3D clustering of gene expression data from systemic autoinflammatory diseases using self-organizing maps (Clust3D).

Background and objective: Systemic autoinflammatory diseases (SAIDs) are characterized by widespread inflammation, but for most of them there is a lack of specific biomarkers for accurate diagnosis. Although a number of machine learning algorithms have been used to analyze SAID datasets, aiding in the discovery of novel biomarkers, there is a growing recognition of the importance of SAID timeseries clustering, as it can capture the temporal dynamics of gene expression patterns. Methodology: This paper proposes a novel clustering methodology to efficiently associate three-dimensional data. The algorithm utilizes competitive learning to create a self-organizing neural network and adjust neuron positions in time-dependent and high dimensional feature space in order to assign them as clustering centers. The quantitative evaluation of the clustering was based on well-known clustering indices. Furthermore, a differential expression analysis and classification pipeline was employed to assess the capability of the proposed methodology to extract more accurate pathway-specific genes from its clusters. For that, a comparative analysis was also conducted against a heuristic timeseries clustering method. Results: The proposed methodology achieved better overall clustering indices scores and classification metrics using genes derived from its clusters. Notable cases include a threefold increase in the Calinski-Harabasz clustering index, a twofold improvement in the Davies-Bouldin clustering index and a ∼60% increase in the classification specificity score. Conclusion: A novel clustering methodology was developed and applied on several gene expression timeseries datasets from systemic autoinflammatory diseases, and its ability to efficiently produce well separated clusters compared to existing heuristic methods was demonstrated.

Ηand dexterities assessment in stroke patients based on augmented reality and machine learning through a box and block test.

A popular and widely suggested measure for assessing unilateral hand motor skills in stroke patients is the box and block test (BBT). Our study aimed to create an augmented reality enhanced version of the BBT (AR-BBT) and evaluate its correlation to the original BBT for stroke patients. Following G-power analysis, clinical examination, and inclusion-exclusion criteria, 31 stroke patients were included in this study. AR-BBT was developed using the Open Source Computer Vision Library (OpenCV). The MediaPipe's hand tracking library uses a palm and a hand landmark machine learning model to detect and track hands. A computer and a depth camera were employed in the clinical evaluation of AR-BBT following the principles of traditional BBT. A strong correlation was achieved between the number of blocks moved in the BBT and the AR-BBT on the hemiplegic side (Pearson correlation = 0.918) and a positive statistically significant correlation (p = 0.000008). The conventional BBT is currently the preferred assessment method. However, our approach offers an advantage, as it suggests that an AR-BBT solution could remotely monitor the assessment of a home-based rehabilitation program and provide additional hand kinematic information for hand dexterities in AR environment conditions. Furthermore, it employs minimal hardware equipment.

Socio-Cognitive Determinants of Lifestyle Behavior in the Context of Dementia Risk Reduction: A Population-Based Study in the Netherlands.

Background: Unhealthy behavior increases the risk of dementia. Various socio-cognitive determinants influence whether individuals persist in or alter these unhealthy behaviors. Objective: This study identifies relevant determinants of behavior associated to dementia risk. Methods: 4,104 Dutch individuals (40-79 years) completed a screening questionnaire exploring lifestyle behaviors associated with dementia risk. Subsequently, 3,065 respondents who engaged in one or more unhealthy behaviors completed a follow-up questionnaire investigating socio-cognitive determinants of these behaviors. Cross-tables were used to assess the accuracy of participants' perceptions regarding their behavior compared to recommendations. Confidence Interval-Based Estimation of Relevance (CIBER) was used to identify the most relevant determinants of behavior based on visual inspection and interpretation. Results: Among the respondents, 91.3% reported at least one, while 65% reported two or more unhealthy lifestyle behaviors associated to dementia risk. Many of them were not aware they did not adhere to lifestyle recommendations. The most relevant determinants identified include attitudes (i.e., lacking a passion for cooking and finding pleasure in drinking alcohol or smoking), misperceptions on social comparisons (i.e., overestimating healthy diet intake and underestimating alcohol intake), and low perceived behavioral control (i.e., regarding changing physical inactivity, altering diet patterns, and smoking cessation). Conclusions: Individual-level interventions that encourage lifestyle change should focus on enhancing accurate perceptions of behaviors compared to recommendations, while strengthening perceived control towards behavior change. Given the high prevalence of dementia risk factors, combining interventions at both individual and environmental levels are likely to be the most effective strategy to reduce dementia on a population scale.

Documenting the de-identification process of clinical and imaging data for AI for health imaging projects.

Artificial intelligence (AI) is revolutionizing the field of medical imaging, holding the potential to shift medicine from a reactive "sick-care" approach to a proactive focus on healthcare and prevention. The successful development of AI in this domain relies on access to large, comprehensive, and standardized real-world datasets that accurately represent diverse populations and diseases. However, images and data are sensitive, and as such, before using them in any way the data needs to be modified to protect the privacy of the patients. This paper explores the approaches in the domain of five EU projects working on the creation of ethically compliant and GDPR-regulated European medical imaging platforms, focused on cancer-related data. It presents the individual approaches to the de-identification of imaging data, and describes the problems and the solutions adopted in each case. Further, lessons learned are provided, enabling future projects to optimally handle the problem of data de-identification. CRITICAL RELEVANCE STATEMENT: This paper presents key approaches from five flagship EU projects for the de-identification of imaging and clinical data offering valuable insights and guidelines in the domain. KEY POINTS: ΑΙ models for health imaging require access to large amounts of data. Access to large imaging datasets requires an appropriate de-identification process. This paper provides de-identification guidelines from the AI for health imaging (AI4HI) projects.

Image Quality Assessment Tool for Conventional and Dynamic Magnetic Resonance Imaging Acquisitions.

Image quality assessment of magnetic resonance imaging (MRI) data is an important factor not only for conventional diagnosis and protocol optimization but also for fairness, trustworthiness, and robustness of artificial intelligence (AI) applications, especially on large heterogeneous datasets. Information on image quality in multi-centric studies is important to complement the contribution profile from each data node along with quantity information, especially when large variability is expected, and certain acceptance criteria apply. The main goal of this work was to present a tool enabling users to assess image quality based on both subjective criteria as well as objective image quality metrics used to support the decision on image quality based on evidence. The evaluation can be performed on both conventional and dynamic MRI acquisition protocols, while the latter is also checked longitudinally across dynamic series. The assessment provides an overall image quality score and information on the types of artifacts and degrading factors as well as a number of objective metrics for automated evaluation across series (BRISQUE score, Total Variation, PSNR, SSIM, FSIM, MS-SSIM). Moreover, the user can define specific regions of interest (ROIs) to calculate the regional signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), thus individualizing the quality output to specific use cases, such as tissue-specific contrast or regional noise quantification.

Multimodal automatic assessment of acute pain through facial videos and heart rate signals utilizing transformer-based architectures.

Accurate and objective pain evaluation is crucial in developing effective pain management protocols, aiming to alleviate distress and prevent patients from experiencing decreased functionality. A multimodal automatic assessment framework for acute pain utilizing video and heart rate signals is introduced in this study. The proposed framework comprises four pivotal modules: the Spatial Module, responsible for extracting embeddings from videos; the Heart Rate Encoder, tasked with mapping heart rate signals into a higher dimensional space; the AugmNet, designed to create learning-based augmentations in the latent space; and the Temporal Module, which utilizes the extracted video and heart rate embeddings for the final assessment. The Spatial-Module undergoes pre-training on a two-stage strategy: first, with a face recognition objective learning universal facial features, and second, with an emotion recognition objective in a multitask learning approach, enabling the extraction of high-quality embeddings for the automatic pain assessment. Experiments with the facial videos and heart rate extracted from electrocardiograms of the BioVid database, along with a direct comparison to 29 studies, demonstrate state-of-the-art performances in unimodal and multimodal settings, maintaining high efficiency. Within the multimodal context, 82.74% and 39.77% accuracy were achieved for the binary and multi-level pain classification task, respectively, utilizing 9.62 million parameters for the entire framework.

Virtual Hemodynamic Assessment of Coronary Lesions: The Advent of Functional Angiography and Coronary Imaging.

The fractional flow reserve (FFR) is well recognized as a gold standard measure for the estimation of functional coronary stenosis. Technological progressions in image processing have empowered the reconstruction of three-dimensional models of the coronary arteries via both non-invasive and invasive imaging modalities. The application of computational fluid dynamics (CFD) techniques to coronary 3D anatomical models allows the virtual evaluation of the hemodynamic significance of a coronary lesion with high diagnostic accuracy. METHODS: Search of the bibliographic database for articles published from 2011 to 2023 using the following search terms: invasive FFR and non-invasive FFR. Pooled analysis of the sensitivity and specificity, with the corresponding confidence intervals from 32% to 94%. In addition, the summary processing times were determined. RESULTS: In total, 24 studies published between 2011 and 2023 were included, with a total of 13,591 patients and 3345 vessels. The diagnostic accuracy of the invasive and non-invasive techniques at the per-patient level was 89% (95% CI, 85-92%) and 76% (95% CI, 61-80%), respectively, while on the per-vessel basis, it was 92% (95% CI, 82-88%) and 81% (95% CI, 75-87%), respectively. CONCLUSION: These opportunities providing hemodynamic information based on anatomy have given rise to a new era of functional angiography and coronary imaging. However, further validations are needed to overcome several scientific and computational challenges before these methods are applied in everyday clinical practice.

Light Color-Controlled pH-Adjustment of Aqueous Solutions Using Engineered Proteoliposomes.

Controlling the pH at the microliter scale can be useful for applications in research, medicine, and industry, and therefore represents a valuable application for synthetic biology and microfluidics. The presented vesicular system translates light of different colors into specific pH changes in the surrounding solution. It works with the two light-driven proton pumps bacteriorhodopsin and blue light-absorbing proteorhodopsin Med12, that are oriented in opposite directions in the lipid membrane. A computer-controlled measuring device implements a feedback loop for automatic adjustment and maintenance of a selected pH value. A pH range spanning more than two units can be established, providing fine temporal and pH resolution. As an application example, a pH-sensitive enzyme reaction is presented where the light color controls the reaction progress. In summary, light color-controlled pH-adjustment using engineered proteoliposomes opens new possibilities to control processes at the microliter scale in different contexts, such as in synthetic biology applications.

A Combined Computational and Experimental Analysis of PLA and PCL Hybrid Nanocomposites 3D Printed Scaffolds for Bone Regeneration.

A combined computational and experimental study of 3D-printed scaffolds made from hybrid nanocomposite materials for potential applications in bone tissue engineering is presented. Polycaprolactone (PCL) and polylactic acid (PLA), enhanced with chitosan (CS) and multiwalled carbon nanotubes (MWCNTs), were investigated in respect of their mechanical characteristics and responses in fluidic environments. A novel scaffold geometry was designed, considering the requirements of cellular proliferation and mechanical properties. Specimens with the same dimensions and porosity of 45% were studied to fully describe and understand the yielding behavior. Mechanical testing indicated higher apparent moduli in the PLA-based scaffolds, while compressive strength decreased with CS/MWCNTs reinforcement due to nanoscale challenges in 3D printing. Mechanical modeling revealed lower stresses in the PLA scaffolds, attributed to the molecular mass of the filler. Despite modeling challenges, adjustments improved simulation accuracy, aligning well with experimental values. Material and reinforcement choices significantly influenced responses to mechanical loads, emphasizing optimal structural robustness. Computational fluid dynamics emphasized the significance of scaffold permeability and wall shear stress in influencing bone tissue growth. For an inlet velocity of 0.1 mm/s, the permeability value was estimated at 4.41 × 10-9 m2, which is in the acceptable range close to human natural bone permeability. The average wall shear stress (WSS) value that indicates the mechanical stimuli produced by cells was calculated to be 2.48 mPa, which is within the range of the reported literature values for promoting a higher proliferation rate and improving osteogenic differentiation. Overall, a holistic approach was utilized to achieve a delicate balance between structural robustness and optimal fluidic conditions, in order to enhance the overall performance of scaffolds in tissue engineering applications.

FHBF: Federated hybrid boosted forests with dropout rates for supervised learning tasks across highly imbalanced clinical datasets.

Although several studies have deployed gradient boosting trees (GBT) as a robust classifier for federated learning tasks (federated GBT [FGBT]), even with dropout rates (federated gradient boosting trees with dropout rate [FDART]), none of them have investigated the overfitting effects of FGBT across heterogeneous and highly imbalanced datasets within federated environments nor the effect of dropouts in the loss function. In this work, we present the federated hybrid boosted forests (FHBF) algorithm, which incorporates a hybrid weight update approach to overcome ill-posed problems that arise from overfitting effects during the training across highly imbalanced datasets in the cloud. Eight case studies were conducted to stress the performance of FHBF against existing algorithms toward the development of robust AI models for lymphoma development across 18 European federated databases. Our results highlight the robustness of FHBF, yielding an average loss of 0.527 compared with FGBT (0.611) and FDART (0.584) with increased classification performance (0.938 sensitivity, 0.732 specificity).

Comparison of pulmonary and small airways function between idiopathic inflammatory myopathies patients with and without interstitial lung disease.

OBJECTIVES: To evaluate pulmonary and small airway function in patients with idiopathic inflammatory myopathies (IIM) and make comparisons between patients with and without interstitial lung disease (ILD). METHODS: Newly diagnosed IIM patients with and without ILD determined by high resolution computed tomography were included in the study. Pulmonary and small airway function was assessed by spirometry, diffusing capacity for carbon monoxide (DLCO), body plethysmography, single and multiple breath nitrogen washout, impulse oscillometry and measurement of respiratory resistance by the interrupter technique (Rint) using the Q-box system. We used discrepancies between lung volumes measured by multiple breath nitrogen washout and body plethysmography to evaluate for small airway dysfunction. RESULTS: Study cohort comprised of 26 IIM patients, 13 with and 13 without ILD. IIM-ILD patients presented more frequently with dyspnoea, fever, arthralgias and positive anti-synthetase antibodies, compared to IIM patients without ILD. Classic spirometric parameters and most lung physiology parameters assessing small airway function did not differ between the two groups. Predicted total lung capacity and residual volume (TLCN2WO, RVN2WO) measured by multiple breath nitrogen washout and the TLCN2WO/TLCpleth ratio were significantly lower in IIM-ILD patients compared to those without ILD (mean: 111.1% vs. 153.4%, p=0.034, median: 171% vs. 210%, p=0.039 and median: 1.28 vs. 1.45, p=0.039, respectively). Rint tended to be higher among IIM-ILD patients (mean:100.5% vs. 76.6%, p=0.053). CONCLUSIONS: Discrepancies between lung volumes measured by multiple breath nitrogen washout and body plethysmography in IIM-ILD patients indicate an early small airways dysfunction in these patients.

Is it time for a retinoic acid-eluting stent or retinoic acid-coated balloon? Insights from experimental studies of systemic and local delivery of retinoids.

Although the incidence of restenosis and stent thrombosis has substantially declined during the last decades, they still constitute the two major causes of stent failure. These complications are partially attributed to the currently used cytostatic drugs, which can cause local inflammation, delay or prevent re-endothelialization and essentially cause arterial cell toxicity. Retinoic acid (RA), a vitamin A (retinol) derivative, is a naturally occurring substance used for the treatment of cell proliferation disorders. The agent has pleiotropic effects on vascular smooth muscle cells and macrophages: it influences the proliferation, migration, and transition of smooth muscle cells to other cell types and modulates macrophage activation. These observations are supported by accumulated evidence from in vitro and in vivo experiments. In addition, systemic and topical administration of RA can decrease the development of atherosclerotic plaques and reduce or inhibit restenosis after vascular injury (caused by embolectomy, balloon catheters, or ligation of arteries) in various experimental models. Recently, an RA-drug eluting stent (DES) has been tested in an animal model. In this review, we explore the effects of RA in atherosclerosis and the potential of the local delivery of RA through an RA-DES or RA-coated balloon for targeted therapeutic percutaneous vascular interventions. Despite promising published results, further experimental study is warranted to examine the safety and efficacy of RA-eluting devices in vascular artery disease.

A Review of Image-Based Food Recognition and Volume Estimation Artificial Intelligence Systems.

The daily healthy diet and balanced intake of essential nutrients play an important role in modern lifestyle. The estimation of a meal's nutrient content is an integral component of significant diseases, such as diabetes, obesity and cardiovascular disease. Lately, there has been an increasing interest towards the development and utilization of smartphone applications with the aim of promoting healthy behaviours. The semi - automatic or automatic, precise and in real-time estimation of the nutrients of daily consumed meals is approached in relevant literature as a computer vision problem using food images which are taken via a user's smartphone. Herein, we present the state-of-the-art on automatic food recognition and food volume estimation methods starting from their basis, i.e., the food image databases. First, by methodically organizing the extracted information from the reviewed studies, this review study enables the comprehensive fair assessment of the methods and techniques applied for segmenting food images, classifying their food content and computing the food volume, associating their results with the characteristics of the used datasets. Second, by unbiasedly reporting the strengths and limitations of these methods and proposing pragmatic solutions to the latter, this review can inspire future directions in the field of dietary assessment systems.

DMpDP: a Diagnostic Multiple-patient DermoFeature Profile store-and-forward teledermoscopy system.

Telehealth demand is rapidly growing along with the necessity of providing wide-scale services covering multiple patients at the same time. In this work, the development of a store-and-forward (SAF) teledermoscopy system was considered. The dermoFeatures profile (DP) was proposed to decrease the size of the original dermoscopy image using its most significant features in the form of a newly generated diagonal alignment to generate a small-sized image DP, which is based on the extraction of a weighted intensity-difference frequency (WIDF) features along with morphological features (MOFs). These DPs were assembled to establish a Diagnostic Multiple-patient DermoFeature Profile (DMpDP). Different arrangements are proposed, namely the horizontally aligned, the diagonal-based, and the sequential-based DMpDPs to support the SAF systems. The DMpDPs are then embedded in a recorded patient-information signal (RPS) using a weight factor ß to boost the transmitted patient-information signal. The effect of the different transform domains, ß values, and number of DPs within the DMpDP were investigated in terms of the diagnostic classification accuracy at the receiver based on the extracted DPs, along with the recorded signal quality evaluation metrics of the recovered RPS. The sequential-based DMpDP achieved the highest classification accuracy, under - 5 dB additive white Gaussian noise, with a realized signal-to-noise ratio of 98.79% during the transmission of 248 DPs using ß = 100, and spectral subtraction filtering.

A comparison study on creating simulated patient data for individuals suffering from chronic coronary disorders.

An emerging area in data science that has lately gained attention is the virtual population (VP) and synthetic data generation. This field has the potential to significantly affect the healthcare industry by providing a means to augment clinical research databases that have a shortage of subjects. The current study provides a comparative analysis of five distinct approaches for creating virtual data populations from real patient data. The data set utilized for the current analyses involved clinical data collected among patients scheduled for elective coronary artery bypass graft surgery (CABG). To that end, the five computational techniques employed to augment the given dataset were: (i) Tabular Preset, (ii) Gaussian Copula Model (iii) Generative Adversarial Network based (GAN) Deep Learning data synthesizer (CTGAN), (iv) a variation of the CTGAN Model (Copula GAN), and (v) VAE-based Deep Learning data synthesizer (TVAE). The performance of these techniques was assessed against their effectiveness in producing high-quality virtual data. For this purpose, dataset correlation matrices, cosine similarity distance, density histograms, and kernel density estimation are employed to perform a comparative analysis of each attribute and the respective synthetic equivalent. Our findings demonstrate that Gaussian Copula Model prevails in creating virtual data with consistent distributions (Kolmogorov-Smirnov (KS) and Chi-Squared (CS) tests equal to 0.9 and 0.98, respectively) and correlation patterns (average cosine similarity equals to 0.95).Clinical Relevance- It has been shown that the use of a VP can increase the predictive performance of a ML model, i.e., above using a smaller non-augmented population.

Using the recurrence plots as indicators for the recognition of Parkinson's disease through phonemes assessment.

Parkinson's disease (PD) is considered to be the second most common neurodegenerative disease which affects the patients' life throughout the years. As a consequence, its early diagnosis is of major importance for the improvement of life quality, implying that the severe symptoms can be delayed through appropriate clinical intervention and treatment. Among the most important premature symptoms of PD are the voice impairments of articulation, phonation and prosody. The objective of this study is to investigate whether the voice's dynamic behavior can be used as possible indicator for PD. Thus in this work, we employ the recurrence plots (RPs) which derive from the analysis of the three modulated vowels /a/, /e/ and /o/, which belong to the PC-GITA dataset, and are fed as input images to a 3-channel Convolutional Neural Network-based (CNN) architecture, which, finally, differentiates the 50 PD patients from 50 healthy subjects. The experimental results obtained provide evidence that the RP-based approach is a promising tool for the recognition of PD patients through the analysis of voice recordings, with a classification accuracy achieved equal to 87%.

Weight Estimation of Mediterranean Food Images using Random Forest Regression Algorithm.

The daily nutrition management is one of the most important issues that concern individuals in the modern lifestyle. Over the years, the development of dietary assessment systems and applications based on food images has assisted experts to manage people's nutritional facts and eating habits. In these systems, the food volume estimation is the most important task for calculating food quantity and nutritional information. In this study, we present a novel methodology for food weight estimation based on a food image, using the Random Forest regression algorithm. The weight estimation model was trained on a unique dataset of 5,177 annotated Mediterranean food images, consisting of 50 different foods with a reference card placed next to the plate. Then, we created a data frame of 6,425 records from the annotated food images with features such as: food area, reference object area, food id, food category and food weight. Finally, using the Random Forest regression algorithm and applying nested cross validation and hyperparameters tuning, we trained the weight estimation model. The proposed model achieves 22.6 grams average difference between predicted and real weight values for each food item record in the data frame and 15.1% mean absolute percentage error for each food item, opening new perspectives in food image-based volume and nutrition estimation models and systems.Clinical Relevance- The proposed methodology is suitable for healthcare systems and applications that monitor an individual's malnutrition, offering the ability to estimate the energy and nutrients consumed using an image of the meal.

An integrated rehabilitation system for the upper limb spasticity assessment and treatment: the Rehabotics passive exoskeletal system.

Limb spasticity is caused by stroke, multiple sclerosis, traumatic brain injury and various central nervous system pathologies such as brain tumors resulting in joint stiffness, loss of hand function and severe pain. This paper presents with the Rehabotics integrated rehabilitation system aiming to provide highly individualized assessment and treatment of the function of the upper limbs for patients with spasticity after stroke, focusing on the developed passive exoskeletal system. The proposed system can: (i) measure various motor and kinematic parameters of the upper limb in order to evaluate the patient's condition and progress, as well as (ii) offer a specialized rehabilitation program (therapeutic exercises, retraining of functional movements and support of daily activities) through an interactive virtual environment. The outmost aim of this multidisciplinary research work is to create new tools for providing high-level treatment and support services to patients with spasticity after stroke.Clinical Relevance- This paper presents a new passive exoskeletal system aiming to provide enhanced treatment and assessment of patients with upper limb spasticity after stroke.

Enhancing risk prediction capabilities in patients with carotid artery disease using a 2-level computational approach.

One of the main causes of death worldwide is carotid artery disease, which causes increasing arterial stenosis and may induce a stroke. To address this problem, the scientific community aims to improve our understanding of the underlying atherosclerotic mechanisms, as well as to make it possible to forecast the progression of atherosclerosis. Additionally, over the past several years, developments in the field of cardiovascular modeling have made it possible to create precise three-dimensional models of patient-specific main carotid arteries. The aforementioned 3D models are then implemented by computational models to forecast either the progression of atherosclerotic plaque or several flow-related metrics which are correlated to risk evaluation. A precise representation of both the blood flow and the fundamental atherosclerotic process within the arterial wall is made possible by computational models, therefore, allowing for the prediction of future lumen stenoses, plaque areas and risk prediction. This work presents an attempt to integrate the outcomes of a novel plaque growth model with advanced blood flow dynamics where the deformed luminal shape derived from the plaque growth model is compared to the actual patient-specific luminal model in terms of several hemodynamic metrics, to identify the prediction accuracy of the aforementioned model. Pressure drop ratios had a mean difference of <3%, whereas OSI-derived metrics were identical in 2/3 cases.Clinical Relevance-This establishes the accuracy of our plaque growth model in predicting the arterial geometry after the desired timeline.

Graph-guided Gaussian Process-based Diagnosis of CVD Severity with Uncertainty Measures.

The severity of coronary artery disease can be assessed invasively using the Fractional Flow Reserve (FFR) index which is a useful diagnostic tool for the clinicians to select the treatment approach. The present work capitalizes a Gaussian process (GP) framework over graphs for the prediction of FFR index using only non-invasive imaging and clinical features. More specifically, taking the per-node one-hop connectivity vector as input, we employed a regression-based task by applying an ensemble of graph-adapted Gaussian process experts, with a data-adaptive fashion via online training. The main novelty of the work lies in the fact that for the first time in a medical field the inference model considers only the similarity condition of the patients, instead of their features. Our results demonstrate the impressive merits of the proposed medical EGP (MedEGP) method, in comparison to the single GP, and Linear Regression (LR) models to predict the FFR index, with well-calibrated uncertainty.Clinical Relevance- This paper establishes an accurate non-invasive approach to predict the FFR for the diagnosis of coronary artery disease.