search for




 

Predictive modeling algorithms for liver metastasis in colorectal cancer: A systematic review of the current literature
Ann Hepatobiliary Pancreat Surg 2024 Feb;28(1):14-24
Published online February 29, 2024;  https://doi.org/10.14701/ahbps.23-078
Copyright © 2024 The Korean Association of Hepato-Biliary-Pancreatic Surgery.

Isaac Seow-En1, Ye Xin Koh2,3,4, Yun Zhao1,5, Boon Hwee Ang5, Ivan En-Howe Tan5, Aik Yong Chok1, Emile John Kwong Wei Tan1, Marianne Kit Har Au5,6

1Department of Colorectal Surgery, Singapore General Hospital and National Cancer Centre Singapore, Singapore,
2Department of Hepatopancreatobiliary and Transplant Surgery, Singapore General Hospital and National Cancer Centre Singapore, Singapore,
3Duke-National University of Singapore Medical School, Singapore,
4Liver Transplant Service, SingHealth Duke-National University of Singapore Transplant Centre, Singapore,
5Group Finance Analytics, Singapore Health Services, Singapore,
6Finance, SingHealth Community Hospitals, Singapore
Correspondence to: Isaac Seow-En, MBBS, MMed, FRCS
Department of Colorectal Surgery, Singapore General Hospital and National Cancer Centre Singapore, Academia, 20 College Road, Singapore 169856
Tel: +65-63214677, Fax: +65-62273787, E-mail: isaac.seow.en@gmail.com
ORCID: https://orcid.org/0000-0001-8287-6812
Received June 26, 2023; Accepted August 16, 2023.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
 Abstract
This study aims to assess the quality and performance of predictive models for colorectal cancer liver metastasis (CRCLM). A systematic review was performed to identify relevant studies from various databases. Studies that described or validated predictive models for CRCLM were included. The methodological quality of the predictive models was assessed. Model performance was evaluated by the reported area under the receiver operating characteristic curve (AUC). Of the 117 articles screened, seven studies comprising 14 predictive models were included. The distribution of included predictive models was as follows: radiomics (n = 3), logistic regression (n = 3), Cox regression (n = 2), nomogram (n = 3), support vector machine (SVM, n = 2), random forest (n = 2), and convolutional neural network (CNN, n = 2). Age, sex, carcinoembryonic antigen, and tumor staging (T and N stage) were the most frequently used clinicopathological predictors for CRCLM. The mean AUCs ranged from 0.697 to 0.870, with 86% of the models demonstrating clear discriminative ability (AUC > 0.70). A hybrid approach combining clinical and radiomic features with SVM provided the best performance, achieving an AUC of 0.870. The overall risk of bias was identified as high in 71% of the included studies. This review highlights the potential of predictive modeling to accurately predict the occurrence of CRCLM. Integrating clinicopathological and radiomic features with machine learning algorithms demonstrates superior predictive capabilities.
Keywords : Colorectal cancer; Liver metastasis; Prediction; Systematic review
INTRODUCTION

Colorectal cancer (CRC) is a global health concern, ranking as the second most frequently diagnosed malignancy worldwide, with an incidence of 1.36 million cases each year [1,2]. Moreover, the global occurrence of CRC has been steadily rising, with an annual increase of 3.2% [3]. Metastases from CRC pose a significant obstacle to curative treatment, representing a pivotal factor contributing to CRC-related mortality [4]. Amongst the organs susceptible to CRC distant metastasis, the liver is the most frequently affected [5]. Population-based studies have revealed that 25% to 30% of CRC patients experience colorectal cancer liver metastases (CRCLM) throughout the course of the disease [6,7], as a result of lower gastrointestinal portal venous drainage [8]. While only 25% of patients with CRCLM qualify for operative resection [9], advancements in the field have expanded the treatment options for CRCLM. Early detection and accurate prediction of CRCLM are paramount to improving prognosis and delivering appropriate care for CRC patients.

The application of predictive modeling techniques in healthcare has brought about a transformative shift in the analysis and interpretation of medical data [10,11]. These advanced computational approaches offer the potential to uncover intricate patterns and relationships that may remain latent within large datasets, eluding traditional statistical methods [12]. Within the realm of CRCLM, the amalgamation of predictive modeling algorithms facilitates the development of robust prognostic tools that can consider the intricate interplay of multiple variables, providing individualized predictions [13-16]. These predictive models offer heightened accuracy by incorporating clinical parameters, pathological characteristics, and molecular biomarkers, empowering clinicians to make informed decisions on treatment strategies and patient management [17].

Despite numerous individual studies exploring the application of predictive models for CRCLM, a comprehensive evaluation of existing literature is currently lacking. A systematic analysis of the evidence is therefore timely.

MATERIALS AND METHODS

Database and search strategy

This study was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA, 2020) guidelines [18]. A comprehensive literature search was conducted in May 2023 using the following terms: (“machine learning” OR “machine intelligen*” OR “machine vision*” OR “artificial intelligen*” OR “deep learning” OR “neural network” OR “supervised learning” OR “unsupervised learning” OR “reinforcement learning” OR “predictive model*” OR “predictive model*”) AND (“colon*” OR “rectal” OR “colorectal” OR “colonic” OR “rectum” OR “bowel” OR “intestine”) AND (“cancer*” OR “malignan*” OR “neoplas*” OR “tumor*” OR “tumour*”) AND (“liver meta*” OR “liver metastasis”) in the PubMed, MEDLINE, Embase, and Web of Science databases.

Eligibility criteria

Studies were included if (1) the study population comprised male or female patients aged 18 years and above; (2) the participants consisted of adult individuals with CRC and liver metastasis; (3) the studies explicitly described and employed predictive modeling techniques to forecast the occurrence of CRCLM; (4) the studies reported the performance metrics of the predictive models, including sensitivity, specificity, accuracy, or the area under the receiver operating characteristic curve (AUC); (5) the full text of the articles was available for analysis; and (6) the articles were written in the English language. Case reports, reviews, and meta-analyses were excluded. The selection criteria did not specify a preferable study design or setting.

Study selection

Two reviewers (YZ and BHA) screened the titles and abstracts of the articles identified in the search to identify potentially eligible studies. Full-text articles were obtained for all potentially eligible studies, and were independently reviewed by these two reviewers to determine eligibility. Any discrepancies were resolved with a third author (ISE) through discussion and consensus. The study selection process was documented using a PRISMA flow diagram.

Data collection and analysis

The data collection was structured as per the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) [19]. The information extracted from each article included: the first author’s name, publication year, country of the study, study design, surgical approach, sample size, model details, model performance, and model evaluation. Due to significant heterogeneity observed in the study design, model development, and validation methodologies across the included studies, a meta-analysis was not performed.

Risk of bias assessment

The risk of bias (RoB) of the selected studies was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST) [20]. This tool consists of four domains: patient selection, predictors, outcomes, and analysis. In addition, another evaluation was conducted to assess the applicability of the included studies across three domains: participants, predictors, and outcomes. Two independent reviewers (YZ and BHA) assessed the RoB for each domain, and assigned a rating of high, low, or unclear RoB. Any discrepancies were resolved through discussion with a third author (ISE). The RoB assessment was documented using a graphical summary.

RESULTS

Overview of predictive modeling techniques

Table 1 presents a summary of CRCLM predictive modeling techniques included in the review. In broad terms, predictive modeling encompasses statistical learning, machine learning, and deep learning approaches (Fig. 1) [21-23]. Statistical learning primarily involves developing and applying statistical methods and algorithms for predictive purposes. Notable examples of statistical learning methods include logistic regression (LR), least absolute shrinkage and selection operator (LASSO) regression, Cox regression, and nomogram. A nomogram represents a graphical tool employed within statistical learning to estimate the probability of an outcome or compute the value of a variable by considering the values of other associated variables [24]. Machine learning, a subfield of artificial intelligence (AI), is dedicated to creating algorithms and models that empower computers to learn from data and make predictions. Prominent machine learning techniques encompass support vector machine (SVM), decision tree, and random forest (RF). Deep learning, a subfield of machine learning, focuses on leveraging neural networks with multiple layers to comprehend intricate patterns and representations within data. The convolutional neural network (CNN) is a type of artificial neural network used in deep learning.

Table 1 . Predictive modeling terminology included in the systematic review

TermDefinition
Predictive modelingThe process of creating a model that can predict future outcomes or events using historical data and statistical techniques
Statistical learningA field of study that focuses on the development and application of statistical methods and algorithms for data analysis and prediction
Machine learningA subfield of AI that focuses on the development of algorithms and models that enable computers to learn and make predictions or decisions without being explicitly programmed
Deep learningA subfield of machine learning that focuses on the development and use of AI neural networks with multiple layers to learn and extract intricate patterns and representations from data
Logistic regressionA statistical modeling technique that predicts the probability of a binary outcome based on one or more independent variables
Least absolute shrinkage and selection operatorA regularization technique used in regression analysis to perform variable selection and shrinkage of coefficients
Survival analysisA statistical method used to analyze the time until an event of interest occurs
Cox regressionA statistical technique used for survival analysis to determine the relationship between predictor variables and the time-to-event outcome
NomogramA graphical tool used in statistic and data analysis to estimate the probability of an outcome or to calculate the value of a variable based on the values of other variables
Support vector machineAn algorithm for machine learning that is used for classification and regression analysis to solve complex nonlinear problems
Decision treeA hierarchical, tree-like model is used for classification and decision-making. It arranges a series of decisions and their various outcomes into a tree-like structure, where each internal node represents a feature or attribute-based decision, and each leaf node represents a class label or an outcome
Random forestA machine learning algorithm that incorporates ensemble learning and decision trees
Convolutional neural networkA deep learning algorithm designed to analyze visual data. It automatically learns and extracts relevant features from the input data through the use of convolutional layers
RadiomicsIt involves quantifying medical images, including computed tomography, magnetic resonance imaging, and positron emission tomography and computed tomography. It incorporates a high-throughput extract of many quantitative image features that capture tumor phenotype, texture, shape, and spatial correlations. Applying machine learning or statistical learning to radiomic features can predict clinical outcomes or make prognostic assessments

AI, artificial intelligence.



Fig 1. Tree diagram of predictive modeling algorithms included in the systematic review. LASSO, least absolute shrinkage and selection operator.

Radiomics is the extraction and analysis of numerous quantitative features from medical images, such as those obtained from computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography with computed tomography (PET-CT), into computationally exploitable information [25,26]. This method entails extracting textural, shape-related, intensity-based, and spatial attributes from images. By employing machine learning or statistical learning techniques on the derived radiomic features, prediction of clinical outcomes becomes possible.

Study characteristics and predictive models

The PRISMA flow diagram (Fig. 2) summarizes the literature screening process. After removing duplicates, the search strategy yielded 117 studies for full-text screening. Seven articles [15,27-32] were included in this systematic review. Table 2 summarizes the baseline characteristics of the included studies. All seven articles were retrospective in design, published between 2019 and 2022, and comprised six single-center studies and one multi-center study with a total of 35,989 participants. Notably, two studies had sample sizes larger than 2,000 patients. The distribution of included predictive models was as follows: radiomics (n = 3), LR (n = 3), Cox regression (n = 2), nomogram (n = 3), SVM (n = 2), RF (n = 2), and CNN (n = 2).

Table 2 . Characteristics of included studies

AuthorYearCountryStudy designStudy periodStudy settingDisease conditionSurgical procedureSample sizePredictive modelInternal validationExternal validationDiscriminationCalibrationPredictor
Liang et al. [27]2019ChinaRetrospective2011–2017Single-centerRectal cancerTotal mesorectal excision108Radiomics + LRCross-validationNoAUC = 0.740No22 radiomic features
Radiomics + SVMAUC = 0.770
Yan et al. [28]2019ChinaRetrospective2004–2015Single-centerColon carcinomaNot specified32,819Cox regression; NomogramBootstrappingNoAUC = 0.825YesAge; CEA; tumor size; tumor grade; N staging
Li et al. [29]2019ChinaRetrospective2015–2018Single-centerColon cancerRadical colectomy48Clinical + SVMCross-validationNoAUC = 0.690NoAge; sex; tumor location; tumor histology; tumor size
Radiomics + SVMAUC = 0.8506 radiomic features
Hybrid + SVMAUC = 0.8706 clinical and radiomic features
Taghavi et al. [15]2021NetherlandsRetrospective2006–2016MulticenterColorectal cancerNot specified91Clinical + RFBootstrapping; Cross-validationNoAUC = 0.860NoAge; sex (male/female); primary tumor site; tumor stage; nodal stage; CEA; chemotherapy
Radiomics + RFAUC = 0.710101 radiomic features
Combined + RFAUC = 0.860104 clinical and radiomic features
Lee et al. [30]2020South KoreaRetrospective2008–2013Single-centerColorectal cancerColectomy2,019CNN + LRCross-validationNoAUC = 0.747NoAge; sex (male/female); T stage; N stage; CT image features
CNN + RFAUC = 0.697
Xiao et al. [31]2022ChinaRetrospective2016–2017Single-centerColorectal cancerRadical colorectal resection611CNNCross-validationNoAUC = 0.758YesDigital pathological images
Cox regression; NomogramBootstrappingAUC = 0.848Digital pathological images; N stage; T stage; VE/LI/PI
Hao et al. [32]2022ChinaRetrospective2016–2019Single-centerColorectal cancerNot specified293LR; NomogramBootstrappingNoAUC = 0.784YesAge; CEA; VI; T stage; N stage; family CRCLM history; KRAS

AUC, area under the receiver operating characteristic curve; CEA, carcinoembryonic antigen; CNN, convolutional neural network; CRCLM, colorectal cancer liver metastasis; KRAS, Kirsten rat sarcoma viral oncogene homologue; LI, lymphatic invasion; LR, logistic regression; PI, perineurial invasion; RF, random forest; SVM, support vector machine; VE, vascular emboli; VI, vascular invasion.



Fig 2. PRISMA flow diagram for data collection. The search returned a total of 141 records, of which 7 studies that reported predictive modeling techniques to predict colorectal caner liver metastasis (CRCLM) were included in the systematic review.

Predictors and outcomes

The predictive outcome of all included studies was the occurrence of CRCLM. Three studies integrated radiomics with LR, SVM, or RF; three employed nomograms in conjunction with LR or Cox regression; and two employed CNN (Table 2). The incorporation of clinicopathological variables as significant predictors was a consistent practice observed across all included studies. Amongst the clinicopathological variables used for predicting CRCLM, age (n = 5), sex (n = 3), carcinoembryonic antigen (CEA, n = 3), N stage (n = 4), and T stage (n = 3) emerged as the most frequently used predictors. Additional clinical predictors reported by individual studies included tumor size, tumor location, chemotherapy, CT images, digital pathological images, vascular emboli, lymphatic invasion, perineurial invasion, family history of CRCLM, and the presence of Kirsten rat sarcoma viral oncogene homologue (KRAS) mutations.

Model performance

The discriminative performance of each predictive model was assessed using the AUC (Table 2). The AUC values, ranging from 0 to 1, were utilized to gauge the predictive performance of the models, with 0.5 denoting random chance, and 1.0 indicating a perfect fit [33]. AUC values surpassing 0.7 indicated a reasonably accurate prediction model [33]. Regarding the prediction of CRCLM, the mean AUCs ranged between 0.697 to 0.870, with 86% of models demonstrating clear discriminative ability (AUC > 0.70). Amongst the diverse models employed, the hybrid approach incorporating both clinical and radiomic features alongside SVM demonstrated the highest discriminative ability (AUC = 0.870). Other well-performing models included radiomics with SVM (AUC = 0.850), clinical features with RF (AUC = 0.860), the combined model integrating both clinical and radiomic features with RF (AUC = 0.860), as well as CNN model coupled with Cox regression and nomogram (AUC = 0.848).

Model evaluation

All included studies conducted internal validation of their models through the resampling methods (Table 2), specifically cross-validation (n = 5) and/or bootstrapping (n = 4). Resampling techniques play a crucial role in evaluating and validating predictive models, ensuring their performance reliability [34]. Cross-validation partitions the available data into distinct subsets, or folds, where the model is trained on one fold (training set), and evaluated on the remaining fold (validation set) [35]. This technique mitigates overfitting risks and gauges the model’s generalizability across diverse data subsets. Conversely, bootstrapping involves generating multiple bootstrap samples through random sampling with replacement from the original dataset [35]. These bootstrap samples, of the same size as the original dataset, enable the training and evaluation of multiple models. Bootstrapping’s diverse resampled datasets facilitate the estimation of model performance variability and calculation of confidence intervals for key metrics, such as accuracy or AUC. The calibration, which pertains to the correspondence between the anticipated probabilities derived from a predictive model and the actual observed outcomes, signifying the precision and dependability of the model’s predictions, was reported for two nomogram models. None of the included studies reported external validation.

Risk of bias

Fig. 3 and Supplementary Table 1, 2 present the results of RoB and applicability assessment. The overall RoB was determined to be high in 71% of the included studies. Within the participants domain, 57% of the studies were assessed as having a low RoB. However, one study [28] was identified as having a high RoB due to insufficiently detailed inclusion criteria, while two studies [30,31] were classified as having an unclear RoB for similar reasons. Regarding the domain of predictors, 43% of the studies were assessed as low RoB. Notably, four studies [15,27,29,30] that utilized radiomic features were assigned a high RoB, due to the inherent complexity associated with these features. As for the outcomes domain, 71% of the studies were assessed as low RoB, with two studies [15,29] identified as having a high RoB due to their relatively small sample sizes (< 100). For the domain of analysis, 71% of the studies were assessed as low RoB, while only one study [29] was deemed to have a high RoB due to a lack of information regarding the 95% confidence interval of AUC, and the absence of details concerning the predictor selection process, coupled with a small sample size.

Fig 3. Methodological evaluation of the included predictive models. Assessment of the RoB based on PROBAST criteria. (A) Summary of RoB assessment. (B) Summary of applicability assessment. PROBAST, prediction model risk of bias assessment tool; RoB, risk of bias.
DISCUSSION

This systematic review encompassed a comprehensive analysis of seven studies, collectively reporting 14 predictive models incorporating diverse risk factors for CRCLM. Our study sought to identify and evaluate the predictive models that exhibited promising discrimination capabilities for CRCLM. By considering the characteristics of the included studies, essential insights regarding the current research landscape of predictive modeling for CRCLM were obtained.

The retrospective design of all seven studies underscored the reliance on historical data to develop and validate predictive models. This approach allowed clinicians and researchers to leverage existing patient information to construct and assess the performance of the models [36]. Furthermore, all studies were published between 2019 and 2022, reflecting the recent interest in predictive modeling for CRCLM. The temporal proximity of these articles suggests an evolving and dynamic research landscape characterized by the ongoing pursuit of innovative strategies for predicting CRCLM.

The distribution of predictive models also exhibited considerable diversity with various statistical/machine/deep learning approaches, including LR, Cox regression, nomogram, SVM, RF, and CNN. The 14 predictive models demonstrated mean AUC values ranging from 0.697 to 0.870, with the majority (71%) achieving an AUC exceeding 0.75, indicating valuable discriminatory performance [37]. Three studies used radiomic features in conjunction with machine learning algorithms to predict CRCLM, with one study resulting in the highest AUC of 0.870 by combining clinical and radiomic features with SVM. This highlights the effectiveness of integrating multiple data sources and advanced computational techniques at enhancing the accuracy of CRCLM prediction.

CT, MRI, and PET-CT are frequently used imaging modalities to detect CRCLM. Nevertheless, their diagnostic sensitivity and accuracy can vary depending on equipment and reporting radiologist’s expertise [38]. In a meta-analysis with a 20-year study period, the detection sensitivities for CRCLM for CT, MRI, and PET-CT were reported as 74.4%, 80.3%, and 81.4%, respectively [39]. Radiomics has shown promise in surpassing the limitations of conventional imaging, by enabling quantitative and comprehensive analysis of tumor characteristics [40]. Its ability to capture hidden patterns and heterogeneity within the tumor microenvironment provides valuable insights into the risk and potential for CRCLM development. Our results showed that radiomic models employing quantitative image features extracted from CT or MRI achieved an AUC greater than 0.70. These findings are consistent with studies that used radiomic models to predict distant metastases in other types of cancer [41-43], suggesting that the combination of radiomic features and machine learning techniques has the potential to improve the predictive accuracy of CRCLM.

However, the application of radiomics in predicting CRCLM faces several challenges. One significant drawback is the potential variability in image features across healthcare settings. Variations in imaging protocols, equipment, and image acquisition techniques can lead to inconsistencies in the extracted radiomic features. As a result, a model developed and validated in one healthcare setting may not perform optimally when applied to another setting. To overcome the lack of generalizability, the integration of clinicopathological alongside radiomic characteristics becomes crucial.

Clinical attributes provide important contextual information that complements the image-based features captured by radiomics. While radiomic features may be influenced by site-specific variations, clinical attributes tend to have a more consistent definition. Age, sex, CEA levels, and tumor stage (T and N staging) were identified as the most widely used predictors for CRCLM. Age is a fundamental demographic feature that may serve as a proxy for multiple factors associated with disease pathogenesis and progression. Age-related alterations in the immune response and decreased immune surveillance, including impaired T-cell proliferation, increased CD8+ cytotoxic cell numbers, and decreased CD4+ T-cell and CD19+ B-cell numbers, have been postulated to affect the immune capacity to identify and eliminate metastatic CRC cells, thereby potentially contributing to an increased risk of CRCLM [44-49].

Similarly, sex disparities in metastatic CRC outcomes have been observed [50,51], establishing sex as a noteworthy predictor for CRCLM. Hormones, including estrogen and testosterone, have been implicated in CRC development and progression [52,53]. Sex-specific hormonal differences influence the susceptibility to CRCLM, as estrogen potentially exerts protective effects against CRCLM development [52,54]. CEA is associated with other key factors, such as large tumor size, advanced tumor stage, lymph node involvement, and its involvement in facilitating tumor cell adhesion, migration, and invasion processes [55-59]. The regular monitoring of CEA levels plays a pivotal role in identifying individuals at heightened risk of CRCLM, and aids in the formulation of appropriate surveillance and treatment strategies [60]. The depth of tumor invasion and lymph node involvement are also high-risk features and predictors for CRCLM development [61].

SVM, RF, and Cox regression with nomogram showed better performance than LR and CNN in the prediction of CRCLM. SVM can effectively handle complex and high-dimensional clinical and radiomic features, capturing intricate patterns and non-linear relationships, which is crucial for accurate predictions [62]. The ability of SVM to separate data points into different classes by finding an optimal hyperplane maximally distant from the data points of different classes enhances its predictive accuracy [63]. RF is an ensemble learning method that combines multiple decision trees to make predictions. By constructing a multitude of decision trees on random subsets of the data and aggregating their predictions, RF can mitigate overfitting, and improve the generalizability of the predictive model [64]. Cox regression with nomogram is a survival analysis technique that considers time-to-event data and covariates. By incorporating clinical variables and constructing a nomogram, which visually represents the contribution of each predictor, this approach allows estimation of individualized probabilities for developing CRCLM.

On the other hand, LR and CNN may exhibit comparatively lower prediction performance. LR assumes linear relationships between predictors and the outcome, which may not adequately capture the complex interactions and non-linear associations present. CNN, although powerful in image analysis tasks, may not fully exploit the relevant features for CRCLM prediction, as it primarily focuses on extracting spatial patterns from medical images instead of incorporating clinical variables. Incorporating CNN for digital pathological image analysis, followed by Cox regression and nomogram, can enhance the predictive accuracy of the model.

Despite the generally high accuracies observed in the predictive models assessed in this review, there remain several limitations. One notable shortcoming is the absence of external validation in all seven included studies. In addition, calibration, which provides information about the agreement between predicted probabilities and observed outcomes, was only reported in three studies (43%) that utilized nomograms. Poor calibration suggests potential under- or overestimation of the desired outcome by the model. Furthermore, the assessment of model performance primarily relied on discrimination measures, specifically AUC, as calibration measures were absent in four (57%) of the included studies. Due to the considerable heterogeneity amongst the included studies, conducting a pooled analysis or comparative meta-analysis of predictive models was not feasible.

Nonetheless, this review provides valuable insights into the current landscape of predictive models for CRCLM. Our findings highlight the potential of various algorithms by augmented by clinical and radiomic features in accurately predicting CRCLM. Future research could address the identified limitations by incorporating external validation in predictive model development. Efforts should also be made to improve the reporting of calibration measures, enhancing model performance and calibration accuracy. Furthermore, the heterogeneity of the included studies highlights the need for standardized methodologies and reporting guidelines in the field of predictive modeling. Developing consensus criteria and guidelines would facilitate more rigorous and comparable evaluations of predictive models, facilitating more robust evidence synthesis and meta-analyses. Collaborative efforts, particularly multi-center studies, are essential to enhance the generalizability and clinical utility of predictive models for CRCLM.

Conclusion

This review demonstrates the potential of predictive modeling for CRCLM. The integration of clinicopathological and radiomic features with machine learning algorithms showed superior predictive capabilities. External validation studies are necessary to establish the reliability and generalizability of predictive models, particularly across diverse healthcare settings. Improved reporting and standardized methodologies are also required to facilitate the integration of predictive models into routine clinical practice.

SUPPLEMENTARY DATA

Supplementary data related to this article can be found at https://doi.org/10.14701/ahbps.23-078.

ahbps-28-1-14-supple.pdf
FUNDING

None.

CONFLICT OF INTEREST

No potential conflict of interest relevant to this article was reported.

AUTHOR CONTRIBUTIONS

Conceptualization: ISE, YZ. Data curation: YXK, YZ, AYC. Methodology: ISE, YXK, YZ. Visualization: YZ. Writing – original draft: ISE, YXK, YZ. Writing – review & editing: All authors.

References
  1. Edwards BK, Ward E, Kohler BA, Eheman C, Zauber AG, Anderson RN, et al. Annual report to the nation on the status of cancer, 1975-2006, featuring colorectal cancer trends and impact of interventions (risk factors, screening, and treatment) to reduce future rates. Cancer 2010;116:544-573.
    Pubmed KoreaMed CrossRef
  2. Morgan E, Arnold M, Gini A, Lorenzoni V, Cabasag C, Laversanne M, et al. Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from GLOBOCAN. Gut 2023;72:338-344.
    Pubmed CrossRef
  3. Bray F, Ferlay J, Soerjomataram I, Siegel RL, Torre LA, Jemal A. Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin 2018;68:394-424.
    Pubmed CrossRef
  4. Yu X, Zhu L, Liu J, Xie M, Chen J, Li J. Emerging role of immunotherapy for colorectal cancer with liver metastasis. Onco Targets Ther 2020;13:11645-11658.
    Pubmed KoreaMed CrossRef
  5. Tauriello DV, Calon A, Lonardo E, Batlle E. Determinants of metastatic competency in colorectal cancer. Mol Oncol 2017;11:97-119.
    Pubmed KoreaMed CrossRef
  6. Engstrand J, Nilsson H, Strömberg C, Jonas E, Freedman J. Colorectal cancer liver metastases-a population-based study on incidence, management and survival. BMC Cancer 2018;18:78.
    Pubmed KoreaMed CrossRef
  7. Martin J, Petrillo A, Smyth EC, Shaida N, Khwaja S, Cheow H, et al. Colorectal liver metastases: current management and future perspectives. World J Clin Oncol 2020;11:761.
    Pubmed KoreaMed CrossRef
  8. Hugen N, van de Velde CJH, de Wilt JHW, Nagtegaal ID. Metastatic pattern in colorectal cancer is strongly influenced by histological subtype. Ann Oncol 2014;25:651-657.
    Pubmed KoreaMed CrossRef
  9. Ivey GD, Johnston FM, Azad NS, Christenson ES, Lafaro KJ, Shubert CR. Current surgical management strategies for colorectal cancer liver metastases. Cancers (Basel) 2022;14:1063.
    Pubmed KoreaMed CrossRef
  10. Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng 2018;2:719-731.
    Pubmed CrossRef
  11. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2017;2:230-243.
    Pubmed KoreaMed CrossRef
  12. Secinaro S, Calandra D, Secinaro A, Muthurangu V, Biancone P. The role of artificial intelligence in healthcare: a structured literature review. BMC Med Inform Decis Mak 2021;21:125.
    Pubmed KoreaMed CrossRef
  13. Vorontsov E, Cerny M, Régnier P, Di Jorio L, Pal CJ, Lapointe R, et al. Deep learning for automated segmentation of liver lesions at CT in patients with colorectal cancer liver metastases. Radiol Artif Intell 2019;1:180014.
    Pubmed KoreaMed CrossRef
  14. Paredes AZ, Hyer JM, Tsilimigras DI, Moro A, Bagante F, Guglielmi A, et al. A novel machine-learning approach to predict recurrence after resection of colorecta liver metastases. Ann Surg Oncol 2020;27:5139-5147.
    Pubmed CrossRef
  15. Taghavi M, Trebeschi S, Simões R, Meek DB, Beckers RC, Lambregts DM, et al. Machine learning-based analysis of CT radiomics model for prediction of colorectal metachronous liver metastases. Abdom Radiol (NY) 2021;46:249-256.
    Pubmed CrossRef
  16. Rompianesi G, Pegoraro F, Ceresa CD, Montalti R, Troisi RI. Artificial intelligence in the diagnosis and management of colorectal cancer liver metastases. World J Gastroenterol 2022;28:108-122.
    Pubmed KoreaMed CrossRef
  17. Visvikis D, Cheze Le Rest C, Jaouen V, Hatt M. Artificial intelligence, machine (deep) learning and radio (geno) mics: definitions and nuclear medicine imaging applications. Eur J Nucl Med Mol Imaging 2019;46:2630-2637.
    Pubmed CrossRef
  18. Page MJ, Mckenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. Int J Surg 2021;88:105906.
    Pubmed CrossRef
  19. Moons KG, de Groot JA, Bouwmeester W, Vergouwe Y, Mallett S, Altman DG, et al. Critical appraisal and data extraction for systematic reviews of prediction modelling studies: the CHARMS checklist. PLoS Med 2014;11:e1001744.
    Pubmed KoreaMed CrossRef
  20. Moons KGM, Wolff RF, Riley RD, Whiting PF, Westwood M, Collins GS, et al. PROBAST: a tool to assess risk of bias and applicability of prediction model studies: explanation and elaboration. Ann Intern Med 2019;170:W1-W33.
    Pubmed CrossRef
  21. Sidey-Gibbons JAM, Sidey-Gibbons CJ. Machine learning in medicine: a practical introduction. BMC Med Res Methodol 2019;19:64.
    Pubmed KoreaMed CrossRef
  22. Pfob A, Lu SC, Sidey-Gibbons C. Machine learning in medicine: a practical introduction to techniques for data pre-processing, hyperparameter tuning, and model comparison. BMC Med Res Methodol 2022;22:282.
    Pubmed KoreaMed CrossRef
  23. Bektaş M, Tuynman JB, Costa Pereira J, Burchell GL, Van Der Peet DL. Machine learning algorithms for predicting surgical outcomes after colorectal surgery: a systematic review. World J Surg 2022;46:3100-3110.
    Pubmed KoreaMed CrossRef
  24. Jalali A, Alvarez-Iglesias A, Roshan D, Newell J. Visualising statistical models using dynamic nomograms. PloS One 2019;14:e0225253.
    Pubmed KoreaMed CrossRef
  25. Avanzo M, Wei L, Stancanello J, Vallieres M, Rao A, Morin O, et al. Machine and deep learning methods for radiomics. Med Phys 2020;47:e185-e202.
    Pubmed KoreaMed CrossRef
  26. Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 2012;48:441-446.
    Pubmed KoreaMed CrossRef
  27. Liang M, Cai Z, Zhang H, Huang C, Meng Y, Zhao L, et al. Machine learning-based analysis of rectal cancer MRI radiomics for prediction of metachronous liver metastasis. Acad Radiol 2019;26:1495-1504.
    Pubmed CrossRef
  28. Yan Y, Liu H, Mao K, Zhang M, Zhou Q, Yu W, et al. Novel nomograms to predict lymph node metastasis and liver metastasis in patients with early colon carcinoma. J Transl Med 2019;17:193.
    Pubmed KoreaMed CrossRef
  29. Li Y, Eresen A, Shangguan J, Yang J, Lu Y, Chen D, et al. Establishment of a new non-invasive imaging prediction model for liver metastasis in colon cancer. Am J Cancer Res 2019;9:2482-2492.
  30. Lee S, Choe EK, Kim SY, Kim HS, Park KJ, Kim D. Liver imaging features by convolutional neural network to predict the metachronous liver metastasis in stage I-III colorectal cancer patients based on preoperative abdominal CT scan. BMC Bioinformatics 2020;21:382.
    Pubmed KoreaMed CrossRef
  31. Xiao C, Zhou M, Yang X, Wang H, Tang Z, Zhou Z, et al. Accurate prediction of metachronous liver metastasis in stage I-III colorectal cancer patients using deep learning with digital pathological images. Front Oncol 2022;12:844067.
    Pubmed KoreaMed CrossRef
  32. Hao M, Li H, Wang K, Liu Y, Liang X, Ding L. Predicting metachronous liver metastasis in patients with colorectal cancer: development and assessment of a new nomogram. World J Surg Oncol 2022;20:80.
    Pubmed KoreaMed CrossRef
  33. Chok AY, Zhao Y, Chen HLR, Tan IE, Chew DHW, Zhao Y, et al. Elderly patients over 80 years undergoing colorectal cancer resection: development and validation of a predictive nomogram for survival. World J Gastrointest Surg 2023;15:892-905.
    Pubmed KoreaMed CrossRef
  34. Xiao J, Wang Y, Chen J, Xie L, Huang J. Impact of resampling methods and classification models on the imbalanced credit scoring problems. Information Sciences 2021;569:508-526.
    CrossRef
  35. International Joint Conferene on Artificial Intelligence (IJCAI); The 1995 International Joint Conference on AI; 1995 Aug 20-25; Montreal, Canada. Montreal: International Joint Conferene on Artificial Intelligence (IJCAI); 1995:1137-1143.
  36. Javaid M, Haleem A, Singh RP, Suman R, Rab S. Significance of machine learning in healthcare: features, pillars and applications. Int J Intell Netw 2022;3:58-73.
    CrossRef
  37. Alba AC, Agoritsas T, Walsh M, Hanna S, Iorio A, Devereaux P, et al. Discrimination and calibration of clinical prediction models: users' guides to the medical literature. JAMA 2017;318:1377-1384.
    Pubmed CrossRef
  38. Schulz A, Viktil E, Godt JC, Johansen CK, Dormagen JB, Holtedahl JE, et al. Diagnostic performance of CT, MRI and PET/CT in patients with suspected colorectal liver metastases: the superiority of MRI. Acta Radiol 2016;57:1040-1048.
    Pubmed CrossRef
  39. Niekel MC, Bipat S, Stoker J. Diagnostic imaging of colorectal liver metastases with CT, MR imaging, FDG PET, and/or FDG PET/CT: a meta-analysis of prospective studies including patients who have not previously undergone treatment. Radiology 2010;257:674-684.
    Pubmed CrossRef
  40. Forghani R, Savadjiev P, Chatterjee A, Muthukrishnan N, Reinhold C, Forghani B. Radiomics and artificial intelligence for biomarker and prediction model development in oncology. Comput Struct Biotechnol J 2019;17:995-1008.
    Pubmed KoreaMed CrossRef
  41. Fan L, Fang M, Tu W, Zhang D, Wang Y, Zhou X, et al. Radiomics signature: a biomarker for the preoperative distant metastatic prediction of stage I nonsmall cell lung cancer. Acad Radiol 2019;26:1253-1261.
    Pubmed CrossRef
  42. Zhang L, Dong D, Li H, Tian J, Ouyang F, Mo X, et al. Development and validation of a magnetic resonance imaging-based model for the prediction of distant metastasis before initial treatment of nasopharyngeal carcinoma: a retrospective cohort study. EBioMedicine 2019;40:327-335.
    Pubmed KoreaMed CrossRef
  43. Coroller TP, Grossmann P, Hou Y, Velazquez ER, Leijenaar RT, Hermann G, et al. CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. Radiother Oncol 2015;114:345-350.
    Pubmed KoreaMed CrossRef
  44. Busse PJ, Mathur SK. Age-related changes in immune function: effect on airway inflammation. J Allergy Clin Immunol 2010;126:690-699.
    Pubmed KoreaMed CrossRef
  45. Parcesepe P, Giordano G, Laudanna C, Febbraro A, Pancione M. Cancer-associated immune resistance and evasion of immune surveillance in colorectal cancer. Gastroenterol Res Pract 2016;2016:6261721.
    Pubmed KoreaMed CrossRef
  46. McConnell BB, Yang VW. The role of inflammation in the pathogenesis of colorectal cancer. Curr Colorectal Cancer Rep 2009;5:69-74.
    Pubmed KoreaMed CrossRef
  47. Smith HA, Kang Y. The metastasis-promoting roles of tumor-associated immune cells. J Mol Med (Berl) 2013;91:411-429.
    Pubmed KoreaMed CrossRef
  48. Kitamura T, Qian BZ, Pollard JW. Immune cell promotion of metastasis. Nat Rev Immunol 2015;15:73-86.
    Pubmed KoreaMed CrossRef
  49. Pancione M, Giordano G, Remo A, Febbraro A, Sabatino L, Manfrin E, et al. Immune escape mechanisms in colorectal cancer pathogenesis and liver metastasis. J Immunol Res 2014;2014:686879.
    Pubmed KoreaMed CrossRef
  50. Hendifar A, Yang D, Lenz F, Lurje G, Pohl A, Lenz C, et al. Gender disparities in metastatic colorectal cancer survival. Clin Cancer Res 2009;15:6391-6397.
    Pubmed KoreaMed CrossRef
  51. Press OA, Zhang W, Gordon MA, Yang D, Lurje G, Iqbal S, et al. Gender-related survival differences associated with EGFR polymorphisms in metastatic colon cancer. Cancer Res 2008;68:3037-3042.
    Pubmed CrossRef
  52. Abancens M, Bustos V, Harvey H, Mcbryan J, Harvey BJ. Sexual dimorphism in colon cancer. Front Oncol 2020;10:607909.
    Pubmed KoreaMed CrossRef
  53. Roshan MH, Tambo A, Pace NP. The role of testosterone in colorectal carcinoma: pathomechanisms and open questions. EPMA J 2016;7:22.
    Pubmed KoreaMed CrossRef
  54. Milette S, Hashimoto M, Perrino S, Qi S, Chen M, Ham B, et al. Sexual dimorphism and the role of estrogen in the immune microenvironment of liver metastases. Nat Commun 2019;10:5745.
    Pubmed KoreaMed CrossRef
  55. Su BB, Shi H, Wan J. Role of serum carcinoembryonic antigen in the detection of colorectal cancer before and after surgical resection. World J Gastroenterol 2012;18:2121-2126.
    Pubmed KoreaMed CrossRef
  56. Hammarström S. The carcinoembryonic antigen (CEA) family: structures, suggested functions and expression in normal and malignant tissues. Sem Cancer Biol 1999;9:67-81.
    Pubmed CrossRef
  57. Kamphues C, Andreatos N, Kruppa J, Buettner S, Wang J, Sasaki K, et al. The optimal cut-off values for tumor size, number of lesions, and CEA levels in patients with surgically treated colorectal cancer liver metastases: an international, multi-institutional study. J Surg Oncol 2021;123:939-948.
    Pubmed CrossRef
  58. Fletcher RH. Carcinoembryonic antigen. Ann Intern Med 1986;104:66-73.
    Pubmed CrossRef
  59. Duffy MJ. Carcinoembryonic antigen as a marker for colorectal cancer: is it clinically useful? Clin Chem 2001;47:624-630.
    Pubmed CrossRef
  60. Hall C, Clarke L, Pal A, Buchwald P, Eglinton T, Wakeman C, et al. A review of the role of carcinoembryonic antigen in clinical practice. Ann Coloproctol 2019;35:294-305.
    Pubmed KoreaMed CrossRef
  61. Enquist IB, Good Z, Jubb AM, Fuh G, Wang X, Junttila MR, et al. Lymph node-independent liver metastasis in a model of metastatic colorectal cancer. Nat Commun 2014;5:3530.
    Pubmed CrossRef
  62. Ahana P, Kavitha G. Radiomic features based severity prediction in dementia MR images using hybrid SSA-PSO optimizer and multi-class SVM classifier. IRBM 2022;43:549-560.
    CrossRef
  63. Awad M, Khanna R. Support vector machines for classification. In: Awad M, Khanna R. eds. Efficient Learning Machines: Theories, Concepts, and Applications for Engineers and System Designers. Apress, 2015:39-66.
    CrossRef
  64. Prasad AM, Iverson LR, Liaw A. Newer classification and regression tree techniques: bagging and random forests for ecological prediction. Ecosystems 2006;9:181-199.
    CrossRef

 

May 2024, 28 (2)