Well-being trajectories in breast cancer and their predictors: A machine-learning approach.

OBJECTIVE: This study aimed to describe distinct trajectories of anxiety/depression symptoms and overall health status/quality of life over a period of 18 months following a breast cancer diagnosis, and identify the medical, socio-demographic, lifestyle, and psychological factors that predict these trajectories. METHODS: 474 females (mean age = 55.79 years) were enrolled in the first weeks after surgery or biopsy. Data from seven assessment points over 18 months, at 3-month intervals, were used. The two outcomes were assessed at all points. Potential predictors were assessed at baseline and the first follow-up. Machine-Learning techniques were used to detect latent patterns of change and identify the most important predictors. RESULTS: Five trajectories were identified for each outcome: stably high, high with fluctuations, recovery, deteriorating/delayed response, and stably poor well-being (chronic distress). Psychological factors (i.e., negative affect, coping, sense of control, social support), age, and a few medical variables (e.g., symptoms, immune-related inflammation) predicted patients' participation in the delayed response and the chronic distress trajectories versus all other trajectories. CONCLUSIONS: There is a strong possibility that resilience does not always reflect a stable response pattern, as there might be some interim fluctuations. The use of machine-learning techniques provides a unique opportunity for the identification of illness trajectories and a shortlist of major bio/behavioral predictors. This will facilitate the development of early interventions to prevent a significant deterioration in patient well-being.

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.

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.

Investigating the feasibility and acceptability of the HOLOBalance system compared with standard care in older adults at risk for falls: study protocol for an assessor blinded pilot randomised controlled study.

INTRODUCTION: Approximately one in three of all older adults fall each year, with wide ranging physical, psychosocial and healthcare-related consequences. Exercise-based interventions are the cornerstone for falls prevention programmes, yet these are not consistently provided, do not routinely address all components of the balance system and are often not well attended. The HOLOBalance system provides an evidence-based balance training programme delivered to patients in their home environment using a novel technological approach including an augmented reality virtual physiotherapist, exergames and a remote monitoring system. The aims of this proof-of-concept study are to (1) determine the safety, acceptability and feasibility of providing HOLOBalance to community dwelling older adults at risk for falls and (2) provide data to support sample size estimates for a future trial. METHODS: A single (assessor) blinded pilot randomised controlled proof of concept study. 120 participants will be randomised to receive an 8-week home exercise programme consisting of either: (1) HOLOBalance or (2) The OTAGO Home Exercise Programme. Participants will be required to complete their exercise programme independently under the supervision of a physiotherapist. Participants will have weekly telephone contact with their physiotherapist, and will receive home visits at weeks 0, 3 and 6. Outcome measures of safety, acceptability and feasibility, clinical measures of balance function, disability, balance confidence and cognitive function will be assessed before and immediately after the 8 week intervention. Acceptability and feasibility will be explored using descriptive statistics, and trends for effectiveness will be explored using general linear model analysis of variance. ETHICS AND DISSEMINATION: This study has received institutional ethical approvals in Germany (reference: 265/19), Greece (reference: 9769/24-6-2019) and the UK (reference: 19/LO/1908). Findings from this study will be submitted for peer-reviewed publications. TRIAL REGISTRATION NUMBER: NCT04053829. PROTOCOL VERSION: V.2, 20 January 2020.

Spatial relationships among hemodynamic, anatomic, and biochemical plaque characteristics in patients with coronary artery disease.

BACKGROUND AND AIMS: We aimed to characterize the spatial proximity of plaque destabilizing features local endothelial shear stress (ESS), minimal luminal area (MLA), plaque burden (PB), and near-infrared spectroscopy (NIRS) lipid signal in high- vs. low-risk plaques. METHODS: Coronary arteries imaged with angiography and NIRS-intravascular ultrasound (IVUS) underwent 3D reconstruction and computational fluid dynamics calculations of local ESS. ESS, PB, MLA, and lipid core burden index (LCBI), for each 3-mm arterial segment were obtained in arteries with large lipid-rich plaque (LRP) vs. arteries with smaller LRP. The locations of the MLA, minimum ESS (minESS), maximum ESS (maxESS), maximum PB (maxPB), and maximum LCBI in a 4-mm segment (maxLCBI4mm) were determined along the length of each plaque. RESULTS: The spatial distributions of minESS, maxESS, maxPB, and maxLCBI4mm, in reference to the MLA, were significantly heterogeneous within and between each variable. The location of maxLCBI4mm was spatially discordant from sites of the MLA (p<0.0001), minESS (p = 0.003), and maxESS (p = 0.003) in arteries with large LRP (maxLCBI4mm ≥ 400) and non-large LRP. Large LRP arteries had higher maxESS (9.31 ± 4.78 vs. 6.32 ± 5.54 Pa; p = 0.023), lower minESS (0.41 ± 0.16 vs. 0.61 ± 0.26 Pa; p = 0.007), smaller MLA (3.54 ± 1.22 vs. 5.14 ± 2.65 mm2; p = 0.002), and larger maxPB (70.64 ± 9.95% vs. 56.70 ± 13.34%, p<0.001) compared with non-large LRP arteries. CONCLUSIONS: There is significant spatial heterogeneity of destabilizing plaque features along the course of both large and non-large LRPs. Large LRPs exhibit significantly more abnormal destabilizing plaque features than non-large LRPs. Prospective, longitudinal studies are required to determine which patterns of heterogeneous destabilizing features act synergistically to cause plaque destabilization.

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.

Local Low Shear Stress and Endothelial Dysfunction in Patients With Nonobstructive Coronary Atherosclerosis.

BACKGROUND: Local hemodynamic factors are important determinants of atherosclerotic plaque development and progression. OBJECTIVES: The goal of this study was to determine the association between low endothelial shear stress (ESS) and microvascular and epicardial endothelial dysfunction in patients with early atherosclerosis. METHODS: Sixty-five patients (mean age 52 ± 11 years) with nonobstructive coronary atherosclerosis (luminal diameter stenosis <30%) were included. Microvascular and epicardial coronary endothelial function was assessed by using intracoronary acetylcholine infusion. Vascular profiling, using 2-plane coronary angiography and intravascular ultrasound, was used to reconstruct the three-dimensional anatomy of the left anterior descending artery. Each reconstructed artery was divided into sequential 3-mm segments and analyzed for local ESS with computational fluid dynamics; that is, lower ESS levels at both a 3-mm regional level (average ESS and low ESS) and at a vessel level (lowest ESS per artery) and for plaque characteristics (plaque area, plaque thickness, and plaque burden). RESULTS: Coronary segments in arteries with abnormal microvascular function exhibited lower ESS compared with segments in arteries with normal microvascular function (average ESS: 1.67 ± 1.04 Pa vs. 2.03 ± 1.72 Pa [p = 0.050]; lowest ESS: 0.54 ± 0.25 Pa vs. 0.72 ± 0.32 Pa [p = 0.014]). Coronary segments in arteries with abnormal epicardial endothelial function also exhibited significantly lower ESS compared with segments in arteries with normal epicardial function (average ESS: 1.49 ± 0.89 Pa vs. 1.93 ± 1.50 Pa [p < 0.0001]; low ESS: 1.26 ± 0.81 Pa vs. 1.56 ± 1.30 Pa [p = 0.001]; lowest ESS: 0.51 ± 0.27 Pa vs. 0.65 ± 0.29 Pa [p = 0.080]). Patients with abnormal microvascular endothelial function exhibited a progressive decrease in average and low ESS, starting from patients with normal epicardial endothelial function to those with both microvascular and epicardial endothelial dysfunction (p < 0.0001 and p = 0.004, respectively). CONCLUSIONS: These data indicate an association between dysfunction of the microvascular and epicardial endothelium and local ESS at the early stages of coronary atherosclerosis in humans.

Role of Low Endothelial Shear Stress and Plaque Characteristics in the Prediction of Nonculprit Major Adverse Cardiac Events: The PROSPECT Study.

OBJECTIVES: This study sought to determine whether low endothelial shear stress (ESS) adds independent prognostication for future major adverse cardiac events (MACE) in coronary lesions in patients with high-risk acute coronary syndrome (ACS) from the United States and Europe. BACKGROUND: Low ESS is a proinflammatory, proatherogenic stimulus associated with coronary plaque development, progression, and destabilization in human-like animal models and in humans. Previous natural history studies including baseline ESS characterization investigated low-risk patients. METHODS: In the PROSPECT (Providing Regional Observations to Study Predictors of Events in the Coronary Tree) study, 697 patients with ACS underwent 3-vessel intracoronary imaging. Independent predictors of MACE attributable to untreated nonculprit (nc) coronary lesions during 3.4-year follow-up were large plaque burden (PB), small minimum lumen area (MLA), and thin-cap fibroatheroma (TCFA) morphology. In this analysis, baseline ESS of nc lesions leading to new MACE (nc-MACE lesions) and randomly selected control nc lesions without MACE (nc-non-MACE lesions) were calculated. A propensity score for ESS was constructed for each lesion, and the relationship between ESS and subsequent nc-MACE was examined. RESULTS: A total of 145 lesions were analyzed in 97 patients: 23 nc-MACE lesions (13 TCFAs, 10 thick-cap fibroatheromas [ThCFAs]), and 122 nc-non-MACE lesions (63 TCFAs, 59 ThCFAs). Low local ESS (<1.3 Pa) was strongly associated with subsequent nc-MACE compared with physiological/high ESS (≥1.3 Pa) (23 of 101 [22.8%]) versus (0 of 44 [0%]). In propensity-adjusted Cox regression, low ESS was strongly associated with MACE (hazard ratio: 4.34; 95% confidence interval: 1.89 to 10.00; p < 0.001). Categorizing plaques by anatomic risk (high risk: ≥2 high-risk characteristics PB ≥70%, MLA ≤4 mm2, or TCFA), high anatomic risk, and low ESS were prognostically synergistic: 3-year nc-MACE rates were 52.1% versus 14.4% versus 0.0% in high-anatomic risk/low-ESS, low-anatomic risk/low-ESS, and physiological/high-ESS lesions, respectively (p < 0.0001). No lesion without low ESS led to nc-MACE during follow-up, regardless of PB, MLA, or lesion phenotype at baseline. CONCLUSIONS: Local low ESS provides incremental risk stratification of untreated coronary lesions in high-risk patients, beyond measures of PB, MLA, and morphology.

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.

Experimental Evaluation of an Invasive Medical Instrument Based on a Displacement Measurement System.

This paper presents a novel method for tracking the position of a medical instrument's tip. The system is based on phase locking a high frequency signal transmitted from the medical instrument's tip to a reference signal. Displacement measurement is established having the loop open, in order to get a low frequency voltage representing the medical instrument's movement; therefore, positioning is established by means of conventional measuring techniques. The voltage-controlled oscillator stage of the phase-locked loop (PLL), combined to an appropriate antenna, comprises the associated transmitter located inside the medical instrument tip. All the other low frequency PLL components, low noise amplifier and mixer, are located outside the human body, forming the receiver part of the system. The operating details of the proposed system were coded in Verilog-AMS. Simulation results indicate robust medical instrument tracking in 1-D. Experimental evaluation of the proposed position tracking system is also presented. The experiments described in this paper are based on a transmitter moving opposite a stationary receiver performing either constant velocity or uniformly accelerated movement, and also together with two stationary receivers performing constant velocity movement again. This latter setup is implemented in order to demonstrate the prototype's accuracy for planar (2-D) motion measurements. Error analysis and time-domain analysis are presented for system performance characterization. Furthermore, preliminary experimental assessment using a saline solution container to more closely approximate the human body as a radio frequency wave transmission medium has proved the system's capability of operating underneath the skin.

Computer simulation of three-dimensional plaque formation and progression in the carotid artery.

Atherosclerosis is becoming the number one cause of death worldwide. In this study, three-dimensional computer model of plaque formation and development for human carotid artery is developed. The three-dimensional blood flow is described by the Navier-Stokes equation, together with the continuity equation. Mass transfer within the blood lumen and through the arterial wall is coupled with the blood flow and is modeled by a convection-diffusion equation. The low-density lipoproteins transports in lumen of the vessel and through the vessel tissue are coupled by Kedem-Katchalsky equations. The inflammatory process is modeled using three additional reaction-diffusion partial differential equations. Fluid-structure interaction is used to estimate effective wall stress analysis. Plaque growth functions for volume progression are correlated with shear stress and effective wall stress distribution. We choose two specific patients from MRI study with significant plaque progression. Plaque volume progression using three time points for baseline, 3- and 12-month follow up is fitted. Our results for plaque localization correspond to low shear stress zone and we fitted parameters from our model using nonlinear least-square method. Determination of plaque location and composition, and computer simulation of progression in time for a specific patient shows a potential benefit for the prediction of disease progression. The proof of validity of three-dimensional computer modeling in the evaluation of atherosclerotic plaque burden may shift the clinical information of MRI from morphological assessment toward a functional tool. Understanding and prediction of the evolution of atherosclerotic plaques either into vulnerable or stable plaques are major tasks for the medical community.

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.

Computer simulation and experimental analysis of LDL transport in the arteries.

Atherosclerosis develops from oxidized low-density lipoprotein molecules (LDL). When oxidized LDL evolves in plaque formations within an artery wall, a series of reactions occur to repair the damage to the artery wall caused by oxidized LDL. Macrophages accumulate inside arterial intima, they started to collect oxidized LDL and form foam cells. Smooth muscle cells accumulate in the atherosclerotic arterial intima, where they proliferate and secrete extracellular matrix to form a fibrous cap. In this study, experimental model of LDL transport on the isolated blood vessel from rabbit on high fat diet after 8 weeks is simulated numerically by using a specific model and histological data. The 3D blood flow is governed by the Navier-Stokes equations, together with the continuity equation. Mass transfer within the blood lumen and through the arterial wall is coupled with the blood flow by the convection-diffusion equation. LDL transport in lumen of the vessel is described by Kedem-Katchalsky equations. The inflammatory process is solved using three additional reaction-diffusion partial differential equations. Matching of histological rabbit data is performed using 3D histological image reconstruction and 3D deformation of elastic body. Computed concentrations of labeled LDL of 5.2 % and macrophages distribution of 4.2% inside the media are found to be in good agreement with experimental results. This simulation study provides a useful tool for understanding and prediction of LDL transport through the arterial wall and evolution of atherosclerotic plaques.