Dataset Information

Machine learning for predicting survival of colorectal cancer patients.

ABSTRACT: Colorectal cancer is one of the most incident types of cancer in the world, with almost 2 million new cases annually. In Brazil, the scenery is the same, around 41 thousand new cases were estimated in the last 3 years. This increase in cases further intensifies the interest and importance of studies related to the topic, especially using new approaches. The use of machine learning algorithms for cancer studies has grown in recent years, and they can provide important information to medicine, in addition to making predictions based on the data. In this study, five different classifications were performed, considering patients' survival. Data were extracted from Hospital Based Cancer Registries of São Paulo, which is coordinated by Fundação Oncocentro de São Paulo, containing patients with colorectal cancer from São Paulo state, Brazil, treated between 2000 and 2021. The machine learning models used provided us the predictions and the most important features for each one of the algorithms of the studies. Using part of the dataset to validate our models, the results of the predictors were around 77% of accuracy, with AUC close to 0.86, and the most important column was the clinical staging in all of them.

SUBMITTER: Buk Cardoso L

PROVIDER: S-EPMC10235087 | biostudies-literature | 2023 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning for predicting survival of colorectal cancer patients.

Buk Cardoso Lucas L Cunha Parro Vanderlei V Verzinhasse Peres Stela S Curado Maria Paula MP Fernandes Gisele Aparecida GA Wünsch Filho Victor V Natasha Toporcov Tatiana T

Scientific reports 20230601 1

Colorectal cancer is one of the most incident types of cancer in the world, with almost 2 million new cases annually. In Brazil, the scenery is the same, around 41 thousand new cases were estimated in the last 3 years. This increase in cases further intensifies the interest and importance of studies related to the topic, especially using new approaches. The use of machine learning algorithms for cancer studies has grown in recent years, and they can provide important information to medicine, in ...[more]

PMID: 37264045

Similar Datasets

Project description:BackgroundMachine learning (ML) methods have shown great potential in predicting colorectal cancer (CRC) survival. However, the ML models introduced thus far have mainly focused on binary outcomes and have not considered the time-to-event nature of this type of modeling.ObjectiveThis study aims to evaluate the performance of ML approaches for modeling time-to-event survival data and develop transparent models for predicting CRC-specific survival.MethodsThe data set used in this retrospective cohort study contains information on patients who were newly diagnosed with CRC between December 28, 2012, and December 27, 2019, at West China Hospital, Sichuan University. We assessed the performance of 6 representative ML models, including random survival forest (RSF), gradient boosting machine (GBM), DeepSurv, DeepHit, neural net-extended time-dependent Cox (or Cox-Time), and neural multitask logistic regression (N-MTLR) in predicting CRC-specific survival. Multiple imputation by chained equations method was applied to handle missing values in variables. Multivariable analysis and clinical experience were used to select significant features associated with CRC survival. Model performance was evaluated in stratified 5-fold cross-validation repeated 5 times by using the time-dependent concordance index, integrated Brier score, calibration curves, and decision curves. The SHapley Additive exPlanations method was applied to calculate feature importance.ResultsA total of 2157 patients with CRC were included in this study. Among the 6 time-to-event ML models, the DeepHit model exhibited the best discriminative ability (time-dependent concordance index 0.789, 95% CI 0.779-0.799) and the RSF model produced better-calibrated survival estimates (integrated Brier score 0.096, 95% CI 0.094-0.099), but these are not statistically significant. Additionally, the RSF, GBM, DeepSurv, Cox-Time, and N-MTLR models have comparable predictive accuracy to the Cox Proportional Hazards model in terms of discrimination and calibration. The calibration curves showed that all the ML models exhibited good 5-year survival calibration. The decision curves for CRC-specific survival at 5 years showed that all the ML models, especially RSF, had higher net benefits than default strategies of treating all or no patients at a range of clinically reasonable risk thresholds. The SHapley Additive exPlanations method revealed that R0 resection, tumor-node-metastasis staging, and the number of positive lymph nodes were important factors for 5-year CRC-specific survival.ConclusionsThis study showed the potential of applying time-to-event ML predictive algorithms to help predict CRC-specific survival. The RSF, GBM, Cox-Time, and N-MTLR algorithms could provide nonparametric alternatives to the Cox Proportional Hazards model in estimating the survival probability of patients with CRC. The transparent time-to-event ML models help clinicians to more accurately predict the survival rate for these patients and improve patient outcomes by enabling personalized treatment plans that are informed by explainable ML models.

Project description:Background: For the majority of patients of metastatic colorectal cancer (mCRC), systematic chemotherapy has been a choice for palliative treatment. When first-line chemotherapies do not work, targeted therapies are administered. Because of inter-individual genetic and epigenetic variations, patients with mCRC who are treated with these therapies may respond differently. It is of great clinical interest to elucidate response mechanisms that could be utilized in predicting individual response to these treatments. Methods: A highly sensitive technique, the 5hmC-Seal was applied to profile genome-wide 5-hydroxymethylcytosines (5hmC) in 155 cfDNA samples from patients with mCRC recruited for two clinical trials at Zhongshan Hospital, Fudan University in China. Response to systematic chemotherapy and targeted therapy (becacizumab or cetuximab) (CR, complete response; PR, partial response; SD, stable disease; PD, progressive disease) was measured and a 5hmC-based predictive model in cfDNA was developed using a machine learning approach in the PROVE Study (NCT03679039) (n = 100), followed by validation in the METHOD Study (NCT03599947) (n = 55). Results: Genome-wide mapping of 5hmC in patient-derived cfDNA suggested a distinct 5hmC landscape showing tissue origin and gene regulatory relevance. A eleven-gene model involving relevant pathways such as Rap1 signaling pathway, cAMP signaling pathway, Phospholipase D signaling pathway and cGMP-PKG signaling pathway, distinguished patients with mCRC who responded to chemotherapy, regardless of targeted therapy, resectability, or mutation status in the validation samples (AUC=0.77; 95% CI, 0.64-0.90), outperforming RAS mutation status (AUC=0.70; 95% CI, 0.57-0.83). In addition, the 5hmC model also showed a trend of capacity for predicting progression-free survival (PFS) for mCRC. Conclusions: Genome-wide mapping reflected relevant pathways and functional interaction networks implicated in the determination of treatment response for patients with mCRC. The 5hmC-Seal model in cfDNA provided a promising non-invasive method for predicting response to systematic chemotherapy in patients with mCRC, who will be essential for personalized medicine.

Project description:ObjectiveDespite existing prognostic markers, breast cancer prognosis remains a difficult subject due to the complex relationships between many contributing factors and survival. This study seeks to integrate multiple clinicopathological and genomic factors with dimensional reduction across machine learning algorithms to compare survival predictions.MethodsThis is a secondary analysis of the data from a prospective cohort study of female patients with breast cancer enrolled in the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC). We constructed a series of predictive models: ensemble models (Gradient Boosting and Random Forest), support vector machine (SVM), and artificial neural networks (ANN) for 5-year survival based on clinicopathological and gene expression data after K-means clustering with K-nearest-neighbor (KNN) classification. Model performance was evaluated by receiver operating characteristic (ROC) curve, accuracy, and calibration slope (CS). Model stability was assessed over 10 random runs in terms of ROC, accuracy, CS, and variable importance.ResultsThe analytic cohort is composed of 1874 patients with breast cancer. Overall, the median age was 62 years; the 5-year survival rate was 75%. ROC and accuracy were not significantly different between models (ROC and accuracy around 0.67 and 0.72 across models, respectively). However, ensemble methods resulted in better fit (CS) with stable measures of variable importance across 10 random training/validation splits. K-means clustering of gene expression profiles on training data points along with KNN classification of validation data points was a robust method of dimensional reduction. Furthermore, the gene expression cluster with the highest mortality risk was an influential factor in model prediction.ConclusionsUsing machine learning methods to construct predictive models for 5-year survival in patients with breast cancer, we demonstrated discrimination ability across models with new insight into the stability and utility of dimensional reduction on genomic features in breast cancer survival prediction.

Dataset Information

Machine learning for predicting survival of colorectal cancer patients.

Publications

Machine learning for predicting survival of colorectal cancer patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets