Latent Risk Intrahepatic Cholangiocarcinoma Susceptible to Adjuvant Treatment After Resection: A Clinical Deep Learning Approach

Seogsong Jeong,Yang Ge,Qingbao Cheng,Bo Zheng,Guijuan Luo,Hongyang Wang,Qiang Xia,Jingfeng Liu,Lei Chen,Feng Shen,Chengjun Sui,Qiang Gao,Meng Sha,Jing Chen

doi:10.3389/fonc.2020.00143

Abstract

Background: Artificial Intelligence (AI) frameworks have emerged as a novel approach in medicine. However, information regarding its applicability and effectiveness in a clinical prognostic factor setting remains unclear.Methods: The AI framework was derived from a pooled dataset of intrahepatic cholangiocarcinoma (ICC) patients from three clinical centers (n = 1,421) by applying the TensorFlow deep learning algorithm to Cox-indicated pathologic (four), serologic (six), and etiologic (two) factors; this algorithm was validated using a dataset of ICC patients from an independent clinical center (n = 234). The model was compared to the commonly used staging system (American Joint Committee on Cancer; AJCC) and methodology (Cox regression) by evaluating the brier score (BS), integrated discrimination improvement (IDI), net reclassification improvement (NRI), and area under curve (AUC) values.Results: The framework (BS, 0.17; AUC, 0.78) was found to be more accurate than the AJCC stage (BS, 0.48; AUC, 0.60; IDI, 0.29; NRI, 11.85; P < 0.001) and the Cox model (BS, 0.49; AUC, 0.70; IDI, 0.46; NRI, 46.11; P < 0.001). Furthermore, hazard ratios greater than three were identified in both overall survival (HR; 3.190; 95% confidence interval [CI], 2.150–4.733; P < 0.001) and disease-free survival (HR, 3.559; 95% CI, 2.500–5.067; P < 0.001) between latent risk and stable groups in validation. In addition, the latent risk subgroup was found to be significantly benefited from adjuvant treatment (HR, 0.459; 95% CI, 0.360–0.586; P < 0.001).Conclusions: The AI framework seems promising in the prognostic estimation and stratification of susceptible individuals for adjuvant treatment in patients with ICC after resection. Future prospective validations are needed for the framework to be applied in clinical practice.

Highlights

Artificial Intelligence (AI) is a field of computer science in which machines mimic, recognize, and learn cognitive functions of the human mind and make empirical predictions using task-specific algorithms [1, 2]
The framework was retrospectively derived using a pooled dataset from patients with Intrahepatic cholangiocarcinoma (ICC) who received surgical resection at the Eastern Hepatobiliary Surgery Hospital, Second Military Medical University (n = 1,477), Renji Hospital, School of Medicine, Shanghai Jiao Tong University (n = 106), and Mengchao Hepatobiliary Hospital, Fujian Medical University (n = 14) between 2008 and 2015, which was independently validated by the patients from Zhongshan Hospital, Fudan University (n = 246)
Albumin (>35 vs. ≤35 g/L), alpha fetoprotein (AFP) (>50 vs. ≤50 ng/ml), and carbohydrate antigen (CA) 19-9 (>37 vs. ≤37 U/ml) were categorized into normal and abnormal groups according to the standardized cut-off values for normal ranges; the platelet count was stratified into 300 × 109/L; carcinoembryonic antigen (CEA) was stratified into 5.0 ng/ml; tumor size was stratified into 5.0 cm; and tumor number was categorized into single, double, and multiple tumors

Summary

Introduction

Artificial Intelligence (AI) is a field of computer science in which machines mimic, recognize, and learn cognitive functions of the human mind and make empirical predictions using task-specific algorithms [1, 2]. It is natural for the human mind to get confused when trying to process a lot of information simultaneously, and this necessitates an auxiliary process. This need has led to the application of AI in clinical medicine [3]. Information regarding its applicability and effectiveness in a clinical prognostic factor setting remains unclear

Methods

Results

Conclusion