: Artificial Intelligence techniques are widely used for medical purposes nowadays. One of the crucial applications is cancer detection. Due to the sensitivity of such applications, medical workers and patients interacting with the system must get a reliable, transparent, and explainable output. Therefore, this paper examines the interpretability and explainability of the Logistic Regression Model (LRM) for breast cancer detection. We analyze the accuracy and transparency of the LRM model. Additionally, we propose an NLP-based interface with a model interpretability summary and a contrastive explanation for users. Together with textual explanations, we provide a visual aid for medical practitioners to understand the decision-making process better.

Introduction/Objective. The purpose of this study was to assess the effectiveness of different approaches in the treatment of metastatic melanoma in daily clinical practice in a situation with limited and late availability of new drugs in a resource-limited country and to compare these parameters with those reported in clinical studies and from other real-world data. Methods. Main methods included assessment of overall survival (OS) and progression-free survival (PFS). Patients were included in the study if they were treated with first or second-line systemic therapy for radiologically/pathologically confirmed metastatic melanoma. Patients were divided into four groups based on the type of therapy they received: chemotherapy (dacarbazin), BRAF inhibitor (vemurafenib), BRAF/MEK inhibitors (vemurafenib/cobimetinib and trametinib/dabrafenib) and anti PD-1 therapy with pembrolizumab. Results. Regardless of the line of therapy, the calculated median OS in chemotherapy and vemurafenib group was nine months. The median OS in the BRAF/MEK inhibitor group was 14 months and 15 months in the pembrolizumab group. Median PFS in the chemotherapy group was four months, seven months for vemurafenib, in the BRAF/MEK inhibitor group nine months and in the pembrolizumab group six months. There was a statistically significant difference in survival between first and second-line therapy in the pembrolizumab group. Conclusion. Our results showed lower median OS and PFS in comparison to reported data from clinical trials. Compared to other real-world data from countries with similar problems related to the late reimbursement of new drugs, our research has shown similar results.

This article aims to summarise the current situation regarding digital archaeological archives in Bosnia and Herzogivina.

We examined dermatoglyphics of children in three Albanian and one Roma population sample (collected from 641 individuals from the Albanian populations and 226 individuals from the Roma population of both sexes). We compared Albanian and Roma populations based on four finger (whorl, radial and ulnar loop, and arch) and thirteen palmar traits (pattern frequencies in the Thenar/I interdigital area, II, III, and IV interdigital area, Hypothenar and axial »t« triradius position). The differences between the populations were more evident for palmar traits. In our study the Albanian and the Roma populations showed the best separation when finger and palmar traits are separately analyzed. As expected, the Albanian and the Roma populations separated in statistical analyses of most traits; the main reason for this is the different origins of two ethnic groups. The observed difference also indicates a low level of admixture between the Albanians and the Roma despite them living beside one another for several centuries.