Machine Learning Model Comparison in the Screening of Cholangiocarcinoma Using Plasma Bile Acids Profiles

Application of AI on cholangiocarcinoma

Cholangiocarcinoma, classified as intrahepatic, perihilar, and extrahepatic, is considered a deadly malignancy of the hepatobiliary system. Most cases of cholangiocarcinoma are asymptomatic. Therefore, early detection of cholangiocarcinoma is significant but still challenging. The routine screening of a tumor lacks specificity and accuracy. With the application of AI, high-risk patients can be easily found by analyzing their clinical characteristics, serum biomarkers, and medical images. Moreover, AI can be used to predict the prognosis including recurrence risk and metastasis. Although they have some limitations, AI algorithms will still significantly improve many aspects of cholangiocarcinoma in the medical field with the development of computing power and technology.

Artificial intelligence in liver cancers: Decoding the impact of machine learning models in clinical diagnosis of primary liver cancers and liver cancer metastases

Liver cancers are the fourth leading cause of cancer-related mortality worldwide. In the past decade, breakthroughs in the field of artificial intelligence (AI) have inspired development of algorithms in the cancer setting. A growing body of recent studies have evaluated machine learning (ML) and deep learning (DL) algorithms for pre-screening, diagnosis and management of liver cancer patients through diagnostic image analysis, biomarker discovery and predicting personalized clinical outcomes. Despite the promise of these early AI tools, there is a significant need to explain the 'black box' of AI and work towards deployment to enable ultimate clinical translatability. Certain emerging fields such as RNA nanomedicine for targeted liver cancer therapy may also benefit from application of AI, specifically in nano-formulation research and development given that they are still largely reliant on lengthy trial-and-error experiments. In this paper, we put forward the current landscape of AI in liver cancers along with the challenges of AI in liver cancer diagnosis and management. Finally, we have discussed the future perspectives of AI application in liver cancer and how a multidisciplinary approach using AI in nanomedicine could accelerate the transition of personalized liver cancer medicine from bench side to the clinic.

Bile acids as drivers and biomarkers of hepatocellular carcinoma

The prevalence of hepatocellular carcinoma (HCC) is rapidly increasing, driven not least in part by the escalating prevalence of non-alcoholic fatty liver disease. Bile acid (BA) profiles are altered in patients with HCC and there is a developing body of evidence from in vitro human cellular models as well as rodent data suggesting that BA are able to modulate fundamental processes that impact on cellular phenotype predisposing to the development of HCC including senescence, proliferation and epithelial-mesenchymal transition. Changes in BA profiles associated with HCC have the potential to be exploited clinically. Whilst excellent diagnostic and imaging tools are available, their use to screen populations with advanced liver disease at risk of HCC is limited by high cost and low availability. The mainstay for HCC screening among subjects with cirrhosis remains frequent interval ultrasound scanning. Importantly, currently available serum biomarkers add little to diagnostic accuracy. Here, we review the current literature on the use of BA measurements as predictors of HCC incidence in addition to their use as a potential screening method for the early detection of HCC. Whilst these approaches do show early promise, there are limitations including the relatively small cohort sizes, the lack of a standardized approach to BA measurement, and the use of inappropriate control comparator samples.

Artificial intelligence using advanced imaging techniques and cholangiocarcinoma: Recent advances and future direction

While cholangiocarcinoma represents only about 3% of all gastrointestinal tumors, it has a dismal survival rate, usually because it is diagnosed at a late stage. The utilization of Artificial Intelligence (AI) in medicine in general, and in gastroenterology has made gigantic steps. However, the application of AI for biliary disease, in particular for cholangiocarcinoma, has been sub-optimal. The use of AI in combination with clinical data, cross-sectional imaging (computed tomography, magnetic resonance imaging) and endoscopy (endoscopic ultrasound and cholangioscopy) has the potential to significantly improve early diagnosis and the choice of optimal therapeutic options, leading to a transformation in the prognosis of this feared disease. In this review we summarize the current knowledge on the use of AI for the diagnosis and management of cholangiocarcinoma and point to future directions in the field.

Novel approaches in search for biomarkers of cholangiocarcinoma

Cholangiocarcinoma (CCA) arises from the ductular epithelium of the biliary tree, either within the liver (intrahepatic CCA) or more commonly from the extrahepatic bile ducts (extrahepatic CCA). This disease has a poor prognosis and a growing worldwide prevalence. The poor outcomes of CCA are partially explained by the fact that a final diagnosis is challenging, especially the differential diagnosis between hepatocellular carcinoma and intrahepatic CCA, or distal CCA and pancreatic head adenocarcinoma. Most patients present with an advanced disease, unresectable disease, and there is a lack in non-surgical therapeutic modalities. Not least, there is an acute lack of prognostic biomarkers which further complicates disease management. Therefore, there is a dire need to find alternative diagnostic and follow-up pathways that can lead to an accurate result, either singlehandedly or combined with other methods. In the "-omics" era, this goal can be attained by various means, as it has been successfully demonstrated in other primary tumors. Numerous variants can reach a biomarker status ranging from circulating nucleic acids to proteins, metabolites, extracellular vesicles, and ultimately circulating tumor cells. However, given the relatively heterogeneous data, extracting clinical meaning from the inconsequential noise might become a tall task. The current review aims to navigate the nascent waters of the non-invasive approach to CCA and provide an evidence-based input to aid clinical decisions and provide grounds for future research.

Artificial intelligence and cholangiocarcinoma: Updates and prospects

Artificial intelligence (AI) is the timeliest field of computer science and attempts to mimic cognitive function of humans to solve problems. In the era of “Big data”, there is an ever-increasing need for AI in all aspects of medicine. Cholangiocarcinoma (CCA) is the second most common primary malignancy of liver that has shown an increase in incidence in the last years. CCA has high mortality as it is diagnosed in later stages that decreases effect of surgery, chemotherapy, and other modalities. With technological advancement there is an immense amount of clinicopathologic, genetic, serologic, histologic, and radiologic data that can be assimilated together by modern AI tools for diagnosis, treatment, and prognosis of CCA. The literature shows that in almost all cases AI models have the capacity to increase accuracy in diagnosis, treatment, and prognosis of CCA. Most studies however are retrospective, and one study failed to show AI benefit in practice. There is immense potential for AI in diagnosis, treatment, and prognosis of CCA however limitations such as relative lack of studies in use by human operators in improvement of survival remains to be seen.

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

Artificial intelligence (AI) is an umbrella term used to describe a cluster of interrelated fields. Machine learning (ML) refers to a model that learns from past data to predict future data. Medicine and particularly gastroenterology and hepatology, are data-rich fields with extensive data repositories, and therefore fruitful ground for AI/ML-based software applications. In this study, we comprehensively review the current applications of AI/ML-based models in these fields and the opportunities that arise from their application. Specifically, we refer to the applications of AI/ML-based models in prevention, diagnosis, management, and prognosis of gastrointestinal bleeding, inflammatory bowel diseases, gastrointestinal premalignant and malignant lesions, other nonmalignant gastrointestinal lesions and diseases, hepatitis B and C infection, chronic liver diseases, hepatocellular carcinoma, cholangiocarcinoma, and primary sclerosing cholangitis. At the same time, we identify the major challenges that restrain the widespread use of these models in healthcare in an effort to explore ways to overcome them. Notably, we elaborate on the concerns regarding intrinsic biases, data protection, cybersecurity, intellectual property, liability, ethical challenges, and transparency. Even at a slower pace than anticipated, AI is infiltrating the healthcare industry. AI in healthcare will become a reality, and every physician will have to engage with it by necessity.

Plasma Bile Acid Profile in Patients with and without Type 2 Diabetes

A paucity of information currently exists on plasma bile acid (BA) profiles in patients with and without type 2 diabetes mellitus (T2DM). We assayed 14 plasma BA species in 224 patients with T2DM and in 102 nondiabetic individuals with metabolic syndrome. Plasma BA levels were measured with ultra-performance liquid chromatography tandem mass spectrometry (UHPLC-MS/MS) technique. Multivariable linear regression analyses were undertaken to assess associations between measured plasma BA species and T2DM status after adjustment for confounding factors. The presence of T2DM was significantly associated with higher plasma concentrations of both primary BAs (adjusted-standardized β coefficient: 0.279, p = 0.005) and secondary BAs (standardized β coefficient: 0.508, p < 0.001) after adjustment for age, sex, adiposity measures, serum alanine aminotransferase and use of statins or metformin. More specifically, the presence of T2DM was significantly associated with higher levels of plasma taurochenodeoxycholic acid, taurodeoxycholic acid, glycochenodeoxycholic acid, hyodeoxycholic acid, glycodeoxycholic acid, glycolithocholic acid, deoxycholic acid, taurochenodeoxycholic acid, taurodeoxycholic acid, glycochenodeoxycholic acid and glycodeoxycholic acid (adjusted-standardized β coefficients ranging from 0.315 to 0.600; p < 0.01 or less), as well as with lower plasma levels of cholic acid (adjusted-standardized β coefficient: −0.250, p = 0.013) and taurocholic acid (adjusted-standardized β coefficient: −0.309, p = 0.001). This study shows that there are marked differences in plasma BA profiles between patients with and without T2DM. Further research will be needed to better understand how these differences in plasma BA profiles may interplay with the pathophysiology of T2DM.

Establishment of a Potential Serum Biomarker Panel for the Diagnosis and Prognosis of Cholangiocarcinoma Using Decision Tree Algorithms

Potential biomarkers which include S100 calcium binding protein A9 (S100A9), mucin 5AC (MUC5AC), transforming growth factor β1 (TGF-β1), and angiopoietin-2 have previously been shown to be effective for cholangiocarcinoma (CCA) diagnosis. This study attempted to measure the sera levels of these biomarkers compared with carbohydrate antigen 19-9 (CA19-9). A total of 40 serum cases of CCA, gastrointestinal cancers (non-CCA), and healthy subjects were examined by using an enzyme-linked immunosorbent assay. The panel of biomarkers was evaluated for their accuracy in diagnosing CCA and subsequently used as inputs to construct the decision tree (DT) model as a basis for binary classification. The findings showed that serum levels of S100A9, MUC5AC, and TGF-β1 were dramatically enhanced in CCA patients. In addition, 95% sensitivity and 90% specificity for CCA differentiation from healthy cases, and 70% sensitivity and 83% specificity for CCA versus non-CCA cases was obtained by a panel incorporating all five candidate biomarkers. In CCA patients with low CA19-9 levels, S100A9 might well be a complementary marker for improved diagnostic accuracy. The high levels of TGF-β1 and angiopoietin-2 were both associated with severe tumor stages and metastasis, indicating that they could be used as a reliable prognostic biomarkers panel for CCA patients. Furthermore, the outcome of the CCA burden from the Classification and Regression Tree (CART) algorithm using serial CA19-9 and S100A9 showed high diagnostic efficiency. In conclusion, results have shown the efficacy of CCA diagnosis and prognosis of the novel CCA-biomarkers panel examined herein, which may prove be useful in clinical settings.

Circulating Bile Acids Profiles in Obese Children and Adolescents: A Possible Role of Sex, Puberty and Liver Steatosis

Background. Childhood obesity is becoming a major health issue and contributes to increasing the risk of cardiovascular disease in adulthood. Since dysregulated metabolism of bile acids (BAs) plays a role in progression of obesity-related disorders, including steatosis and hypertension, this study aimed to investigate BAs profiles in obese children with and without steatosis and hypertension, as well as exploring the interplay between BAs profile and vascular function. Methods. BAs concentrations were quantified with liquid chromatography-tandem mass spectrometry in 69 overweight/obese children and adolescents (mean age, 11.6 ± 2.5 years; 30 females). Liver steatosis was defined with abdomen ultrasonography, whilst hypertension was defined according to the current European guidelines. Vascular function was assessed with ultrasound technique, by measuring carotid intima media thickness (cIMT) and common carotid artery distensibility (cDC). Results. Total and individual glycine-conjugated BAs concentrations were found to be significantly higher in males compared to females, as well as in pre-pubertal compared to pubertal stage (p < 0.05 for both). No difference in BAs concentration was observed between hypertensive and normotensive subjects. Total BAs and glycine conjugated BAs were significantly higher in participants with steatosis compared to those without (p = 0.004 for both). The values of total glycine-conjugate acids were positively correlated with cDC and this association remained significant in linear regression after adjusting for sex, age, pubertal stage, body mass index and aspartate aminotransferase. Conclusion. The results suggest a possible role of BAs in the pathogenesis of liver and/or vascular damage in children and adolescent. Further studies are hence needed to validate these preliminary findings.