Copyright ©The Author(s) 2021.
World J Gastroenterol. May 7, 2021; 27(17): 1920-1935
Published online May 7, 2021. doi: 10.3748/wjg.v27.i17.1920
Table 1 Artificial intelligence in diagnosis and risk prediction of inflammatory bowel disease
AI classifier vs comparator
IBD type
Study design and sample size
Study results/validation cohort
Mossotto et al[18], 2017Support vector machines (SVM) vs linear discriminantPeds CD/UCProspective cohort, 287 IBD patientsEndoscopic and histologic inflammationDiagnosis of IBDDiagnostic accuracy of 82.7% with an AUC of 0.87 in diagnosing Crohn's disease or ulcerative colitis. Validation cohort included
Wei et al[19], 2013SVM with gradient boosted trees (GBT) vs simple log odds methodCD/UCCross-sectional, 30000 IBD patients, 22000 healthy controlsGenetics, ImmunoChipRisk of IBDThe SVM demonstrated very comparable performance (AUC 0.862 and 0.826 for CD and UC, respectively), whereas GBT showed inferior performance (AUC 0.802 and0.782 for CD and UC, respectively. Validation cohort included
Romagnoni et al[20], 2019Artificial neural networks (ANNs) vs penalized logistic regression (LR), and GBTCD Cross-sectional, 18227 CD patients, 34050 healthy controlsGenetics, ImmunoChipRisk of IBDUsing single nucleotide polymorphisms (SNPs), final predictive model achieved AUC of 0.80. Validation cohort included
Isakov et al[21], 2017Random forest (RF), SVM with svmPoly), extreme gradient boosting vs elastic net regularized generalized linear model (glmnet)CD/UCCross-sectional, 180 CD patients, 149 UC patients, 90 healthy controlsExpression data (microarray and RNA-seq)Risk of IBDThe method was used to classify a list of 16390 genes. Each gene received a score that was used to prioritize it according to its predicted association to IBD. The combined model demonstrated AUC, sensitivity, specificity, and accuracy values of 0.829, 0.577, 0.88, and 0.808, respectively. Validation cohort included
Yuan et al[22], 2017Sequential minimal optimization vs DisGeNET (Version 4.0)CD/UCCross-sectional, 59 CD patients, 26 UC patients, 42 healthy controlsGene Expression datasetsRisk of IBDBy analyzing the gene expression profiles using minimum redundancy maximum relevance and incremental feature selection, 21 genes were obtained that could effectively distinguish samples from IBD and the non-IBD samples. Highest total prediction accuracy was 97.64% using the 1170th feature set. Validation cohort included
Hübenthal et al[23], 2015SVM vs RFCD/UCCross-sectional, 40 CD patients, 36 UC patients, 38 healthy controlsMicroRNAsDiagnosis of IBDMeasured by the AUC the corresponding median holdout-validated accuracy was estimated as ranging from 0.75 to 1.00 and 0.89 to 0.98, respectively. In combination, the corresponding models provide tools for the distinction of CD and UC as well as CD, UC and healthy control with expected classification error rates of 3.1 and 3.3%, respectively. Validation cohort included
Tong et al[24], 2020RF vs convolutional neural network (CNN)CD/UCRetrospective Cohort, 875 CD patients, 5128 UC patientsColonoscopy Endoscopic ImagesDiagnosis of IBDRF sensitivities/specificities of UC/CD were 0.89/0.84, 0.83/0.82, and 0.72/0.77, respectively, while the values for the CNN of CD was 0.90/0.77. The precisions/recalls of UC-CD when employing RF were 0.97/0.97, 0.65/0.53, respectively, and when employing the CNN were 0.99/0.97 and 0.87/0.83, respectively. Validation cohort included
Smolander et al[25], 2019Deep belief networks (DBNs) vs SVMCD/UCCross-sectional, 59 CD patients, 26 UC patients, 42 healthy controlsGene Expression datasetsDiagnosis of IBDUsing DBN only, accuracy for diagnosis of UC was 97.06% and CD was 97.07%. Using both DBN and SVM, accuracy for diagnosis of UC was 97.06% and CD was 97.03%. Validation cohort included
Abbas et al[26], 2019RF vs network-based biomarker discoveryPeds CD/UCCross-sectional, 657 IBD patients, 316 healthy controlsLarge dataset of new-onset pediatric IBD metagenomics biopsy samplesDiagnosis of IBDFor the diagnosis of IBD, highest AUC attained by top Random Forest classifiers was 0.77. No validation cohort included
Khorasani et al[27], 2020SVM vs recently developed feature selection algorithm (robustness-performance tradeoff, RPT)UCCross-sectional, 146 UC patients, 60 healthy controlsGene Expression datasetDiagnosis of IBDOur model perfectly detected all active cases and had an average precision of 0.62 in the inactive cases. Validation cohort included
Rubin et al[28], 2019CITRUS supervised machine learning algorithm. No comparatorCD/UCCross-sectional, 68 IBD patientsPeripheral blood mononuclear cells and intestinal biopsies mass cytometryDiagnosis of IBDAn 8-parameter immune signature distinguished Crohn's disease from ulcerative colitis with an AUC = 0.845 (95%CI: 0.742-0.948). No validation cohort included
Pal et al[29], 2017Naïve Bayes and with a consensus machine learning method vs Critical Assessment of Genome Interpretation (CAGI) 4 methodCDCross-sectional, 64 CD patients, 47 healthy controlsGenotypes from Exome Sequencing DataRisk of IBDThe AUC for predicting risk of Crohn's disease using the SNP model was 0.72. No validation cohort included
Aoki et al[30], 2019Deep CNN. No comparatorCDRetrospective Cohort, 115 IBD patientsWireless capsule endoscopy imagesDiagnosis of IBDThe AUC for the detection of erosions and ulcerations was 0.958 (95%CI: 0.947-0.968). The sensitivity, specificity, and accuracy of the CNN were 88.2% (95%CI: 84.8-91.0), 90.9% (95%CI: 90.3-91.4), and 90.8% (95%CI: 90.2-91.3), respectively. Validation cohort included
Bielecki et al[31], 2012SVM vs human reader (pathologist)CD/UCCross-sectional, 14 CD patients, 13 UC patients, 11 healthy controlsRaman spectroscopic imaging of epithelium cellsDiagnosis of IBDRaman maps of human colon tissue sections were analyzed by utilizing innovative chemometric approaches. Using SVM, it was possible to separate between healthy control patients, patients with Crohn's Disease, and patients with ulcerative colitis with an accuracy of 98.90%. No validation cohort included
Cui et al[32], 2013Recursive SVM vs unsupervised learning strategyCD/UCCross-sectional, 124 IBD patients, 99 healthy controls16S rRNA gene analysisDiagnosis of IBDSelection level of 200 features results in the best leave-one-out cross-validation result (accuracy = 88%, sensitivity = 92%, specificity = 84%). Validation cohort included
Duttagupta et al[33], 2012SVM. No comparatorUCCross-sectional, 20 UC patients, 20 healthy controlsMicroRNAsDiagnosis of IBDSVM classifier measurements revealed a predictive score of 92.8% accuracy, 96.2% specificity and 89.5% sensitivity in distinguishing ulcerative colitis patients from normal individuals. Validation cohort included
Daneshjou et al[34], 2017Naïve bayes, neural networks, random forests vs CAGI methodsCDCross-sectional, 64 ICD patients, 47 healthy controlsExome SequencingDiagnosis of IBDIn CAGI4, 111 exomes were derived from a mix of 64 Crohn’s disease patients. Top performing methods had an AUC of 0.87. Validation cohort included
Geurts et al[35], 2005RF vs SVMCD/UCProspective cohort, 30 CD patients, 30 CD patientsProteomic Mass SpectrometryDiagnosis of IBDRandom forest model to diagnosis IBD had a sensitivity of 81.67%, specificity of 81.17%. Support vector machine model to diagnosis IBD had a sensitivity of 87.92%, specificity of 87.87%. Validation cohort included
Li et al[36], 2020RF vs ANNUCCross-sectional, 193 UC patients, 21 healthy controlsGene Expression ProfilesDiagnosis of IBDThe random forest algorithm was introduced to determine 1 downregulated and 29 upregulated differentially expressed genes contributing highest to ulcerative colitis occurrence. ANN was developed to calculate differentially expressed genes weights to ulcerative colitis. Prediction results agreed with that of an independent data set (AUC = 0.9506/PR-AUC = 0.9747). Validation cohort included
Wingfield et al[37], 2019RF vs SVMCDCross-sectional, 668 CD patientsMetagenomic DataDiagnosis of IBDHighest RPT measure for Crohn’s disease was random forest 0.60 and SVM 0.58. For ulcerative colitis, RPT was random forest 0.70 and SVM 0.48. Validation cohort included
Han et al[38], 2018RF vs LR, CORGCD/UCCross-sectional, 24 CD patients, 59 UC patients, 76 healthy controlsGene Expression ProfilesDiagnosis of IBDThe gene-based feature sets had median AUC on the validation sets ranging from 0.6 to 0.76). Validation cohort included
Wang et al[39], 2019AVADx (Analysis of Variation for Association with Disease) vs two GWAS-based CD evaluation methodsCDCross-sectional, 64 CD patients, 47 healthy controlsWhole Exome or Genome Sequencing DataDiagnosis of IBDAVADx highlighted known CD genes including NOD2and new potential CD genes. AVADx identified 16% (at strict cutoff) of CD patients at 99% precision and 58% of the patients (at default cutoff) with 82% precision in over 3000 individuals from separately sequenced panels. Validation cohort included
Table 2 Artificial Intelligence in assessment of disease severity in inflammatory bowel disease
AI classifier vs comparator
IBD type
Study design and sample size
Study results/validation cohort
Kumar et al[40], 2012Support vector machines (SVM) vs human observersCDCross-sectional, 50000 images (number of patients not given)Small bowel capsule endoscopyEndoscopic InflammationDatabase of 47 studies including 50000 capsule endoscopy images evaluating severity of small bowel lesions. Method had good precision (> 90% for lesion detection) and recall (> 90%) for lesions of varying severity. Validation cohort included
Biasci et al[41], 2019Logistic regression with an adaptive Elastic-Net penalty. No comparatorCD/UCProspective cohort, 118 IBD patientsTranscriptomics from purified CD8 T cells and/or whole bloodDisease severity, medication escalationA 17-gene qPCR-based classifier stratified patients into two distinct subgroups. IBDhi patients experienced significantly more aggressive disease than IBDlo patients (analogous to IBD2), with earlier need for treatment escalation [HR 2.65 (CD), 3.12 (UC)] and more escalations over time [for multiple escalations within 18 months: sensitivity=72.7% (CD), 100% (UC); negative predictive value = 90.9% (CD), 100% (UC)]. Validation cohort included
Waljee et al[42], 2019RF. No comparatorCDPost-hoc analysis of prospective clinical trials, 401 CD patientsClinical and laboratory data from publicly available clinical trials (UNITI-1, UNITI-2, and IM-UNITI)Crohn's disease remission, C-reactive protein < 5 mg/LA prediction model using the week-6 albumin to C-reactive protein ratio had an AUC of 0.76 [95% confidence interval (CI): 0.71-0.82]. Validation cohort included
Mahapatra et al[43], 2016RF. No comparatorCDCross-sectional, 35 CD patientsAbdominal magnetic resonance imagingSegmentation of diseased colon (intestinal inflammation)Model segmentation accuracy ranged from 82.7% to 92.2%. Validation cohort included
Reddy et al[44], 2019Gradient boosting machines vs logistic regressionCDRetrospective, 3335 CD patientsElectronic medical recordSeverity of intestinal inflammation (by C-reactive protein)Machine-learning-based analytic methods such as gradient boosting machines can predict the inflammation severity with a very high accuracy (AUC) = 92.82%. Validation cohort included
Douglas et al[45], 2018RF. No comparatorPeds CDCross-sectional, 20 CD patients, 20 healthy controlsShotgun metagenomics (MGS), 16S rRNA gene sequencingDisease State (Relapse/Remission)MGS modules significantly classified samples by disease state (accuracy = 68.4%, P = 0.043 and accuracy = 65.8%, P = 0.03, respectively), 16S datasets had a maximum accuracy of 68.4% and P = 0.016 based on strain level for disease state. Validation cohort included
Maeda et al[46], 2019SVM vs human readerUCRetrospective cohort, 187 UC patientsEndocytoscopyHistologic inflammationComputer aided diagnosis (CAD) of histologic inflammation provided diagnostic sensitivity, specificity, and accuracy as follows: 74% (95%CI: 65-81), 97% (95%CI: 95-99), and 91% (95%CI: 83-95), respectively. Its reproducibility was perfect (k = 1). Validation cohort included
Charisis et al[47], 2016SVM vs human readerCDRetrospective cohort, 13 CD patientsWireless capsule endoscopy (WCE) imagesEndoscopic InflammationExperimental results, along with comparison with other related efforts, have shown that the hybrid adaptive filtering [HAF-Differential Lacunarity (DLac) analysis (HAF-DLac)] via SVM approach evidently outperforms them in the field of WCE image analysis for automated lesion detection, providing higher classification results, up to 93.8% (accuracy), 95.2% (sensitivity), 92.4% (specificity) and 92.6% (precision). Validation cohort included
Klang et al[48], 2020Convolutional neural network (CNN) vs human readerCDRetrospective cohort, 49 CD patientsWCE imagesEndoscopic InflammationDataset included 17640 CE images from 49 patients: 7391 images with mucosal ulcers and 10249 images of normal mucosa. For randomly split images results, AUC was 0.99 with accuracies ranging from 95.4% to 96.7%. For individual patient-level experiments, the AUCs were 0.94-0.99. Validation cohort included
Ungaro et al[49], 2021Random survival forest. No comparatorPeds CDRetrospective case-control, 265 peds CD patientsProtein biomarkers using a proximity extension assay (Olink Proteomics)Penetrating and stricturing complicationsA model with 5 protein markers predicted penetrating complications with an AUC of 0.79 (95%CI: 0.76-0.82) compared to 0.69 (95%CI: 0.66-0.72) for serologies and 0.74 (95%CI: 0.71-0.77) for clinical variables. A model with 4 protein markers predicted structuring complications with an AUC of 0.68 (95%CI: 0.65-0.71) compared to 0.62 (95%CI: 0.59-0.65) for serologies and 0.52 (95%CI: 0.50-0.55) for clinical variables. Validation cohort included
Barash et al[50], 2021Ordinal CNN. No comparatorCDRetrospective cohort, 49 CD patientsWCE imagesUlcer Severity GradingThe classification accuracy of the algorithm was 0.91 (95%CI: 0.867-0.954) for grade 1 vs grade 3 ulcers, 0.78 (95%CI: 0.716-0.844) for grade 2 vs grade 3, and 0.624 (95%CI: 0.547-0.701) for grade 1 vs grade 2. Validation cohort included
Lamash et al[51], 2019CNN vs semi-supervised and active learning modelsCDRetrospective cohort, 23 CD patientsMagnetic resonance imagingActive Crohn’s DiseaseCNN exhibited Dice similarity coefficient of 75% ± 18%, 81% ± 8%, and 97% ± 2% for the lumen, wall, and background, respectively. The extracted markers of wall thickness at the location of min radius (P = 0.0013) and the median value of relative contrast enhancement (P = 0.0033) could differentiate active and nonactive disease segments. Other extracted markers could differentiate between segments with strictures and segments without strictures (P < 0.05). Validation cohort included
Takenaka et al[52], 2020Deep neural networks vs human reader (endoscopist)UCProspective cohort, 2012 UC patientsColonoscopy imagesEndoscopic inflammationDeep neural network identified patients with endoscopic remission with 90.1% accuracy (95%CI: 89.2-90.9) and a kappa coefficient of 0.798 (95%CI: 0.780-0.814), using findings reported by endoscopists as the reference standard. Validation cohort included
Bossuyt et al[53], 2020Computer algorithm based on red density (RD) vs blinded central readersUCProspective cohort, 29 UC patients, 6 healthy controlsColonoscopy ImagesEndoscopic and histologic inflammationIn the construction cohort, RD correlated with rhi (r = 0.74, P < 0.0001), Mayo endoscopic subscores (r = 0.76, P < 0.0001) and Endoscopic index of severity scores (r = 0.74, P < 0.0001). The RD sensitivity to change had a standardized effect size of 1.16. in the validation set, RD correlated with rhi (r = 0.65, P = 0.00002). Validation cohort included
Bhambhvani et al[54], 2021CNN vs human reader (endoscopist)UCRetrospective cohort, 777 UC patientsColonoscopy imagesMayo Endoscopic Scores (MES)The final model classified MES 3 disease with an AUC of 0.96, MES 2 disease with an AUC of 0.86, and MES 1 disease with an AUC 0.89. Overall accuracy was 77.2%. Across MES 1, 2, and 3, average specificity was 85.7%, average sensitivity was 72.4%, average PPV was 77.7%, and the average NPV was 87.0%. Validation cohort included
Ozawa et al[55], 2019CNN vs human reader (endoscopist)UCRetrospective cohort, 841 UC patientsColonoscopy imagesMESThe CNN-based CAD system showed a high level of performance with AUC of 0.86 and 0.98 to identify Mayo 0 and 0-1, respectively. The performance of the CNN was better for the rectum than for the right side and left side of the colon when identifying Mayo 0 (AUC = 0.92, 0.83, and 0.83, respectively). Validation cohort included
Bossuyt et al[56], 2021Automated CAD Algorithm vs human readerUCProspective cohort, 48 UC patientsColonoscopy images with confocal laser endomicroscopyHistologic RemissionThe current automated CAD algorithm detects histologic remission with a high performance (sensitivity of 0.79 and specificity of 0.90) compared with the UCEIS (sensitivity of 0.95 and specificity of 0.69) and MES (sensitivity of 0.98 and specificity of 0.61). No validation cohort included
Stidham et al[57], 2019CNN vs human readerUCRetrospective cohort, 3082 UC patientsColonoscopy imagesEndoscopy severityThe CNN was excellent for distinguishing endoscopic remission from moderate-to-severe disease with an AUC of 0.966 (95%CI: 0.967-0.972); a PPV of 0.87 (95%CI: 0.85-0.88) with a sensitivity of 83.0% (95%CI: 80.8-85.4) and specificity of96.0% (95%CI: 95.1-97.1); and NPV of 0.94 (95%CI: 0.93-0.95). No validation cohort included
Gottlieb et al[58], 2021Neural network vs human central readerUCProspective cohort, 249 UC patientsColonoscopy imagesEndoscopy severityThe model's agreement metric was excellent, with a quadratic weighted kappa of 0.844 (95%CI: 0.787-0.901) for endoscopic Mayo Score and 0.855 (95%CI: 0.80-0.91) for UCEIS. No validation cohort included
Table 3 Artificial intelligence in prediction of therapy response and clinical outcomes in inflammatory bowel disease
AI classifier vs comparator
IBD type
Study design and sample size
Study results/validation cohort
Waljee et al[59], 2018Random forest (RF). No comparatorCD/UCPost-hoc analysis of prospective clinical trial, 594 CD patientsVeteran’s Health Administration Electronic Health Record (EHR)Outpatient corticosteroids prescribed for IBD and inpatient hospitalizations associated with a diagnosis of IBDAUC for the RF longitudinal model was 0.85 [95% confidence interval (CI): 0.84–0.85]. AUC for the RF longitudinal model using previous hospitalization or steroid use was 0.87 (95%CI: 0.87-0.88). Validation cohort included
Uttam et al[60], 2019Support vector machines (SVM) vs nanoscale nuclear architecture mapping (NanoNAM)CD/UCProspective cohort, 103 IBD patients3-dimensional NanoNAM of normal-appearing rectal biopsiesColonic neoplasiaNanoNAM detects colonic neoplasia with an AUC of 0.87 ± 0.04, sensitivity of 0.81 ± 0.09, and specificity of 0.82 ± 0.07 in the independent validation set. Validation cohort included
Waljee et al[61], 2017RF. No comparatorCD/UCRetrospective cohort, 1080 IBD patientsEHR, lab valuesRemission and clinical outcomes with thiopurinesAUC for algorithm-predicted remission in the validation set was 0.79 vs 0.49 for 6-TGN. The mean number of clinical events per year in patients with sustained algorithm-predicted remission (APR) was 1.08 vs 3.95 in those that did not have sustained APR (P < 1 × 10-5). Validation cohort included
Popa et al[62], 2020Neural network model. No comparatorUCProspective cohort, 55 UC patientsClinical and biological parameters and the endoscopic Mayo scoreDisease activity after one year of anti-TNF treatmentThe classifier achieved an excellent performance predicting the disease activity at one year with an accuracy of 90% and AUC 0.92 on the test set and an accuracy of 100% and an AUC of 1 on the validation set. Validation cohort included
Douglas et al[45], 2018RF. No comparatorPeds CDCross-sectional, 20 CD patients, 20 healthy controlsShotgun metagenomics (MGS), 16S rRNA gene sequencingResponse to induction therapy16S genera were again the top dataset (accuracy = 77.8%; P = 0.008) for predicting response to therapy. MGS strain (P = 0.029), genus (P = 0.013), and KEGG pathway (P = 0.018) datasets could also classify patients according to therapy response with accuracy = 72.2% for all three. Validation cohort included
Waljee et al[63], 2010RF vs boosted trees, RuleFitCD/UCCross-sectional, 774 IBD patientsEHR, lab values (thiopurine metabolites)Response to thiopurine therapyA RF algorithm using laboratory values and patient age differentiated clinical response from nonresponse in the model validation data set with an AUC of 0.856 (95%CI: 0.793-0.919). Validation cohort included
Menti et al[64], 2016Naïve bayes vs Bayesian additive regression trees vs Bayesian networksCD/UCRetrospective cohort, 152 CD patientsGenomic DNA, genetic polymorphismPresence of extra-intestinal manifestations in IBD patientsBayesian networks achieved accuracy of 82% when considering only clinical factors and 89% when considering also genetic information, outperforming the other techniques. Validation cohort included
Waljee et al[65], 2017RF vs baseline regression modelCD/UCRetrospective cohort, 20368 IBD patientsEHR, lab valuesCorticosteroid-free biologic remission with vedolizumabThe AUC for corticosteroid-free biologic remission at week 52 using baseline data was only 0.65 (95%CI: 0.53-0.77), but was 0.75 (95%CI: 0.64-0.86) with data through week 6 of vedolizumab. Validation cohort included
Morilla et al[66], 2019Deep neural networks. No comparatorUCRetrospective cohort, 47 UC patientsColonic microrna profilesResponses to therapyA deep neural network-based classifier identified 9 microRNAs plus 5 clinical factors, routinely recorded at time of hospital admission, that were associated with responses of patients to treatment. This panel discriminated responders to steroids from non-responders with 93% accuracy (AUC, 0.91). Three algorithms, based on microRNA levels, identified responders to infliximab vs non-responders (84% accuracy, AUC 0.82) and responders to cyclosporine vs non-responders (80% accuracy, AUC 0.79). Validation cohort included
Wang et al[67], 2020Back-propagation neural network (BPNN), SVM vs logistic regressionCD Cross-sectional, 446 CD patientsEHRMedication nonadherence to maintenance therapyThe average classification accuracy and AUC of the three models were 85.9% and 0.912 for BPNN, and 87.7% and 0.930 for SVM, respectively. Validation cohort included
Bottigliengo et al[68], 2019Bayesian machine learning techniques (BMLTs) vs logistic regressionCD/UCRetrospective cohort, 142 IBD patientsEHR, genetic polymorphismsPresence of extra-intestinal manifestations in IBD patientsBMLTs had an AUC of 0.50 for classifying the presence of extra-intestinal manifestations. Validation cohort included
Ghoshal et al[69], 2020Nonlinear artificial neural network (ANN) vs multivariate linear PCAUCProspective cohort, 263 UC patientsEHRResponses to therapyThe multilayer perceptron neural network was trained by back-propagation algorithm (10 networks retained out of 16 tested). The classification accuracy rate was 73% in correctly classifying response to medical treatment in UC patients. No validation cohort included
Sofo et al[70], 2020SVM leave-one-out cross-validation. No comparatorUCRetrospective cohort, 32 UC patientsEHRPost-surgical complications after colectomyEvaluating only preoperative features, machine learning algorithms were able to predict minor postoperative complications with a high strike rate (84.3%), high sensitivity (87.5%) and high specificity (83.3%) during the testing phase. Validation cohort included
Kang et al[71], 2017ANN vs logistic regressionUCCross-sectional, 24 UC patientsGene expression profilesResponse to anti-TNFBalanced accuracy in cross validation test for predicting response to anti-TNF therapy in ulcerative colitis patient was 82%. Validation cohort included
Babic et al[72], 1997CART vs back propagation neural network (BPNN)CD/UCCross-sectional, 200 IBD patientsEHRQuality of lifeBest reached classification accuracy did not exceed 80% in any case. Other classifiers namely, K-nearest-neighbor, learning vector quantization and BPNN confirmed that outcome. Validation cohort included
Dong et al[73], 2019RF, SVM, ANN vs logistic regressionCDRetrospective cohort, 239 CD patientsEHR, laboratory testsCrohn's related surgeryThe results revealed that RF predictive model performed better than LR model in terms of accuracy (93.11% vs 91.15%), precision (53.42% vs 44.81%), F1 score (0.6016 vs 0.5763), TN rate (95.08% vs 92.00%), and the AUC (0.8926 vs 0.8809). The AUCs were excellent at 0.9864 in RF,0.9538 in LR, 0.8809 in DT, 0.9497 in SVM, and 0.9059 in ANN, respectively. Validation cohort included
Lerrigo et al[74], 2019Latent Dirichlet allocation, unsupervised machine learning algorithm. No comparatorCD/UCRetrospective cohort, 28623 IBD patientsOnline posts from the Crohn’s and colitis foundation community forumImpact of online community forums on well-being and their emotional content10702 (20.8%) posts were identified expressing: gratitude (40%), anxiety/fear (20.8%), empathy (18.2%), anger/frustration (13.4%), hope (13.2%), happiness (10.0%), sadness/depression (5.8%), shame/guilt (2.5%), and/or loneliness (2.5%). A common subtheme was the importance of fostering social support. No validation cohort included