A major requirement for credit scoring models is to provide a maximally accurate risk prediction. Additionally, regulators demand these models to be transparent and auditable. Thus, in credit scoring, very simple predictive models such as logistic regression or decision trees are still widely used and the superior predictive power of modern machine learning algorithms cannot be fully leveraged. Significant potential is therefore missed, leading to higher reserves or more credit defaults. This article works out different dimensions that have to be considered for making credit scoring models understandable and presents a framework for making “black box” machine learning models transparent, auditable, and explainable. Following this framework, we present an overview of techniques, demonstrate how they can be applied in credit scoring and how results compare to the interpretability of scorecards. A real world case study shows that a comparable degree of interpretability can be achieved while machine learning techniques keep their ability to improve predictive power.

Background: Diabetes mellitus (DM) is one of the major risk factors contributing to Acute Coronary Syndromes (ACS) and is associated with an increased risk of adverse clinical outcomes following percutaneous coronary intervention (PCI), even when the second generation of drug-eluting stents (DES) is used. In order to overcome the disadvantages of permanent caging of a vessel with metallic DES, bioresorbable scaffold (BRS) technology has been recently developed. However, the prognosis of patients with DM and ACS treated with PCI via subsequent implantation of Magmaris (Biotronik, Berlin, Germany)—a novel magnesium-bioresorbable scaffold—is poorly investigated. Methods: A total of 193 consecutive subjects with non-ST elevation acute coronary syndrome (NSTE-ACS) who, from October 2016 to March 2020, received one or more Magmaris scaffolds were enrolled in this study. The diabetic group was compared with non-diabetic subjects. Results: There were no significant differences in the occurrence of primary endpoints (cardiovascular death, myocardial infarction, and in-stent thrombosis) and principal secondary endpoints (target-lesion failure, scaffold restenosis, death from any reason, and other cardiovascular events) between the two compared groups in a 1-year follow-up period. Conclusions: The early 1-year-outcome of magnesium bioresorbable scaffold (Magmaris) seems to be favorable and suggests that this novel BRS is safe and effective in subjects with NSTE-ACS and co-existing DM.

Railway infrastructure monitoring is crucial for transportation reliability and travelers’ safety. However, it requires plenty of human resources that generate high costs and is limited to the efficiency of the human eye. Integrating machine learning into the railway monitoring process can overcome these problems. Since advanced algorithms perform equally to humans in many tasks, they can provide a faster, cost-effective, and reproducible evaluation of the infrastructure. The main issue with this approach is that training machine learning models involves acquiring a large amount of labeled data, which is unavailable for rail infrastructure. We trained YOLOv5 and MobileNet architectures to meet this challenge in low-data-volume scenarios. We established that 120 observations are enough to train an accurate model for the object-detection task for railway infrastructure. Moreover, we proposed a novel method for extracting background images from railway images. To test our method, we compared the performance of YOLOv5 and MobileNet on small datasets with and without background extraction. The results of the experiments show that background extraction reduces the sufficient data volume to 90 observations.

Background: Acute coronary syndrome (ACS) as a clinical manifestation of coronary artery disease (CAD) remains a significant cause of mortality and morbidity, as reported worldwide annually. The second generation of drug-eluting stents (DES) is a gold standard in percutaneous interventions in ACS patients however, permanent caging of the vessel with metallic DES has some drawbacks. Bioresorbable vascular scaffolds (BRS) were designed as a temporal vessel-supporting technology allowing for anatomical and functional restoration. Nevertheless, following the initial encouraging reports, numerous concerns about the safety of BRS occurred. Methods: In this study, a 1-year performance of 193 patients with magnesium BRS — Magmaris (Biotronik, Berlin, Germany) was evaluated in comparison to 160 patients with polymer BRS — Absorb (Abbott-Vascular, Chicago, USA) in the non-ST-segment elevation-ACS setting. Results: The Magmaris, when compared to Absorb showed a significantly lower rate of primary endpoint (death from cardiac causes, myocardial infarction, stent thrombosis) as well as target lesion failure in 30-day and 1 year follow-up. In the Absorb group, a significantly higher rate of stent thrombosis was observed. Conclusions: Data from the present study suggests encouraging safety a profile and more favorable clinical outcomes of Magnesium BRS in comparison to the polymer Absorb — BRS. Background: Acute coronary syndrome (ACS) as a clinical manifestation of coronary artery disease (CAD) remains a significant cause of mortality and morbidity, as reported worldwide annually. The second generation of drug-eluting stents (DES) is a gold standard in percutaneous interventions in ACS patients however, permanent caging of the vessel with metallic DES has some drawbacks. Bioresorbable vascular scaffolds (BRS) were designed as a temporal vessel-supporting technology allowing for anatomical and functional restoration. Nevertheless, following the initial encouraging reports, numerous concerns about the safety of BRS occurred. Methods: In this study, a 1-year performance of 193 patients with magnesium BRS — Magmaris (Biotronik, Berlin, Germany) was evaluated in comparison to 160 patients with polymer BRS — Absorb (Abbott-Vascular, Chicago, USA) in the non-ST-segment elevation-ACS setting. Results: The Magmaris, when compared to Absorb showed a significantly lower rate of primary endpoint (death from cardiac causes, myocardial infarction, stent thrombosis) as well as target lesion failure in 30-day and 1 year follow-up. In the Absorb group, a significantly higher rate of stent thrombosis was observed. Conclusions: Data from the present study suggests encouraging safety a profile and more favorable clinical outcomes of Magnesium BRS in comparison to the polymer Absorb — BRS.