Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina , Ioannina , Greece
Auto-generated profile, based on publicly available information
Vasileios S. Loukas
Unit of Medical Technology and Intelligent Information Systems, Department of Materials Science and Engineering, University of Ioannina , Ioannina , Greece
Aims: Coronary artery disease (CAD) is a highly prevalent disease with modifiable risk factors. In patients with suspected obstructive CAD, evaluating the pre-test probability model is crucial for diagnosis, although its accuracy remains controversial. Machine learning (ML) predictive models can help clinicians detect CAD early and improve outcomes. This study aimed to identify early-stage CAD using ML in conjunction with a panel of clinical and laboratory tests. Methods and results: The study sample included 3316 patients enrolled in the Ludwigshafen Risk and Cardiovascular Health (LURIC) study. A comprehensive array of attributes was considered, and an ML pipeline was developed. Subsequently, we utilized five approaches to generating high-quality virtual patient data to improve the performance of the artificial intelligence models. An extension study was carried out using data from the Young Finns Study (YFS) to assess the results’ generalizability. Upon applying virtual augmented data, accuracy increased by approximately 5%, from 0.75 to –0.79 for random forests (RFs), and from 0.76 to –0.80 for Gradient Boosting (GB). Sensitivity showed a significant boost for RFs, rising by about 9.4% (0.81–0.89), while GB exhibited a 4.8% increase (0.83–0.87). Specificity showed a significant boost for RFs, rising by ∼24% (from 0.55 to 0.70), while GB exhibited a 37% increase (from 0.51 to 0.74). The extension analysis aligned with the initial study. Conclusion: Accurate predictions of angiographic CAD can be obtained using a set of routine laboratory markers, age, sex, and smoking status, holding the potential to limit the need for invasive diagnostic techniques. The extension analysis in the YFS demonstrated the potential of these findings in a younger population, and it confirmed applicability to atherosclerotic vascular disease.
16 May 2024 in IEEE Open Journal of Engineering in Medicine and Biology
In this work, a methodology for the in-silico evaluation of drug eluting stents (DES) is presented. A stent model developed by Rontis S.A. has been employed. For modeling purposes two different stent parts have been considered: the metal core and the coating. For the arterial models, we used animal specific imaging data and realistic geometries were reconstructed which were used as input to the drug-delivery model. More specifically, optical coherence tomography (OCT) imaging data from two coney iliac arterial segments were 3D reconstructed, and the preprocessed 3D stent was deployed in-silico. The deformed geometries of the in-silico deployed stents and the dilated arterial segments were used as input to the drug elution model. The same reconstructed arteries were used in three different cases: (i) Case A. The coatings contain retinoic acid at an initial concentration 49.2% w/w. (ii) Case B. The coatings contain retinoic acid at an initial concentration 1% w/w. (iii) Case C. The coatings contain sirolimus at an initial concentration 0.85% w/w. In each case, two different coatings were examined: (a) polylactic acid and (b) polylactic-co-glycolic acid. The results proved that retinoic acid is a very promising drug candidate for DES due to its binding time to the smooth muscle cells of the arterial wall that exceeds the corresponding time of sirolimus, while being non-toxic to the smooth muscle cells.