Search

Introduction: Leukemia is the eleventh most prevalent type of cancer worldwide, with acute myeloid leukemia (AML) being the most frequent malignant blood malignancy in adults. Microscopic blood tests are the most common methods for identifying leukemia subtypes. An automated optical image- processing system using artificial intelligence (AI) has recently been applied to facilitate clinical decisionmaking. This study aims evaluate the performance of all AI-based approaches for the detection and diagnosis of AML. Methods: Medical databases, including PubMed, Web of Science, and Scopus, were searched until December 2023. We used the "metafor" and "metagen" libraries in R to analyze the different models used in the studies. Accuracy and sensitivity were the primary outcome measures. Results: Ten studies were included in our review and metaanalysis, conducted between 2016 and 2023. Most deep-learning models have been utilized, including convolutional neural networks (CNNs). The common and random effects models had accuracies of 1.0000 [0.9999; 1.0001] and 0.9557 [0.9312; 0.9802], respectively. The common effect model and random effects model had high sensitivity values of 1.0000 and 0.8581, respectively, indicating that the machine learning models in this study can accurately detect true-positive leukemia cases. Studies have shown substantial variation in accuracy and sensitivity, as shown by the Q-values and I² statistics. Conclusion: Our systematic review and meta-analysis found an overall high accuracy and sensitivity of AI models in correctly identifying true-positive cases of AML. Future research should focus on unifying reporting methods and performance assessment metrics of AI-based diagnostics. [ABSTRACT FROM AUTHOR]

Introduction: Soft tissue sarcomas (STS) are a rare group of malignancies. Diagnostic biopsies require experts and are invasive with long diagnostic intervals. Artificial intelligence (AI) based STS models may be accurate detection and categorization tools; however, their diagnostic performance is questionable. Method: The PubMed, Scopus, and Web of Science databases were searched for related studies published until January 10,2024. Studies that developed or used AI-based models to diagnose STS were included. Results: Eleven studies were included in this meta-analysis. The common effects model yielded an accuracy of 0.8923 [0.8831; 0.9016], and the random-effects model yielded an accuracy of 0.8524 [0.8132; 0.8916], The Tau2 was 0.0094 [0.0055; 0.0202], and the I² statistic was 93.2% [91.1%; 94.7%], suggesting a high level of heterogeneity among the studies. The most accurate model was the Decision Tree (DT) model used in the study by Alaoui et al. (2021), with an accuracy of 0.9900 [0.9675; 1.0125], The least accurate model was the MLP model used in the study by Yang et al. (2021), with an accuracy of 0.5720 [0.5107; 0.6333], Conclusion: AI-based models show promising results for the diagnosis of STS. However, future studies should address the value of AI in the real-world setting. [ABSTRACT FROM AUTHOR]

Diabetic ketoacidosis (DKA) is a life-threatening complication of type 1 diabetes mellitus in children. Despite the presence of dehydration, hypertension occurs in a significant proportion of children with DKA. There is a lack of clarity in the literature regarding the management of hypertension in patients with paediatric DKA. Herein, we report the case of an adolescent boy who presented with DKA and severe hypertension. His neurological status was closely monitored. There was a gradual decline in his blood pressure with an improvement in the pH over the next 72 hours. The combination of severe DKA and hypertension can be a challenging clinical dilemma, especially regarding fluid management. Studies on severe DKA in children are exacting, given the rarity of this condition. A multi-centre study is suggested to provide a meaningful analysis of this aspect of DKA. [ABSTRACT FROM AUTHOR]

Severe acute respiratory syndrome-coronavirus-2 (SARS-CoV2), also known as COVID-19, has rapidly spread resulting in a worldwide pandemic. Although COVID-19 infections in children are generally mild and nonfatal, there is increasing recognition of its association with the multisystem inflammatory syndrome in children (MIS-C), leading to serious illness and possible long-term complications. This report describes a 6-month-old Indian infant who presented with a 4-day history of fever with nonspecific signs of viral illness and erythematous rash. Although the initial echocardiogram was normal, subsequent scans showed progressive dilatation of bilateral coronary arteries. Despite the timely intervention, he developed left coronary artery thrombosis, leading to myocardial infarction. His SARS-CoV-2 antibody titers were strongly positive. Through this case, we discuss the management of MIS-C with coronary artery involvement. The long-term outcome of coronary artery aneurysm due to MIS-C remains unknown and close follow-up is important. Further research is pivotal for a better understanding of MIS-C. [ABSTRACT FROM AUTHOR]