Nikolas Iosif
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Nikolas Iosif has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Amalia Georgiou
Maria Hilf Krankenhaus, Krefeld, Germany, Germany
2 shared publications - Filippos Triposkiadis
School of Medicine, European University Cyprus, Nicosia 2404, Cyprus
2 shared publications - Georghios P. Georghiou
School of Medicine, European University Cyprus, Nicosia 2404, Cyprus
2 shared publications - Konstantinos Lampropoulos
School of Medicine, European University Cyprus, Nicosia, Cyprus, Cyprus
2 shared publications - Panos Georghiou
Barts and The London School of Medicine and Dentistry, Queen Mary University of London, Turner St., London E1 2AD, UK
2 shared publications Sotiris Kyriakou
Barts and The London School of Medicine and Dentistry, Queen Mary University of London, London, United Kingdom, UK
2 shared publications
Latest Publications
- Open Access
- 26 June 2026
- Published by MDPI AG in Preprints.org
The Use of Artificial Intelligence (AI) for the Early Detection of Postoperative Complications in Cardiothoracic Surgery
Artificial intelligence (AI) and machine learning (ML) are increasingly being evaluated as decision-support tools for forecasting postoperative complications after cardiothoracic surgery. This narrative review synthesises peer-reviewed clinical, biomedical informatics, and digital-health literature across acute kidney injury (AKI), postoperative atrial fibrillation (POAF), pulmonary complications, neurological outcomes, mortality, wound monitoring, wearable surveillance, and post-discharge monitoring. Rather than treating reported AUC values as interchangeable evidence of algorithmic superiority, this review emphasises that model performance depends on at least three interacting factors: algorithmic architecture, data richness, and validation strategy. Conventional tools such as EuroSCORE II and Society of Thoracic Surgeons (STS) models remain clinically useful because they are familiar, transparent, and externally established; however, many rely on static perioperative snapshots and are less suited to continuously updated intraoperative and postoperative data streams. Contemporary ML models, including gradient-boosting approaches, support-vector methods, convolutional neural networks, and wearable-based algorithms, may improve discrimination in selected settings, particularly when dynamic laboratory trajectories, physiological time-series, imaging data, or remote-monitoring signals are available. However, current evidence remains limited by single-centre development, heterogeneous endpoints, inconsistent calibration reporting, limited decision-curve analysis, low positive predictive values in surveillance applications, and sparse prospective implementation. Future work should prioritise multicentre external validation, calibration, clinical utility analysis, standards-based electronic medical record interoperability, and implementation pathways that preserve clinician oversight.
- 26 June 2026
- Published by MDPI AG in Preprints.org
Open AccessThe Use of Artificial Intelligence (AI) for the Early Detection of Postoperative Complications in Cardiothoracic Surgery
Artificial intelligence (AI) and machine learning (ML) are increasingly being evaluated as decision-support tools for forecasting postoperative complications after cardiothoracic surgery. This narrative review synthesises peer-reviewed clinical, biomedical informatics, and digital-health literature across acute kidney injury (AKI), postoperative atrial fibrillation (POAF), pulmonary complications, neurological outcomes, mortality, wound monitoring, wearable surveillance, and post-discharge monitoring. Rather than treating reported AUC values as interchangeable evidence of algorithmic superiority, this review emphasises that model performance depends on at least three interacting factors: algorithmic architecture, data richness, and validation strategy. Conventional tools such as EuroSCORE II and Society of Thoracic Surgeons (STS) models remain clinically useful because they are familiar, transparent, and externally established; however, many rely on static perioperative snapshots and are less suited to continuously updated intraoperative and postoperative data streams. Contemporary ML models, including gradient-boosting approaches, support-vector methods, convolutional neural networks, and wearable-based algorithms, may improve discrimination in selected settings, particularly when dynamic laboratory trajectories, physiological time-series, imaging data, or remote-monitoring signals are available. However, current evidence remains limited by single-centre development, heterogeneous endpoints, inconsistent calibration reporting, limited decision-curve analysis, low positive predictive values in surveillance applications, and sparse prospective implementation. Future work should prioritise multicentre external validation, calibration, clinical utility analysis, standards-based electronic medical record interoperability, and implementation pathways that preserve clinician oversight.
- Open Access
- 26 June 2026
- Published by MDPI AG in Preprints.org
Aortitis as a High-Risk Vascular Syndrome: Integrating Phenotype-Driven Diagnosis, Multidisciplinary Assessment, and Personalised Management
Aortitis—inflammation of the aortic wall—presents at the interface of vasculitis, infection, structural aortic disease, and cardiovascular risk. It may occur in giant cell arteritis (GCA), Takayasu arteritis, IgG4-related disease, drug-induced injury, infection, or as an isolated finding after aortic surgery. Modern imaging detects aortic inflammation more frequently, but the main challenge is classification rather than detection: determining whether disease is infectious or immune-mediated, active or dominated by fixed structural damage, systemic or isolated, and whether the dominant threat is aneurysm, dissection, undertreated infection, or avoidable immunosuppression. This review considers aortitis as a high-risk vascular syndrome requiring aetiology-first classification rather than descriptive labelling. Before escalating immunosuppression, infection must be actively excluded and inflammatory activity distinguished from fixed vascular damage. Treatment should be individualised according to phenotype, age, vascular territory, comorbidity, and toxicity risk, with surveillance continuing even after symptoms and inflammatory markers improve. Optimal care depends on multidisciplinary assessment integrating rheumatology, infectious diseases, vascular surgery, radiology, and cardiology expertise. Progress will require standardised imaging definitions, registries linking inflammatory control with structural vascular outcomes, and validation of artificial intelligence (AI) tools before clinical adoption.
- 26 June 2026
- Published by MDPI AG in Preprints.org
Open AccessAortitis as a High-Risk Vascular Syndrome: Integrating Phenotype-Driven Diagnosis, Multidisciplinary Assessment, and Personalised Management
Aortitis—inflammation of the aortic wall—presents at the interface of vasculitis, infection, structural aortic disease, and cardiovascular risk. It may occur in giant cell arteritis (GCA), Takayasu arteritis, IgG4-related disease, drug-induced injury, infection, or as an isolated finding after aortic surgery. Modern imaging detects aortic inflammation more frequently, but the main challenge is classification rather than detection: determining whether disease is infectious or immune-mediated, active or dominated by fixed structural damage, systemic or isolated, and whether the dominant threat is aneurysm, dissection, undertreated infection, or avoidable immunosuppression. This review considers aortitis as a high-risk vascular syndrome requiring aetiology-first classification rather than descriptive labelling. Before escalating immunosuppression, infection must be actively excluded and inflammatory activity distinguished from fixed vascular damage. Treatment should be individualised according to phenotype, age, vascular territory, comorbidity, and toxicity risk, with surveillance continuing even after symptoms and inflammatory markers improve. Optimal care depends on multidisciplinary assessment integrating rheumatology, infectious diseases, vascular surgery, radiology, and cardiology expertise. Progress will require standardised imaging definitions, registries linking inflammatory control with structural vascular outcomes, and validation of artificial intelligence (AI) tools before clinical adoption.