Machine-learning Approach for the Development of a Novel Predictive Model for the Diagnosis of Hepatocellular Carcinoma

Abstract

Because of its multifactorial nature, predicting the presence of cancer using a single biomarker is difficult. We aimed to establish a novel machine-learning model for predicting hepatocellular carcinoma (HCC) using real-world data obtained during clinical practice. To establish a predictive model, we developed a machine-learning framework which developed optimized classifiers and their respective hyperparameter, depending on the nature of the data, using a grid-search method. We applied the current framework to 539 and 1043 patients with and without HCC to develop a predictive model for the diagnosis of HCC. Using the optimal hyperparameter, gradient boosting provided the highest predictive accuracy for the presence of HCC (87.34%) and produced an area under the curve (AUC) of 0.940. Using cut-offs of 200 ng/mL for AFP, 40 mAu/mL for DCP, and 15% for AFP-L3, the accuracies of AFP, DCP, and AFP-L3 for predicting HCC were 70.67% (AUC, 0.766), 74.91% (AUC, 0.644), and 71.05% (AUC, 0.683), respectively. A novel predictive model using a machine-learning approach reduced the misclassification rate by about half compared with a single tumor marker. The framework used in the current study can be applied to various kinds of data, thus potentially become a translational mechanism between academic research and clinical practice.

Machine learning for characterizing risk of type 2 diabetes mellitus in a rural Chinese population: the Henan Rural Cohort Study

“…Our data also indicated that obesity was a major risk factor for the development of T2DM 43 . The previous studies have demonstrated the significant role of boosting method in other medical fields, such as urinary tract infections 44 , hepatocellular carcinoma diagnosis 45 , prediction of hip fracture 46 . Our results confirmed the outstanding performance of the boosting method in the risk assessment of T2DM.…”

Identification of a novel gene signature for the prediction of recurrence in HCC patients by machine learning of genome-wide databases

“…Although surgery, transcatheter arterial chemoembolization (TACE), radiofrequency ablation, radiotherapy and other therapeutic approaches can control the progress of HCC, generally speaking, HCC is still under exploration in the areas of molecular typing, molecular diagnosis and gene target selection. Although CDH 21 , LDH 22 , NCOR1 23 and other mutant genes are new biomarkers in HCC subtype classification 24,25 , identification of gene mutations that affect recurrence is complex but will have clinical significance. Meanwhile, various probability theories and linear algebra algorithms can be used for comprehensive analysis.…”

Prediction of Vestibular Dysfunction by Applying Machine Learning Algorithms to Postural Instability

“…Machine learning has recently become utilized in the field of medicine (5,18), including for the detection of hepatocellular carcinoma (19), the prediction of urinary tract infections in the emergency department (20), the prediction of hip fractures (21), the diagnosis of diabetic retinopathy (22), and the prediction of heart failure (23). Machine learning is also applied in the field of neurotology where it has been evaluated for use as a new diagnostic posturographic tool for disorders of stance, with an overall sensitivity and specificity of about 0.9 (8).…”