Published online Apr 15, 2020. doi: 10.4251/wjgo.v12.i4.483
Peer-review started: December 21, 2019
First decision: January 19, 2020
Revised: February 5, 2020
Accepted: March 22, 2020
Article in press: March 22, 2020
Published online: April 15, 2020
Processing time: 116 Days and 3.8 Hours
Tumor markers are increased in the blood in early gastric cancer (GC). The levels of these markers have been used as important indexes for GC screening, early diagnosis and prognostic evaluation.
Specific tumor markers have not yet been discovered. Diagnosis based on a single tumor marker has limited significance. The detection rate of GC is still very low.
In this study, we aimed to improve the diagnostic value of blood markers for GC.
In this study, to distinguish between healthy controls (Ctrls) vs GC, gastric polyp (GP) and GC, we analyzed the routine blood detection indexes of GC diagnosis by using binary logistic regression, discriminant analysis, classification tree and artificial neural network.
By analyzing the data, there are 27 indexes in the final Ctrls vs GC with P values < 0.01, the area under the curve (AUC) of albumin is the largest in Ctrls vs GC, and the AUC was 0.907. For 30 indexes in GP vs GC have P values < 0.01. Among them, the D-dimer showed an AUC of 0.729. The 27 indexes in Ctrls vs GC and 30 indexes in GP vs GC were used for binary logistic regression, discriminant analysis, classification tree analysis and artificial neural network analysis model. The overall prediction accuracy was 92.9%, and the AUC was 0.992 (0.980, 1.000).
The diagnostic effect of multi-parameter joint artificial neural networks analysis is significantly better than the single-index test diagnosis, and it may provide an assistant method for the detection of GC.
We propose that the artificial neural network analysis method has good prospects for the multi-index joint detection of tumors, and further research in this area should be carried out in the future.