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.

Multicenter Study on COVID-19 Lung Computed Tomography Segmentation with varying Glass Ground Opacities using Unseen Deep Learning Artificial Intelligence Paradigms: COVLIAS 1.0 Validation.

Variations in COVID-19 lesions such as glass ground opacities (GGO), consolidations, and crazy paving can compromise the ability of solo-deep learning (SDL) or hybrid-deep learning (HDL) artificial intelligence (AI) models in predicting automated COVID-19 lung segmentation in Computed Tomography (CT) from unseen data leading to poor clinical manifestations. As the first study of its kind, "COVLIAS 1.0-Unseen" proves two hypotheses, (i) contrast adjustment is vital for AI, and (ii) HDL is superior to SDL. In a multicenter study, 10,000 CT slices were collected from 72 Italian (ITA) patients with low-GGO, and 80 Croatian (CRO) patients with high-GGO. Hounsfield Units (HU) were automatically adjusted to train the AI models and predict from test data, leading to four combinations-two Unseen sets: (i) train-CRO:test-ITA, (ii) train-ITA:test-CRO, and two Seen sets: (iii) train-CRO:test-CRO, (iv) train-ITA:test-ITA. COVILAS used three SDL models: PSPNet, SegNet, UNet and six HDL models: VGG-PSPNet, VGG-SegNet, VGG-UNet, ResNet-PSPNet, ResNet-SegNet, and ResNet-UNet. Two trained, blinded senior radiologists conducted ground truth annotations. Five types of performance metrics were used to validate COVLIAS 1.0-Unseen which was further benchmarked against MedSeg, an open-source web-based system. After HU adjustment for DS and JI, HDL (Unseen AI) > SDL (Unseen AI) by 4% and 5%, respectively. For CC, HDL (Unseen AI) > SDL (Unseen AI) by 6%. The COVLIAS-MedSeg difference was < 5%, meeting regulatory guidelines.Unseen AI was successfully demonstrated using automated HU adjustment. HDL was found to be superior to SDL.

REVERSIBILITY OF LIPOATROPHY IN HIV-INFECTED PATIENTS TAKING ANTIRETROVIRAL THERAPY: A COHORT STUDY WITH ULTRASOUND ASSESSMENT.

The aim of this study was to characterize and compare changes in subcutaneous fat in the malar, brachial and crural region in a cohort of HIV-infected patients taking antiretroviral therapy. This prospective longitudinal study included 77 patients who were selected from the initial cohort evaluated in 2007 and 2008. We examined reversibility of lipoatrophy measured by ultrasound over at least five-year period and factors related to its reversibility. All 46 patients who used stavudine switched from stavudine to another combination. Of 58 patients on zidovudine, 16 (28%) were on a zidovudine based regimen at the second follow up. There was evidence for subcutaneous fat increase in the malar area (p<0.001) and no increase in the brachial and crural areas. Patients who were smokers and had poor adherence to the Mediterranean diet had a thinner malar area at the follow up measurement (p=0.030) and smaller increase in subcutaneous malar fat compared to others (p=0.040). Our study suggested that modest increase of subcutaneous fat in malar area coincided with stopping stavudine and fewer usage of zidovudine. Lifestyle with non-adherence to the Mediterranean diet and smoking were associated with a smaller increase in subcutaneous malar fat.

A Review on Joint Carotid Intima-Media Thickness and Plaque Area Measurement in Ultrasound for Cardiovascular/Stroke Risk Monitoring: Artificial Intelligence Framework.

Cardiovascular diseases (CVDs) are the top ten leading causes of death worldwide. Atherosclerosis disease in the arteries is the main cause of the CVD, leading to myocardial infarction and stroke. The two primary image-based phenotypes used for monitoring the atherosclerosis burden is carotid intima-media thickness (cIMT) and plaque area (PA). Earlier segmentation and measurement methods were based on ad hoc conventional and semi-automated digital imaging solutions, which are unreliable, tedious, slow, and not robust. This study reviews the modern and automated methods such as artificial intelligence (AI)-based. Machine learning (ML) and deep learning (DL) can provide automated techniques in the detection and measurement of cIMT and PA from carotid vascular images. Both ML and DL techniques are examples of supervised learning, i.e., learn from "ground truth" images and transformation of test images that are not part of the training. This review summarizes (1) the evolution and impact of the fast-changing AI technology on cIMT/PA measurement, (2) the mathematical representations of ML/DL methods, and (3) segmentation approaches for cIMT/PA regions in carotid scans based for (a) region-of-interest detection and (b) lumen-intima and media-adventitia interface detection using ML/DL frameworks. AI-based methods for cIMT/PA segmentation have emerged for CVD/stroke risk monitoring and may expand to the recommended parameters for atherosclerosis assessment by carotid ultrasound.

Human Alveolar Echinococcosis, Croatia.

Alveolar echinococcosis is a parasitic disease caused by the tapeworm larval stage of Echinococcus multilocularis. This zoonotic disease has not been known to occur in Croatia. We report a confirmed case of human alveolar echinococcosis in a patient in Croatia who had never visited a known E. multilocularis-endemic area.

Integration of cardiovascular risk assessment with COVID-19 using artificial intelligence.

Artificial Intelligence (AI), in general, refers to the machines (or computers) that mimic "cognitive" functions that we associate with our mind, such as "learning" and "solving problem". New biomarkers derived from medical imaging are being discovered and are then fused with non-imaging biomarkers (such as office, laboratory, physiological, genetic, epidemiological, and clinical-based biomarkers) in a big data framework, to develop AI systems. These systems can support risk prediction and monitoring. This perspective narrative shows the powerful methods of AI for tracking cardiovascular risks. We conclude that AI could potentially become an integral part of the COVID-19 disease management system. Countries, large and small, should join hands with the WHO in building biobanks for scientists around the world to build AI-based platforms for tracking the cardiovascular risk assessment during COVID-19 times and long-term follow-up of the survivors.

Atypical adult-onset subacute sclerosing panencephalitis.

Although subacute sclerosing panencephalitis is almost exclusively a childhood disease, it can occur in adults as well. We present an atypical case of adult-onset subacute sclerosing panencephalitis. The disease was characterized by prolonged insidious course followed by accelerated and aggressive phase, atypical EEG findings, and absence of myoclonic jerks. The diagnostic and treatment-related pitfalls are discussed.

Comparison of four international cardiovascular disease prediction models and the prevalence of eligibility for lipid lowering therapy in HIV infected patients on antiretroviral therapy.

AIM: To compare four cardiovascular disease (CVD) risk models and to assess the prevalence of eligibility for lipid lowering therapy according to the 2013 American College of Cardiology/American Heart Association (ACC/AHA) guidelines, European AIDS Clinical Society Guidelines (EACS), and European Society of Cardiology and the European Atherosclerosis Society (ESC/EAS) guidelines for CVD prevention in HIV infected patients on antiretroviral therapy. METHODS: We performed a cross-sectional analysis of 254 consecutive HIV infected patients aged 40 to 79 years who received antiretroviral therapy for at least 12 months. The patients were examined at the HIV-treatment centers in Belgrade and Zagreb in the period February-April 2011. We compared the following four CVD risk models: the Framingham risk score (FRS), European Systematic Coronary Risk Evaluation Score (SCORE), the Data Collection on Adverse Effects of Anti-HIV Drugs study (DAD), and the Pooled Cohort Atherosclerotic CVD risk (ASCVD) equations. RESULTS: The prevalence of current smoking was 42.9%, hypertension 31.5%, and hypercholesterolemia (>6.2 mmol/L) 35.4%; 33.1% persons were overweight, 11.8% were obese, and 30.3% had metabolic syndrome. A high 5-year DAD CVD risk score (>5%) had substantial agreement with the elevated (≥7.5%) 10-year ASCVD risk equation score (kappa=0.63). 21.3% persons were eligible for statin therapy according to EACS (95% confidence intervals [CI], 16.3% to 27.4%), 25.6% according to ESC/EAS (95% CI, 20.2% to 31.9%), and 37.9% according to ACC/AHA guidelines (95% CI, 31.6 to 44.6%). CONCLUSION: In our sample, agreement between the high DAD CVD risk score and other CVD high risk scores was not very good. The ACC/AHA guidelines would recommend statins more often than ESC/EAS and EACS guidelines. Current recommendations on treatment of dyslipidemia should be applied with caution in the HIV infected population.

Validation of Diagnostic Accuracy and Disease Severity Correlation of Chest Computed Tomography Severity Scores in Patients with COVID-19 Pneumonia.

The aim of our study was to establish and compare the diagnostic accuracy and clinical applicability of published chest CT severity scoring systems used for COVID-19 pneumonia assessment and to propose the most efficient CT scoring system with the highest diagnostic performance and the most accurate prediction of disease severity. This retrospective study included 218 patients with PCR-confirmed SARS-CoV-2 infection and chest CT. Two radiologists blindly evaluated CT scans and calculated nine different CT severity scores (CT SSs). The diagnostic validity of CT SSs was tested by ROC analysis. Interobserver agreement was excellent (intraclass correlation coefficient: 0.982-0.995). The predominance of either consolidations or a combination of consolidations and ground-glass opacities (GGOs) was a predictor of more severe disease (both p < 0.005), while GGO prevalence alone was not. Correlation between all CT SSs was high, ranging from 0.848 to 0.971. CT SS 30 had the highest diagnostic accuracy (AUC = 0.805) in discriminating mild from severe COVID-19 disease compared to all the other proposed scoring systems (AUC range 0.755-0.788). In conclusion, CT SS 30 achieved the highest diagnostic accuracy in predicting the severity of COVID-19 disease while maintaining simplicity, reproducibility, and applicability in complex clinical settings.

Ultrasound measurements of carotid intima-media thickness and plaque in HIV-infected patients on the Mediterranean diet.

AIM: To evaluate the influence of food habits, specifically adherence to the Mediterranean diet, on carotid intima-media thickness (CIMT) and the presence of plaques in HIV-infected patients taking antiretroviral therapy (ART) and non-HIV-infected participants and to determine if HIV infection contributes independently to subclinical atherosclerosis. METHODS: We conducted a cross-sectional study of 110 HIV-infected patients on ART and 131 non-HIV-infected participants at the University Hospital for Infectious Diseases in Zagreb, Croatia, from 2009-2011. CIMT measurement and determination of carotid plaque presence was detected by ultrasound. Adherence to the Mediterranean diet was assessed by a 14-point food-item questionnaire. Subclinical atherosclerosis was defined by CIMT≥0.9 mm or ≥1 carotid plaque. RESULTS: In HIV-infected patients, subclinical atherosclerosis was associated with older age (Plt;0.001; Mann-Whitney test), higher body mass index (P=0.051; Mann-Whitney test), hypertension (Plt;0.001; χ(2) test), and a lower Mediterranean diet score (P=0.035; Mann-Whitney test), and in non-HIV-infected participants with older age (P lt; 0.001; Mann-Whitney test) and hypertension (P=0.006; χ(2) test). Multivariate analysis showed that decreased adherence to the Mediterranean diet was associated with higher odds of subclinical atherosclerosis (odds ratio [OR] 2.28, 95% confidence interval [CI] 1.10-4.72, P=0.027) as was current smoking (OR 2.86, 95% CI 1.28-6.40), hypertension (OR 3.04, 95% CI 1.41-6.57), and male sex (OR 2.35, 95% CI 0.97-5.70). There was a significant interaction of age and HIV status, suggesting that older HIV-infected patients had higher odds of subclinical atherosclerosis than controls (OR 3.28, 95% CI 1.24-8.71, P=0.017 at the age of 60 years). CONCLUSION: We confirmed the association between lower adherence to the Mediterranean diet and increased risk of subclinical atherosclerosis and found that treated HIV infection was a risk factor for subclinical atherosclerosis in older individuals.

Primary uterine cervical cancer: correlation of preoperative magnetic resonance imaging and clinical staging (FIGO) with histopathology findings.

The most commonly used staging system for cervical cancer is based on the International Federation of Gynaecology and Obstetrics (FIGO) staging system. Magnetic resonance imaging (MRI) has been accepted as the optimal tool for evaluation of the main prognostic factors and selection of therapeutic strategy. The purpose of this study was to compare the preoperative clinical examination FIGO staging findings with MRI and postoperative pathology report in females with primary cancer of the cervix. The study prospectively included 46 females consecutively hospitalized at the Department of Gynaecology and Obstetrics at the "Sestre milosrdnice" University Hospital Center in Zagreb. Interviews, clinical examination, transvaginal ultrasound and MRI were performed in all patients. In selected patients the surgical procedure was done and the correlation of clinical findings according to FIGO classifications, MRI and histopathological findings was completed. According to FIGO classification, positive clinical findings for stage IIA were found in 26/46 (55.5%) and stage IIB in 20/46 (44.5%)patients. FIGO MR modified classification confirmed stage IIA in 30/46 (66.6%) and stage IIB in 16/46 (33.4%) patients. Surgery (Wertheim radical hysterectomy with bilateral pelvic and selective para-aortic lymphadenectomy) was performed in 33/46 (71%) patients with clinically, MR, cytologically and pathohistologically confirmed findings of cervical cancer: 26 patients with IIA clinically FIGO stage and 7 with IIB stage. MRI examination proved better than clinical examination in staging of cervical carcinoma with 90.9% versus 79.0% accuracy rate. We suggest the application of the following MR protocol in all clinically staged FIGO IIA and IIB patients: T1W, T2WI and postcontrast dynamic T1WI after 3 and 60 seconds and after 5 minutes, performed on 1.5T MR machine.

Case Report: Amphotericin B and Mefloquine as a Salvage Treatment of Alveolar Echinococcosis.

Alveolar echinococcosis is an emerging zoonotic disease caused by the parasite Echinococcus multilocularis. Most patients are diagnosed at a late stage, when lifelong treatment with benzimidazoles is required to stop disease progression. However, for patients who do not tolerate benzimidazole therapy, there are no alternatives. Here, we present a patient with advanced alveolar echinococcosis who was successfully treated with amphotericin B deoxycholate and mefloquine as a rescue therapy after he developed albendazole intolerance.

Emergence of Echinococcus multilocularis in Central Continental Croatia: A Human Case Series and Update on Prevalence in Foxes.

Human alveolar echinococcosis (HAE), caused by the metacestode stage of Echinococcus multilocularis, has emerged in many European countries over the last two decades. Here, we report the first data on the new HAE focus with increasing incidence in central Croatia, describe its clinical presentation and outcomes in diagnosed patients, and provide an update on the prevalence and geographic distribution of Echinococcus multilocuaris in red foxes. After the initial case in 2017 from the eastern state border, from 2019 to 2022, five new autochthonous HAE cases were diagnosed, all concentrated in the Bjelovar-Bilogora County (the county incidence in 2019 and 2021: 0.98/105, in 2022: 2.94/105/year; prevalence for 2019-2022: 4.91/105). The age range among four female and two male patients was 37-67 years. The patients' liver lesions varied in size from 3.1 to 15.5 cm (classification range: P2N0M0-P4N1M0), and one patient had dissemination to the lungs. While there were no fatalities, postoperative complications in one patient resulted in liver transplantation. In 2018, the overall prevalence of red foxes was 11.24% (28/249). A new focus on HAE has emerged in central continental Croatia, with the highest regional incidence in Europe. Screening projects among residents and the implementation of veterinary preventive measures following the One Health approach are warranted.

Hantavirus Pulmonary Syndrome Caused by Puumala Orthohantavirus-A Case Report and Literature Review.

In this article, we report on a rare case of acute respiratory distress syndrome (ARDS) caused by the Puumala orthohantavirus (PUUV), which is typically associated with hemorrhagic fever with renal syndrome (HFRS). This is the first documented case of PUUV-associated ARDS in Southeast Europe. The diagnosis was confirmed by serum RT-PCR and serology and corroborated by phylogenetic analysis and chemokine profiling. The patient was a 23-year-old male from Zagreb, Croatia, who had recently traveled throughout Europe. He presented with fever, headache, abdominal pain, and sudden onset of ARDS. Treatment involved high-flow nasal cannula oxygen therapy and glucocorticoids, which resulted in a full recovery. A systematic literature review identified 10 cases of hantavirus pulmonary syndrome (HPS) caused by PUUV in various European countries and Turkey between 2002 and 2023. The median age of patients was 53 years (range 24-73), and six of the patients were male. Most patients were treated in intensive care units, but none received antiviral therapy targeting PUUV. Eight patients survived hospitalization. The presented case highlights the importance of considering HPS in the differential diagnosis of ARDS, even in areas where HFRS is the dominant form of hantavirus infection.

Cardiovascular disease/stroke risk stratification in deep learning framework: a review.

The global mortality rate is known to be the highest due to cardiovascular disease (CVD). Thus, preventive, and early CVD risk identification in a non-invasive manner is vital as healthcare cost is increasing day by day. Conventional methods for risk prediction of CVD lack robustness due to the non-linear relationship between risk factors and cardiovascular events in multi-ethnic cohorts. Few recently proposed machine learning-based risk stratification reviews without deep learning (DL) integration. The proposed study focuses on CVD risk stratification by the use of techniques mainly solo deep learning (SDL) and hybrid deep learning (HDL). Using a PRISMA model, 286 DL-based CVD studies were selected and analyzed. The databases included were Science Direct, IEEE Xplore, PubMed, and Google Scholar. This review is focused on different SDL and HDL architectures, their characteristics, applications, scientific and clinical validation, along with plaque tissue characterization for CVD/stroke risk stratification. Since signal processing methods are also crucial, the study further briefly presented Electrocardiogram (ECG)-based solutions. Finally, the study presented the risk due to bias in AI systems. The risk of bias tools used were (I) ranking method (RBS), (II) region-based map (RBM), (III) radial bias area (RBA), (IV) prediction model risk of bias assessment tool (PROBAST), and (V) risk of bias in non-randomized studies-of interventions (ROBINS-I). The surrogate carotid ultrasound image was mostly used in the UNet-based DL framework for arterial wall segmentation. Ground truth (GT) selection is vital for reducing the risk of bias (RoB) for CVD risk stratification. It was observed that the convolutional neural network (CNN) algorithms were widely used since the feature extraction process was automated. The ensemble-based DL techniques for risk stratification in CVD are likely to supersede the SDL and HDL paradigms. Due to the reliability, high accuracy, and faster execution on dedicated hardware, these DL methods for CVD risk assessment are powerful and promising. The risk of bias in DL methods can be best reduced by considering multicentre data collection and clinical evaluation.

Ensemble Deep Learning Derived from Transfer Learning for Classification of COVID-19 Patients on Hybrid Deep-Learning-Based Lung Segmentation: A Data Augmentation and Balancing Framework.

BACKGROUND AND MOTIVATION: Lung computed tomography (CT) techniques are high-resolution and are well adopted in the intensive care unit (ICU) for COVID-19 disease control classification. Most artificial intelligence (AI) systems do not undergo generalization and are typically overfitted. Such trained AI systems are not practical for clinical settings and therefore do not give accurate results when executed on unseen data sets. We hypothesize that ensemble deep learning (EDL) is superior to deep transfer learning (TL) in both non-augmented and augmented frameworks. METHODOLOGY: The system consists of a cascade of quality control, ResNet-UNet-based hybrid deep learning for lung segmentation, and seven models using TL-based classification followed by five types of EDL's. To prove our hypothesis, five different kinds of data combinations (DC) were designed using a combination of two multicenter cohorts-Croatia (80 COVID) and Italy (72 COVID and 30 controls)-leading to 12,000 CT slices. As part of generalization, the system was tested on unseen data and statistically tested for reliability/stability. RESULTS: Using the K5 (80:20) cross-validation protocol on the balanced and augmented dataset, the five DC datasets improved TL mean accuracy by 3.32%, 6.56%, 12.96%, 47.1%, and 2.78%, respectively. The five EDL systems showed improvements in accuracy of 2.12%, 5.78%, 6.72%, 32.05%, and 2.40%, thus validating our hypothesis. All statistical tests proved positive for reliability and stability. CONCLUSION: EDL showed superior performance to TL systems for both (a) unbalanced and unaugmented and (b) balanced and augmented datasets for both (i) seen and (ii) unseen paradigms, validating both our hypotheses.

Acute encephalopathy associated with Campylobacter jejuni enteritis.

We present for the first time a case of acute encephalopathy in an adult patient induced by Campylobacter jejuni enteritis. Possible pathogenic mechanisms and importance of neuropsychological testing in the assessment of infection-related encephalopathy are discussed.

Endoscopic Endonasal Surgery for a Pterygopalatine Fossa Hydatid Cyst.

Background: Cystic echinococcosis is a manifestation of a zoonosis caused by larvae of the tapeworm Echinococcus granulosus sensu lato and pterygopalatine fossa cases are extremely rare. Clinical Presentation and Findings: A 45-year-old Caucasian female with a history of repeated surgeries for HC was referred to our center for treatment of a cystic mass of the pterygopalatine fossa. Multiorgan dissemination was noted on preoperative imaging. Interventions: An endonasal endoscopic procedure was carried over under general anesthesia and the CE completely removed. Etiology was confirmed by molecular diagnostics. Three weeks after the skull base procedure, the patient underwent a combined abdominal/urological procedure for treatment of other cysts. Conclusion: This case shows that the pterygopalatine fossa HC are amenable to surgical treatment using the endonasal endoscopic approach. Extensive preoperative workup is essential to assess the extent of the disease.

Four Types of Multiclass Frameworks for Pneumonia Classification and Its Validation in X-ray Scans Using Seven Types of Deep Learning Artificial Intelligence Models.

Background and Motivation: The novel coronavirus causing COVID-19 is exceptionally contagious, highly mutative, decimating human health and life, as well as the global economy, by consistent evolution of new pernicious variants and outbreaks. The reverse transcriptase polymerase chain reaction currently used for diagnosis has major limitations. Furthermore, the multiclass lung classification X-ray systems having viral, bacterial, and tubercular classes­including COVID-19­are not reliable. Thus, there is a need for a robust, fast, cost-effective, and easily available diagnostic method. Method: Artificial intelligence (AI) has been shown to revolutionize all walks of life, particularly medical imaging. This study proposes a deep learning AI-based automatic multiclass detection and classification of pneumonia from chest X-ray images that are readily available and highly cost-effective. The study has designed and applied seven highly efficient pre-trained convolutional neural networks­namely, VGG16, VGG19, DenseNet201, Xception, InceptionV3, NasnetMobile, and ResNet152­for classification of up to five classes of pneumonia. Results: The database consisted of 18,603 scans with two, three, and five classes. The best results were using DenseNet201, VGG16, and VGG16, respectively having accuracies of 99.84%, 96.7%, 92.67%; sensitivity of 99.84%, 96.63%, 92.70%; specificity of 99.84, 96.63%, 92.41%; and AUC of 1.0, 0.97, 0.92 (p < 0.0001 for all), respectively. Our system outperformed existing methods by 1.2% for the five-class model. The online system takes <1 s while demonstrating reliability and stability. Conclusions: Deep learning AI is a powerful paradigm for multiclass pneumonia classification.