Introduction: Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are critical for improving patients’ outcomes, as over 40% of patients with EC are diagnosed after metastasis. Recent advances in machine learning (ML) techniques, particularly in computer vision, have demonstrated promising applications in medical image processing, assisting clinicians in making more accurate and faster diagnostic decisions. Given the significance of early detection of EC, this systematic review aims to summarize and discuss the current state of research on ML-based methods for the early detection of EC. Methods: We conducted a comprehensive systematic search of five databases (PubMed, Scopus, Web of Science, Wiley, and IEEE) using search terms such as “ML”, “Deep Learning (DL (“, “Neural Networks (NN)”, “Esophagus”, “EC” and “Early Detection”. After applying inclusion and exclusion criteria, 31 articles were retained for full review. Results: The results of this review highlight the potential of ML-based methods in the early detection of EC. The average accuracy of the reviewed methods in the analysis of endoscopic and computed tomography (CT (images of the esophagus was over 89%, indicating a high impact on early detection of EC. Additionally, the highest percentage of clinical images used in the early detection of EC with the use of ML was related to white light imaging (WLI) images. Among all ML techniques, methods based on convolutional neural networks (CNN) achieved higher accuracy and sensitivity in the early detection of EC compared to other methods. Conclusion: Our findings suggest that ML methods may improve accuracy in the early detection of EC, potentially supporting radiologists, endoscopists, and pathologists in diagnosis and treatment planning. However, the current literature is limited, and more studies are needed to investigate the clinical applications of these methods in early detection of EC. Furthermore, many studies suffer from class imbalance and biases, highlighting the need for validation of detection algorithms across organizations in longitudinal studies.

Hepatic encephalopathy (HE) is defined as a specific type of cerebral dysfunction that encompasses a wide range of cognitive, psychomotor, and psychiatric disturbances. The burgeoning field of Artificial Intelligence (AI), particularly Machine Learning (ML), offers promising avenues for early detection and enhanced control of HE. This scoping review aims to provide a consolidated overview of AI’s role in the diagnosis and management of HE, thereby informing and guiding future research endeavors in this domain. We followed Arksey and O’Malley’s methodological framework to perform this scoping review, using PubMed, Web of Science, Scopus, ScienceDirect, and IEEE databases to find relevant articles. We also utilized the PRISMA standard to report our review in a standardized manner. Studies that focused on the applications of AI or ML techniques in relation to the prediction or diagnosis of HE disease were included. Out of the 231 articles identified, 20 were ultimately included in this scoping review. The integration of artificial neural networks and expert systems represented an early and pioneering approach in applying AI to HE. Among supervised learning algorithms, Support Vector Machine emerged as the most frequently employed technique in HE research, based on our review of the selected studies. Notably, the primary application of AI in HE studies has been predictive modeling (n = 14), followed by five studies focused on classifying HE stages and one study analyzing patient survival using AI methodologies. This scoping review highlights the growing use of AI and ML diagnostic models and predictive tools utilizing various data types. These advancements have the potential to positively impact patient outcomes. Future research should focus on validating and implementing these AI models in clinical settings to assess their real-world effectiveness in improving patient care.

Introduction: Esophageal cancer (EC) is a significant global health problem, with an estimated 7th highest incidence and 6th highest mortality rate. Timely diagnosis and treatment are critical for improving patients' outcomes, as over 40% of patients with EC are diagnosed after metastasis. Recent advances in machine learning (ML) techniques, particularly in computer vision, have demonstrated promising applications in medical image processing, assisting clinicians in making more accurate and faster diagnostic decisions. Given the significance of early detection of EC, this systematic review aims to summarize and discuss the current state of research on ML-based methods for the early detection of EC. Methods: We conducted a comprehensive systematic search of five databases (PubMed, Scopus, Web of Science, Wiley, and IEEE) using search terms such as "ML", "Deep Learning (DL(", "Neural Networks (NN)", "Esophagus”, “EC" and “Early Detection”. After applying inclusion and exclusion criteria, 31 articles were retained for full review. Results: The results of this review highlight the potential of ML-based methods in the early detection of EC. The average accuracy of the reviewed methods in the analysis of endoscopic and computed tomography (CT (images of the esophagus was over 89%, indicating a high impact on early detection of EC. Additionally, the highest percentage of clinical images used in the early detection of EC with the use of ML was related to white light imaging (WLI) images. Among all ML techniques, methods based on convolutional neural networks (CNN) achieved higher accuracy and sensitivity in the early detection of EC compared to other methods. Conclusion: Our findings suggest that ML methods may improve accuracy in the early detection of EC, potentially supporting radiologists, endoscopists, and pathologists in diagnosis and treatment planning. However, the current literature is limited, and more studies are needed to investigate the clinical applications of these methods in early detection of EC. Furthermore, many studies suffer from class imbalance and biases, highlighting the need for validation of detection algorithms across organizations in longitudinal studies.