التصنيف: الأبحاث

Manual vetting of radiology referrals is an essential daily task to ensure the appropriateness of the received referrals. Such tasks require sufficient clinical experience and may challenge the radiology staff. With the emerging of artificial intelligence (AI) technology and advancement in natural language processing NLP, most of the available machine learning-based NLP models targeted research cohort building and healthcare qua lity. Other healthcare management tasks such as auto-vetting radiology referrals have not been adequately encoded. Furthermore, challenges, including class imbalance and lack of direct comparison with humans, are yet to be investigated sufficiently. In this study, a set of machine learning and deep learning models were developed for auto-vetting of lumbar spine magnetic resonance imaging LSMRI referrals as indicated or not indicated for scanning using referrals from two hospitals. The impact of applying one of the text augmentation techniques on the models’ performance has been investigated. In addition, the performance of four different feature extraction techniques has been critically analyzed. Moreover, a comparison has been conducted between the developed models with two expert radiologists who were not involved in establishing the gold standard labels using an unseen dataset. The results show that the models’ performances significantly improved with the augmented data, with an increase in F1 scores ranging from 1% to 8%. Support vector machine with bag of words achieved the highest AUC reaching 0.99. Convolutional neural network model achieved the second-highest model with AUC = 0.97. All models outperformed the two expert radiologists when comparisons were conducted on the unseen dataset.

The rapid advancement of artificial intelligence (AI) continues to gain interest in the healthcare sectors, particularly in radiology. There has been an extensive debate about AI-based applications and their potential effects on the future of radiology. The current advancement in AI-based applications such as machine-learning (ML) and deep learning (DL) algorithms has proven their effectiveness in administration task s (e.g., scheduling), diagnostic tasks such as objects detection (e.g., detection of abnormalities) and image classifications (e.g., classify tumours into benign or malignant) with efficient accuracy.

Referrals vetting is a necessary daily task to ensure the appropriateness of radiology referrals. Vetting requires extensive clinical knowledge and may challenge those responsible. This study aims to develop AI models to automate the vetting process and to compare their performance with healthcare professionals.

Breast imaging faces significant challenges with the increasing volume of medical imaging requests and the potential for missed lesions in breast screening programs. Solutions to address these challenges are being actively sought, particularly with the recent advancements and adoption of artificial intelligence (AI)-based applications to enhance workflow efficiency and improve patient-healthcare outcomes. AI tools have been proposed and used to analyze various forms of breast imaging, and most published studies focus on their use for detecting and classifying breast lesions, segmenting breast tissue, evaluating breast density, and assessing breast cancer risk. This article reviews the background of conventional computer-aided detection (CAD) systems and AI, as well as AI-based applications in breast medical imaging for lesion identification, segmentation, and classification, breast density evaluation, and cancer risk assessment. Additionally, the challenges and limitations of AI-based applications in breast imaging are discussed.