Survival Prediction and Feature Selection in Patients with Breast Cancer Using Support Vector Regression

Integrated Bioinformatics and Experimental Validation to Identify a Disulfidptosis-Related lncRNA Model for Prognostic Prediction in Papillary Renal Cell Carcinoma

AIMS

This study aimed to construct a prognostic model for papillary renal cell carcinoma (pRCC) utilizing disulfidptosis-associated long non-coding RNAs (lncRNAs). Additionally, it investigated the potential of these lncRNAs in predicting immune responses and drug sensitivity in pRCC.

BACKGROUND

LncRNAs have been implicated in the progression and prognosis of pRCC. Recently, disulfidptosis, an emerging form of regulated cell death, has shown potential as a therapeutic approach for cancer. However, the potential association between disulfidptosis-related lncRNAs and pRCC remains unclear.

METHODS

We analyzed transcriptome profiling and clinical data of pRCC patients from The Cancer Genome Atlas database. Using Pearson correlation analysis, we identified lncRNAs associated with disulfidptosis. Based on the disulfidptosis-related lncRNAs that were correlated with overall survival (OS), we constructed a novel prediction model using least absolute shrinkage and selection operator, univariable Cox regression, and multivariable Cox regression analyses. The model's utility was assessed through Kaplan-Meier survival, receiver operating characteristics, and principal component analyses. Moreover, functional analysis helped identify potential prognostic mechanisms, and the prediction of chemical drugs for pRCC was also performed. Finally, qRT-PCR validated the expression of prognostic lncRNAs in pRCC cells and patient samples.

RESULTS

Our prediction model was based on nine disulfidptosis-related lncRNAs. Evaluation and validation analyses demonstrated that the model had excellent, consistent, and independent prognostic value for pRCC patients, with area under the curve values of 0.954, 0.910, and 0.830 for 1-, 3-, and 5-year OS, respectively. Through functional analysis, we discovered a significant correlation between the identified prognostic signature and immunity. Additionally, in terms of chemotherapy sensitivity, our analysis indicated that the low-risk group exhibited higher sensitivity to sunitinib and pazopanib. Furthermore, the expression patterns of the identified lncRNAs were validated in samples obtained from pRCC cells and patients.

CONCLUSION

This study successfully established and validated a novel disulfidptosis-related prediction model. The findings suggest the potential involvement of immune-related pathways in lncRNA signature-associated survival. This model holds promise for differentiating prognosis and improving personalized therapeutic strategies for pRCC in clinical practice.

Smart Biosensor for Breast Cancer Survival Prediction Based on Multi-View Multi-Way Graph Learning

Biosensors play a crucial role in detecting cancer signals by orchestrating a series of intricate biological and physical transduction processes. Among various cancers, breast cancer stands out due to its genetic underpinnings, which trigger uncontrolled cell proliferation, predominantly impacting women, and resulting in significant mortality rates. The utilization of biosensors in predicting survival time becomes paramount in formulating an optimal treatment strategy. However, conventional biosensors employing traditional machine learning methods encounter challenges in preprocessing features for the learning task. Despite the potential of deep learning techniques to automatically extract useful features, they often struggle to effectively leverage the intricate relationships between features and instances. To address this challenge, our study proposes a novel smart biosensor architecture that integrates a multi-view multi-way graph learning (MVMWGL) approach for predicting breast cancer survival time. This innovative approach enables the assimilation of insights from gene interactions and biosensor similarities. By leveraging real-world data, we conducted comprehensive evaluations, and our experimental results unequivocally demonstrate the superiority of the MVMWGL approach over existing methods.

Breast tumor localization and segmentation using machine learning techniques: Overview of datasets, findings, and methods

The Global Cancer Statistics 2020 reported breast cancer (BC) as the most common diagnosis of cancer type. Therefore, early detection of such type of cancer would reduce the risk of death from it. Breast imaging techniques are one of the most frequently used techniques to detect the position of cancerous cells or suspicious lesions. Computer-aided diagnosis (CAD) is a particular generation of computer systems that assist experts in detecting medical image abnormalities. In the last decades, CAD has applied deep learning (DL) and machine learning approaches to perform complex medical tasks in the computer vision area and improve the ability to make decisions for doctors and radiologists. The most popular and widely used technique of image processing in CAD systems is segmentation which consists of extracting the region of interest (ROI) through various techniques. This research provides a detailed description of the main categories of segmentation procedures which are classified into three classes: supervised, unsupervised, and DL. The main aim of this work is to provide an overview of each of these techniques and discuss their pros and cons. This will help researchers better understand these techniques and assist them in choosing the appropriate method for a given use case.

Predicting VO2max in Children and Adolescents Aged between 6 and 17 Using Physiological Characteristics and Participation in Sport Activities: A Cross-Sectional Study Comparing Different Regression Models Stratified by Gender

Background: The aim of this study is to use different regression models to capture the association between cardiorespiratory fitness VO2max (measured in mL/kg/min) and somatometric characteristics and sports activities and making better predictions. Methods: multiple linear regression (MLR), quantile regression (QR), ridge regression (RR), support vector regression (SVR) with three different kernels, artificial neural networks (ANNs), and boosted regression trees (RTs) were compared to explain and predict VO2max and to choose the best performance model. The sample consisted of 4908 children (2314 males and 2594 females) aged between 6 and 17. Cardiorespiratory fitness was assessed by the 20 m maximal multistage shuttle run test and maximal oxygen uptake (VO2max) was calculated. Welch t-tests, Mann−Whitney-U tests, X2 tests, and ANOVA tests were performed. The performance measures were root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). All analyses were stratified by gender. Results: A comparison of the statistical indices for both the predicted and actual data indicated that in boys, the MLR model outperformed all other models in all indices, followed by the linear SVR model. In girls, the MLR model performed better than the other models in R2 but was outperformed by SVR-RBF in terms of RMSE and MAE. The overweight and obesity categories in both sexes (p < 0.001) and maternal prepregnancy obesity in girls had a significant negative effect on VO2max. Age, weekly football training, track and field, basketball, and swimming had different positive effects based on gender. Conclusion: The MLR model showed remarkable performance against all other models and was competitive with the SVR models. In addition, this study’s data showed that changes in cardiorespiratory fitness were dependent, to a different extent based on gender, on BMI category, weight, height, age, and participation in some organized sports activities. Predictors that are not considered modifiable, such as gender, can be used to guide targeted interventions and policies.

Using machine learning to predict gamma passing rate in volumetric-modulated arc therapy treatment plans

PURPOSE

This study aims to develop an algorithm to predict gamma passing rate (GPR) in the volumetric-modulated arc therapy (VMAT) technique.

MATERIALS AND METHODS

A total of 118 clinical VMAT plans, including 28 mediastina, 25 head and neck, 40 brains intensity-modulated radiosurgery, and 25 prostate cases, were created in RayStation treatment planning system for Edge and TrueBeam linacs. In-house scripts were developed to compute Modulation indices such as plan-averaged beam area (PA), plan-averaged beam irregularity (PI), total monitor unit (MU), leaf travel/arc length, mean dose rate variation, and mean gantry speed variation. Pretreatment verifications were performed on ArcCHECK phantom with SNC software. GPR was calculated with 3%/2 mm and 10% threshold. The dataset was randomly split into a training (70%) and a test (30%) dataset. A random forest regression (RFR) model and support vector regression (SVR) with linear kernel were trained to predict GPR using the complexity metrics as input. The prediction performance was evaluated by calculating the mean absolute error (MAE), R² , and root mean square error (RMSE).

RESULTS

RMSEs at γ 3%/2 mm for RFR and SVR were 1.407 ± 0.103 and 1.447 ± 0.121, respectively. MAE was 1.14 ± 0.084 for RFR and 1.101 ± 0.09 for SVR. R² was equal to 0.703 ± 0.027 and 0.689 ± 0.053 for RFR and SVR, respectively. GPR of 3%/2 mm with a 10% threshold can be predicted with an error smaller than 3% for 94% of plans using RFR and SVR models. The most important metrics that had the greatest impact on how accurately GPR can be predicted were determined to be the PA, PI, and total MU.

CONCLUSION

In terms of its prediction values and errors, SVR (linear) appeared to be comparable with RFR for this dataset. Based on our results, the PA, PI, and total MU calculations may be useful in guiding VMAT plan evaluation and ultimately reducing uncertainties in planning and radiation delivery.

A systematic review on machine learning and deep learning techniques in cancer survival prediction

Cancer is a disease which is characterised by the unusual and uncontrollable growth of body cells. This usually happens asymptomatically and gets spread to other parts of the body. The major problem in treating cancer is that its progress is not monitored once it is diagnosed. The progress or the prognosis can be done through survival analysis. The survival analysis is the branch of statistics that deals in predicting the time of event of occurrence. In the case of cancer prognosis the event is the survival time of the patient from the onset of the disease or it can be the recurrence of the disease after undergoing a treatment. This study aims to bring out the machine learning and deep learning models involved in providing the prognosis to the cancer patients.

Deep learning based feature-level integration of multi-omics data for breast cancer patients survival analysis

BACKGROUND

Breast cancer is the most prevalent and among the most deadly cancers in females. Patients with breast cancer have highly variable survival lengths, indicating a need to identify prognostic biomarkers for personalized diagnosis and treatment. With the development of new technologies such as next-generation sequencing, multi-omics information are becoming available for a more thorough evaluation of a patient's condition. In this study, we aim to improve breast cancer overall survival prediction by integrating multi-omics data (e.g., gene expression, DNA methylation, miRNA expression, and copy number variations (CNVs)).

METHODS

Motivated by multi-view learning, we propose a novel strategy to integrate multi-omics data for breast cancer survival prediction by applying complementary and consensus principles. The complementary principle assumes each -omics data contains modality-unique information. To preserve such information, we develop a concatenation autoencoder (ConcatAE) that concatenates the hidden features learned from each modality for integration. The consensus principle assumes that the disagreements among modalities upper bound the model errors. To get rid of the noises or discrepancies among modalities, we develop a cross-modality autoencoder (CrossAE) to maximize the agreement among modalities to achieve a modality-invariant representation. We first validate the effectiveness of our proposed models on the MNIST simulated data. We then apply these models to the TCCA breast cancer multi-omics data for overall survival prediction.

RESULTS

For breast cancer overall survival prediction, the integration of DNA methylation and miRNA expression achieves the best overall performance of 0.641 ± 0.031 with ConcatAE, and 0.63 ± 0.081 with CrossAE. Both strategies outperform baseline single-modality models using only DNA methylation (0.583 ± 0.058) or miRNA expression (0.616 ± 0.057).

CONCLUSIONS

In conclusion, we achieve improved overall survival prediction performance by utilizing either the complementary or consensus information among multi-omics data. The proposed ConcatAE and CrossAE models can inspire future deep representation-based multi-omics integration techniques. We believe these novel multi-omics integration models can benefit the personalized diagnosis and treatment of breast cancer patients.

A Translational Pipeline for Overall Survival Prediction of Breast Cancer Patients by Decision-Level Integration of Multi-Omics Data

Breast cancer is the most prevalent and among the most deadly cancers in females. Patients with breast cancer have highly variable survival rates, indicating a need to identify prognostic biomarkers. By integrating multi-omics data (e.g., gene expression, DNA methylation, miRNA expression, and copy number variations (CNVs)), it is likely to improve the accuracy of patient survival predictions compared to prediction using single modality data. Therefore, we propose to develop a machine learning pipeline using decision-level integration of multi-omics tumor data from The Cancer Genome Atlas (TCGA) to predict the overall survival of breast cancer patients. With multi-omics data consisting of gene expression, methylation, miRNA expression, and CNVs, the top performing model predicted survival with an accuracy of 85% and area under the curve (AUC) of 87%. Furthermore, the model was able to identify which modalities best contributed to prediction performance, identifying methylation, miRNA, and gene expression as the best integrated classification combination. Our method not only recapitulated several breast cancer-specific prognostic biomarkers that were previously reported in the literature but also yielded several novel biomarkers. Further analysis of these biomarkers could lend insight into the molecular mechanisms that lead to poor survival.

Application of a combined model with seasonal autoregressive integrated moving average and support vector regression in forecasting hand-foot-mouth disease incidence in Wuhan, China

Hand-foot-mouth disease (HFMD) is a serious public health problem with increasing cases and substantial financial burden in China, especially in Wuhan city. Hence, there is an urgent need to construct a model to predict the incidence of HFMD that could make the prevention and control of this disease more effective.The incidence data of HFMD of Wuhan city from January 2009 to December 2016 were used to fit a combined model with seasonal autoregressive integrated moving average (SARIMA) model and support vector regression (SVR) model. Then, the SARIMA-SVR hybrid model was constructed. Subsequently, the fitted SARIMA-SVR hybrid model was applied to obtain the fitted HFMD incidence from 2009 to 2016. Finally, the fitted SARIMA-SVR hybrid model was used to forecast the incidence of HFMD of the year 2017. To assess the validity of the model, the mean square error (MSE) and mean absolute percentage error (MAPE) between the actual values and predicted values of HFMD incidence (2017) were calculated.From 2009 to 2017, a total of 107636 HFMD cases were reported in Wuhan City, Hubei Province, and the male-to-female ratio is 1.60:1. The age group of 0 to 5 years old accounts for 95.06% of all reported cases and scattered children made up the large proportion (accounted for 56.65%). There were 2 epidemic peaks, from April to July and September to December, respectively, with an emphasis on the former. High-prevalence areas mainly emerge in Dongxihu District, Jiangxia District, and Hongshan District. SARIMA (1,0,1)(0,0,2)[12] is the optimal model given with a minimum Akaike information criterion (AIC) (700.71), then SVR model was constructed by using the optimum parameter (C = 100000, =0.00001, =0.01). The forecasted incidences of single SARIMA model and SARIMA-SVR hybrid model from January to December 2017 match the actual data well. The single SARIMA model shows poor performance with large MSE and MAPE values in comparison to SARIMA-SVR hybrid model.The SARIMA-SVR hybrid model in this study showed that accurate forecasting of the HFMD incidence is possible. It is a potential decision supportive tool for controlling HFMD in Wuhan, China.