Deciphered coagulation profile to diagnose the antiphospholipid syndrome using artificial intelligence

An update on laboratory detection and interpretation of antiphospholipid antibodies for diagnosis of antiphospholipid syndrome: guidance from the ISTH-SSC Subcommittee on Lupus Anticoagulant/Antiphospholipid Antibodies

Antiphospholipid syndrome (APS) diagnosis is dependent on the accurate detection and interpretation of antiphospholipid antibodies (aPL). Lupus anticoagulant (LA), anticardiolipin antibodies (aCL), and anti-beta2 glycoprotein I antibodies (aβ2GPI) remain the cornerstone of the laboratory part of APS diagnosis. In the 2023 American College of Rheumatology (ACR)/European Alliance of Associations for Rheumatology (EULAR) APS classification criteria, the type of laboratory parameters remain essentially unchanged compared with the updated Sapporo classification criteria, and aCL and aβ2GPI measurement are still restricted to enzyme-linked immunosorbent assays (ELISAs) with moderate and high titer aPL thresholds defined as 40 and 80 Units, respectively, and a cutoff calculated by the 99th percentile has been abandoned. We must differentiate between classification criteria and assessment of aPL in clinical care. Classification criteria are strict and meant for participant inclusion in studies and trials to study homogeneous populations of patients. In contrast, laboratory detection for APS diagnosis in daily practice is broader, meant to diagnose each APS patient to optimize their management. Nowadays, there is increasing use of measurement of aPL by methods other than ELISAs , the semiquantitative reporting of titers is a matter of debate, as well as the role of the isotypes immunoglobulin (Ig)M and IgA, and the role of other aPL, such as antiphosphatidylserine (aPS)/prothrombin (PT) antibodies. Patients diagnosed with the disease may or may not fulfill the classification criteria, and inappropriate use of classification criteria may lead to mis(under)diagnosis. The aim of this guidance, based on literature and expert opinion, is to provide guidance recommendations for laboratory workers and clinicians on routine diagnostic assessment of patients with suspected APS.

Navigating antiphospholipid syndrome: from personalized therapies to cutting-edge research

APS is an autoimmune disorder characterized by thrombosis and pregnancy complications, primarily driven by aPLs such as LA, aCL and anti-β2 glycoprotein I (a-β2GPI). Despite advances in anticoagulation therapies, managing refractory APS cases remains challenging. Emerging therapies, including rituximab, eculizumab and HCQ, show potential in addressing the underlying mechanisms of APS. Additionally, research into genetic and environmental factors, particularly the gut microbiome's role through molecular mimicry, suggests new therapeutic pathways. Diagnostic advancements, such as the adjusted Global Antiphospholipid Syndrome Score (aGAPSS), metabolomic profiling and MRI, have improved risk stratification and early detection. Non-traditional biomarkers like anti-phosphatidylserine/prothrombin (aPS/PT) and anti-Domain I antibodies further enhance risk assessment. Future research should aim to validate these approaches, optimizing patient outcomes and minimizing long-term APS complications.

Heyde Syndrome Unveiled: A Case Report with Current Literature Review and Molecular Insights

Heyde syndrome, marked by aortic stenosis, gastrointestinal bleeding from angiodysplasia, and acquired von Willebrand syndrome, is often underreported. Shear stress from a narrowed aortic valve degrades von Willebrand factor multimers, leading to angiodysplasia formation and von Willebrand factor deficiency. This case report aims to raise clinician awareness of Heyde syndrome, its complexity, and the need for a multidisciplinary approach. We present a 75-year-old man with aortic stenosis, gastrointestinal bleeding from angiodysplasia, and acquired von Willebrand syndrome type 2A. The patient was successfully treated with argon plasma coagulation and blood transfusions. He declined further treatment for aortic stenosis but was in good overall health with improved laboratory results during follow-up. Additionally, we provide a comprehensive review of the molecular mechanisms involved in the development of this syndrome, discuss current diagnostic and treatment approaches, and offer future perspectives for further research on this topic.

Thrombosis in Antiphospholipid Syndrome: Current Perspectives and Challenges in Laboratory Testing for Antiphospholipid Antibodies

Antiphospholipid syndrome (APS) diagnosis hinges on identifying antiphospholipid antibodies (aPL). Currently, laboratory testing encompasses lupus anticoagulant (LA), anticardiolipin (aCL), and anti-β2-glycoprotein I antibodies (aβ2GPI) IgG or IgM, which are included in the APS classification criteria. All the assays needed to detect aPL antibodies have methodological concerns. LA testing remains challenging due to its complexity and susceptibility to interference from anticoagulant therapy. Solid phase assays for aCL and aβ2GPI exhibit discrepancies between different assays. Antibody profiles aid in identifying the patients at risk for thrombosis through integrated interpretation of all positive aPL tests. Antibodies targeting domain I of β2-glycoprotein and antiphosphatidylserine-prothrombin antibodies have been evaluated for their role in thrombotic APS but are not yet included in the APS criteria. Detecting these antibodies may help patients with incomplete antibody profiles and stratify the risk of APS patients. The added diagnostic value of other methodologies and measurements of other APS-associated antibodies are inconsistent. This manuscript describes laboratory parameters useful in the diagnosis of thrombotic APS and will concentrate on the laboratory aspects, clinical significance of assays, and interpretation of aPL results in the diagnosis of thrombotic APS.

Genetic factors, risk prediction and AI application of thrombotic diseases

In thrombotic diseases, coagulation, anticoagulation, and fibrinolysis are three key physiological processes that interact to maintain blood in an appropriate state within blood vessels. When these processes become imbalanced, such as excessive coagulation or reduced anticoagulant function, it can lead to the formation of blood clots. Genetic factors play a significant role in the onset of thrombotic diseases and exhibit regional and ethnic variations. The decision of whether to initiate prophylactic anticoagulant therapy is a matter that clinicians must carefully consider, leading to the development of various thrombotic risk assessment scales in clinical practice. Given the considerable heterogeneity in clinical diagnosis and treatment, researchers are exploring the application of artificial intelligence in medicine, including disease prediction, diagnosis, treatment, prevention, and patient management. This paper reviews the research progress on various genetic factors involved in thrombotic diseases, analyzes the advantages and disadvantages of commonly used thrombotic risk assessment scales and the characteristics of ideal scoring scales, and explores the application of artificial intelligence in the medical field, along with its future prospects.

Machine learning techniques for prediction in pregnancy complicated by autoimmune rheumatic diseases: Applications and challenges

Autoimmune rheumatic diseases are chronic conditions affecting multiple systems and often occurring in young women of childbearing age. The diseases and the physiological characteristics of pregnancy significantly impact maternal-fetal health and pregnancy outcomes. Currently, the integration of big data with healthcare has led to the increasing popularity of using machine learning (ML) to mine clinical data for studying pregnancy complications. In this review, we introduce the basics of ML and the recent advances and trends of ML in different prediction applications for common pregnancy complications by autoimmune rheumatic diseases. Finally, the challenges and future for enhancing the accuracy, reliability, and clinical applicability of ML in prediction have been discussed. This review will provide insights into the utilization of ML in identifying and assisting clinical decision-making for pregnancy complications, while also establishing a foundation for exploring comprehensive management strategies for pregnancy and enhancing maternal and child health.

A thrombin-driven neural net diagnoses the antiphospholipid syndrome without the need for interruption of anticoagulation

ABSTRACT

Thrombosis is an important manifestation of the antiphospholipid syndrome (APS). The thrombin generation (TG) test is a global hemostasis assay, and increased TG is associated with thrombosis. APS is currently diagnosed based on clinical and laboratory criteria, the latter defined as anti-cardiolipin, anti-β2-glycoprotein I antibodies, or lupus anticoagulant (LA). APS testing is often performed after a thrombotic episode and subsequent administration of anticoagulation, which might hamper the interpretation of clotting assays used for LA testing. We set out to develop an artificial neural network (NN) that can diagnose APS in patients who underwent vitamin K antagonist (VKA) treatment, based on TG test results. Five NNs were trained to diagnose APS in 48 VKA-treated patients with APS and 64 VKA-treated controls, using TG and thrombin dynamics parameters as inputs. The 2 best-performing NNs were selected (accuracy, 96%; sensitivity, 96%-98%; and specificity, 95%-97%) and further validated in an independent cohort of VKA-anticoagulated patients with APS (n = 33) and controls (n = 62). Independent clinical validation favored 1 of the 2 selected NNs, with a sensitivity of 88% and a specificity of 94% for the diagnosis of APS. In conclusion, the combined use of TG and NN methodology allowed for us to develop an NN that diagnoses APS with an accuracy of 92% in individuals with VKA anticoagulation (n = 95). After further clinical validation, the NN could serve as a screening and diagnostic tool for patients with thrombosis, especially because there is no need to interrupt anticoagulant therapy.

Application of the thrombin generation assay in patients with antiphospholipid syndrome: A systematic review of the literature

Background

The antiphospholipid syndrome (APS) is classified by the presence of antiphospholipid antibodies (aPL) and thrombotic and/or adverse obstetric outcomes. The diagnosis and risk assessment of APS is challenging. This systematic review investigated if the thrombin generation (TG) assay could be helpful for APS diagnosis and risk assessment.

Methods

A systemic review was performed by searching two databases (MEDLINE and Embase) until March 31, 2022, using a search strategy with two concepts: APS and TG, and related keywords. Two reviewers independently screened the articles based on predefined inclusion and exclusion criteria. Data extraction and quality assessment with the Newcastle-Ottawa Scale (NOS) were performed independently. Synthesis Without Meta-analysis guidelines were followed for data synthesis reporting.

Results

Fourteen studies with 677 APS and 1,349 control subjects were included with variable quality according to the NOS. Twelve studies measured TG via the calibrated automated thrombogram (CAT) method using a fluorogenic substrate, whereas two used a chromogenic substrate-based TG assay. One study compared the CAT assay to the fully-automated ST Genesia® (Stago, France). Two studies initiated TG using platelet-rich plasma, whereas the rest of the studies used platelet-poor plasma. Resistance to activated protein C (aPC) was examined in ten studies. They reported a significant increase in aPC-resistance in APS patients compared to healthy controls, aPL-carriers, and thrombotic controls. Based on two studies, the prevalence of aPC-resistance was higher in APS patients compared to healthy controls and thrombotic controls with odds ratios of 5.9 and 6.8–12.8, respectively (p < 0.05). In contrast, no significant difference in aPC-resistance was found between APS patients and autoimmune disease controls. Furthermore, 7/14 studies reported TG-parameters including peak height, endogenous thrombin potential, lag time, and time to peak, but these outcomes were highly variable between studies. Furthermore, TG methodology between studies differed greatly, impacting the comparability of the studies.

Conclusion

aPC-resistance measured with TG was increased in APS patients compared to healthy and thrombotic controls, but the diagnostic and prognostic value is unclear compared to current diagnostic strategies. Studies of other TG-parameters were heterogeneous and more research is needed to identify their potential added value in APS diagnosis.

Systematic Review Registration

https://www.PROSPERO/, identifier: CRD42022308363

Hematology and Machine Learning

BACKGROUND

Substantial improvements in computational power and machine learning (ML) algorithm development have vastly increased the limits of what autonomous machines are capable of. Since its beginnings in the 19th century, laboratory hematology has absorbed waves of progress yielding improvements in both of accuracy and efficiency. The next wave of change in laboratory hematology will be the result of the ML revolution that has already touched many corners of healthcare and society at large.

CONTENT

This review will describe the manifestations of ML and artificial intelligence (AI) already utilized in the clinical hematology laboratory. This will be followed by a topical summary of the innovative and investigational applications of this technology in each of the major subdomains within laboratory hematology.

SUMMARY

Application of this technology to laboratory hematology will increase standardization and efficiency by reducing laboratory staff involvement in automatable activities. This will unleash time and resources for focus on more meaningful activities such as the complexities of patient care, research and development, and process improvement.

Laboratory Diagnosis of Antiphospholipid Syndrome: Insights and Hindrances

Diagnosis of antiphospholipid syndrome (APS) requires the presence of a clinical criterion (thrombosis and/or pregnancy morbidity), combined with persistently circulating antiphospholipid antibodies (aPL). Currently, laboratory criteria aPL consist of lupus anticoagulant (LAC), anticardiolipin antibodies (aCL) IgG/IgM, and anti-β2 glycoprotein I antibodies (aβ2GPI) IgG/IgM. Diagnosis and risk stratification of APS are complex and efforts to standardize and optimize laboratory tests have been ongoing since the initial description of the syndrome. LAC detection is based on functional coagulation assays, while aCL and aβ2GPI are measured with immunological solid-phase assays. LAC assays are especially prone to interference by anticoagulation therapy, but strategies to circumvent this interference are promising. Alternative techniques such as thrombin generation for LAC detection and to estimate LAC pathogenicity have been suggested, but are not applicable yet in routine setting. For aCL and aβ2GPI, a lot of different assays and detection techniques such as enzyme-linked immunosorbent and chemiluminescent assays are available. Furthermore, a lack of universal calibrators or standards results in high variability between the different solid-phase assays. Other non-criteria aPL such as anti-domain I β2 glycoprotein I and antiphosphatidylserine/prothrombin antibodies have been suggested for risk stratification purposes in APS, while their added value to diagnostic criteria seems limited. In this review, we will describe laboratory assays for diagnostic and risk evaluation in APS, integrating applicable guidelines and classification criteria. Current insights and hindrances are addressed with respect to both laboratory and clinical implications.