Tr en Amaç: Bu çalışmada bir Aile Hekimliği Anabilim Dalı’na bağlı Eğitim Aile Sağlığı Merkezleri'nde (EASM) aşı reddi oranlarının ve etkileyen faktörlerin belirlenmesi amaçlanmıştır. Yöntem: Bu çalışma karma bir araştırma olarak tasarlanmış ve XXXX Üniversitesi Aile Hekimliği Anabilim Dalı'nın iki EASM’sinde yürütülmüştür. Çalışmaya 2018 yılında Sağlık Bakanlığı'nın Genişletilmiş Bağışıklık Programı kapsamında yapılması gerekli aşılardan en az birini almayan ebeveynler dahil edilmiştir. Veri toplama yöntemi olarak telefonda yarı yapılandırılmış görüşme tekniği kullanılmış ve içerik analizi uygulanmıştır. Çalışmaya katılmaya gönüllü 6 ebeveyn ile derinlemesine bir görüşme yapılmıştır. Bulgular: Her iki ebeveyn için ortalama yaş 30±1.2 yıldı. Aşı reddi yapan tüm ebeveynler (n=6) üniversite mezunuydu. Ebeveynlerin %66,7'si (n=4) yüksek gelir düzeyine sahipti. 2018 yılında aşılanması gereken 0-16 yaş arası 749 çocuğun tıbbi kayıtlarına göre, 9 çocukta (%1,2) en az bir aşının eksik olduğu gözlendi. Dört çocuğa aşıya güvensizlik nedeniyle aşı yapılmamıştı. Ebeveynlerden üçü ise önceki aşılardan sonra gelişen komplikasyonlar nedeniyle aşılamayı reddetmişti. Sonuç: EASM'lerde aşı reddi oranları düşük bulundu ve aşı reddi yapan ebeveynlerin sosyoekonomik düzeyleri yüksekti. Aşı reddini etkileyen en önemli faktörler, aşı içeriğine duyulan güvensizlik ve aşılar hakkında yetersiz bilgi idi. Objective: It was aimed to determine the vaccine rejection rates and affecting factors in the Training Family Health Centers (TFHC) affiliated with a department of family medicine. Method: This study was designed as a mixed research and conducted in two TFHC of Department of Family Medicine of XXXX University. In 2018, parents who did not receive at least one of the vaccines required under the Ministry of Health's Extended Immunity Program were included. Semi-structured interview technique was used on the telephone as the data collection method. Content analysis was applied statistically. It was observed that in 9 children at least one vaccine was missing. An in-depth interview was done with 6 volunteering parents. Results: The mean age was 30±1.2 years for both parents. All parents (n=6) who refused vaccination were university graduates. 66.7% of the parents (n=4) had high monthly income. Missing vaccinations were observed in 3 (3.3%) out of 89 children aged 0-2 years registered to the TFHC-1 (3 units), and 4 (1.32%) of 301 children between the ages of 0-2 registered to the second TFHC-2 (2 units). Four children were not vaccinated due to distrust to the vaccine. Three of the parents refused vaccination due to complications developed after previous vaccinations. One parent rejected the immunization due to the different schedules between countries and changes in the schedules. One parent thought that the vaccine was not so important because it was not obligatory. One child was not vaccinated because he was afraid of vaccination. Conclusion: Vaccine rejection rates were found low in our TFHCs and socioeconomic levels of those who rejected the vaccine were high. The most important factors affecting vaccine rejection were the lack of confidence in the vaccine content and insufficient information about vaccines.
16 October 2025 in The Eurasian Journal of Medicine
Atherosclerotic cardiovascular disease (ASCVD) is one of the leading causes of global morbidity and mortality. The current study provides a systematic review of the use of artificial intelligence (AI) technologies applied to the prediction and management of ASCVD. Traditional risk assessment approaches have their restrictions, leading to a growing preference for AI and machine learning techniques in risk assessment. First, this study tackles the complex pathophysiology of ASCVD and the problems associated with the current diagnosis, followed by an in-depth analysis of the wide variety of AI models that can be applied to electronic health records, medical imaging data, and other biomarkers. Special attention will be paid toward the potential of natural language processing models like bidirectional encoder representations from transformers in predicting risk from textual clinical data, and the overwhelming success of convolutional neural networks such as residual neural network and visual geometry group in plaque-based analysis through imaging modalities. Although the research results show that these models have a lot to offer in the clinical world, the authors also describe some serious disadvantages: data bias, interpretability of the model, and computational needs. It highlights, in particular, the need for multicenter validation studies as well as developing explainable AI techniques. Overall, AI-based approaches may pave the way for a new paradigm in ASCVD management. Nevertheless, deploying these technologies in everyday clinical practice will require overcoming technical, ethical, and regulatory challenges. As such, interdisciplinary collaboration and thorough clinical validation studies are essential for fulfilling the promise of these novel strategies to enhance patient outcomes.Cite this article as: Şakiroğlu F, Çolak C, Çolak MC. Pre-trained artificial intelligence models in the prediction and classification of atherosclerotic cardiovascular disease. Eurasian J Med. 2025, 57(3), 0937, doi:10.5152/eurasianjmed.2025.25937.
The digital transformation in healthcare has led to an increase in the use of telemedicine and artificial intelligence (AI)based applications. This study a
27 October 2026 in Challenge Journal of Perioperative Medicine
Objective: The aim was to evaluate the relationship between health literacy, decision conflict, and body image in early-stage breast cancer patients eligible for breast-conserving surgery (BCS) who opted for either breast-conserving surgery or mastectomy.Methods: This prospective, cross-sectional study included 60 female patients eligible for BCS (30 mastectomy, 30 BCS). Health literacy was assessed using the European Health Literacy Survey Questionnaire-6 (HLS-EU-Q6); decision conflict was evaluated using the SURE and the Decision Conflict Scale (DCS); and body image was assessed using the Body Image Scale. The groups were compared using appropriate statistical methods, and factors associated with decisional conflict were explored using logistic regression analysis.Results: The groups were similar in terms of age, marital status, and education level (p > 0.05). The level of health literacy was significantly higher in the mastectomy group compared to the BCS group (median 3.52 vs. 2.36; p < 0.001). In contrast, body image satisfaction was higher in the BCS group (3.50 vs. 2.00; p < 0.001), while body image-related anxiety was lower (2.00 vs. 4.00; p < 0.001). While SURE scores were higher in the mastectomy group (4.00 vs. 2.00; p < 0.001), the total DCS score was higher in the BCS group (47.65 vs. 14.66; p < 0.001). In the multivariable analysis, age and health literacy were not found to be significant independent predictors of decision conflict (p > 0.05).Conclusion: Health literacy, decisional conflict, and body image differed significantly between patients who underwent mastectomy and those who underwent breast-conserving surgery. Because these variables were assessed after the surgical decision had already been finalized, these findings should be interpreted as associations rather than causal determinants of surgical choice; larger, longitudinal studies assessing these factors before the decision is made are needed to clarify their role in shared decision-making.
Background: The clinical adoption of artificial intelligence in emergency departments (ED) is hindered by the “black-box” nature of complex models and retrospective data leakage from downstream laboratory results. Aims: We aimed to develop a transparent, dynamic machine learning model to predict hospital admissions by establishing a pre-laboratory “information ceiling” using structured electronic health record (EHR) data. Study Design: Retrospective cohort study. Methods: Utilizing 387,407 patient encounters in the MIMIC-IV-ED (v2.2) database, we developed a dynamic Explainable Boosting Machine (EBM) validated across chronologically distinct anchor_year_group blocks (2008–2016 training vs. 2017–2019 testing) with strict patient-level separation. Anchoring clock-zero (T = 0) at ED arrival (intime) with baseline triage parameters and pre-existing historical records, the model evaluated patients sequentially in 30 min landmarks up to 120 min (T = 120), incorporating timestamped physiological volatility and early medication administrations (pyxis) recorded strictly prior to the prediction landmark and disposition decision. Predictive performance was compared against a black-box HistGradientBoosting (HGB) model and an L2-regularized logistic regression baseline. Results: The dynamic EBM provided strong baseline discrimination at T = 0 with an ROC-AUC of 0.8048 [95% CI: 0.800–0.806] and a PR-AUC of 0.7395 [95% CI: 0.732–0.742]. Incorporating longitudinal physiological trajectories over a two-hour window yielded a modest, statistically significant improvement at T = 120 (ROC-AUC: 0.8168 [95% CI: 0.813–0.819], PR-AUC: 0.7595 [95% CI: 0.754–0.763], Sensitivity: 80.74%, Specificity: 65.09%, Positive Predictive Value: 61.16%; ΔROC-AUC = +0.0120, p < 0.0001). At T = 120, the opaque HGB benchmark achieved a slightly higher ROC-AUC of 0.8208 [95% CI: 0.817–0.824] (ΔROC-AUC = −0.0040, p = 0.0018), whereas EBM substantially outperformed the linear logistic regression baseline (ROC-AUC: 0.7420 [95% CI: 0.738–0.746]). Without relying on post hoc approximations, EBM generated directly inspectable shape functions capturing non-linear clinical risk relationships, including an observational risk inflection at five home medications and substantial risk penalties for transient hypoxic dips and extreme pulse pressures. Conclusions: By modeling early ED evaluation as a dynamic trajectory, the EBM achieves discriminative performance closely approaching black-box ensemble methods while maintaining full architectural transparency. Although predicting historical admission decisions requires prospective validation before clinical deployment, this calibrated glass-box framework offers an interpretable foundation for early risk stratification in the ED.
28 April 2026 in Essentials of Frontline Medicine Journal
Objective: Atherosclerotic Cardiovascular Disease (ASCVD) remains a leading cause of morbidity and mortality worldwide and represents a substantial public health burden. Artificial Intelligence (AI) and Machine Learning (ML) are increasingly integrated into ASCVD diagnosis, prediction, and management. This review aims to evaluate the role and potential of Incremental Learning (IL) in improving ASCVD risk prediction and classification, addressing the limitations of static ML models. Methods: This narrative review was developed in accordance with the SANRA criteria. Current AI/ML models commonly applied in ASCVD—such as Logistic Regression, Random Forests, and Convolutional Neural Networks—were examined with a focus on their reliance on static datasets and vulnerability to performance degradation caused by concept drift. The challenges of data heterogeneity, quality issues in Electronic Health Records (EHRs), and the computational burden of repeated full-model retraining were analyzed. Literature on Incremental Learning algorithms was reviewed to assess their applicability in continuously evolving clinical environments. Results: Incremental Learning enables AI models to integrate new data over time while preserving previously acquired knowledge, thus enhancing adaptability in the context of evolving ASCVD risk factors, diagnostic criteria, and clinical guidelines. The approach supports more accurate and individualized risk prediction and reduces computational overhead. However, catastrophic forgetting—loss of earlier knowledge during adaptation to new data—emerged as a key limitation. Advanced IL strategies, including experience replay, have shown potential in mitigating this issue, but further validation is required for clinical implementation. Conclusion: Incremental Learning offers a forward-looking, adaptive framework for ASCVD prediction and classification, outperforming traditional static ML models in dynamic and heterogeneous data settings. Despite its advantages, ensuring model stability and preventing catastrophic forgetting remain essential for safe and reliable clinical deployment. Future research should prioritize methodological refinements and robust validation to support the integration of continuously learning AI systems into ASCVD management.