Motivation: The price of medical treatment continues to rise due to (i) an increasing population; (ii) an aging human growth; (iii) disease prevalence; (iv) a rise in the frequency of patients that utilize health care services; and (v) increase in the price. Objective: Artificial Intelligence (AI) is already well-known for its superiority in various healthcare applications, including the segmentation of lesions in images, speech recognition, smartphone personal assistants, navigation, ride-sharing apps, and many more. Our study is based on two hypotheses: (i) AI offers more economic solutions compared to conventional methods; (ii) AI treatment offers stronger economics compared to AI diagnosis. This novel study aims to evaluate AI technology in the context of healthcare costs, namely in the areas of diagnosis and treatment, and then compare it to the traditional or non-AI-based approaches. Methodology: PRISMA was used to select the best 200 studies for AI in healthcare with a primary focus on cost reduction, especially towards diagnosis and treatment. We defined the diagnosis and treatment architectures, investigated their characteristics, and categorized the roles that AI plays in the diagnostic and therapeutic paradigms. We experimented with various combinations of different assumptions by integrating AI and then comparing it against conventional costs. Lastly, we dwell on three powerful future concepts of AI, namely, pruning, bias, explainability, and regulatory approvals of AI systems. Conclusions: The model shows tremendous cost savings using AI tools in diagnosis and treatment. The economics of AI can be improved by incorporating pruning, reduction in AI bias, explainability, and regulatory approvals.

Robot-assisted minimally invasive esophagectomy (RAMIE) was introduced as a further development of the conventional minimally invasive esophagectomy, aiming to further improve the high morbidity and mortality associated with open esophagectomy. We aimed to compare the outcomes between RAMIE and open esophagectomy, which remains a popular approach for resectable esophageal cancer. Ten studies meeting our inclusion criteria were identified, including five retrospective cohort, four prospective cohort, and one randomized controlled trial. RAMIE was associated with significantly lower rates of overall pulmonary complications (odds ratio (OR): 0.38, 95% confidence interval (CI): [0.26, 0.56]), pneumonia (OR: 0.39, 95% CI: [0.26, 0.57]), atrial fibrillation (OR: 0.53, 95% CI: [0.29, 0.98]), and wound infections (OR: 0.20, 95% CI: [0.07, 0.57]) and resulted in less blood loss (weighted mean difference (WMD): −187.08 mL, 95% CI: [−283.81, −90.35]) and shorter hospital stays (WMD: −9.22 days, 95% CI: [−14.39, −4.06]) but longer operative times (WMD: 69.45 min, 95% CI: [34.39, 104.42]). No other statistically significant difference was observed regarding surgical and short-term oncological outcomes. Similar findings were observed when comparing totally robotic procedures only to OE. RAMIE is a safe and feasible procedure, resulting in decreased cardiopulmonary morbidity, wound infections, blood loss, and shorter hospital stays compared to open esophagectomy.

Challenges and opportunities in the application of artificial intelligence in gastroenterology and hepatology

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the “COVLIAS 2.0-cXAI” system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

There is substantial lack of guidance when it comes to the implementation of non-technical skills (NTS) in undergraduate medical education. This review aimed to identify and critically evaluate published literature on learning strategies for NTS in undergraduate medical education and to derive a training framework targeted towards standardizing future training interventions. A systematic review of the MEDLINE database was performed using a prospective protocol following PRISMA guidelines. Studies evaluating undergraduate medical students exposed to NTS interventions, which measured subjective or objective outcomes in selected attributes, were included. Initial systematic search yielded a total of 5079 articles, out of which 68 fulfilled the inclusion criteria. A total of 24 NTS were identified, with communication skills being the most commonly reported skill evaluated (n = 37). A variety of educational tools were used (n = 32), noteworthy being the use of simulated patients. Great heterogeneity was also observed in measured outcomes and methods of assessment. A 'triad of outcomes' in NTS training was devised (knowledge, skill performance and attitude towards skills) and used for classification of all reported outcomes. Extracted data were used to design a non-technical skill training framework. The existing literature describes a plethora of NTS interventions in undergraduate medical education, with varied outcomes and assessments. We hereby propose the 'NTS Training Framework', in an attempt to coordinate future research and catalyze the identification of an ideal NTS course structure to form tomorrow's physicians.