Background: Accurate prediction of short-term mortality in patients with acute pulmonary embolism (PE) is critical for optimizing treatment strategies and improving patient outcomes. The Pulmonary Embolism Severity Index (PESI) is the current reference score used for this purpose, but it has limitations regarding predictive accuracy. Our aim was to develop a new short-term mortality prediction model for PE patients based on deep learning (DL) with multimodal data, including imaging and clinical/demographic data.Methods and Results: We developed a novel multimodal deep learning (mmDL) model using contrast-enhanced multidetector computed tomography scans combined with clinical and demographic data to predict short-term mortality in patients with acute PE. We benchmarked various machine learning architectures, including XGBoost, convolutional neural networks (CNNs), and Transformers. Our cohort included 207 acute PE patients, of whom 53 died during their hospital stay. The mmDL model achieved an area under the receiver operating characteristic curve (AUC) of 0.98 (P<0.001), significantly outperforming the PESI score, which had an AUC of 0.86 (P<0.001). Statistical analysis confirmed that the mmDL model was superior to PESI in predicting short-term mortality (P<0.001).Conclusions: Our proposed mmDL model predicts short-term mortality in patients with acute PE with high accuracy and significantly outperforms the current standard PESI score.

Artificial Intelligence (AI) is reshaping healthcare through advancements in clinical decision support and diagnostic capabilities. While human expertise remains foundational to medical practice, AI-powered tools are increasingly matching or exceeding specialist-level performance across multiple domains, paving the way for a new era of democratized healthcare access. These systems promise to reduce disparities in care delivery across demographic, racial, and socioeconomic boundaries by providing high-quality diagnostic support at scale. As a result, advanced healthcare services can be affordable to all populations, irrespective of demographics, race, or socioeconomic background. The democratization of such AI tools can reduce the cost of care, optimize resource allocation, and improve the quality of care. In contrast to humans, AI can potentially uncover complex relationships in the data from a large set of inputs and generate new evidence-based knowledge in medicine. However, integrating AI into healthcare raises several ethical and philosophical concerns, such as bias, transparency, autonomy, responsibility, and accountability. In this study, we examine recent advances in AI-enabled medical image analysis, current regulatory frameworks, and emerging best practices for clinical integration. We analyze both technical and ethical challenges inherent in deploying AI systems across healthcare institutions, with particular attention to data privacy, algorithmic fairness, and system transparency. Furthermore, we propose practical solutions to address key challenges, including data scarcity, racial bias in training datasets, limited model interpretability, and systematic algorithmic biases. Finally, we outline a conceptual algorithm for responsible AI implementations and identify promising future research and development directions.

Hayıroğlu Mİ, et al. J Lipid Atheroscler. 2022 Sep;11(3):280-287. https://doi.org/10.12997/jla.2022.11.3.280

Background: Currently, recommended pre-operative risk assessment models including the revised cardiac risk index (RCRI) are not very effective in predicting postoperative myocardial damage after non-elective surgery, especially for elderly patients. Aims: This study aimed to create a new risk prediction model to assess myocardial injury after non-cardiac surgery (MINS) in elderly patients and compare it with the RCRI, a well-known pre-operative risk prediction model. Materials and Methods: This retrospective study included 370 elderly patients who were over 65 years of age and had non-elective surgery in a tertiary hospital. Each patient underwent detailed physical evaluations before the surgery. The study cohort was divided into two groups: patients who had MINS and those who did not. Results: In total, 13% (48 out of 370 patients) of the patients developed MINS. Multivariable analysis revealed that creatinine, lymphocyte, aortic regurgitation (moderate-severe), stroke, hemoglobin, ejection fraction, and D-dimer were independent determinants of MINS. By using these parameters, a model called “CLASHED” was developed to predict postoperative MINS. The ROC analysis comparison demonstrated that the new risk prediction model was significantly superior to the RCRI in predicting MINS in elderly patients undergoing non-elective surgery (AUC: 0.788 vs. AUC: 0.611, p < 0.05). Conclusions: Our study shows that the new risk preoperative model successfully predicts MINS in elderly patients undergoing non-elective surgery. In addition, this new model is found to be superior to the RCRI in predicting MINS.

Patients with atrial fibrillation (AF) constitute a significant portion of hip fracture patients, and both diseases tend to present more frequently in older age. Our goal was to evaluate the long-term mortality of patients with AF who were free from heart failure undergoing hip fracture surgery. This observational, retrospective study was done in a single research and training hospital setting. Hospital electronic health record data, National Health Registry data, and National Death Registry System data for 233 consecutive patients who were above 65 years of age and were planned to undergo surgery for hip fracture were retrieved and analyzed. An experienced cardiologist evaluated the patients prior to surgery. Each member of the research cohort was categorized into one of the two groups based on their survival status (survivor and non-survivor groups). Of the 233 cases, 89 (38.2%) who were included in the investigation died during the follow-up period. The median long-term follow-up period was 34 (12-42) months. The frequency of AF was significantly higher in the non-survivor group. In multivariable Cox regression analysis, AF (HR: 2.195, 95%CI 1.365-3.415, p<0.001), advanced age, and blood urea level were determined as independent predictors for all-cause long-term mortality. AF is an independent predictor for long-term death in hip fracture cases above 65 years of age who were free from heart failure.

SUMMARY INTRODUCTION In the current literature, there has been an upsurge of cases of COVID-19-induced acute myocarditis. In this case-based review, we aimed to describe the clinical characteristics, imaging findings, and in-hospital course of acute myocarditis. In addition, the limitations of the myocarditis diagnosis were discussed since only fulminant myocarditis cases have been mentioned in the current literature. METHODS We performed a review of the literature of all patients who were diagnosed with COVID-19-induced acute myocarditis using the databases of PubMed, Embase, and the Cochrane. RESULTS 16 case reports were found to be related to COVID-19-induced acute myocarditis. We observed that the ECG findings in most of the COVID-19 patients were non-specific, including diffuse ST-segment elevation, non-specific intraventricular conduction delay, sinus tachycardia, and inverted T-waves in anterior leads. Echocardiographic findings of COVID-19-induced acute myocarditis patients ranged from preserved left ventricular ejection fraction (LVEF) without segmental abnormalities to reduced LVEF with global hypokinesia. Interestingly, a few patients with COVID-19-induced acute fulminant myocarditis were steroid-responsive and had an amelioration with glucocorticoid and immunoglobulin therapy. CONCLUSION Despite the COVID-19 pandemic worldwide, a limited number of cases has been shared in the current literature. There are a lot of difficulties in the differential diagnosis of acute myocarditis in the context of COVID-19.