Large-scale deep learning analysis to identify adult patients at risk for combined and common variable immunodeficiencies.

BACKGROUND: Primary immunodeficiency (PI) is a group of heterogeneous disorders resulting from immune system defects. Over 70% of PI is undiagnosed, leading to increased mortality, co-morbidity and healthcare costs. Among PI disorders, combined immunodeficiencies (CID) are characterized by complex immune defects. Common variable immunodeficiency (CVID) is among the most common types of PI. In light of available treatments, it is critical to identify adult patients at risk for CID and CVID, before the development of serious morbidity and mortality. METHODS: We developed a deep learning-based method (named "TabMLPNet") to analyze clinical history from nationally representative medical claims from electronic health records (Optum® data, covering all US), evaluated in the setting of identifying CID/CVID in adults. Further, we revealed the most important CID/CVID-associated antecedent phenotype combinations. Four large cohorts were generated: a total of 47,660 PI cases and (1:1 matched) controls. RESULTS: The sensitivity/specificity of TabMLPNet modeling ranges from 0.82-0.88/0.82-0.85 across cohorts. Distinctive combinations of antecedent phenotypes associated with CID/CVID are identified, consisting of respiratory infections/conditions, genetic anomalies, cardiac defects, autoimmune diseases, blood disorders and malignancies, which can possibly be useful to systematize the identification of CID and CVID. CONCLUSIONS: We demonstrated an accurate method in terms of CID and CVID detection evaluated on large-scale medical claims data. Our predictive scheme can potentially lead to the development of new clinical insights and expanded guidelines for identification of adult patients at risk for CID and CVID as well as be used to improve patient outcomes on population level.

Primary immunodeficiencies (PI) are disorders that weaken the immune system, increasing the incident of life-threatening infections, organ damage and the development of cancer and autoimmune diseases. Although PI is estimated to affect 1-2% of the global population, 70-90% of these patients remain undiagnosed. Many patients are diagnosed during adulthood, after other serious diseases have already developed. We developed a computational method to analyze the clinical history from a large group of people with and without PI. We focused on combined (CID) and common variable immunodeficiency (CVID), which are among the least studied and most common PI subtypes, respectively. We could identify people with CID or CVID and combinations of diseases and symptoms which could make it easier to identify CID or CVID. Our method could be used to more readily identify adults at risk of CID or CVID, enabling treatment to start earlier and their long-term health to be improved.

The Potential Role of Salivary NT-proBNP in Heart Failure.

BACKGROUND: Serum natriuretic peptides (NPs) have an established role in heart failure (HF) diagnosis. Saliva NT-proBNP that may be easily acquired has been studied little. METHODS: Ninety-nine subjects were enrolled; thirty-six obese or hypertensive with dyspnoea but no echocardiographic HF findings or raised NPs served as controls, thirteen chronic HF (CHF) patients and fifty patients with acute decompensated HF (ADHF) requiring hospital admission. Electrocardiogram, echocardiogram, 6 min walking distance (6MWD), blood and saliva samples, were acquired in all participants. RESULTS: Serum NT-proBNP ranged from 60-9000 pg/mL and saliva NT-proBNP from 0.64-93.32 pg/mL. Serum NT-proBNP was significantly higher in ADHF compared to CHF (p = 0.007) and in CHF compared to controls (p < 0.05). There was no significant difference in saliva values between ADHF and CHF, or between CHF and controls. Saliva and serum levels were positively associated only in ADHF patients (R = 0.352, p = 0.012). Serum NT-proBNP was positively associated with NYHA class (R = 0.506, p < 0.001) and inversely with 6MWD (R = -0.401, p = 0.004) in ADHF. Saliva NT-proBNP only correlated with age in ADHF patients. CONCLUSIONS: In the current study, saliva NT-proBNP correlated with serum values in ADHF patients, but could not discriminate between HF and other causes of dyspnoea. Further research is needed to explore the value of saliva NT-proBNP.

The clinical phenotype of primary Sjögren's syndrome patients with lymphadenopathy.

OBJECTIVES: Previous cohort studies have shown that around 10% of patients with primary Sjögren's syndrome (pSS) develop lymphadenopathy during their disease course. However, no studies have described their clinical phenotype. The present study aims to describe the clinical manifestations and laboratory findings of pSS patients presenting long-standing lymphadenopathy. METHODS: From a total of 1234 consecutive pSS patients fulfilling the 2016 ACR-EULAR criteria, those with stable lymphadenopathy unrelated to lymphoma were identified (lymphadenopathy group). Their clinical data were collected and compared with 2 control groups: a) the remaining unmatched pSS patients without lymphadenopathy (unmatched non-lymphadenopathy group) and b) pSS patients without lymphadenopathy matched for age, sex, and disease duration, in an approximately 1:1 ratio (matched non-lymphadenopathy group). RESULTS: One hundred and sixty-five (13.37%) patients presented persistent, stable lymphadenopathy. They were characterised by younger age at both pSS onset and diagnosis, and by shorter disease duration. Compared to the unmatched nonlymphadenopathy group, patients with lymphadenopathy had more frequently salivary gland enlargement (p<0.001), higher focus score at first salivary gland biopsy (p=0.017), palpable purpura (p<0.001), peripheral nervous system involvement (p=0.012), glomerulonephritis (p<0.001), and leukopenia (p<0.001), while the results of the matched comparison were similar. Regarding the serological profile, the comparison with the unmatched group demonstrated higher frequency of ANA (p=0.013), anti-Ro/SSA (p=0.001), and anti-La/SSB (p<0.001) positivity for the lymphadenopathy group, while in the matched comparison only higher rates of anti-Ro/SSA positivity (p=0.002) remained statistically significant. CONCLUSIONS: pSS patients presenting non-lymphoma related stable lymphadenopathy constitute a subgroup of younger individuals with B-cell hyperactivation.

A Domain Enriched Deep Learning Approach to Classify Atherosclerosis using Intravascular Ultrasound Imaging.

Intravascular ultrasound (IVUS) imaging is widely used for diagnostic imaging in interventional cardiology. The detection and quantification of atherosclerosis from acquired images is typically performed manually by medical experts or by virtual histology IVUS (VH-IVUS) software. VH-IVUS analyzes backscattered radio frequency (RF) signals to provide a color-coded tissue map, and is the method of choice for assessing atherosclerotic plaque in situ. However, a significant amount of tissue cannot be analyzed in reasonable time because the method can be applied just once per cardiac cycle. Furthermore, only hardware and software compatible with RF signal acquisition and processing may be used. We present an image-based tissue characterization method that can be applied to entire acquisition sequences post hoc for the assessment of diseased vessels. The pixel-based method utilizes domain knowledge of arterial pathology and physiology, and leverages technological advances of convolutional neural networks to segment diseased vessel walls into the same tissue classes as virtual histology using only grayscale IVUS images. The method was trained and tested on patches extracted from VH-IVUS images acquired from several patients, and achieved overall accuracy of 93.5% for all segmented tissue. Imposing physically-relevant spatial constraints driven by domain knowledge was key to achieving such strong performance. This enriched approach offers capabilities akin to VH-IVUS without the constraints of RF signals or limited once-per-cycle analysis, offering superior potential information acquisition speed, reduced hardware and software requirements, and more widespread applicability. Such an approach may well yield promise for future clinical and research applications.

A novel hybrid approach for reconstruction of coronary bifurcations using angiography and OCT.

The aim of this study is to present a new method for three-dimensional (3D) reconstruction of coronary bifurcations using biplane Coronary Angiographies and Optical Coherence Tomography (OCT) imaging. The method is based on a five step approach by improving a previous validated work in order to reconstruct coronary arterial bifurcations. In the first step the lumen borders are detected on the Frequency Domain (FD) OCT images. In the second step a semi-automated method is implemented on two angiographies for the extraction of the 2D bifurcation coronary artery centerline. In the third step the 3D path of the bifurcation artery is extracted based on a back projection algorithm. In the fourth step the lumen borders are placed onto the 3D catheter path. Finally, in the fifth step the intersection of the main and side branches produces the reconstructed model of the coronary bifurcation artery. Data from three patients are acquired for the validation of the proposed methodology and the results are compared against a reconstruction method using quantitative coronary angiography (QCA). The comparison between the two methods is achieved using morphological measures of the vessels as well as comparison of the wall shear stress (WSS) mean values.

ARTreat Project: three-dimensional numerical simulation of plaque formation and development in the arteries.

Atherosclerosis is a progressive disease characterized by the accumulation of lipids and fibrous elements in arteries. It is characterized by dysfunction of endothelium and vasculitis, and accumulation of lipid, cholesterol, and cell elements inside blood vessel wall. In this study, a continuum-based approach for plaque formation and development in 3-D is presented. The blood flow is simulated by the 3-D Navier-Stokes equations, together with the continuity equation while low-density lipoprotein (LDL) transport in lumen of the vessel is coupled with Kedem-Katchalsky equations. The inflammatory process was solved using three additional reaction-diffusion partial differential equations. Transport of labeled LDL was fitted with our experiment on the rabbit animal model. Matching with histological data for LDL localization was achieved. Also, 3-D model of the straight artery with initial mild constriction of 30% plaque for formation and development is presented.