Copyright ©The Author(s) 2022.
Artif Intell Gastrointest Endosc. Jun 28, 2022; 3(3): 31-43
Published online Jun 28, 2022. doi: 10.37126/aige.v3.i3.31
Table 1 Overview of screening studies
Wang et al[19], 2019Effect of computer aided detection deep learning models on polyps and adenoma detection ratesIncrease in adenoma detection rates [29.1% vs 20.3%, P < 0.001] and mean number of identified adenomas per patient [0.53 vs 0.31, P <0.001]; More hyperplastic adenomas (114 vs 52, P < 0.001) and diminutive polyps (185 vs 102, P < 0.001) identified
Nazarian et al[20], 2021Detection rates of polyp and adenoma with AI vs without AIIncrease in both polyp detection rates (odds ratio [OR] 1.75, 95%CI 1.56-1.96; P < 0.001) as well as adenoma detection rates (OR 1.53, 95%CI 1.32-1.77; P < 0.001)
Johnson et al[23], 2008; Pickhardt et al[24], 2003Degree to which CTC is effective in detecting asymptomatic colorectal lesions Reported identification of 90% of patients with asymptomatic adenomas or cancers (≥ 10 mm in diameter) using CT colonography
Grosu et al[25], 2021Development of machine learning method differentiating between benign and precancerous lesions in average risk asymptomatic patients using CTCSensitivity of 82%, specificity of 85% and AUC of 0.91
Song et al[26], 2015Development of virtual pathological model to assess the suitability of using image high-order differentiations to distinguish colorectal lesionsImprovement of ROC curve (AUC) from 0.74 to 0.85
Blanes-Vidal et al[30], 2019Algorithms developed to match CE and colonoscopy-identified polyps based on their estimated size, morphology and location as well as utilizing deep convolutional neural networks for automatic colorectal polyp detectionLocalization resulted in high sensitivity (97.1%), specificity (93.3%), and accuracy (96.4%) for identifying polyps when compared to the manual process of polyp detection
Kinar et al[35], 2017AI-assisted prediction model (MeScore®, Calgary, Alberta, Canada) was designed to identify people at high risk for CRC Revealed a 2.1-fold increase in cancer detection rates when the model is used in combination with FOBT
Gupta et al[36], 2019Using CellMax (CMx®) platform to detect and isolate circulating tumor cells in peripheral blood samplesA sensitivity and specificity of 80%
Table 2 Overview of diagnosis studies
Min et al[40], 2019System designed to predict the histology of colorectal polyps by analyzing linked color imaging83.3% sensitivity, 70.1% specificity, 82.6% PPV, 71.2% NPV and an accuracy of 78.4% when compared to expert endoscopists
Gross et al[45], 2011Development of computer-assisted model for polyp classification by analyzing 9 vessel features, from patients who underwent magnifying endoscopy with NBIHigher sensitivity (95% vs 86%), specificity (90.3% vs 87.8%) and accuracy (93.1% vs 86.8%) when compared to novice endoscopists but comparable to those of expert endoscopists (sensitivity, specificity, and accuracy of 93.4%, 91.8% and 92.7%, respectively)
Chen et al[46], 2018Designed a deep learning model to classify diminutive colorectal polyps using magnifying NBI images with 284 diminutive colorectal polyps extractedAble to distinguish between neoplastic and hyperplastic lesions in a shorter period compared to expert endoscopists (0.45 vs 1.54 seconds) and had a sensitivity, specificity, accuracy, PPV, and NPV of 96.3%, 78.1%, 90.1%, 89.6% and 91.5% respectively
Mori et al[48], 2015Computer-aided algorithm designed to histologically differentiate colorectal lesions in vivo using endocytoscopy92% sensitivity and 89.2% accuracy in establishing a histological diagnosis.
Takeda et al[51], 2017Model investigated the role of a computer-aided endocytoscopy system on the diagnosis of invasive colorectal carcinoma 89.4% sensitivity, 98.9% specificity, 98.8% PPV, 90.1% NPV and 94.1% accuracy
Takemura et al[53], 2010Software model to automatically quantify and classify pit patterns. Used texture and quantitative analysis to classify pit patternsType I and II pit patterns were in complete agreement with the endoscopic diagnosis on discriminant analysis. Type III was diagnosed in 29 of 30 cases (96.7%) and type IV was diagnosed in one case. Twenty-nine of 30 cases (96.7%) were diagnosed as type IV pit pattern. The overall accuracy of the computerized recognition system was 132 of 134 (98.5%)
André et al[55], 2012Automated polyp characterization system to distinguish between benign and malignant lesions using the k-nearest neighbor classificationAccuracy of 89.6%
Ştefănescu et al[56], 2016A neural network analysis algorithm differentiating advanced colorectal adenocarcinomas from the normal mucosaAccuracy of 84.5%
Table 3 Overview of treatment, toxicity, and prognosis studies
Huang et al[69], 2020Artificial neural network K-nearest neighbors, support vector machine, naïve Bayesian classifier, mixed logistic regression models were used to predict response Accuracy of 0.88, AUC of 0.86 and sensitivity of 0.94
Ferrari et al[70], 2019AI models to assess response to therapy in locally advanced rectal cancerAble to identify patients who will have complete response at the end of the treatment and those who will not respond to therapy at an early stage of the treatment with an AUC of 0.83
Shayesteh et al[71], 2019MRI based ensemble learning methods to predict the response to nCRTAUC of 95% and accuracy of 90%
Ferrari et al[71], 2019Algorithms to identify pathological CR and NR patients after neoadjuvant chemoradiotherapy (CRT) in locally advanced rectal cancer AUC of 0.86 and 0.83 for pathological CRs and NRs
Oyaga-Iriarte et al[73], 2019Algorithms in metastatic CRC patients to predict Irinotecan toxicity Accuracy of 76%, 75%, and 91% for predicting leukopenia, neutropenia, and diarrhea respectively
Sailer et al[81], 2015Compared ten data mining algorithms to predict the 5-yr survival based on seven attributesAccuracy of 67.7% compared to clinical judgment of 59%