Venoarterial extracorporeal membrane oxygenation (va-ECMO) is an advanced life support for critically ill patients with refractory cardiogenic shock. This temporary support bridges time for recovery, permanent assist, or transplantation in patients with high risk of mortality. However, the benefit of this modality is still subject of discussion and despite the continuous development of critical care medicine, severe cardiogenic shock remains associated with high mortality. Therefore, this work aims to analyze the current literature regarding in-hospital mortality and complication rates of va-ECMO in patients with cardiogenic shock. We conducted a systematic review and meta-analysis of the most recent literature to analyze the outcomes of va-ECMO support. Using the PRISMA guidelines, Medline (PubMed) and Scopus (Elsevier) databases were systematically searched up to May 2022. Meta-analytic pooled estimation of publications variables was performed using a weighted random effects model for study size. Thirty-two studies comprising 12756 patients were included in the final analysis. Between 1994 and 2019, 62% (pooled estimate, 8493/12756) of patients died in the hospital. More than one-third of patients died during ECMO support. The most frequent complications were renal failure (51%, 693/1351) with the need for renal replacement therapy (44%, 4879/11186) and bleeding (49%, 1971/4523), bearing the potential for permanent injury or death. Univariate meta-regression analyses identified age over 60 years, shorter ECMO duration and presence of infection as variables associated with in-hospital mortality, while the studies reporting a higher incidence of cannulation site bleeding were unexpectedly associated with a reduced in-hospital mortality. Extracorporeal membrane oxygenation is an invasive life support with a high risk of complications. We identified a pooled in-hospital mortality of 62% with patient age, infection and ECMO support duration being associated with a higher mortality. Protocols and techniques must be developed to reduce the rate of adverse events. Finally, randomized trials are necessary to demonstrate the effectiveness of va-ECMO in cardiogenic shock.

The development of extracorporeal life support technology has added a new dimension to the care of critically ill patients who fail conventional treatment options. Extracorporeal membrane oxygenation (ECMO)—specialized temporary life support for patients with severe cardiac or pulmonary failure—plays a role in bridging the time for organ recovery, transplant, or permanent assistance. The overall patient outcome is dependent on the underlying disease, comorbidities, patient reaction to critical illness, and potential adverse events during ECMO. Moreover, the contact of the blood with the large artificial surface of an extracorporeal system circuit triggers complex inflammatory and coagulation responses. These processes may further lead to endothelial injury and disrupted microcirculation with consequent end-organ dysfunction and the development of adverse events like thromboembolism. Therefore, systemic anticoagulation is considered crucial to alleviate the risk of thrombosis and failure of ECMO circuit components. The gold standard and most used anticoagulant during extracorporeal life support is unfractionated heparin, with all its benefits and disadvantages. However, therapeutic anticoagulation of a critically ill patient carries the risk of clinically relevant bleeding with the potential for permanent injury or death. Similarly, thrombotic events may occur. Therefore, different anticoagulation strategies are employed, while the monitoring and the balance of procoagulant and anticoagulatory factors is of immense importance. This narrative review summarizes the most recent considerations on anticoagulation during ECMO support, with a special focus on anticoagulation monitoring and future directions.

Papillary thyroid carcinoma (PTC) is generally considered an indolent cancer. However, patients with cervical lymph node metastasis (LNM) have a higher risk of local recurrence. This study evaluated and compared four machine learning (ML)-based classifiers to predict the presence of cervical LNM in clinically node-negative (cN0) T1 and T2 PTC patients. The algorithm was developed using clinicopathological data from 288 patients who underwent total thyroidectomy and prophylactic central neck dissection, with sentinel lymph node biopsy performed to identify lateral LNM. The final ML classifier was selected based on the highest specificity and the lowest degree of overfitting while maintaining a sensitivity of 95%. Among the models evaluated, the k-Nearest Neighbor (k-NN) classifier was found to be the best fit, with an area under the receiver operating characteristic curve of 0.72, and sensitivity, specificity, positive and negative predictive values, F1 and F2 scores of 98%, 27%, 56%, 93%, 72%, and 85%, respectively. A web application based on a sensitivity-optimized kNN classifier was also created to predict the potential of cervical LNM, allowing users to explore and potentially build upon the model. These findings suggest that ML can improve the prediction of LNM in cN0 T1 and T2 PTC patients, thereby aiding in individual treatment planning.

The aim was to explore the factors associated with the financial burden (FB) of medical care, dental care, and medicines among older-aged people in Slovenia, Serbia, and Croatia using EU-SILC 2017. The highest frequency of FB of medical care and medicines was in Croatia (50% and 69.1%, respectively) and of dental care in Slovenia (48.5%). The multivariate logistic regression analysis with FB as an outcome variable showed that the FB of medical care was associated with being married (OR: 1.54), reporting not severe (OR: 1.51) and severe limitations in daily activities (OR: 2.05), having higher education (OR: 2.03), and heavy burden of housing costs (OR: 0.51) in Slovenia, with very bad self-perceived health (OR: 5.23), having the slight (OR: 0.69) or heavy (OR: 0.47) burden of housing costs, making ends meet fairly easily or with some difficulty (OR: 3.58) or with difficulty or great difficulty (OR: 6.80) in Serbia, and with being married (OR: 1.43), having heavy burden of housing costs (OR: 0.62), and making ends meet fairly easily or with some difficulty (OR: 2.08) or with difficulty or great difficulty (OR: 2.52) in Croatia. The older-aged have the FB of healthcare, especially the poorest or those with health problems.

After primary treatment of localized prostate carcinoma (PC), up to a third of patients have disease recurrence. Different predictive models have already been used either for initial stratification of PC patients or to predict disease recurrence. Recently, artificial intelligence has been introduced in the diagnosis and management of PC with a potential to revolutionize this field. The aim of this study was to analyze machine learning (ML) classifiers in order to predict disease progression in the moment of prostate‐specific antigen (PSA) elevation during follow‐up. The study cohort consisted of 109 PC patients treated with external beam radiotherapy alone or in combination with androgen deprivation therapy. We developed and evaluated the performance of two ML algorithms based on artificial neural networks (ANN) and naïve Bayes (NB). Of all patients, 72.5% was randomly selected for a training set while the remaining patients were used for testing of the models. The presence/absence of disease progression was defined as the output variable. The input variables for models were conducted from the univariate analysis preformed among two groups of patients in the training set. They included two pretreatment variables (UICC stage and Gleason’s score risk group) and five posttreatment variables (nadir PSA, time to nadir PSA, PSA doubling time, PSA velocity, and PSA in the moment of disease reevaluation). The area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, negative predictive value, and predictive accuracy was calculated to test the models’ performance. The results showed that specificity was similar for both models, while NB achieved better sensitivity then ANN (100.0% versus 94.4%). The ANN showed an accuracy of 93.3%, and the matching for NB model was 96.7%. In this study, ML classifiers have shown potential for application in routine clinical practice during follow‐up when disease progression was suspected.

Background: Recurrent disease in post-irradiation patients with cervical cancer is often difficult to delineate on magnetic resonance imaging (MRI), because posttreatment changes can have a similar appearance, and further evaluation is often required. The aims of the study were to evaluate positron emission tomography/computed tomography with 18F-fluorodeoxyglucose (FDG PET-CT) diagnostic role in suspected recurrent cervical cancer after radiotherapy, compare it to MRI, and assess their prognostic impact in these patients. Patients and methods: This cohort retrospective study included patients previously treated with radiotherapy for carcinoma of uterine cervix with suspected recurrence, who had undergone MRI of abdomen and pelvis, and were subsequently evaluated on FDG PET-CT, with minimum follow-up period of 12 months. Results: In the total of 84 patients included in analysis, MRI vs . FDG PET-CT showed sensitivity, specificity and accuracy of 80.1%, 52.4% and 66.7%, vs . 97.6%, 61.9% and 79.8%, respectively. Patients with positive findings on MRI (Log Rank, p = 0.003) and PET-CT (Log Rank, p < 0.001) had shorter progression-free survival (PFS) than those with negative results. In univariate Cox regression models, MRI and FDG PET-CT results were found to be related to PFS (p = 0.005 and p < 0.001, respectively). However, multivariate analysis proved only FDG PET-CT to be independent prognostic factor, where patients with positive FDG PET-CT results had almost nine times higher risk of progression (p < 0.001). Conclusion: FDG PET-CT represents useful diagnostic tool in suspected recurrent cervical cancer after radiotherapy, showing high sensitivity in its detection. In addition, it is an independent factor in predicting progression-free survival in these patients.