Review
Copyright ©The Author(s) 2021.
World J Gastroenterol. Jul 7, 2021; 27(25): 3734-3747
Published online Jul 7, 2021. doi: 10.3748/wjg.v27.i25.3734
Table 1 Applications of artificial intelligence in organ segmentation of the small intestine
Ref.
Diagnostic method
AI technology
Training set
Validating set
Outcomes
Tong et al[11]CT ML90 images - DSC of duodenum: 69.26%
Kim et al[9]CTCNN80 images40 imagesDSC of duodenum: 0.595
Peng et al[10]CTCNN43 images - DSC of duodenum: 0.61
Fu et al[12]MRICNN100 images20 imagesDice coefficient of duodenum: 65.50% ± 8.90%
Dice coefficient of bowel: 86.60% ± 2.69%
Chen et al[13]MRIDL66 images36 imagesDSC of duodenum: 0.80
Takiyama et al[15]EGDCNN27335 images17081 imagesAUCs: 0.99
Igarashi et al[16]EGDML49174 images36072 imagesAccuracy (Ts: 0.993, Vs: 0.965)
Table 2 Applications of artificial intelligence in celiac disease
Ref.
Diagnostic method
AI technology
Training set
Testing set
Outcomes
Chetcuti et al[62]CEML81 patients - Accuracy: 75.3%
Li et al[63]CEComputer-assisted recognitionEp: 240, Cp: 220 - Accuracy: 93.9%
Vicnesh et al[64]CEComputerized algorithm21 patients - Accuracy: 89.82%
Zhou et al[65]CECNNEp: 6, Cp: 5Ep: 5, Cp: 5Accuracy: 100%
Gadermayr et al[59]EGDComputer-assisted290 patients (2835 images) - Accuracy: 94%-100%
Das et al[67]Mucosal biopsiesComputer-assistedEp: 124, Cp: 137Ep: 120, Cp: 105Sen: 90.3%, Spe: 93.5%, AUCs: 96.2%
Wei et al[66]Mucosal biopsiesDL212 images - Accuracy: 95.3%, AUCs > 0.95
Pastore et al[70]Clinical dataComputer-assisted100 patients - Reliability: 0.813
Tenório et al[60]Clinical dataDecision trees, Bayesian inference, k-nearest neighbor algorithm, support vector machines, artificial neural networks178 patients38 patientsAccuracy: 80.0%, Sen: 0.78, Spe: 0.80, AUCs: 0.84
Virta et al[68]Micro-CTComputer-assisted point cloud analysis81 patients - Accuracy: 100%
Sangineto et al[69]Gene expression in PBMCsML, random forest algorithmEp: 17, Cp: 20 - Accuracy: 100%
Table 3 Applications of artificial intelligence in small intestinal Crohn’s disease
Ref.
Diagnostic method
AI technology
Training set
Testing set
Outcomes
Yang et al[78]MicroultrasoundCNN43 mice - AUCs: 0.8831
Shen et al[80]Clinical dataComputerized algorithmEp1: 61, Cp1: 78Ep2:42, Cp2: 57; Ep3:84, Cp3: 495AUCs: 0.92
Bottigliengo et al[81]Clinical dataBMLTs (NB, BN, BART)152 patients - AUCs without genetic variables (NB: 0.71, BN: 0.50, BART: 0.76), AUCs with genetic variables (NB: 0.75, BN: 0.67, BART: 0.78)
Taylor et al[79]Clinical dataML (elastic net and random forest)480 first-degree relatives - AUCs (elastic net): 0.80, AUCs (random forest): 0.87
Menti et al[82]Clinical dataBMLTs152 patients - Accuracy without genetic variables: 82%, accuracy with genetic variables: 89%
Klang et al[77]CEDL49 patients (17640 images) - AUCs: 0.94-0.99, accuracy: 95.4%-96.7%
Parfеnov et al[76]CEComputerized algorithm25 patients - 44% patients confirmed only with the help of AI
Lamash et al[74,75]MRICNN15 patients8 patientsDice coefficients: 75%-97%
Table 4 Applications of artificial intelligence in primary small intestinal tumor
Ref.
Diagnostic method
AI technology
Training set
Testing set
Outcomes
Inoue et al[88]EGDCNN531 images1080 imagesAccuracy: 94.7%-100%
Liu et al[90]CESVM89 patients - Sen: 97.8%, Spe: 96.7%
Vieira et al[89,91]CESVM29 patients (936 images) - This SVM outperforms others by more than 5%
Barbosa et al[93]CECNNEp: 104, Cp: 100Ep: 92, Cp: 100Sen: 98.7%, Spe: 96.6%
Panarelli et al[94]MicroRNA sequencing ML84 samples - Accuracy (Ts: 98.5%, Vs: 94.4%)
Drozdov et al[95]Gene expression profilingML73 samples - Differentiated from normal cells (Sen: 100%, Spe: 92%), metastases prediction (Sen: 100%, Spe: 100%)
Kjellman et al[96]Plasma protein multibiomarker Random forestmodelEp:135, Cp: 143 - AUCs: 0.97
Yan et al[97]CTRandom forestmodel213 patients - AUCs: 0.943