Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Emmanouil S. Rigas has a total of 95 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Evaluating and Adapting Quality Criteria for Digital Health Apps in Frailty and Dementia Care

    by Emmanouil S. Rigas, Antonios Billis, Luc Nicolas, Panagiotis D. Bamidis

    Digital health applications have the potential to transform conventional healthcare delivery. They range from simple apps that track activity to more sophisticated ones that can monitor a plethora of health conditions. One important aspect in this developing landscape is the evaluation and assurance of the quality of these apps. Currently, many initiatives initiated by both public and private actors exist to address this issue. These include the Organisation for the Review of Care and Health Applications (ORCHA), the Digitale Gesundheitsanwendungen (DiGA), and the ISO/TC 215 N 3535. Each initiative defines quality criteria for digital health apps. In this paper, we focus on apps related to frailty and/or dementia, that primarily affect older adults and, using the criteria defined in the previous initiatives, we propose an initial list of quality criteria tailored for this context.

  • Open Access

    Editorial: AI and robotics for the smart hospitals of the future

    by Antonios Billis, Emmanouil Rigas, Izidor Mlakar, Patrick Weber, Lacramioara Stoicu-Tivadar

  • Open Access

    Debiasing for trustworthy AI-based prediction of preterm birth

    by Eleni Mpousiou, Emmanouil S. Rigas, Ioannis Tsakiridis, Themistoklis Dagklis, Nick Bassiliades, Antonios Billis, Panagiotis D. Bamidis

    Objective: Preterm birth (PTB), defined as delivery before 37 weeks of gestation, is the leading cause of perinatal morbidity and mortality. Timely prediction of PTB is crucial for physicians to take preventive action. In this work, we propose an AI-based clinical decision support system to address this challenge. Methods: We use an existing dataset containing demographic and clinical variables from 973 pregnant women and begin by examining it for potential data-level bias and representativeness issues. Upon identifying an outcome prevalence imbalance in one of the variables, we revised the dataset through a preprocessing adjustment. We then applied several Machine Learning (ML) algorithms to predict PTB as a binary outcome. Results: During internal model evaluation we found that an optimized ensemble (voting) of Logistic Regression and XGBoost performed best, achieving an accuracy of 96% and a recall of 98%. We also compared the predictive performance using the original (biased) and revised (de-biased) datasets, observing statistically significant improvements in the revised dataset as confirmed by the Wilcoxon signed-rank test, with p-values less than 0.05 for Accuracy, Recall, and F1-score. Conclusion: The results highlight the importance of data quality and dataset representativeness in developing reliable and trustworthy AI-based applications for PTB prediction.

  • Optimizing UAV Station Placement for Pharmaceutical Transfers between Hospitals

    by Anastasios Biblias, Emmanouil S. Rigas, Antonios Billis, Panagiotis D. Bamidis

    Unmanned aerial vehicles (UAVs) or simply drones are a fast growing technology with many applications in several sectors, one of them being the transportation of pharmaceuticals. In this work, we study the use of UAVs for transporting pharmaceuticals between hospitals, and we solve the specific problem of the placement of the stations where the UAVs will be based and controlled. The aim of this work is to calculate the minimum number of drone stations required, as well as their locations, to connect a set of hospitals. To achieve this, we consider both the range of the drones and the operational range of the stations, which is defined by the distance over which a drone can be controlled. We initially identify and exclude hospitals that cannot be served because they are beyond the range of drones or stations. Then, we apply a heuristic algorithm to generate an initial set of potential locations for the stations. This solution is given as input to a metaheuristic algorithm that is an adaptation of the well-known Tabu search algorithm. This algorithm improves the initial solution through an iterative process. We evaluated our algorithm through both numerical experiments and a realistic case study, confirming its efficiency and applicability to the task at hand.

  • Open Access

    Clinical Performance Evaluation of an Artificial Intelligence–Based Tool for Predicting the Presence of Obstructive Coronary Artery Disease: Protocol for a Cohort Observational Study

    by Georgios Rampidis, Evangelos Logaras, Athanasios Samaras, Emmanouil S Rigas, Ilias Kyparissidis-Kokkinidis, Styliana Siakopoulou, Panagiotis-Emmanouil Kartsidis, Konstantinos Kouskouras, George Giannakoulas, Panagiotis Bamidis, et al.

    Background: A significant number of individuals undergoing coronary computed tomography angiography (CCTA) for suspected (CAD) have nonobstructive or no CAD. There is a need for clinically proven models that can predict the pretest probability of stable CAD and help to identify low-risk individuals. Optimizing patient stratification is of paramount importance to improve diagnostic yield and cost-effectiveness. Objective: We aimed to determine whether each patient needs to undergo CCTA because of suspected CAD. The main objective of this study is to evaluate the clinical performance of an artificial intelligence (AI)-based tool in predicting significant coronary artery stenosis (>50%), as well as its utility by medical professionals. Methods: Data for this study have been acquired from 750 participants as part of routine clinical practice in AHEPA (American Hellenic Educational Progressive Association) General Hospital of Thessaloniki. The dataset has several features, including demographics (eg, age, gender), medical history (eg, diabetes mellitus, arterial hypertension), and clinical variables (eg, creatinine, epicardial fat volume). At least 2 expert cardiologists and 2 expert radiologists are involved in this study, who provide the ground truth. A trained AI-based model embedded in an easy-to-use and user-friendly web application is implemented in practice. Several AI algorithms are being examined, and the model found to perform best so far is the Optimized Voting model, which is a combination of the best performing iterations of random forest and extreme gradient boosting. The performance metrics that are being used are accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve, and area under the precision-recall curve. Results: Recruitment for this study began in July 2023. Data collection, development, training, and deployment of the AI web tool were completed by May 2024. In total, data from 500 individuals were collected for training and internal validation, while the best performing model was validated externally in another 250 individuals. For training and internal validation, the dataset was split into 70% for training and 20% for validation and 10% for testing. Currently, the best performing model achieves an accuracy of approximately 82% in successfully predicting stenosis greater than 50%. Additionally, an explainable AI algorithm is used to provide explanations in relation to the decisions made aiming to increase the trust of the clinicians in the tool. Conclusions: The proposed study represents a novel approach of a web-based AI-driven solution with explainability features for optimizing patient stratification with the goal of improving diagnostic yield and cost-effectiveness of CCTA utilization within the context of cardiology clinical practice. International Registered Report Identifier (IRRID): DERR1-10.2196/67697


  • Open Access

    Economic Evaluation of Artificially Intelligent (AI) Diagnostic Systems: Cost Consequence Analysis of Clinician-Friendly Interpretable Computer-Aided Diagnosis (ICADX) Tested in Cardiology, Obstetrics, and Gastroenterology, from the HosmartAI Horizon 2020 Project

    by Magda Chatzikou, Dimitra Latsou, Georgios Apostolidis, Antonios Billis, Vasileios Charisis, Emmanouil S. Rigas, Panagiotis D. Bamidis, Leontios Hadjileontiadis

    Objectives: This study evaluates the economic impact of digital health interventions (DHIs) developed under the HosmartAI EU-funded program, focusing on obstetrics, cardiology, and gastroenterology. Methods: A Cost Consequence Analysis (CCA) was chosen in order to be able to examine the costs and consequences of AI technologies in early diagnosis of preterm births, echocardiography, coronary computed tomography angiography (CCTA), and capsule endoscopy (CE). Results: The results show that in obstetrics and CCTA, the AI technologies are cost-saving, with the AI-based preterm birth detection leading to savings of 99,840 EUR due to reduced severity of prematurity. In the echocardiography scenario, the new AI technology slightly increased costs (9409 vs. 2116 EUR), but offered benefits in diagnostic accuracy and shorter interpretation duration, particularly for less experienced physicians. Similarly, the capsule endoscopy AI technology raised annual costs by 6626 EUR but improved productivity, accuracy, and user satisfaction. Conclusions: The findings emphasize the need for standardized frameworks to guide economic evaluations of DHIs, ensuring informed healthcare investment and reimbursement decisions in the future.


  • Conceptualization and Functional Specifications of an e-learning Ecosystem Towards the Support of Older Adults and Their Supports in Developing Digital and Health Literacy Skills

    by Antonios Billis, Despoina Mantziari, Vasiliki Kalfa, Emmanouil Rigas, Styliani-Olympia Tsormpatzoudi, Maria Karagianni, Konstantinos Diamantis, Panagiotis D. Bamidis


  • Open Access

    Insights on Training and Certification in Digital Health Technologies

    by Emmanouil Rigas, Lacramioara Stoicu-Tivadar, Mihaela Crişan-Vida, Antonis Billis, Maria Nikolaidou, Savvas Anastasiadis, Styliana Siakopoulou, Panagiotis Bamidis, John Mantas

    Digital health is growing rapidly with several technologies aiming to revolutionize the healthcare domain. In this context, the need for training and certification programs becomes imperative. Although such programs do exist, they need to be further expanded and enhanced to cover the pressing needs of the current landscape. In this paper, we describe insights on training and certification in digital health technologies as these were obtained through a related workshop. We outline the profiles and the expertise of the workshop’s participants, the main gaps in knowledge and competencies, the governance and legislation issues and the need for certification in the digital health domain.


  • Open Access

    Clinical Performance Evaluation of an Artificial Intelligence–Based Tool for Predicting the Presence of Obstructive Coronary Artery Disease: Protocol for a Cohort Observational Study (Preprint)

    by Georgios Rampidis, Evangelos Logaras, Athanasios Samaras, Emmanouil S Rigas, Ilias Kyparissidis-Kokkinidis, Styliana Siakopoulou, Panagiotis-Emmanouil Kartsidis, Konstantinos Kouskouras, George Giannakoulas, Panagiotis Bamidis, et al.

    BACKGROUND A significant number of individuals undergoing coronary computed tomography angiography (CCTA) for suspected (CAD) have nonobstructive or no CAD. There is a need for clinically proven models that can predict the pretest probability of stable CAD and help to identify low-risk individuals. Optimizing patient stratification is of paramount importance to improve diagnostic yield and cost-effectiveness. OBJECTIVE We aimed to determine whether each patient needs to undergo CCTA because of suspected CAD. The main objective of this study is to evaluate the clinical performance of an artificial intelligence (AI)-based tool in predicting significant coronary artery stenosis (>50%), as well as its utility by medical professionals. METHODS Data for this study have been acquired from 750 participants as part of routine clinical practice in AHEPA (American Hellenic Educational Progressive Association) General Hospital of Thessaloniki. The dataset has several features, including demographics (eg, age, gender), medical history (eg, diabetes mellitus, arterial hypertension), and clinical variables (eg, creatinine, epicardial fat volume). At least 2 expert cardiologists and 2 expert radiologists are involved in this study, who provide the ground truth. A trained AI-based model embedded in an easy-to-use and user-friendly web application is implemented in practice. Several AI algorithms are being examined, and the model found to perform best so far is the Optimized Voting model, which is a combination of the best performing iterations of random forest and extreme gradient boosting. The performance metrics that are being used are accuracy, precision, recall, F1-score, area under the receiver operating characteristic curve, and area under the precision-recall curve. RESULTS Recruitment for this study began in July 2023. Data collection, development, training, and deployment of the AI web tool were completed by May 2024. In total, data from 500 individuals were collected for training and internal validation, while the best performing model was validated externally in another 250 individuals. For training and internal validation, the dataset was split into 70% for training and 20% for validation and 10% for testing. Currently, the best performing model achieves an accuracy of approximately 82% in successfully predicting stenosis greater than 50%. Additionally, an explainable AI algorithm is used to provide explanations in relation to the decisions made aiming to increase the trust of the clinicians in the tool. CONCLUSIONS The proposed study represents a novel approach of a web-based AI-driven solution with explainability features for optimizing patient stratification with the goal of improving diagnostic yield and cost-effectiveness of CCTA utilization within the context of cardiology clinical practice. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/67697

  • Open Access

    An AI‐Enabled, Patient‐Centred Digital Platform for Integrated Chronic Heart Failure Management: Architecture, Validation and Clinical Insights

    by George Petridis, Apostolia Karabatea, Constantinos Bakogiannis, Emmanouil S. Rigas, Haridimos Kondylakis, Alexander Berler, Konstantinos Kangelidis, Nikolaos Malamas, Angelina Kouroubali, Dimitrios Katehakis, et al.

    Healthcare systems across Europe and globally are increasingly challenged by the need to deliver high‐quality, coordinated care for complex patient populations, such as those living with chronic heart failure (CHF). Many national healthcare policies consider the adoption and implementation of patient‐centred and interoperable information communication technologies‐enabled solutions offered in a single digital platform as a key facilitator towards the transition to integrated and coordinated care. Aiming to support CHF patients and to assist their management, in this paper, we present CareCardia, a modular digital solution designed to support the comprehensive management of CHF. CareCardia offers an interoperable ecosystem that connects healthcare professionals, informal caregivers and patients along a unified CHF care pathway spanning across diagnosis, acute care and jointly managed long‐term care. Specifically, CareCardia integrates state‐of‐the‐art, clinical evidence‐based technologies such as a clinical decision support system and an exergaming platform that will follow patients through the CHF journey. This paper outlines the system architecture and core functionalities of CareCardia prototype. We also present early findings from the initial exploration of the tool, discussing its anticipated impact on CHF and its potential to foster patient empowerment across the continuum of care.