Copyright ©The Author(s) 2023.
Artif Intell Cancer. Dec 8, 2023; 4(2): 11-22
Published online Dec 8, 2023. doi: 10.35713/aic.v4.i2.11
Table 1 Published studies on artificial intelligence and machine learning in rectal carcinoma
No. of patients in AI-based study
1Pham et al[29], 2023N = 53, rectal cancer biopsyCNN based extraction of IHC imagesSVMs extraction; total accuracy = 85%, Prediction of survival rate of more than 5 yr = 90%, and less than 5 yr = 75%Use of AI can be informative for clinical decision making- whether required preoperative therapy or not
2Kim et al[67], 2023N = 39, mid to lower rectal cancer patients who underwent chemoradiotherapyDeep learning-based imaging reconstruction (DLR) effect on MRI qualityCompared to conventional MRI DLR-MRI showed significantly higher specificity values (P < 0.036)Compared to conventional MRI, DLR significantly increased the specificity of MRI for identifying pathological complete response (pCR)
3Wang et al[68], 2023N = 1651, machine learning model used for predicting major LARS following laparoscopic surgery of rectal cancer and their quality of lifeThe trained random forest (RF) model performed, and clinical utility of the model was tested by decision curve analysisCompared to the conventional preoperative LARS score model, current machine learning model exhibited superior predictive performance in predicting major LARSThis model could potentially be used in the clinic to identify patients with a high risk of developing major LARS and then improve the quality of life
4Qiu et al[69], 2023N = 27180, used eight machine learning Model for predicting chances lung metastasis in rectal cancer patientsThey used DCA and calibration analysis to test all the models to predict risk of lung metastasis in patients with rectal cancerXGB model had better clinical decision making and prediction ability than other modelsXGB model based on clinicopathological information to predict the risk of lung metastasis in patients with rectal cancer, which may help physicians make clinical decisions
5Shao et al[39], 2023N = 2469, consecutive patients with stage I-III rectal adenocarcinoma who received anterior resection and did not receive neoadjuvant therapyFive AI algorithms, (SVM), logistic regression (LR), Naive Bayes (NB), stochastic gradient descent (SGD) and random forest (RF), were employed to generate five modelsIn summary, the present study developed a high-performance AI model based on clinical preoperative and intraoperative les, which may be supportive for the guidance of the intraoperative decision-making by calculating the risk of ALThe application of this app can predict the risk of AL in patients with rectal cancer who have undergone anterior resection
6Xia et al[70], 2023172 rectal cancer patients were used for model training, and 18 patients were used for model validation. Another 40 rectal cancer patients were used for an end-to-end evaluation for both auto-segmentation and treatment planningThe PTV and OAR segmentation was compared with manual segmentationThe PTV DICE similarity coefficient was greater than 0.85 for all 40 patients in the evaluation dataset while the DICE indices of the OARs also indicated good performanceDeep learning-based automatic solution for rectal cancer treatment that can improve the efficiency of treatment planning