Development of artificial intelligence technology in diagnosis, treatment, and prognosis of colorectal cancer

Table 3 Artificial intelligence in prognosis evaluation of colorectal cancer

Type of study	Ref.	Method	Conclusion
Case control study	Zhang et al[128], 2017	Heterogeneous ensemble learning model	Heterogeneous ensemble learning model could use big data to identify high-risk groups of CRC patients
Retrospective study	Morgado et al[129], 2017	Decision support system	Decision support system could evaluate the risk of CRC by processing incomplete, unknown, or even contradictory data
Case control study	Anand et al[131], 1999	Intelligent hybrid system	Each AI technology produced a different set of important attributes. Intelligent hybrid system would be the trend of prognosis evaluation in the future
Case control study	Gupta et al[132], 2019	ML	ML could help to predict tumor stage and survival period
Case control study	Li et al[133], 2018	ML	Combining ML and database, clinicians might add race factor to evaluate prognosis
Case control study	Barsainya et al[134], 2018	Decision tree classifier	Decision tree classifier could predict recurrence and death according to various influencing factors
Cohort study	Dimitriou et al[135], 2018	ML	A framework for accurate prognosis prediction of CRC based on ML datasets
Case control study	Popovici et al[136], 2017	SVM	The accuracy of using SVM to distinguish CRC subtypes was very high
Experimental study	Hoogendoorn et al[137], 2016	AI	AI helped doctors to extract useful predictors from non-coding medical records
Experimental study	Kop et al[138], 2016	ML	The combination of ML and electronic medical records could help early detection and intervention
Case control study	Geessink et al[139], 2015	Supervised learning	Supervised learning helped to predict the survival ability of tumor, so as to accurately stratify the prognosis of tumor patients
Review	Wright et al[140], 2014	RF	RF could reduce the workload of pathologists by automatically calculating the area ratio of each slide
Meta-analysis	Wang et al[141], 2019	A two-stage ML model	Compared with the single-stage regression model, the two-stage model could obtain more accurate prediction results
Experimental study	Oliveira et al[142], 2013	CDSS	CDSS based on cancer patients records and knowledge could provide support for surgeons
Meta-analysis	Lo et al[143], 2000	CDSS	CDSS could select the appropriate treatment from the aspects of curative effect, overall survival rate, and side effect rate
Case control study	Harrington et al[144], 2018	ML	ML could be used to predict the risk of recurrence of colon polyps and cancer based on the pathological characteristics of medical records
Case control study	Xie et al[145], 2018	RF model	RF model helped to speculate the influencing factors of early CRC in China
Retrospective study	Bokhorst et al[146], 2018	DL	DL helped reduce FP by detecting tumor bud
Cohort study	Zhao et al[147], 2020	DL	The method allowed objective and standardized application while reducing the workload of pathologists
Retrospective study	Syafiandini et al[148], 2016	DBM	DBM helped to predict the survival time of cancer patients
Retrospective study	Roadknight et al[149], 2013	ML	ML helped predict the prognosis of patients according to the immune status and other information
Case control study	Cui et al[150], 2013	SSL	SSL improved the accuracy of predicting clinical results according to gene expression profile
Retrospective study	Park et al[151], 2014	SSL	SSL could improve the accuracy of predicting cancer recurrence
Retrospective study	Du et al[152], 2014	Supervised learning	Supervised learning could help to improve the accuracy of identifying cancer-related mutations
Case control study	Chi et al[153], 2019	Semi-supervised logistic regression method	Semi-supervised logistic regression method had better clinical prediction effect than supervised learning method
Review	Ong et al[154], 1997	CARES system	CARES system helped early detection of cancer recurrence in high-risk patients
Case control study	Reichling et al[155], 2020	DGMate	DGMate could judge the prognosis of tumor by detecting immunophenotype
Experimental study	Chowdhury et al[156], 2011	Crane algorithm	Crane algorithm helped to describe the coordination of multiple genes and effectively predicted the metastasis of CRC
Review	Mohamad et al[157], 2019	Nominal group technique	Nominal group technique was used in the content development of mobile app and the app used as a tool for CRC screening education
Retrospective study	Hacking et al[158], 2020	AI	AI could improve the prognosis of patients by increasing the diagnostic accuracy of slide images

CRC: Colorectal cancer; AI: Artificial intelligence; ML: Machine learning; SVM: Support vector machine; RF: Random forest; CDSS: Clinical Decision Support System; DBM: Deep Boltzmann Machine; SSL: Semi-supervised learning.