MRI-Based Random Survival Forest Model Improves the Prediction of Progression-Free Survival to Induction Chemotherapy plus Concurrent Chemoradiotherapy in Locoregionally Advanced Nasopharyngeal Carcinoma

BackgroundThe present study aimed to explore the application value of random survival forest (RSF) model and Cox model in predicting the progression-free survival (PFS) among patients with locoregionally advanced nasopharyngeal carcinoma (LANPC) after induction chemotherapy plus concurrent chemoradiotherapy (IC+CCRT).MethodsEligible LANPC patients underwent magnetic resonance imaging (MRI) scan before treatment were subjected to radiomics feature extraction. Radiomics and clinical features of patients in the training cohort were subjected to RSF analysis to predict PFS and were tested in the testing cohort. The performance of an RSF model with clinical and radiologic predictors was assessed with the area under the receiver operating characteristic (ROC) curve (AUC) and Delong test and compared with Cox models based on clinical and radiologic parameters. Further, the Kaplan-Meier method was used for risk stratification of patients.ResultsA total of 294 LANPC patients (206 in the training cohort; 88 in the testing cohort) were enrolled and underwent magnetic resonance imaging (MRI) scans before treatment. The AUC value of the clinical Cox model, radiomics Cox model, clinical + radiomics Cox model, and clinical + radiomics RSF model in predicting 3- and 5-year PFS for LANPC patients was [0.545 vs 0.648 vs 0.648 vs 0.899 (training cohort), and 0.566 vs 0.736 vs 0.73 vs 0.861 (testing cohort); 0.556 vs 0.604 vs 0.611 vs 0.897 (training cohort), and 0.591 vs 0.661 vs 0.676 vs 0.847 (testing cohort), respectively]. Delong test showed that the RSF model and the other three Cox models were statistically significant, and the RSF model markedly improved prediction performance (P<0.001). Additionally, the PFS of the high-risk group was lower than that of the low-risk group in the RSF model (P<0.001), while comparable in the Cox model (P>0.05).ConclusionThe RSF model may be a potential tool for prognostic prediction and risk stratification of LANPC patients.

Predicting Factors Affecting the First Recurrence of Epithelial Ovarian Cancer Using Random Survival Forest

Predicting survival time has many Effective implications in life quality management for the remainder of the patient's life. Also, survival data are highly variable and make accurate predictions difficult or impossible. Random Survival Forest by repeated tree construction on Bootstrap samples and averaging on the results of these trees reduce the prediction error and cause further generalization of these results. In this retrospective study, the records of 141 patients with epithelial ovarian cancer who were referred to the oncology and radiotherapy ward of Imam Hossein Hospital in Tehran from 2007 to 2018 were used. Random Survival Forest was fitted to the data to investigate the key factors affecting the first recurrence of epithelial ovarian cancer. The mean age of the patients in our study was 52 (23-82) years and the median time to the first recurrence in these was 17 (0.5-127) months, respectively. According to RSF results, using variable importance criterion (VIMP) metastatic tumor with relative importance 2.665 and also using minimal (MD) by depth 2.349, tumor stage with relative importance 1.993 and depth 2.678, and maximum platelet count with relative importance 2.132 and depth 2.683 were the most important variables affecting in the first recurrence of Epithelial Ovarian Cancer. One of the disadvantages of classical methods is the inappropriate fitting of many variables and the need for specific assumptions. More advanced methods such as RSF without the need for any specific assumptions with less prediction error can well explain event variations when exposed to high-dimensional data.

Machine Learning Incorporating Host Factors for Predicting Survival in Head and Neck Squamous Cell Carcinoma Patients

Prognostication for cancer patients is integral for patient counseling and treatment planning, yet providing accurate prediction can be challenging using existing patient-specific clinical indicators and host factors. In this work, we evaluated common machine learning models in predicting head and neck squamous cell carcinoma (HNSCC) patients’ overall survival based on demographic, clinical features and host factors. We found random survival forest had best performance among the models evaluated, which achieved a C-index of 0.729 and AUROC of 0.792 in predicting two-year overall survival. In addition, we verified that host factors are independently predictive of HNSCC overall survival, which improved the C-index by a margin of 0.026 and the AUROC by 0.034. Due to the strong correlation among host factors, we showed that proper dimension reduction is an important step before their incorporation into the machine learning models, which provides a host factor score reflecting the patients’ nutrition and inflammation status. The score by itself showed excellent discriminating capacity with the high-risk group having a hazard ratio of 3.76 (1.93–7.32, p < 0.0001) over the low-risk group. The hazard ratios were further improved to 7.41 (3.66–14.98, p < 0.0001) by the random survival forest model after including demographic and clinical features.

Paediatric/young versus adult patients with long QT syndrome

IntroductionLong QT syndrome (LQTS) is a less prevalent cardiac ion channelopathy than Brugada syndrome in Asia. The present study compared the outcomes between paediatric/young and adult LQTS patients.MethodsThis was a population-based retrospective cohort study of consecutive patients diagnosed with LQTS attending public hospitals in Hong Kong. The primary outcome was spontaneous ventricular tachycardia/ventricular fibrillation (VT/VF).ResultsA total of 142 LQTS (mean onset age=27±23 years old) were included. Arrhythmias other than VT/VF (HR 4.67, 95% CI (1.53 to 14.3), p=0.007), initial VT/VF (HR=3.25 (95% CI 1.29 to 8.16), p=0.012) and Schwartz score (HR=1.90 (95% CI 1.11 to 3.26), p=0.020) were predictive of the primary outcome for the overall cohort, while arrhythmias other than VT/VF (HR=5.41 (95% CI 1.36 to 21.4), p=0.016) and Schwartz score (HR=4.67 (95% CI 1.48 to 14.7), p=0.009) were predictive for the adult subgroup (>25 years old; n=58). A random survival forest model identified initial VT/VF, Schwartz score, initial QTc interval, family history of LQTS, initially asymptomatic and arrhythmias other than VT/VF as the most important variables for risk prediction.ConclusionClinical and ECG presentation varies between the paediatric/young and adult LQTS population. Machine learning models achieved more accurate VT/VF prediction.

A Comparison of Survival Models for Prediction of Eight-year Revision Risk Following Total Knee and Hip Arthroplasty

BackgroundThere is increasing interest in the development and use of clinical prediction models, but a lack of evidence-supported guidance on the merits of different modelling approaches. This is especially true for time-to-event outcomes, where limited studies have compared the vast number of modelling approaches available. This study compares prediction accuracy and variable importance measures for four modelling approaches in prediction of time-to-revision surgery following total knee arthroplasty (TKA) and total hip arthroplasty (THA). Methods The study included 321 945 TKA and 151 113 THA procedures performed between 1 January 2003 and 31 December 2017. Accuracy of the Cox model, Weibull parametric model, flexible parametric model, and random survival forest were compared, with patient age, sex, comorbidities, and prosthesis characteristics considered as predictors. Prediction accuracy was assessed using the Index of Prediction Accuracy (IPA), c-index, and smoothed calibration curves. Variable importance rankings from the Cox model and random survival forest were also compared. ResultsOverall, the Cox and flexible parametric survival models performed best for prediction of both TKA (integrated IPA 0.056 (95% CI [0.054, 0.057]) compared to 0.054 (95% CI [0.053, 0.056]) for the Weibull parametric model), and THA revision. (0.029 95% CI [0.027, 0.030] compared to 0.027 (95% CI [0.025, 0.028]) for the random survival forest). The c-index showed broadly similar discrimination between all modelling approaches. Models were generally well calibrated, but random survival forest underfitted the predicted risk of TKA revision compared to regression approaches. The most important predictors of revision were similar in the Cox model and random survival forest for TKA (age, opioid use, and patella resurfacing) and THA (femoral cement, depression, and opioid use). ConclusionThe Cox and flexible parametric models had superior overall performance, although all approaches performed similarly. Notably, this study showed no benefit of a tuned random survival forest over regression models in this setting.

Development and validation of a risk index to predict kidney graft survival: the kidney transplant risk index

Background Kidney graft failure risk prediction models assist evidence-based medical decision-making in clinical practice. Our objective was to develop and validate statistical and machine learning predictive models to predict death-censored graft failure following deceased donor kidney transplant, using time-to-event (survival) data in a large national dataset from Australia. Methods Data included donor and recipient characteristics (n = 98) of 7,365 deceased donor transplants from January 1st, 2007 to December 31st, 2017 conducted in Australia. Seven variable selection methods were used to identify the most important independent variables included in the model. Predictive models were developed using: survival tree, random survival forest, survival support vector machine and Cox proportional regression. The models were trained using 70% of the data and validated using the rest of the data (30%). The model with best discriminatory power, assessed using concordance index (C-index) was chosen as the best model. Results Two models, developed using cox regression and random survival forest, had the highest C-index (0.67) in discriminating death-censored graft failure. The best fitting Cox model used seven independent variables and showed moderate level of prediction accuracy (calibration). Conclusion This index displays sufficient robustness to be used in pre-transplant decision making and may perform better than currently available tools.

Identification of the Signature Associated With m6A RNA Methylation Regulators and m6A-Related Genes and Construction of the Risk Score for Prognostication in Early-Stage Lung Adenocarcinoma

BackgroundN6-methyladenosine (m6A) RNA modification is vital for cancers because methylation can alter gene expression and even affect some functional modification. Our study aimed to analyze m6A RNA methylation regulators and m6A-related genes to understand the prognosis of early lung adenocarcinoma.MethodsThe relevant datasets were utilized to analyze 21 m6A RNA methylation regulators and 5,486 m6A-related genes in m6Avar. Univariate Cox regression analysis, random survival forest analysis, Kaplan–Meier analysis, Chi-square analysis, and multivariate cox analysis were carried out on the datasets, and a risk prognostic model based on three feature genes was constructed.ResultsRespectively, we treated GSE31210 (n = 226) as the training set, GSE50081 (n = 128) and TCGA data (n = 400) as the test set. By performing univariable cox regression analysis and random survival forest algorithm in the training group, 218 genes were significant and three prognosis-related genes (ZCRB1, ADH1C, and YTHDC2) were screened out, which could divide LUAD patients into low and high-risk group (P &lt; 0.0001). The predictive efficacy of the model was confirmed in the test group GSE50081 (P = 0.0018) and the TCGA datasets (P = 0.014). Multivariable cox manifested that the three-gene signature was an independent risk factor in LUAD. Furthermore, genes in the signature were also externally validated using the online database. Moreover, YTHDC2 was the important gene in the risk score model and played a vital role in readers of m6A methylation.ConclusionThe findings of this study suggested that associated with m6A RNA methylation regulators and m6A-related genes, the three-gene signature was a reliable prognostic indicator for LUAD patients, indicating a clinical application prospect to serve as a potential therapeutic target.