Machine Learning-based Development and Validation of a Scoring System for Screening High-Risk Esophageal Varices

Dong, Tien S.; Kalani, Amir; Aby, Elizabeth S.; Le, Long; Luu, Kayti; Hauer, Meg; Kamath, Rahul; Lindor, Keith D.; Tabibian, James H.

doi:10.1016/j.cgh.2019.01.025

Cited by 55 publications

(45 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There was a strong power in machine learning approach on constructing new scoring system based on existing clinical indicators. Despite some scoring systems for cancer have been created and validated by the novel method of machine learning [35], the evidence of scoring system based on inflammation biomarkers for gastric cancer is still lacking and elusive. Thus, more studies using the novel method of machine learning are needed to discover more effective biomarker in gastric cancer.…”

Section: Discussionmentioning

confidence: 99%

The prognostic value of preoperative fibrinogen-to-prealbumin ratio and a novel FFC score in patients with resectable gastric cancer

et al. 2020

View full text Add to dashboard Cite

Background: Chronic inflammation is considered as a hallmark of gastric cancer (GC) and plays a critical role in GC progression and metastasis. This study aimed to explore the prognostic values of preoperative fibrinogen-toprealbumin ratio (FPR), fibrinogen-to-albumin ratio (FAR), and novel FPR-FAR-CEA (FFC) score in patients with GC undergoing gastrectomy. Methods: A total of 273 patients with resectable GC were included in this retrospective study. We performed Kaplan-Meier and Cox regression analyses to assess the prognostic role of preoperative FPR, FAR, and FFC score in patients with GC and analyze their relationships with clinicopathological features. Results: Receiver operating characteristic curve (ROC) analysis revealed that the optimal cutoff values for FPR and FAR were 0.0145 and 0.0784, respectively. The FFC score had a higher area under the ROC curve than FAR and CEA. Elevated FPR (≥ 0.0145) and FAR (≥ 0.0784) were significantly associated with old age, large tumor size, tumor invasion depth, lymph nodes metastasis, advanced TNM stage, large Borrmann type, and anemia status. Kaplan-Meier analysis showed that high FPR, FAR, and FFC score were related to poor survival. Multivariate analyses indicated that FPR, FFC score, TNM stage, and tumor size were significant independent factors for survival. Conclusions: Preoperative FPR and FFC score could be used as prospective noninvasive prognostic biomarkers for resectable GC.

show abstract

Section: Discussionmentioning

confidence: 99%

The prognostic value of preoperative fibrinogen-to-prealbumin ratio and a novel FFC score in patients with resectable gastric cancer

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Sixteen studies focused on hepatology. Of those studies, 7 aimed to detect fibrosis associated with viral hepatitis, [124][125][126][127][128][129][130] 6 developed AI strategies to detect nonalcoholic fatty liver disease, [131][132][133][134][135][136] 2 were developed to identify patients with esophageal varices, 137,138 and 1 to assess patients with chronic liver disease of any cause. 139 Thirteen studies used data from electronic medical records and/or biologic features to build the algorithms and 3 studies used data from elastography.…”

Section: Liver and Pancreatobiliary Disordersmentioning

confidence: 99%

Application of Artificial Intelligence to Gastroenterology and Hepatology

et al. 2020

View full text Add to dashboard Cite

Since 2010, substantial progress has been made in artificial intelligence (AI) and its application to medicine. AI is explored in gastroenterology for endoscopic analysis of lesions, in detection of cancer, and to facilitate the analysis of inflammatory lesions or gastrointestinal bleeding during wireless capsule endoscopy. AI is also tested to assess liver fibrosis and to differentiate patients with pancreatic cancer from those with pancreatitis. AI might also be used to establish prognoses of patients or predict their response to treatments, based on multiple factors. We review the ways in which AI may help physicians make a diagnosis or establish a prognosis and discuss its limitations, knowing that further randomized controlled studies will be required before the approval of AI techniques by the health authorities.

show abstract

“…The prevalence of EV in cirrhotic patients is approximately 60-80%, and the 1-year rate of first variceal hemorrhage is approximately 12% [5% for lowrisk varices and 15% for high-risk varices (HRV)] [1][2][3]. The mortality of variceal bleeding ranges from 15 to 55% [4]. Esophagogastroduodenoscopy (EGD) is usually recommended to identify those at risk of bleeding who should undergo prophylaxis treatment in patients with established cirrhosis [5].…”

Section: Introductionmentioning

confidence: 99%

Development and Validation of an Easy-to-Use Risk Scoring System for Screening High-Risk Varices in Patients with HBV-Related Compensated Advanced Chronic Liver Disease

et al. 2021

View full text Add to dashboard Cite

Background A large portion of patients with compensated advanced chronic liver disease (cACLD) do not have varices or only have low risk varices. Aims To create and validate an easy-to-use risk scoring system to identify high-risk varices (HRV) and spare esophagogastroduodenoscopy (EGD) in patients with hepatitis B virus (HBV)-related cACLD. Methods In total, 334 patients with HBV-related cACLD who had undergone routine laboratory tests and ultrasound examination were enrolled. Multivariate logistic regression analysis was used to determine which variables were the independent risk factors for the presence of HRV, so as to establish the scoring system for screening HRV. The criteria were tested in a training cohort with 221 patients and validated in a validation cohort with 113 patients. Results In the training cohort, the prevalence of HRV was 29.5%. Albumin (ALB) [OR 0.83; 95% confidence index (CI) 0.77–0.90; P < 0.0001], platelet count (PLT) (OR 0.96, 95% CI 0.96–0.99; P < 0.0001) and portal vein diameter (OR 1.40; 95% CI 1.15–1.71; P = 0.001) were independent risk factors for the presence of HRV. The negative predictive value was > 95%, when albumin-platelet-portal vein diameter varices scores (APP score) were < 0.24. One hundred twenty-five of 221 (56.6%) patients met an APP score < 0.24 with a 4.8% HRV miss rate. In the validation cohort, 59 of 113 (51.3%) patients met the APP score < 0.24 with a 1.7% HRV miss rate. Conclusions APP score is a potential model for safely screening HRV and sparing EGDs in patients with HBV-related cACLD.

show abstract

Machine Learning-based Development and Validation of a Scoring System for Screening High-Risk Esophageal Varices

Cited by 55 publications

References 17 publications

The prognostic value of preoperative fibrinogen-to-prealbumin ratio and a novel FFC score in patients with resectable gastric cancer

The prognostic value of preoperative fibrinogen-to-prealbumin ratio and a novel FFC score in patients with resectable gastric cancer

Application of Artificial Intelligence to Gastroenterology and Hepatology

Development and Validation of an Easy-to-Use Risk Scoring System for Screening High-Risk Varices in Patients with HBV-Related Compensated Advanced Chronic Liver Disease

Contact Info

Product

Resources

About