Cardiovascular Risk Prediction in Ankylosing Spondylitis: From Traditional Scores to Machine Learning Assessment

Pain catastrophizing negatively impacts drug retention rate in patients with Psoriatic Arthritis and axial Spondyloarthritis: results from a 2-years perspective multicenter GIRRCS (Gruppo Italiano di Ricerca in Reumatologia Clinica) study

BACKGROUND

Chronic pain and inflammation are common features of rheumatic conditions such as Psoriatic Arthritis (PsA) and Axial Spondyloarthritis (axSpA), often needing prolonged medication treatment for effective management. Maintaining drug retention is essential for both achieving disease control and improving patients' quality of life. This study investigates the influence of pain catastrophizing, a psychological response to pain, on the drug retention rates of PsA and axSpA patients.

METHODS

A two-year prospective multicenter observational study involved 135 PsA and 71 axSpA patients. Pain Catastrophizing Scale (PCS) was employed to assess pain catastrophizing. Univariable and multivariable regression analyses were utilized to identify factors associated with drug retention.

RESULTS

In the PsA group, patients early discontinuing therapy showed higher baseline disease activity as well as higher incidence of comorbid fibromyalgia. Notably, pain catastrophizing, specifically the domains of Helplessness, Magnification, and Rumination, were significantly elevated in PsA patients who interrupted the treatment. Multivariable analysis confirmed pain catastrophizing as an independent predictor of drug suspension within two years. In axSpA, drug discontinuation was associated with female gender, shorter disease duration, higher baseline disease activity as well as elevated levels of pain catastrophizing. Univariable analysis supported the role of pain catastrophizing, including its domains, as predictors of treatment interruption. However, limited events in axSpA patients precluded a multivariate analysis.

CONCLUSION

This prospective study emphasizes the impact of pain catastrophizing on drug retention in patients with PsA and axSpA.

Impact of inflammation and anti-inflammatory therapies on the incidence of major cardiovascular events in patients with ankylosing spondylitis: A population-based study

OBJECTIVE

To examine the independent effect of inflammatory burden and various treatments on the risk of incident major adverse cardiovascular events (MACE) in ankylosing spondylitis (AS) patients.

METHODS

AS patients were retrospectively selected from a territory-wide database between 2006 and 2015, and were followed until the end of 2018. The primary outcome was the first occurrence of MACE. Multivariate time-varying Cox proportional hazard models were used to determine the associations between inflammatory burden (measured by c-reactive protein [CRP] and erythrocyte sedimentation rate [ESR]) and different therapies with incident MACE, after adjusting for traditional cardiovascular (CV) risk factors.

RESULTS

A total of 3827 patients with AS (mean age: 45.2 ± 15.0 years, male: 2911 [76.1 %]) were recruited. After a follow-up of 23,275 person-years, 135 patients (3.5 %) developed a first MACE. Univariate analyses showed that elevated ESR and CRP levels, and the use of glucocorticoids were associated with a significantly higher risk of MACE, while the use of sulfasalazine (SLZ), biologic DMARDs and non-cyclooxygenase-2 inhibitors (non-COX-IIi) were associated with reduced risk of MACE. After adjusting for CV risk factors in the multivariable models, only ESR (HR: 1.02; ESR ≥30 mm/h, HR:1.94) and CRP level (HR: 1.14; CRP >3 mg/dl HR:5.43) remained significantly associated with increased risk of MACE, while SLZ use (HR: 0.41-0.52) was protective against MACE.

CONCLUSION

High inflammatory burden was an independent predictor associated with an increased risk of MACE, while the use of SLZ might reduce risk of incident MACE in patients with AS.

Combined use of QRISK3 and SCORE2 increases identification of ankylosing spondylitis patients at high cardiovascular risk: Results from the CARMA Project cohort after 7.5 years of follow-up

OBJECTIVE

To establish the predictive value of the QRESEARCH risk estimator version 3 (QRISK3) algorithm in identifying Spanish patients with ankylosing spondylitis (AS) at high risk of cardiovascular (CV) events and CV mortality. We also sought to determine whether to combine QRISK3 with another CV risk algorithm: the traditional SCORE, the modified SCORE (mSCORE) EULAR 2015/2016 or the SCORE2 may increase the identification of AS patients with high-risk CV disease.

METHODS

Information of 684 patients with AS from the Spanish prospective CARdiovascular in ReuMAtology (CARMA) project who at the time of the initial visit had no history of CV events and were followed in rheumatology outpatient clinics of tertiary centers for 7.5 years was reviewed. The risk chart algorithms were retrospectively tested using baseline data.

RESULTS

After 4,907 years of follow-up, 33 AS patients had experienced CV events. Linearized rate=6.73 per 1000 person-years (95 % CI: 4.63, 9.44). The four CV risk scales were strongly correlated. QRISK3 correctly discriminated between people with lower and higher CV risk, although the percentage of accumulated events over 7.5 years was clearly lower than expected according to the risk established by QRISK3. Also, mSCORE EULAR 2015/2016 showed the same discrimination ability as SCORE, although the percentage of predicted events was clearly higher than the percentage of actual events. SCORE2 also had a strong discrimination capacity according to CV risk. Combining QRISK3 with any other scale improved the model. This was especially true for the combination of QRISK3 and SCORE2 which achieved the lowest AIC (406.70) and BIC (415.66), so this combination would be the best predictive model.

CONCLUSIONS

In patients from the Spanish CARMA project, the four algorithms tested accurately discriminated those AS patients with higher CV risk and those with lower CV risk. Moreover, a model that includes QRISK3 and SCORE2 combined the best discrimination ability of QRISK3 with the best calibration of SCORE2.

Entry point of machine learning in axial spondyloarthritis

Axial spondyloarthritis (axSpA) is a globally prevalent and challenging autoimmune disease. Characterised by insidious onset and slow progression, the absence of specific clinical manifestations and biomarkers often leads to misdiagnosis, thereby complicating early detection and diagnosis of axSpA. Furthermore, the high heterogeneity of axSpA, its complex pathogenesis and the lack of specific drugs means that traditional classification standards and treatment guidelines struggle to meet the demands of personalised treatment. Recently, machine learning (ML) has seen rapid advancements in the medical field. By integrating large-scale data with diverse algorithms and using multidimensional data, such as patient medical records, laboratory examinations, radiological data, drug usage and molecular biology information, ML can be modelled based on real-world clinical issues. This enables the diagnosis, stratification, therapeutic efficacy prediction and prognostic evaluation of axSpA, positioning it as an emerging research topic. This study explored the application and progression of ML in the diagnosis and therapy of axSpA from five perspectives: early diagnosis, stratification, disease monitoring, drug efficacy evaluation and comorbidity prediction. This study aimed to provide a novel direction for exploring rational diagnostic and therapeutic strategies for axSpA.

Increased Prevalence of Headaches and Migraine in Patients with Psoriatic Arthritis and Axial Spondyloarthritis: Insights from an Italian Cohort Study

BACKGROUND

Psoriatic arthritis (PsA) and axial spondyloarthritis (axSpA) are inflammatory diseases with shared genetic backgrounds and clinical comorbidities. Headache, a common global health issue, affects over 50% of adults and encompasses various types, including migraine, tension-type, and cluster headaches. Migraine, the most prevalent, recurrent, and disabling type, is often associated with other medical conditions such as depression, epilepsy, and psoriasis, but little is known about the relationship between autoimmune disease and the risk of migraine.

METHODS

A cross-sectional study was conducted from July to November 2022, enrolling 286 participants, including 216 with PsA, 70 with axSpA, and 87 healthy controls.

RESULTS

Headache prevalence was significantly higher in the PsA (39.81%) and axSpA (45.71%) patients compared to the healthy controls. The prevalence of migraine without aura was also significantly higher in both the PsA (18.52%) and axSpA (28.57%) groups compared to the healthy controls.

CONCLUSIONS

These findings underscore the high burden of headache and migraine in PsA and axSpA participants, highlighting the need for improved management and treatment strategies for these patients.

Artificial intelligence-based preventive, personalized and precision medicine for cardiovascular disease/stroke risk assessment in rheumatoid arthritis patients: a narrative review

The challenges associated with diagnosing and treating cardiovascular disease (CVD)/Stroke in Rheumatoid arthritis (RA) arise from the delayed onset of symptoms. Existing clinical risk scores are inadequate in predicting cardiac events, and conventional risk factors alone do not accurately classify many individuals at risk. Several CVD biomarkers consider the multiple pathways involved in the development of atherosclerosis, which is the primary cause of CVD/Stroke in RA. To enhance the accuracy of CVD/Stroke risk assessment in the RA framework, a proposed approach involves combining genomic-based biomarkers (GBBM) derived from plasma and/or serum samples with innovative non-invasive radiomic-based biomarkers (RBBM), such as measurements of synovial fluid, plaque area, and plaque burden. This review presents two hypotheses: (i) RBBM and GBBM biomarkers exhibit a significant correlation and can precisely detect the severity of CVD/Stroke in RA patients. (ii) Artificial Intelligence (AI)-based preventive, precision, and personalized (aiP3) CVD/Stroke risk AtheroEdge™ model (AtheroPoint™, CA, USA) that utilizes deep learning (DL) to accurately classify the risk of CVD/stroke in RA framework. The authors conducted a comprehensive search using the PRISMA technique, identifying 153 studies that assessed the features/biomarkers of RBBM and GBBM for CVD/Stroke. The study demonstrates how DL models can be integrated into the AtheroEdge™-aiP3 framework to determine the risk of CVD/Stroke in RA patients. The findings of this review suggest that the combination of RBBM with GBBM introduces a new dimension to the assessment of CVD/Stroke risk in the RA framework. Synovial fluid levels that are higher than normal lead to an increase in the plaque burden. Additionally, the review provides recommendations for novel, unbiased, and pruned DL algorithms that can predict CVD/Stroke risk within a RA framework that is preventive, precise, and personalized.

Cardiovascular risk in axial spondyloarthritis-a systematic review

Cardiovascular manifestations are common in patients suffering axial spondyloarthritis and can result in substantial morbidity and disease burden. To give an overview of this important aspect of axial spondyloarthritis, we conducted a systematic literature search of all articles published between January 2000 and 25 May 2023 on cardiovascular manifestations. Using PubMed and SCOPUS, 123 out of 6792 articles were identified and included in this review. Non-radiographic axial spondyloarthritis seems to be underrepresented in studies; thus, more evidence for ankylosing spondylitis exists. All in all, we found some traditional risk factors that led to higher cardiovascular disease burden or major cardiovascular events. These specific risk factors seem to be more aggressive in patients with spondyloarthropathies and have a strong connection to high or long-standing disease activity. Since disease activity is a major driver of morbidity, diagnostic, therapeutic, and lifestyle interventions are crucial for better outcomes. Key Points • Several studies on axial spondyloarthritis and associated cardiovascular diseases have been conducted in the last few years addressing risk stratification of these patients including artificial intelligence. • Recent data suggest distinct manifestations of cardiovascular disease entities among men and women which the treating physician needs to be aware of. • Rheumatologists need to screen axial spondyloarthritis patients for emerging cardiovascular disease and should aim at reducing traditional risk factors like hyperlipidemia, hypertension, and smoking as well as disease activity.

ASNET: A Novel AI Framework for Accurate Ankylosing Spondylitis Diagnosis from MRI

BACKGROUND

Ankylosing spondylitis (AS) is a chronic, painful, progressive disease usually seen in the spine. Traditional diagnostic methods have limitations in detecting the early stages of AS. The early diagnosis of AS can improve patients' quality of life. This study aims to diagnose AS with a pre-trained hybrid model using magnetic resonance imaging (MRI).

MATERIALS AND METHODS

In this research, we collected a new MRI dataset comprising three cases. Furthermore, we introduced a novel deep feature engineering model. Within this model, we utilized three renowned pretrained convolutional neural networks (CNNs): DenseNet201, ResNet50, and ShuffleNet. Through these pretrained CNNs, deep features were generated using the transfer learning approach. For each pretrained network, two feature vectors were generated from an MRI. Three feature selectors were employed during the feature selection phase, amplifying the number of features from 6 to 18 (calculated as 6 × 3). The k-nearest neighbors (kNN) classifier was utilized in the classification phase to determine classification results. During the information phase, the iterative majority voting (IMV) algorithm was applied to secure voted results, and our model selected the output with the highest classification accuracy. In this manner, we have introduced a self-organized deep feature engineering model.

RESULTS

We have applied the presented model to the collected dataset. The proposed method yielded 99.80%, 99.60%, 100%, and 99.80% results for accuracy, recall, precision, and F1-score for the collected axial images dataset. The collected coronal image dataset yielded 99.45%, 99.20%, 99.70%, and 99.45% results for accuracy, recall, precision, and F1-score, respectively. As for contrast-enhanced images, accuracy of 95.62%, recall of 80.72%, precision of 94.24%, and an F1-score of 86.96% were attained.

CONCLUSIONS

Based on the results, the proposed method for classifying AS disease has demonstrated successful outcomes using MRI. The model has been tested on three cases, and its consistently high classification performance across all cases underscores the model's general robustness. Furthermore, the ability to diagnose AS disease using only axial images, without the need for contrast-enhanced MRI, represents a significant advancement in both healthcare and economic terms.

Exploring sex disparities in cardiovascular disease risk factors using principal component analysis and latent class analysis techniques

BACKGROUND

This study used machine learning techniques to evaluate cardiovascular disease risk factors (CVD) and the relationship between sex and these risk factors. The objective was pursued in the context of CVD being a major global cause of death and the need for accurate identification of risk factors for timely diagnosis and improved patient outcomes. The researchers conducted a literature review to address previous studies' limitations in using machine learning to assess CVD risk factors.

METHODS

This study analyzed data from 1024 patients to identify the significant CVD risk factors based on sex. The data comprising 13 features, such as demographic, lifestyle, and clinical factors, were obtained from the UCI repository and preprocessed to eliminate missing information. The analysis was performed using principal component analysis (PCA) and latent class analysis (LCA) to determine the major CVD risk factors and to identify any homogeneous subgroups between male and female patients. Data analysis was performed using XLSTAT Software. This software provides a comprehensive suite of tools for Data Analysis, Machine Learning, and Statistical Solutions for MS Excel.

RESULTS

This study showed significant sex differences in CVD risk factors. 8 out of 13 risk factors affecting male and female patients found that males and females share 4 of the eight risk factors. Identified latent profiles of CVD patients, suggesting the presence of subgroups among CVD patients. These findings provide valuable insights into the impact of sex differences on CVD risk factors. Moreover, they have important implications for healthcare professionals, who can use this information to develop individualized prevention and treatment plans. The results highlight the need for further research to elucidate these disparities better and develop more effective CVD prevention measures.

CONCLUSIONS

The study explored the sex differences in the CVD risk factors and the presence of subgroups among CVD patients using ML techniques. The results revealed sex-specific differences in risk factors and the existence of subgroups among CVD patients, thus providing essential insights for personalized prevention and treatment plans. Hence, further research is necessary to understand these disparities better and improve CVD prevention.

High inflammatory burden predicts cardiovascular events in patients with axial spondyloarthritis: a long-term follow-up study

Background

Axial spondyloarthritis (axSpA) patients are at higher risk of cardiovascular (CV) disease (CVD) than the general population, partly due to consequences of inflammation or its treatment. But relationship between inflammation in axSpA and cardiovascular events (CVE) is unknown.

Objectives

To examine whether inflammatory burden over time can predict CVE independent of baseline CV risk factors in axSpA patients.

Design

A cohort analysis was performed in patients who had been recruited since January 2001. The primary outcome was a first CVE occurring between January 2001 and December 2020.

Methods

Three CVD risk scores were computed at baseline. The performance of the original and modified (*1.5 multiplication factor) CV risk algorithms were assessed. Time-varying Cox proportional hazard models and Kaplan-Meier survival analysis were used to assess whether inflammatory burden (Bath ankylosing spondylitis disease activity index [BASDAI] and inflammatory markers), nonsteroidal anti-inflammatory drugs (NSAIDs) and disease modifying antirheumatic drugs (DMARDs) can predict the development of first CVE.

Results

463 patients (35 [26-45] years, male: 360 [77.8%]) were recruited. After a median follow-up of 12 (7-19) years, 61 patients (13.2%) experienced a first CVE. Traditional/modified CV risk scores underestimated CV risk. Erythrocyte sedimentation rate (ESR) ⩾ 20 mm/h was associated with a significantly higher risk of CVE during follow-up (HR: 2.07, 95%CI [1.10, 3.98], p = 0.008). Active disease as indicated by a rising BASDAI also showed positive trend towards a higher risk of developing CVE over time. After adjusting for CV risk scores in the multivariable models, high ESR level (ESR ⩾ 20 mm/h) over time remained significantly associated with a higher risk of developing CV events.

Conclusion

Increased inflammatory burden as reflected by elevated ESR levels (ESR ⩾ 20) was associated with increased risk of CVE, while the use of NSAIDs and DMARDs were not.

The comparison of cardiovascular disease risk prediction scores and evaluation of subclinical atherosclerosis in rheumatoid arthritis: a cross-sectional study

OBJECTIVES

Primary objectives estimated prevalence of traditional cardiovascular disease (CVD) risk factors and compared different CVD risk prediction algorithms in an Indian rheumatoid arthritis (RA) population. Secondary objectives evaluated associations between carotid intima-media thickness (CIMT) and subclinical atherosclerosis (SCA) with CVD risk factors and CVD risk scores.

METHODS

The presence of CVD risk factors were recorded, and 10-year CVD risk was predicted using Framingham risk scoring (FRS) using lipids (FRS-Lipids), FRS using body mass index (FRS-BMI), QRISK-2, SCORE, and the algorithm recommended by ACC/AHA (ASCVD). CIMT was measured on the far-wall of the common carotid artery. Subclinical atherosclerosis was defined as CIMT > 0.9 mm or the presence of carotid plaque.

RESULTS

A total of 332 patents were enrolled, 12% had diabetes mellitus, 21.4% hypertension, and 6.9% were current/past smokers. Proportions of RA with predicted 10-year CVD risk > 10% varied from 16.2 to 41.9% between scores. Highest magnitude of risk was predicted by FRS-BMI. Agreement between scores in predicting risk was moderate in general. Mean CIMT was 0.70 ± 0.15 mm. Age, male sex, and extra-articular manifestations associated with greater CIMT. All risk scores except SCORE moderately correlated with CIMT. About one-seventh had SCA defined as CIMT > 0.9 mm or the presence of carotid plaques, associated with increasing age, male gender, or higher ratio of total cholesterol to high-density lipoprotein cholesterol. ASCVD and QRISK-2 scores had maximum area under curve for distinguishing SCA.

CONCLUSION

Individual CVD risk scores predict 10-year CVD risk differently in Indian patients with RA, and require validation for predicting hard end points (CVD events, mortality). Key Points • Diabetes mellitus and hypertension are the most prevalent cardiovascular disease risk factors in Indian patients with RA. • Individual cardiovascular risk prediction scores predict risk differently in Indian patients with RA, highest risk being predicted by the FRS-BMI. • Carotid intima-media thickness in RA associated with increasing age, male sex and extra-articular manifestations. • 14% RA had subclinical atherosclerosis, associated with increasing age, male sex, and higher total cholesterol to HDL-C ratio, best distinguished by ASCVD and QRISK-2 scores.

Persistence of C-reactive protein increased levels and high disease activity are predictors of cardiovascular disease in patients with axial spondyloarthritis

An accurate prediction of cardiovascular (CV) risk in patients with Axial Spondyloarthritis (axSpA) is a strong unmet need, as CV risk algorithms poorly perform in these subjects. The aim of this study was to establish whether the persistence of high C-reactive protein (CRP) and high disease activity may be considered predictive factors of CVD in axSpA. 295 patients without personal history of CVD, were consecutively enrolled in this study. To evaluate the relationship between CV events occurrence (fatal and non-fatal) and the persistence of increased CRP levels, ASDAS (Ankylosing Spondylitis Disease Activity Score) > 2.1, and BASDAI (Bath Ankylosing Spondylitis Disease Activity) > 4 during the follow-up, univariable and multivariable Cox Proportional Hazard Models have been performed. During follow-up (we analyzed 10-years retrospective data), 23 patients had a CV event. Multivariable Cox Proportional Hazard Models showed a strong association between CV event and the persistency of increased CRP levels (namely, percentage of visits in which CRP levels were increased) (HR = 1.03; 95%CI 1.015-1.045; p < 0.001), of ASDAS > 2.1 (HR = 1.014, 95%CI 1.000-1.028, p = 0.047), and of BASDAI > 4 (HR 1.019, 95%CI 1.006-1.033, p = 0.006) during follow-up, after adjustment for age, sex, and diabetes. This study suggests that persistence of increased CRP levels and high disease activity may be considered biomarkers to identify those axSpA patients at higher risk of CVD. Innovative axSpA-specific CV risk score, including these variables, have to be developed.

Therapeutic Targets for Ankylosing Spondylitis - Recent Insights and Future Prospects

Ankylosing spondylitis (AS) is a chronic inflammatory rheumatic disease belonging to the axial spondyloarthritis (axSpA), a group of diseases that affects the axial skeleton and causes severe pain and disability. An early diagnosis and appropriate treatment can reduce the severity of the disease and the risk of progression. TNF-α inhibitors demonstrated efficacy and effectiveness in axSpA patients by reducing disease activity, minimizing inflammation and improving the quality of life. More recently, new insights in pathogenesis of axSpA, including the discovery of the role of IL-23/IL-17 axis and intracellular pathways, led to the development of new biologics and small molecules that improve our therapeutic armamentarium. New alternatives are also being soon available. The aim of this paper is to narratively review the recent insights and future prospects in the treatment of AS and, more in general, axSpA.

Cardiovascular risk prediction: from classical statistical methods to machine learning approaches

Nowadays, cardiovascular risk prediction scores are commonly used in primary prevention settings. Estimating the cardiovascular individual risk is of crucial importance for effective patient management and optimal therapy identification, with relevant consequences on secondary prevention settings. To reach this goal, a plethora of risk scores have been developed in the past, most of them assuming that each cardiovascular risk factor is linearly dependent on the outcome. However, the overall accuracy of these methods often remains insufficient to solve the problem at hand. In this scenario, machine learning techniques have repeatedly proved successful in improving cardiovascular risk predictions, being able to capture the non-linearity present in the data. In this concern, we present a detailed discussion concerning the application of classical versus machine learning-based cardiovascular risk scores in the clinical setting. This review aimed to give an overview of the current risk scores based on classical statistical approaches and machine learning techniques applied to predict the risk of several cardiovascular diseases, comparing them, discussing their similarities and differences, and highlighting their main drawbacks to aid the physician having a more critical understanding of these tools.

Cardio-Rheumatology: Prevention of Cardiovascular Disease in Inflammatory Disorders

Inflammation plays a well-established role in the development and progression of atherosclerosis. Individuals exposed to chronic inflammation are at an increased risk of developing cardiovascular disease, including coronary artery disease and heart failure, independent of associated traditional risk factors. Traditional risk assessment tools and calculators underestimate the true cardiac risk in this population. In addition to this, there is a lack of awareness on the association between inflammation and cardiovascular disease. These factors lead to undertreatment in terms of preventive cardiac care in patients with chronic inflammatory disease.

Lifestyle modification and inflammation in people with axial spondyloarthropathy-A scoping review

INTRODUCTION

People with axial spondyloarthritis (AS) have an inflammatory profile, increasing the risk of hypertension, type 2 diabetes, obesity, and dyslipidaemia. Consequently, AS is linked with co-morbidities such as cardiovascular disease (CVD). Physical inactivity, diet, smoking, alcohol consumption, and obesity influence inflammation, but knowledge of the interaction between these with inflammation, disease activity, and CVD risk in AS is dominated by cross-sectional research.

METHODS

A review of the literature was conducted between July 2020 and December 2021. The focus of the scoping review is to summarise longitudinal and randomised control trials in humans to investigate how tracking or modifying lifestyle influences inflammation and disease burden in patients with AS. KEY MESSAGES: (1) Lifestyle modifications, especially increased physical activity (PA), exercise, and smoking cessation, are critical in managing AS. (2) Smoking is negatively associated with patient reported outcome measures with AS, plus pharmaceutical treatment adherence, but links with structural radiographic progression are inconclusive. (3) Paucity of data warrant structured studies measuring inflammatory cytokine responses to lifestyle modification in AS.

CONCLUSION

Increased PA, exercise, and smoking cessation should be supported at every given opportunity to improve health outcomes in patients with AS. The link between smoking and radiographic progression needs further investigation. Studies investigating the longitudinal effect of body weight, alcohol, and psychosocial factors on disease activity and physical function in patients with AS are needed. Given the link between inflammation and AS, future studies should also incorporate markers of chronic inflammation beyond the standard C-reactive protein and erythrocyte sedimentation rate measurements.

Your neighborhood matters: A machine-learning approach to the geospatial and social determinants of health in 9-1-1 activated chest pain

Healthcare disparities in the initial management of patients with acute coronary syndrome (ACS) exist. Yet, the complexity of interactions between demographic, social, economic, and geospatial determinants of health hinders incorporating such predictors in existing risk stratification models. We sought to explore a machine-learning-based approach to study the complex interactions between the geospatial and social determinants of health to explain disparities in ACS likelihood in an urban community. This study identified consecutive patients transported by Pittsburgh emergency medical service for a chief complaint of chest pain or ACS-equivalent symptoms. We extracted demographics, clinical data, and location coordinates from electronic health records. Median income was based on US census data by zip code. A random forest (RF) classifier and a regularized logistic regression model were used to identify the most important predictors of ACS likelihood. Our final sample included 2400 patients (age 59 ± 17 years, 47% Females, 41% Blacks, 15.8% adjudicated ACS). In our RF model (area under the receiver operating characteristic curve of 0.71 ± 0.03) age, prior revascularization, income, distance from hospital, and residential neighborhood were the most important predictors of ACS likelihood. In regularized regression (akaike information criterion = 1843, bayesian information criterion = 1912, χ²  = 193, df = 10, p < 0.001), residential neighborhood remained a significant and independent predictor of ACS likelihood. Findings from our study suggest that residential neighborhood constitutes an upstream factor to explain the observed healthcare disparity in ACS risk prediction, independent from known demographic, social, and economic determinants of health, which can inform future work on ACS prevention, in-hospital care, and patient discharge.

An introduction to machine learning and analysis of its use in rheumatic diseases

Machine learning (ML) is a computerized analytical technique that is being increasingly employed in biomedicine. ML often provides an advantage over explicitly programmed strategies in the analysis of multidimensional information by recognizing relationships in the data that were not previously appreciated. As such, the use of ML in rheumatology is increasing, and numerous studies have employed ML to classify patients with rheumatic autoimmune inflammatory diseases (RAIDs) from medical records and imaging, biometric or gene expression data. However, these studies are limited by sample size, the accuracy of sample labelling, and absence of datasets for external validation. In addition, there is potential for ML models to overfit or underfit the data and, thereby, these models might produce results that cannot be replicated in an unrelated dataset. In this Review, we introduce the basic principles of ML and discuss its current strengths and weaknesses in the classification of patients with RAIDs. Moreover, we highlight the successful analysis of the same type of input data (for example, medical records) with different algorithms, illustrating the potential plasticity of this analytical approach. Altogether, a better understanding of ML and the future application of advanced analytical techniques based on this approach, coupled with the increasing availability of biomedical data, may facilitate the development of meaningful precision medicine for patients with RAIDs.

Potential relation of cardiovascular risk factors to disease activity in patients with axial spondyloarthritis

Background:

Axial spondyloarthritis (axSpA) patients are known to have a higher prevalence of several comorbidities, including, among others, an increased risk of atherosclerosis, hypertension, dyslipidemia, and diabetes. The purpose of the present study was to determine whether the sum of traditional cardiovascular (CV) risk factors is related to disease characteristics, such as disease activity, in patients with axSpA.

Methods:

A cross-sectional study that encompassed 804 patients with axSpA was conducted. Patients were assessed for the presence of five traditional CV risk factors (diabetes mellitus, dyslipidemia, hypertension, obesity, and smoking status), and disease activity measurements. A multivariable regression analysis was performed to evaluate whether the number of classic CV risk factors was independently associated with specific features of the disease, to include disease activity.

Results:

A multivariable analysis showed that Ankylosing Spondylitis Disease Activity Score–C reactive protein (ASDAS-CRP) activity score was significantly higher in patients with 1 [beta coefficient 0.3 (95% confidence interval (CI) 0.1–0.5), p = 0.001] and ⩾2 [beta coefficient 0.5 (95% CI 0.3–0.7), p = 0.000] CV risk factors compared with those without CV risk factors. Similarly, patients with 1 [OR 2.00 (95%CI 0.99–4.02), p = 0.053] and ⩾2 [OR 3.39 (95%CI 1.82–6.31), p = 0.000] CV risk factors had a higher odds ratio for the presence of high disease activity compared with the zero CV category. The Bath Ankylosing Spondylitis Disease Activity Index (BASDAI) activity score was significantly associated with the number of CV risk factors, being higher in patients with more CV risk factors. These relationships showed a CV risk factor-dependent effect being beta coefficients and ORs higher for the effect of ⩾2 over 1 CV risk factor.

Conclusion:

Among patients with axSpA, as the number of traditional CV risk factors increased, disease activity similarly increases in an independent manner.

Cardiovascular risk estimation in young patients with ankylosing spondylitis: A new model based on a prospective study in Constanta County, Romania

Cardiovascular (CV) risk assessment charts are useful in establishing a patient therapeutic plan, but the most commonly used charts have essential limitations when applied to special populations. Our aim was to determine whether the Systematic Coronary Risk Evaluation (SCORE) chart underestimates the CV risk in young patients with ankylosing spondylitis (AS) and to promote the necessity of new risk assessment models. We conducted a prospective study in Constanta County, Romania including 70 consecutive patients ≤50 years of age, previously diagnosed with AS, without a history of established CV disease, diabetes mellitus and chronic kidney disease. We estimated the CV risk using SCORE based on total cholesterol, applied for a high-risk population, such as the Romanian population. Estimation of CV risk was also conducted with the relative risk (RR) chart, considering the following variables: Smoking, systolic blood pressure and total cholesterol. The majority of patients (n=46, 65.71%) had low risk according to the SCORE chart and only 24 (34.28%) were found to have moderate CV risk; none of them with high or very high CV risk. Ten patients (21.74%) of the 46 who were considered to have a low risk based on the SCORE system presented with carotid plaques. Twelve patients (50%) of the remaining 24 with moderate CV risk were found to have carotid plaques. According to 2016 'European Society of Cardiology' (ESC) guidelines, 22 of all 70 patients were at high/very high CV risk due to the presence of carotid plaques. Comparing the RR chart with carotid plaque detection, only 4 out of 30 (13.3%) patients with RR=1 had carotid plaques; the frequency was higher in those with RR>1. Our results attested that the SCORE system underestimates the risk in patients with carotid plaques. Carotid ultrasound provided a more heightened sensitivity of the RR chart. C-reactive protein (CRP) >3 mg/dl is associated with RR>1, making this chart a better CV risk predictive system in this particular category of patients.