologic, Dartmouth, NS) were performed using archived LAC-positive plasmas from 5 unique patients not on anticoagulation, and titered with normal pooled plasma (NPP) (Precision Biologic, Dartmouth, NS) to a screen/confirm ratio of 1.20-1.35, near the assay cutoff for DRVVTC (<1.20) and analyzed on the ACL TOP 750 (Werfen, Bedford, MA). Warfarin donor plasma was then mixed in the same dilution scheme with each of the LAC-positive plasmas so that the final dilution factors for LAC-NPP and LAC-Warfarin contrived samples were the same. The DRVVT screen/ confirm ratios of the LAC-NPP and LAC-Warfarin plasma contrived samples were compared. Additionally, a DRVVT Mix Screen and Mix Confirm were performed after mixing in a 1:1 ratio with NPP. Results: The average prothrombin time (PT) in the LAC-Warfarin samples was significantly longer than the LAC-NPP samples (20.7±8.5s vs 10.6±0.2s, p=0.03). All 5 LAC-NPP contrived samples had a positive DRVVT screen/ confirm ratio >1.20, while all of the LAC-Warfarin contrived samples had a negative DRVVT screen/ confirm ratio (1.26±0.04 vs 1.02±0.11, p<0.01). When the DRVVT screening time was divided by the DRVVT Mix Confirm time, 4 of the 5 LAC-Warfarin contrived samples reverted to positive using a cutoff of 1.20 (values of 1.30, 1.21, 1.21, 1.02 and 1.23 for LAC-Warfarin samples) and a similar pattern was observed with the LAC-NPP samples (values of 1.32, 1.29, 1.27, 1.14, 1.27, respectively, for LAC-NPP samples). Conclusion: This study confirms our anecdotal observation that warfarin and/ or factor deficiencies in the common pathway can result in a false-negative DRVVT screen/ confirm ratio using the Precision Biologic LA Sure and LA Check reagents, similar to findings described for apixaban. The DRVVT assay is widely considered to be the most sensitive or responsive to LAC and this in vitro observation raises questions about whether negative DRVVT screen/ confirm ratios can reliably be used to exclude the presence of a LAC in patients on warfarin using this reagent system. Larger studies are required using pre-treatment and on-treatment paired specimens to confirm these findings, and to further explore the utility of the DRVVT Screen/Mix Confirm ratio in this patient population.

Background: Flow cytometry (FC) is widely utilized for the identification of minimal residual disease (MRD) in chronic lymphocytic leukemia (CLL), providing an essential laboratory indicator for prognostic assessment and therapeutic management. Unfortunately, the high level of expertise required, long manual analysis time, and complexity of FC data files limit the offering of this testing to selected reference laboratories. Methods: We developed an artificial intelligence (AI) pipeline to automatically enhance unaltered FC files, minimizing the expertise and manual analysis time needed to detect CLL MRD on a single-tube 10-color panel (CD5, CD19, CD20, CD22, CD38, CD43, CD45, CD200, kappa and lambda). Raw FC files corresponding to peripheral blood or bone marrow specimens from 166 CLL MRD positive cases (MRD < 5%, median = 0.17%, 122 patients), and 61 MRD-negative cases (45 patients) were processed through our CCADDAS (Clustering and Classification of All events, Dimensionality reduction, Downsampling and Aberrancy Scaling) pipeline on a cloud environment (Google Vertex AI). Automated processing steps included elimination of acquisition errors (FlowCut), state-of-the-art clustering (PARC), dimensionality reduction (UMAP), cluster-based anomaly detection compared to negative controls (15 bone marrow aspirates and 14 peripheral bloods), and cluster-informed downsampling with preservation of low-event subsets. In addition, a deep neural network (DNN) trained on expert-defined subpopulations from negative controls was included for automatic gating of normal subsets (Tensorflow v2). AI-enhanced data files were analyzed using a general purpose flow cytometry analysis software (Kaluza v 3.5, Beckman Coulter), and %MRD estimates compared to reported results based on expert analysis of original FC files. Results: Cluster-informed downsampling reduced the number of cells per case to be manually analyzed from 1.1 million to 165,010 cells on average (85% cellularity reduction); resulting in a smaller FC data file (from 62.1 MB to 15.2 MB; 75% data reduction). Importantly, low-level MRD events were adequately preserved after downsampling (median 100% retention for both MRD<0.01% and MRD 0.01-1%). True number of events were accurately estimated on gated subsets using an “upsampling factor” parameter [observed # events x mean (upsampling factor)]. Gating of normal subsets was completely automated using a DNN classifier parameter. Rapid identification of suspected MRD was aided by an AI-generated “aberrancy scale” parameter that discriminated CLL MRD (mean ± 2SD: 969 ± 144) from background B-lymphoid cells (mean ± 2SD: 395 ± 401) (p<0.0001) (AUC = 0.98), with a performance superior to CD5 (AUC = 0.93), CD20 (AUC = 0.83), CD43 (AUC = 0.8) and CD200 (AUC = 0.7). Immunoglobulin light chain-positive CLL MRD was visually identified on a pre-calculated UMAP plot as a single-colored cluster, after dual coloring for kappa and lambda. The use of AI-enhanced files reduced manual analysis time from 11.6 minutes (SD = 4.5) to 0.8 minutes (SD = 0.4) per case, on average (p < 0.01) (93% reduction). CLL MRD was detected in all positive cases above clinically relevant threshold (≥0.01%, as recommended by NCCN guidelines), and in 17 of 21 (81%) cases below this threshold, with excellent quantitative correlation with conventional analysis on original FC files (linear regression slope = 1.02, intercept = 0.001%, R squared = 0.98, P < 0.0001). Conclusion: We introduce a largely unsupervised AI pipeline that transforms raw CLL-MRD FC data into a markedly smaller, AI-annotated and software-agnostic FC file, including comparison to normal controls. This CCADDAS pipeline simplifies and accelerates detection of CLL-MRD in clinical diagnostics, reducing number of cells analyzed by 85% and manual analysis time by 93%, without impacting test performance. Moreover, CCADDAS can be utilized for any laboratory-developed CLL-MRD assay, and its small-sized export is compatible with any clinical FC software, computing platform and analysis strategy. Adoption of CCADDAS is likely to facilitate the implementation of CLL MRD FC analysis by more clinical laboratories.

Context.— Generative artificial intelligence (GAI) is a promising new technology with the potential to transform communication and workflows in health care and pathology. Although new technologies offer advantages, they also come with risks that users, particularly early adopters, must recognize. Given the fast pace of GAI developments, pathologists may find it challenging to stay current with the terminology, technical underpinnings, and latest advancements. Building this knowledge base will enable pathologists to grasp the potential risks and impacts that GAI may have on the future practice of pathology. Objective.— To present key elements of GAI development, evaluation, and implementation in a way that is accessible to pathologists and relevant to laboratory applications. Data Sources.— Information was gathered from recent studies and reviews from PubMed and arXiv. Conclusions.— GAI offers many potential benefits for practicing pathologists. However, the use of GAI in clinical practice requires rigorous oversight and continuous refinement to fully realize its potential and mitigate inherent risks. The performance of GAI is highly dependent on the quality and diversity of the training and fine-tuning data, which can also propagate biases if not carefully managed. Ethical concerns, particularly regarding patient privacy and autonomy, must be addressed to ensure responsible use. By harnessing these emergent technologies, pathologists will be well placed to continue forward as leaders in diagnostic medicine.