Data-driven decision-making for precision diagnosis of digestive diseases

Table 3 Data-driven precision diagnosis in digestive diseases based on transcriptomics

First author, year	Disease	n	Data source and specific task	ML method	Diagnostic performance	Refs.
Xu, 2022	CRC	322	Transcriptomics data of patient platelets; classification based on DEGs	SVM/PSO	AUC: 0.915–0.928	[105]
Zhao, 2021	GC	6	Transcriptomics data sets of gastric tissues; classification based on hub DEGs	Ridge regression	AUC: 0.797–0.930	[106]
Kaur, 2020	HCC	3981	Large-scale transcriptomic profiling data sets of HCC; classification based on three DEGs	Naive Bayes/RF/LR	AUC: 0.970–1.000	[108]
Sallis, 2018	EoE	193	Transcriptomics data of esophageal biopsy tissues; classification based on mRNA transcript patterns	RF/PCA	AUC: 0.985	[109]
Samadi, 2022	CRC	3523	Transcriptomic data sets from GEO database; classification based on the integration of mRNA, miRNA and lncRNA	RF/SVM/LASSO/XGBoost/CNN/BPNN	AUC: 0.885–0.999	[110]
Maurya, 2021	CRC	695	TCGA mRNA data set of CRC tissues, classification based on DEGs	LASSO/RF/KNN/ANN	Accuracy: 100%	[111]
Long, 2019	CRC	311	RNA-seq data sets of CRC from TCGA and GTEx cohorts, classification based on DEGs	RF/KNN/Naive Bayes	Accuracy: 99.8%	[112]
Sallis, 2018	EoE	215	Transcriptomics data of esophageal biopsy tissues; classification based on mRNA patterns	PCA/RF	AUC: 0.990	[113]
Su, 2022	CRC	521	TCGA transcriptomic data of CRC tissues, classification based on DEGs	RF/SVM/LASSO/DT	Accuracy: 99.81%	[114]
Lu, 2022	UC	267	Transcriptomic data sets of UC from GEO database; classification based on DEGs	LR	AUC: 0.721–0.850	[115]

Full names of abbreviations are given in the Abbreviations section of the manuscript

ISSN: 1475-925X