Artificial Intelligence Predictive Models of Response to Cytotoxic Chemotherapy Alone or Combined to Targeted Therapy for Metastatic Colorectal Cancer Patients: A Systematic Review and Meta-Analysis

Abstract

Tailored treatments for metastatic colorectal cancer (mCRC) have not yet completely evolved due to the variety in response to drugs. Therefore, artificial intelligence has been recently used to develop prognostic and predictive models of treatment response (either activity/efficacy or toxicity) to aid in clinical decision making. In this systematic review, we have examined the ability of learning methods to predict response to chemotherapy alone or combined with targeted therapy in mCRC patients by targeting specific narrative publications in Medline up to April 2022 to identify appropriate original scientific articles. After the literature search, 26 original articles met inclusion and exclusion criteria and were included in the study. Our results show that all investigations conducted on this field have provided generally promising results in predicting the response to therapy or toxic side-effects. By a meta-analytic approach we found that the overall weighted means of the area under the receiver operating characteristic (ROC) curve (AUC) were 0.90, 95% C.I. 0.80–0.95 and 0.83, 95% C.I. 0.74–0.89 in training and validation sets, respectively, indicating a good classification performance in discriminating response vs. non-response. The calculation of overall HR indicates that learning models have strong ability to predict improved survival. Lastly, the delta-radiomics and the 74 gene signatures were able to discriminate response vs. non-response by correctly identifying up to 99% of mCRC patients who were responders and up to 100% of patients who were non-responders. Specifically, when we evaluated the predictive models with tests reaching 80% sensitivity (SE) and 90% specificity (SP), the delta radiomics showed an SE of 99% and an SP of 94% in the training set and an SE of 85% and SP of 92 in the test set, whereas for the 74 gene signatures the SE was 97.6% and the SP 100% in the training set.

Predictive Models for Assessing Patients’ Response to Treatment in Metastatic Prostate Cancer: A Systematic Review

“…Additionally, missing data, and handling of missing data, were reported rarely. This was also observed in other systematic reviews of predictive models [41] , [42] . Finally, there was some heterogeneity across the predictors used in the identified models, even where the models aimed to predict the same outcome [29] , [31] , [35] .…”

“…An additional two studies validated existing predictive models externally. External validation is critical to ensuring model generalisability and is an important step before model application in clinical settings [41] . The lack of external validation may be in part due to the novelty of predictive models in cancer research.…”

Application of artificial intelligence in diagnosis and treatment of colorectal cancer: A novel Prospect

“…Russo et al used AI-based prediction model to analyze the patients who may have drug resistance before and after treatment. They achieved a sound effect (average AUC = 0.90) in the classification and targeted precision treatment ( 154 ). Interestingly, with the help of artificial algorithms, Hu et al studied the competitive endogenous RNA (ceRNA) network about lncRNA and proposed 144 core genes for the first time, which could be used as target drugs for the treatment of CRC ( 155 ).…”

Role of artificial intelligence in risk prediction, prognostication, and therapy response assessment in colorectal cancer: current state and future directions

“…In a more recent systematic review and meta-analysis, Russo et al. analyzed the use of AI in predictive models of the response to cytotoxic chemotherapy alone or combined with targeted therapy in patients with metastatic CRC in 26 original articles ( 25 ). In their meta-analysis, which included ten articles, they found that the overall weighted means of the AUC were 0.90 in the training sets and 0.83 in the validation sets.…”