Application of machine learning to identify top determinants of fibrofatty plaque burden by CCTA in humans with psoriasis

Introduction

Fibrofatty plaque burden (FFB) is a high-risk, vulnerable plaque feature comprised of an atheromatous core and fibrous cap with increased risk of coronary artery disease (CAD) [1]. Psoriasis (PSO) is a chronic inflammatory disease linked with atherosclerotic risk and premature cardiovascular disease, driven in part by vulnerable plaque rupture [2,3]. Machine learning (ML) previously showed the prognostic value of FFB in predicting 5-year risk of cardiac-related mortality in patients with CAD [4]. Whether ML can predict FFB in psoriasis is understudied.

Purpose

To use ML to identify top determinants of FFB by CCTA in PSO.

Methods

320 consecutive participants with psoriasis were recruited as part of an ongoing cohort study, of whom 307 had FFB analyzed with coronary computed tomography angiography (CCTA) and quantified by QAngio CT (Medis, The Netherlands). 140 out of 182 potential determinants were subjected to ML algorithms analyzed by random forest and validated by 5-fold cross validation to select the top determinants based on R-square criteria. Lipid concentration and size were measured by nuclear magnetic resonance (NMR) and sdLDL-C was calculated by Sampson's formula.

Results

The top 21 determinants of FFB at baseline were grouped into 3 categories: cardiometabolic risk factors (BMI, sex, DBP, mean arterial pressure, exercise, heart rate, glucose, anxiety, psoriasis disease duration), clinical measurements (basophils, platelets, hemoglobin, RBC, alkaline phosphatase, ALT, creatinine, neutrophil-to-lymphocyte ratio), and lipoproteins (LDL particle size, apolipoprotein A1, apolipoprotein B-to-A1 ratio, calculated sdLDL-C).

Conclusion

ML confirmed that FFB strongly correlates with cardiometabolic risk factors, clinical measurements, and lipoproteins. Further investigations into these top determinants of FFB over time may provide insight into potential therapeutic interventions that decrease cardiovascular risk in patients with chronic inflammatory diseases and should be validated in larger studies.

Funding Acknowledgement

Type of funding sources: Public Institution(s). Main funding source(s): This study was supported by the National Heart, Lung and Blood Institute (NHLBI) IntramuralResearch Program (ZIA-HL-06193). This research was made possible through the NIH MedicalResearch Scholars Program, a public-private partnership supported jointly by the NIH andcontributions to the Foundation for the NIH from the Doris Duke Charitable Foundation,Genentech, the American Association for Dental Research, the Colgate-Palmolive Company, andother private donors.

Engineered HA hydrogel for stem cell transplantation in the brain: Biocompatibility data using a design of experiment approach

This article presents data related to the research article “Systematic optimization of an engineered hydrogel allows for selective control of human neural stem cell survival and differentiation after transplantation in the stroke brain” (P. Moshayedi, L.R. Nih, I.L. Llorente, A.R. Berg, J. Cinkornpumin, W.E. Lowry et al., 2016) [1] and focuses on the biocompatibility aspects of the hydrogel, including its stiffness and the inflammatory response of the transplanted organ. We have developed an injectable hyaluronic acid (HA)-based hydrogel for stem cell culture and transplantation, to promote brain tissue repair after stroke. This 3D biomaterial was engineered to bind bioactive signals such as adhesive motifs, as well as releasing growth factors while supporting cell growth and tissue infiltration. We used a Design of Experiment approach to create a complex matrix environment in vitro by keeping the hydrogel platform and cell type constant across conditions while systematically varying peptide motifs and growth factors. The optimized HA hydrogel promoted survival of encapsulated human induced pluripotent stem cell derived-neural progenitor cells (iPS-NPCs) after transplantation into the stroke cavity and differentially tuned transplanted cell fate through the promotion of glial, neuronal or immature/progenitor states. The highlights of this article include: (1) Data of cell and bioactive signals addition on the hydrogel mechanical properties and growth factor diffusion, (2) the use of a design of Experiment (DOE) approach (M.W. 2 Weible and T. Chan-Ling, 2007) [2] to select multi-factorial experimental conditions, and (3) Inflammatory response and cell survival after transplantation.

Simultaneous concentration and detection of biomarkers on paper

The lateral-flow immunoassay (LFA) is an inexpensive point-of-care (POC) paper-based diagnostic device with the potential to rapidly detect disease biomarkers in resource-poor settings. Although LFA is inexpensive, easy to use, and requires no laboratory equipment, it is limited by its sensitivity, which remains inferior to that of gold standard laboratory-based assays. Our group is the only one to have previously utilized various aqueous two-phase systems (ATPSs) to enhance LFA detection. In those studies, the sample was concentrated by an ATPS in a test tube and could only be applied to LFA after it had been extracted manually. Here, we bypass the extraction step by seamlessly integrating a polyethylene glycol-potassium phosphate ATPS with downstream LFA detection in a simple, inexpensive, power-free, and portable all-in-one diagnostic device. We discovered a new phenomenon in which the target biomarkers simultaneously concentrate as the ATPS solution flows through the paper membranes, and our device features a 3-D paper well that was designed to exploit this phenomenon. Studies with this device, which were performed at room temperature in under 25 min, demonstrated a 10-fold improvement in the detection limit of a model protein, transferrin. Our next-generation LFA technology is rapid, affordable, easy-to-use, and can be applied to existing LFA products, thereby providing a new platform for revolutionizing the current state of disease diagnosis in resource-poor settings.

[The association of risk of development of cardiomyopathies with polymorphic variants of genes of angiotensin converting enzyme, glutathione-S-transferase, interleukins 8 and 10]

The article presents the results of study of association of risk of development and clinical course of cardiomyopathies with polymorphic variants of genes ACE, GSTM1, IL8 and IL10. The purpose of research was to find out molecular genetic markers of risk of development and clinical course of various types of cardiomyopathies. The analysis used the DNA samples extracted from lymphocytes of peripheral venous blood of patients with cardiomyopathies (N = 89) and control group (N = 426). The standard analysis techniques of polymerase chain reaction and restriction fragment length polymorphism were applied to detect polymorphic loci of genes candidates. It is established that genotype of DD-polymorphic locus of I/DgeneACE is a marker of development of ischemic cardiomyopathy. The allele D is a marker of development of increased rate of manifestation of extra-systoles, growth of inter-ventricular septum and reduction of fraction of discharge in patients with cardiomyopathies.

Lymphoplasmacytic lymphoma. Report of a case with three monoclonal proteins derived from a single neoplastic clone

The unique case of a 60-year-old patient with a non-Hodgkin's B-cell lymphoma of the lymphoplasmacytic type and three associated monoclonal proteins, is described. The patient also exhibited various autoimmune phenomena that were consistent with the diagnoses of Sjögren's syndrome and autoimmune thyroiditis. The evolution from production of a single monoclonal protein (IgM-kappa) to three monoclonal proteins (IgG-kappa, IgA-kappa, and IgM-kappa) suggested that the lymphoplasmacytic cells were at different stages of terminal differentiation within a single neoplastic clone. The chronic antigenic stress imposed on the immune system by the autoimmune disorder may have played a role in the development of lymphoma and in the heavy chain immunoglobulin switching that occurred during the patients' clinical course.

The undifferentiated malignant neoplasm. Identification of lymphoma arising in skeletal muscle by immunohistochemical analysis

The undifferentiated malignant neoplasm presents a significant problem in the intelligent selection of therapy. Because of advances in chemotherapy, there are cancers that are effectively palliated, and sometimes cured if appropriately treated. Characterization of tumors by immunohistochemical stains drastically reduces the incidence of "undifferentiated" diagnoses and will optimize patient management, as illustrated by two cases of large-cell lymphoma arising in skeletal muscle.