Decision making in Hepatobiliary and Pancreatic Surgery is challenging, not least because of the significant complications that may occur following surgery and the complexity of interventions to treat them. Machine Learning (ML) relates to the use of computer derived algorithms and systems to enhance knowledge in order to facilitate decision making and could be of great benefit to surgical patients. ML could be employed pre- or peri-operatively to shape treatment choices prospectively, or could be utilised in the post-hoc analysis of complications in order to inform future practice. ML could reduce errors by drawing attention to known risks of complications through supervised learning, and gain greater insights by identifying previously under-appreciated aspects of care through unsupervised learning. Accuracy, validity and integrity of data are of fundamental importance if predictive models generated by ML are to be successfully integrated into surgical practice. The choice of appropriate ML models and the interface between ML, traditional statistical methodologies and human expertise will also impact the potential to incorporate data science techniques into daily clinical practice.
Pancreatic ductal adenocarcinoma (PDAC) is the third most lethal cancer in the United States, with a 5-year life expectancy of 11%. Most symptoms manifest at an advanced stage of the disease when surgery is no longer appropriate. The dire prognosis of PDAC warrants new strategies to improve the outcomes of patients, and early detection has garnered significant attention. However, early detection of PDAC is most often incidental, emphasizing the importance of developing new early detection screening strategies. Due to the low incidence of the disease in the general population, much of the focus for screening has turned to individuals at high risk of PDAC. This enriches the screening population and balances the risks associated with pancreas interventions. The cancers that are found in these high-risk individuals by MRI and/or EUS screening show favorable 73% 5-year overall survival. Even with the emphasis on screening in enriched high-risk populations, only a minority of incident cancers are detected this way. One strategy to improve early detection outcomes is to integrate artificial intelligence (AI) into biomarker discovery and risk models. This expert review summarizes recent publications that have developed AI algorithms for the applications of risk stratification of PDAC using radiomics and electronic health records. Furthermore, this review illustrates the current uses of radiomics and biomarkers in AI for early detection of PDAC. Finally, various challenges and potential solutions are highlighted regarding the use of AI in medicine for early detection purposes.
Aim: Artificial Intelligence (AI) and its applications in healthcare are rapidly developing. The healthcare industry generates ever-increasing volumes of data that should be used to improve patient care. This review aims to examine the use of AI and its applications in hepatopancreatic and biliary (HPB) surgery, highlighting studies leveraging large datasets.
Methods: A PRISMA-ScR compliant scoping review using Medline and Google Scholar databases was performed (5th August 2022). Studies focusing on the development and application of AI to HPB surgery were eligible for inclusion. We undertook a conceptual mapping exercise to identify key areas where AI is under active development for use in HPB surgery. We considered studies and concepts in the context of patient pathways - before surgery (including diagnostics), around the time of surgery (supporting interventions) and after surgery (including prognostication).
Results: 98 studies were included. Most studies were performed in China or the USA (n = 45). Liver surgery was the most common area studied (n = 51). Research into AI in HPB surgery has increased rapidly in recent years, with almost two-thirds published since 2019 (61/98). Of these studies, 11 have focused on using “big data” to develop and apply AI models. Nine of these studies came from the USA and nearly all focused on the application of Natural Language Processing. We identified several critical conceptual areas where AI is under active development, including improving preoperative optimization, image guidance and sensor fusion-assisted surgery, surgical planning and simulation, natural language processing of clinical reports for deep phenotyping and prediction, and image-based machine learning.
Conclusion: Applications of AI in HPB surgery primarily focus on image analysis and computer vision to address diagnostic and prognostic uncertainties. Virtual 3D and augmented reality models to support complex HPB interventions are also under active development and likely to be used in surgical planning and education. In addition, natural language processing may be helpful in the annotation and phenotyping of disease, leading to new scientific insights.
Hepatocellular carcinoma (HCC) is the fourth leading cause of cancer-related death worldwide and prognosis remains poor. The recent paradigm shifts in management algorithms of such patients have resulted in unique challenges in the early identification of HCC, prognosis, surgical outcomes, prioritization of potential transplant recipients, donor-recipient matching, and so on. In recent years, advancements in artificial intelligence (AI) capabilities have shown potential in HCC treatment.
In this narrative review, we outline first the different types of AI models that are applied in clinical practice and then focus on the frontiers of AI research in the diagnosis, prognostication, and treatment of HCC, particularly in classification of indeterminate liver lesions, tumor staging, survival prediction, improving equity in transplant recipient selection, prediction of treatment response and prognosis. We show that US coupled with AI-driven predictive models can provide accurate noninvasive screening tools for early disease. While AI models applied to contrast-enhanced CT, MRI and PET studies may appear to have limited clinical utility in disease diagnosis and differentials, owing to their accuracy, we highlighted the importance of such models in predicting pathological findings preoperatively. Despite the availability of many accurate, sensitive, and specific AI algorithms that outperform traditional scoring systems, they have not been widely used in clinical practice. The challenges in AI application, including distributional shift and imbalanced data, lack of standardization, and the ‘black box’ phenomenon, are addressed here. The importance of AI in the future of HCC makes it important for clinicians to have a good understanding of different AI techniques, their benefits, and potential pitfalls.
The field of totally endoscopic, robotic-assisted mitral valve surgery has progressively gained popularity over the last twenty-five years. In this editorial, we sought to discuss this expanding field from a historical perspective, a technical perspective, and a training perspective.