Predictive Value of Genetic Risk Scores in the Development of Colorectal Adenomas

Gargallo-Puyuelo, C J; Aznar-Gimeno, Rocío; Carrera‐Lasfuentes, Patricia; Lanas, Ángel; Ferrández, Ángel; Quintero, Enrique; Carrillo, Marta; Alonso‐Abreu, Inmaculada; Esteban, Luis; Rodrigálvarez-Chamarro, María de la Vega; del-Hoyo-Alonso, Rafael; García-González, María Asunción

doi:10.1007/s10620-021-07218-5

Cited by 5 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This AUC value was slightly better than those reported in other studies, which use predictive models based on dietary habits and lifestyle, such as the Betés score [15] (AUC 0.65 for advanced CRN; 95% CI (0.61-0.68)) or the Kaminski score [31] with an AUC of 0.62 for advanced CRN (95% CI, 0.60-0.64). Along the same line, our score also demonstrates a predictive capability better than previously developed scores based on more complex and costly genetic analyses [32][33][34]. For example, Jeon et al [32] with a combined model of genetic, environmental, and lifestyle factors showed a discriminatory capacity of 0.63 for men and 0.62 for women.…”

Section: Discussionsupporting

confidence: 63%

“…Ibáñez et al [33] reported a similar discriminatory capacity (0.63) using genetic, environmental risk factors, and family history. Our research group reported an AUC of 0.66 with a genetic model combined with age and sex [34]. Finally, between the studies with the highest predictive capacity, Cai et al [16] reported an AUC of 0.74 (95% CI: 0.70-0.78), using age, sex, smoking, diabetes mellitus, and the consumption of green vegetables, pickles, fried foods, and white meats; however, some these factors are prone to recall bias.…”

Section: Discussionmentioning

confidence: 70%

See 1 more Smart Citation

Predictive Score for Advanced Colorectal Neoplasia Based on Cardiovascular and Colorectal Cancer Risk Factors

Ruiz-Belmonte,

Carrera-Lasfuentes,

Cebollada-Solanas

et al. 2024

JCM

Self Cite

View full text Add to dashboard Cite

Background and Aims: Cardiovascular disease and colorectal cancer (CRC) are significant health problems and share some risk factors. The aim of our study was to develop and validate a predictive score for advanced colorectal neoplasia (CRN) based on risk factors for cardiovascular disease and CRC. Materials and Methods: A cross-sectional study comprising a derivation cohort and an external validation cohort of 1049 and 308 patients, respectively. A prediction score for advanced CRN (CRNAS: Colorectal Neoplasia Advanced Score) was developed from a logistic regression model, comprising sex, age, first-degree family history for CRC, systolic and diastolic blood pressure, total cholesterol, HDL cholesterol, body mass index, diabetes, smoking, and antihypertensive treatment. Other cardiovascular risk scores (Framingham–Wilson, REGICOR, SCORE, and FRESCO) were also used to predict the risk of advanced CRN. The discriminatory capacity of each score was evaluated using the area under the curve (AUC). Results: CRN were found in 379 subjects from the derivation cohort (36%), including 228 patients (22%) with an advanced CRN. Male sex, age, diabetes, and smoking were identified as independent risk factors for advanced CRN. The newly created score (CRNAS) showed an AUC of 0.68 (95% CI: 0.64–0.73) for advanced CRN, which was better than cardiovascular risk scores (p < 0.001). In the validation cohort, the AUC of CRNAS for advanced CRN was 0.67 (95% CI: 0.57–0.76). Conclusions: The newly validated CRNAS has a better discriminatory capacity to predict advanced CRN than cardiovascular scores. It may be useful for selecting candidates for screening colonoscopy, especially in those with cardiovascular risk factors.

show abstract

Section: Discussionsupporting

confidence: 63%

Section: Discussionmentioning

confidence: 70%

Predictive Score for Advanced Colorectal Neoplasia Based on Cardiovascular and Colorectal Cancer Risk Factors

Ruiz-Belmonte,

Carrera-Lasfuentes,

Cebollada-Solanas

et al. 2024

JCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…This AUC value was slightly better than those reported in other studies, which use predictive models based on dietary habits and lifestyle, such as the Betés score [13] (AUC 0.65 for advanced CRN; 95% CI (0.61-0.68)) or the Kaminski score [29] with an AUC of 0.62 for advanced CRN (95% CI, 0.60-0.64). In the same line, our score also demonstrates a predictive capability better than previously developed scores based on more complex and costly genetic analyses [30][31][32]. For example, Jeon et al [30] with a combined model of genetic, environmental, and lifestyle factors showed a discriminatory capacity of 0.63 for men and 0.62 for women.…”

Section: Discussionsupporting

confidence: 63%

“…Ibáñez et al [31] reported a similar discriminatory capacity (0.63) using genetic, environmental risk factors and family history. Our research group reported an AUC of 0.66 with a genetic model combined with age and sex [32]. Finally, between the studies with the highest predictive capacity, Cai et al [14] reported an AUC of 0.74 (95% CI: 0.70-0.78), using age, sex, smoking, diabetes mellitus, and the consumption of green vegetables, pickles, fried foods, and white meats.…”

Section: Discussionsupporting

confidence: 48%

Predictive Score for Advanced Colorectal Neoplasia Based on Cardiovascular and Colorectal Cancer Risk Factors

Ruiz Belmonte,

Carrera-Lasfuentes,

Cebollada-Solanas

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND AND AIMS: Cardiovascular disease and colorectal cancer (CRC) are significant health problems and share some risk factors. The aim of our study was to develop and validate a predictive score for advanced colorectal neoplasia (CRN) based on risk factors for cardiovascular disease and CRC. MATERIALS AND METHODS: A cross-sectional study comprising a derivation cohort and an external validation cohort of 1049 and 308 patients respectively. A prediction score for advanced CRN (CRNAS: Colorectal Neoplasia Advanced Score) was developed from a logistic regression model, comprising sex, age, first-degree family history for CRC, systolic and diastolic blood pressure, total cholesterol, HDL-cholesterol, body mass index, diabetes, smoking, and antihypertensive treatment. Other cardiovascular risk scores (Framingham-Wilson, REGICOR, SCORE and FRESCO) were also used to predict the risk of advanced CRN. The discriminatory capacity of each score was evaluated using the area under the curve (AUC). RESULTS: CRN were found in 379 subjects from the derivation cohort (36%) including 228 patients (22%) with an advanced CRN. Male sex, age, diabetes, and smoking were identified as independent risk factors for advanced CRN. The newly created score (CRNAS), showed an AUC of 0.68 (95% CI: 0.64-0.73) for advanced CRN, which was better than cardiovascular risk scores (p

show abstract

“…The linear combination of multiple biomarkers is often used in clinical practice [1] for disease diagnosis due to its ease of interpretation and performance [2], which is usually superior to considering each biomarker separately [3][4][5][6][7][8]. These new biomarkers are key for disease screening or understanding the evolution of a disease after diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Comparing the Min–Max–Median/IQR Approach with the Min–Max Approach, Logistic Regression and XGBoost, Maximising the Youden Index

et al. 2023

Self Cite

View full text Add to dashboard Cite

Although linearly combining multiple variables can provide adequate diagnostic performance, certain algorithms have the limitation of being computationally demanding when the number of variables is sufficiently high. Liu et al. proposed the min–max approach that linearly combines the minimum and maximum values of biomarkers, which is computationally tractable and has been shown to be optimal in certain scenarios. We developed the Min–Max–Median/IQR algorithm under Youden index optimisation which, although more computationally intensive, is still approachable and includes more information. The aim of this work is to compare the performance of these algorithms with well-known Machine Learning algorithms, namely logistic regression and XGBoost, which have proven to be efficient in various fields of applications, particularly in the health sector. This comparison is performed on a wide range of different scenarios of simulated symmetric or asymmetric data, as well as on real clinical diagnosis data sets. The results provide useful information for binary classification problems of better algorithms in terms of performance depending on the scenario.

show abstract

Predictive Value of Genetic Risk Scores in the Development of Colorectal Adenomas

Cited by 5 publications

References 18 publications

Predictive Score for Advanced Colorectal Neoplasia Based on Cardiovascular and Colorectal Cancer Risk Factors

Predictive Score for Advanced Colorectal Neoplasia Based on Cardiovascular and Colorectal Cancer Risk Factors

Predictive Score for Advanced Colorectal Neoplasia Based on Cardiovascular and Colorectal Cancer Risk Factors

Comparing the Min–Max–Median/IQR Approach with the Min–Max Approach, Logistic Regression and XGBoost, Maximising the Youden Index

Contact Info

Product

Resources

About