Random Survival Forest Algorithm Research Articles

A novel prognostic signature related to programmed cell death in osteosarcoma.

Osteosarcoma primarily affects children and adolescents, with current clinical treatments often resulting in poor prognosis. There has been growing evidence linking programmed cell death (PCD) to the occurrence and progression of tumors. This study aims to enhance the accuracy of OS prognosis assessment by identifying PCD-related prognostic risk genes, constructing a PCD-based OS prognostic risk model, and characterizing the function of genes within this model. We retrieved osteosarcoma patient samples from TARGET and GEO databases, and manually curated literature to summarize 15 forms of programmed cell death. We collated 1621 PCD genes from literature sources as well as databases such as KEGG and GSEA. To construct our model, we integrated ten machine learning methods including Enet, Ridge, RSF, CoxBoost, plsRcox, survivalSVM, Lasso, SuperPC, StepCox, and GBM. The optimal model was chosen based on the average C-index, and named Osteosarcoma Programmed Cell Death Score (OS-PCDS). To validate the predictive performance of our model across different datasets, we employed three independent GEO validation sets. Moreover, we assessed mRNA and protein expression levels of the genes included in our model, and investigated their impact on proliferation, migration, and apoptosis of osteosarcoma cells by gene knockdown experiments. In our extensive analysis, we identified 30 prognostic risk genes associated with programmed cell death (PCD) in osteosarcoma (OS). To assess the predictive power of these genes, we computed the C-index for various combinations. The model that employed the random survival forest (RSF) algorithm demonstrated superior predictive performance, significantly outperforming traditional approaches. This optimal model included five key genes: MTM1, MLH1, CLTCL1, EDIL3, and SQLE. To validate the relevance of these genes, we analyzed their mRNA and protein expression levels, revealing significant disparities between osteosarcoma cells and normal tissue cells. Specifically, the expression levels of these genes were markedly altered in OS cells, suggesting their critical role in tumor progression. Further functional validation was performed through gene knockdown experiments in U2OS cells. Knockdown of three of these genes-CLTCL1, EDIL3, and SQLE-resulted in substantial changes in proliferation rate, migration capacity, and apoptosis rate of osteosarcoma cells. These findings underscore the pivotal roles of these genes in the pathophysiology of osteosarcoma and highlight their potential as therapeutic targets. The five genes constituting the OS-PCDS model-CLTCL1, MTM1, MLH1, EDIL3, and SQLE-were found to significantly impact the proliferation, migration, and apoptosis of osteosarcoma cells, highlighting their potential as key prognostic markers and therapeutic targets. OS-PCDS enables accurate evaluation of the prognosis in patients with osteosarcoma.

Mitochondrial RNA modification-based signature to predict prognosis of lower grade glioma: a multi-omics exploration and verification study

Mitochondrial RNA modification (MRM) plays a crucial role in regulating the expression of key mitochondrial genes and promoting tumor metastasis. Despite its significance, comprehensive studies on MRM in lower grade gliomas (LGGs) remain unknown. Single-cell RNA-seq data (GSE89567) was used to evaluate the distribution functional status, and correlation of MRM-related genes in different cell types of LGG microenvironment. We developed an MRM scoring system by selecting potential MRM-related genes using LASSO regression analysis and the Random Survival Forest algorithm, based on multiple bulk RNA-seq datasets from TCGA, CGGA, GSE16011, and E-MTAB-3892. Analysis was performed on prognostic and immunological features, signaling pathways, metabolism, somatic mutations and copy number variations (CNVs), treatment responses, and forecasting of potential small-molecule agents. A total of 35 MRM-related genes were selected from the literature. Differential expression analysis of 1120 normal brain tissues and 529 LGGs revealed that 22 and 10 genes were upregulated and downregulated, respectively. Most genes were associated with prognosis of LGG. METLL8, METLL2A, TRMT112, and METTL2B were extensively expressed in all cell types and different cell cycle of each cell type. Almost all cell types had clusters related to mitochondrial RNA processing, ribosome biogenesis, or oxidative phosphorylation. Cell–cell communication and Pearson correlation analyses indicated that MRM may promoting the development of microenvironment beneficial to malignant progression via modulating NCMA signaling pathway and ICP expression. A total of 11 and 9 MRM-related genes were observed by LASSO and the RSF algorithm, respectively, and finally 6 MRM-related genes were used to establish MRM scoring system (TRMT2B, TRMT11, METTL6, METTL8, TRMT6, and TRUB2). The six MRM-related genes were then validated by qPCR in glioma and normal tissues. MRM score can predict the malignant clinical characteristics, abundance of immune infiltration, gene variation, clinical outcome, the enrichment of signaling pathways and metabolism. In vitro experiments demonstrated that silencing METTL8 significantly curbs glioma cell proliferation and enhances apoptosis. Patients with a high MRM score showed a better response to immunotherapies and small-molecule agents such as arachidonyl trifluoromethyl ketone, MS.275, AH.6809, tacrolimus, and TTNPB. These novel insights into the biological impacts of MRM within the glioma microenvironment underscore its potential as a target for developing precise therapies, including immunotherapeutic approaches.

Mortality prediction and influencing factors for intensive care unit patients with acute tubular necrosis: random survival forest and cox regression analysis

Background: Patients with acute tubular necrosis (ATN) not only have severe renal failure, but also have many comorbidities, which can be life-threatening and require timely treatment. Identifying the influencing factors of ATN and taking appropriate interventions can effectively shorten the duration of the disease to reduce mortality and improve patient prognosis.Methods: Mortality prediction models were constructed by using the random survival forest (RSF) algorithm and the Cox regression. Next, the performance of both models was assessed by the out-of-bag (OOB) error rate, the integrated brier score, the prediction error curve, and area under the curve (AUC) at 30, 60 and 90 days. Finally, the optimal prediction model was selected and the decision curve analysis and nomogram were established.Results: RSF model was constructed under the optimal combination of parameters (mtry = 10, nodesize = 88). Vasopressors, international normalized ratio (INR)_min, chloride_max, base excess_min, bicarbonate_max, anion gap_min, and metastatic solid tumor were identified as risk factors that had strong influence on mortality in ATN patients. Uni-variate and multivariate regression analyses were used to establish the Cox regression model. Nor-epinephrine, vasopressors, INR_min, severe liver disease, and metastatic solid tumor were identified as important risk factors. The discrimination and calibration ability of both predictive models were demonstrated by the OOB error rate and the integrated brier score. However, the prediction error curve of Cox regression model was consistently lower than that of RSF model, indicating that Cox regression model was more stable and reliable. Then, Cox regression model was also more accurate in predicting mortality of ATN patients based on the AUC at different time points (30, 60 and 90 days). The analysis of decision curve analysis shows that the net benefit range of Cox regression model at different time points is large, indicating that the model has good clinical effectiveness. Finally, a nomogram predicting the risk of death was created based on Cox model.Conclusion: The Cox regression model is superior to the RSF algorithm model in predicting mortality of patients with ATN. Moreover, the model has certain clinical utility, which can provide clinicians with some reference basis in the treatment of ATN and contribute to improve patient prognosis.

Long-Term Mortality Predictors Using a Machine-Learning Approach in Patients With Chronic Limb-Threatening Ischemia After Peripheral Vascular Intervention.

Patients with chronic limb-threatening ischemia (CLTI) face a high long-term mortality risk. Identifying novel mortality predictors and risk profiles would enable individual health care plan design and improved survival. We aimed to leverage a random survival forest machine-learning algorithm to identify long-term all-cause mortality predictors in patients with CLTI undergoing peripheral vascular intervention. Patients with CLTI undergoing peripheral vascular intervention from 2017 to 2018 were derived from the Medicare-linked VQI (Vascular Quality Initiative) registry. We constructed a random survival forest to rank 66 preprocedural variables according to their relative importance and mean minimal depth for 3-year all-cause mortality. A random survival forest of 2000 trees was built using a training sample (80% of the cohort). Accuracy was assessed in a testing sample (20%) using continuous ranked probability score, Harrell C-index, and out-of-bag error rate. A total of 10 114 patients were included (mean±SD age, 72.0±11.0 years; 59% men). The 3-year mortality rate was 39.1%, with a median survival of 1.4 years (interquartile range, 0.7-2.0 years). The most predictive variables were chronic kidney disease, age, congestive heart failure, dementia, arrhythmias, requiring assisted care, living at home, and body mass index. A total of 41 variables spanning all domains of the biopsychosocial model were ranked as mortality predictors. The accuracy of the model was excellent (continuous ranked probability score, 0.172; Harrell C-index, 0.70; out-of-bag error rate, 29.7%). Our random survival forest accurately predicts long-term CLTI mortality, which is driven by demographic, functional, behavioral, and medical comorbidities. Broadening frameworks of risk and refining health care plans to include multidimensional risk factors could improve individualized care for CLTI.

Abstract PO2-01-14: Development of Artificial Intelligence-based Machine Learning Models for Predicting Survival In Hormone-Receptor-Positive/HER2-Negative Early Breast Cancer undergoing Neoadjuvant Chemotherapy

Abstract Background. In hormone-receptor positive (HoR)/HER2 negative early breast cancer (BC) multiple efforts have been made to predict disease recurrence and survival. Machine learning techniques have been used but few studies have looked into their applicability in predicting survival on the basis of clinico-pathological characteristics. The aim of this study was to evaluate a random survival forest model to predict the prognosis of this specific BC subtype. Methods. In this multicenter, retrospective study, patients who fulfilled the following inclusion criteria were included: (1) diagnosis of pathologically confirmed HoR-positive/HER2-negative invasive BC; (2) early or locally advanced, stage I-II-III (3) patients receiving neoadjuvant anthracycline and/or taxane-based chemotherapy, concurrently or sequentially; (4) patients undergoing surgery for primary BC. Survival endpoints were disease-free survival (DFS) and overall survival (OS). A random survival forest algorithm was used to develop the predictive model. Ten-fold cross-validation was performed. The C-index and the continuous rank probability score (CRPS) were used to evaluate the discrimination of the predictive model, and a ROC curve was used to evaluate model precision. A cut point analysis based on maximally selected rank statistics was conducted to evaluate the best cut-off in the out-of-bag (OOB) mortality that could maximize DFS and OS prediction. Variable importance was assessed using Breiman-Cutler permutation importance. Results. Overall, 572 patients with HoR-positive/HER2-negative early BC were included. At univariate analysis age, T stage, N stage, grading, ER, PR and Ki67 were found to be significantly associated with DFS and ER, PgR, HER2, pCR ypT and ypN retained statistical significance at multivariate analysis. ER, pCR, pathological T and N stage were found to be significantly associated with OS at univariate and multivariate analysis. The following variables were included in the final model: menopausal status, age, histology, grade, clinical T/N, ER/PgR, Ki67 and HER2, pathological complete response (pCR), ypT and ypN. For DFS, the cross-validated C-index was 0.68 (95% CI 0.63-0.73) and the OOB CRPS was 0.15, with a OOB performance error of 0.31. The AUC calculated at 60 months was 0.91 (95% CI 0.88-0.94). Out-of bag RSF-based risk scores for individual patients were calculated and an optimal cut-off of 22.58 was identified. The HR between high risk and low risk group was 3.08 (95% CI 2.16-4.39, p< 0.001). For OS, the cross-validated C-index was 0.66 (95% CI 0.60-0.71) and the OOB CRPS was 0.17, with a OOB performance error of 0.35. The AUC calculated at 60 months 0.91 (95% CI 0.88-0.95). An optimal cut-off of 21.54 was identified and the HR between low risk and high risk group was 2.50 (95% CI 1.73-3.61, p< 0.001). For DFS, the most important variables were cN (9.00), ypN (7.35), ER (7.21), ypT (5.38), PgR (4.11), pCR (4.01) and age (2.82) while for OS the most important variables were cN (7.88), ER (5.37), PgR (3.61), age (3.37), pCR (2.80), ypT (2.64) and ypN (2.60). Discussion. We analyzed the performance of RSF in the prediction of DFS and OS based on the contribution of clinico-pathological features commonly available at the baseline of the NCT and post-surgery. By selecting patients with HoR-positive HER2-negative disease, we were able to show which clinico-pathological features within a ML model have greater predictive importance. The model could be integrated with image-based tumor and radiology features to improve its predictive accuracy. This retrospective multicenter study suggests that the combination of easily accessible clinico-pathological features within a ML model may reliably predict DFS and OS in the context of HoR-positive/HER2-negative BCs. Citation Format: Luca Mastrantoni, Giovanna Garufi, Noemi Maliziola, Elena Di Monte, Giorgia Arcuri, Valentina Frescura, Angelachiara Rotondi, Giulia Giordano, Luisa Carbognin, Alessandra Fabi, Ida Paris, Gianluca Franceschini, Armando Orlandi, Antonella Palazzo, Giovanni Scambia, Giampaolo Tortora, Emilio Bria. Development of Artificial Intelligence-based Machine Learning Models for Predicting Survival In Hormone-Receptor-Positive/HER2-Negative Early Breast Cancer undergoing Neoadjuvant Chemotherapy [abstract]. In: Proceedings of the 2023 San Antonio Breast Cancer Symposium; 2023 Dec 5-9; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2024;84(9 Suppl):Abstract nr PO2-01-14.

Triglyceride-inflammation score established on account of random survival forest for predicting survival in patients with nasopharyngeal carcinoma: a retrospective study.

This study aimed to establish an effective prognostic model based on triglyceride and inflammatory markers, including neutrophil-to-lymphocyte ratio (NLR), lymphocyte-to-monocyte ratio (LMR), and platelet-to-lymphocyte ratio (PLR), to predict overall survival (OS) in patients with nasopharyngeal carcinoma (NPC). Additionally, we aimed to explore the interaction and mediation between these biomarkers in their association with OS. A retrospective review was conducted on 259 NPC patients who had blood lipid markers, including triglyceride and total cholesterol, as well as parameters of peripheral blood cells measured before treatment. These patients were followed up for over 5 years, and randomly divided into a training set (n=155) and a validation set (n=104). The triglyceride-inflammation (TI) score was developed using the random survival forest (RSF) algorithm. Subsequently, a nomogram was created. The performance of the prognostic model was measured by the concordance index (C-index), time-dependent receiver operating characteristic (ROC) curve, and decision curve analysis (DCA). The interaction and mediation between the biomarkers were further analyzed. Bioinformatics analysis based on the GEO dataset was used to investigate the association between triglyceride metabolism and immune cell infiltration. The C-index of the TI score was 0.806 in the training set, 0.759 in the validation set, and 0.808 in the entire set. The area under the curve of time-dependent ROC of TI score in predicting survival at 1, 3, and 5 years were 0.741, 0.847, and 0.871 respectively in the training set, and 0.811, 0.837, and 0.758 in the validation set, then 0.771, 0.848, and 0.862 in the entire set, suggesting that TI score had excellent performance in predicting OS in NPC patients. Patients with stage T1-T2 or M0 had significantly lower TI scores, NLR, and PLR, and higher LMR compared to those with stage T3-T3 or M1, respectively. The nomogram, which integrated age, sex, clinical stage, and TI score, demonstrated good clinical usefulness and predictive ability, as evaluated by the DCA. Significant interactions were found between triglyceride and NLR and platelet, but triglyceride did not exhibit any medicating effects in the inflammatory markers. Additionally, NPC tissues with active triglyceride synthesis exhibited high immune cell infiltration. The TI score based on RSF represents a potential prognostic factor for NPC patients, offering convenience and economic advantages. The interaction between triglyceride and NLR may be attributed to the effect of triglyceride metabolism on immune response.

A prediction model based on random survival forest analysis of the overall survival of elderly female papillary thyroid carcinoma patients: a SEER-based study.

Papillary thyroid carcinoma (PTC) is a common malignancy whose incidence is three times greater in females than in males. The prognosis of ageing patients is poor. This research was designed to construct models to predict the overall survival of elderly female patients with PTC. We developed prediction models based on the random survival forest (RSF) algorithm and traditional Cox regression. The data of 4539 patients were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Twelve variables were analysed to establish the models. The C-index and the Brier score were selected to evaluate the discriminatory ability of the models. Time-dependent receiver operating characteristic (ROC) curves were also drawn to evaluate the accuracy of the models. The clinical benefits of the two models were compared on the basis of the DCA curve. In addition, the Shapley Additive Explanations (SHAP) plot was used to visualize the contribution of the variables in the RSF model. The C-index of the RSF model was 0.811, which was greater than that of the Cox model (0.781). According to the Brier score and the area under the ROC curve (AUC), the RSF model performed better than the Cox model. On the basis of the DCA curve, the RSF model demonstrated fair clinical benefit. The SHAP plot showed that age was the most important variable contributing to the outcome of PTC in elderly female patients. The RSF model we developed performed better than the Cox model and might be valuable for clinical practice.

Development and validation of a prospective study to predict the risk of readmission within 365 days of respiratory failure: based on a random survival forest algorithm combined with COX regression modeling

BackgroundThere is a need to develop and validate a widely applicable nomogram for predicting readmission of respiratory failure patients within 365 days.MethodsWe recruited patients with respiratory failure at the First People’s Hospital of Yancheng and the People’s Hospital of Jiangsu. We used the least absolute shrinkage and selection operator regression to select significant features for multivariate Cox proportional hazard analysis. The Random Survival Forest algorithm was employed to construct a model for the variables that obtained a coefficient of 0 following LASSO regression, and subsequently determine the prediction score. Independent risk factors and the score were used to develop a multivariate COX regression for creating the line graph. We used the Harrell concordance index to quantify the predictive accuracy and the receiver operating characteristic curve to evaluate model performance. Additionally, we used decision curve analysiso assess clinical usefulness.ResultsThe LASSO regression and multivariate Cox regression were used to screen hemoglobin, diabetes and pneumonia as risk variables combined with Score to develop a column chart model. The C index is 0.927 in the development queue, 0.924 in the internal validation queue, and 0.922 in the external validation queue. At the same time, the predictive model also showed excellent calibration and higher clinical value.ConclusionsA nomogram predicting readmission of patients with respiratory failure within 365 days based on three independent risk factors and a jointly developed random survival forest algorithm has been developed and validated. This improves the accuracy of predicting patient readmission and provides practical information for individualized treatment decisions.

Machine learning-based clinical decision support system for treatment recommendation and overall survival prediction of hepatocellular carcinoma: a multi-center study

The treatment decisions for patients with hepatocellular carcinoma are determined by a wide range of factors, and there is a significant difference between the recommendations of widely used staging systems and the actual initial treatment choices. Herein, we propose a machine learning-based clinical decision support system suitable for use in multi-center settings. We collected data from nine institutions in South Korea for training and validation datasets. The internal and external datasets included 935 and 1750 patients, respectively. We developed a model with 20 clinical variables consisting of two stages: the first stage which recommends initial treatment using an ensemble voting machine, and the second stage, which predicts post-treatment survival using a random survival forest algorithm. We derived the first and second treatment options from the results with the highest and the second-highest probabilities given by the ensemble model and predicted their post-treatment survival. When only the first treatment option was accepted, the mean accuracy of treatment recommendation in the internal and external datasets was 67.27% and 55.34%, respectively. The accuracy increased to 87.27% and 86.06%, respectively, when the second option was included as the correct answer. Harrell’s C index, integrated time-dependent AUC curve, and integrated Brier score of survival prediction in the internal and external datasets were 0.8381 and 0.7767, 91.89 and 86.48, 0.12, and 0.14, respectively. The proposed system can assist physicians by providing data-driven predictions for reference from other larger institutions or other physicians within the same institution when making treatment decisions.

Clinical and therapeutical significances of the cluster and signature based on oxidative stress for osteosarcoma.

It is of great clinical significance to find out the ideal tumor biomarkers and therapeutic targets to improve the prognosis of patients with osteosarcoma (OS). Oxidative stress (OXS) can directly target intracellular macromolecules and exhibit dual effects of tumor promotion and suppression. OXS-related genes (OXRGs) were extracted from public databases, including TARGET and GEO. Univariate Cox regression analysis, Random Survival Forest algorithm, and LASSO regression were performed to identify prognostic genes and establish the OXS-signature. The efficacy of the OXS-signature was further evaluated by Kaplan-Meier curves and timeROC package. Evaluation of immunological characteristics was achieved based on ESTIMATE algorithm and ssGSEA. Submap algorithm was used to explore the response to anti-PD1 and anti-CTLA4 therapy for OS. Drug response prediction was conducted by using pRRophetic package. The expression values of related genes in the OXS-signature were detected with PCR assays. Two OXS-clusters were identified for OS, with remarkable differences of clusters presented in prognosis. Kyoto Encyclopedia of Genes Genomes (KEGG) analysis showed that differentially expressed genes (DEGs) between the OXS-clusters were significantly enriched in several immune-related pathways. Patients with lower OS-scores attained better clinical outcomes, and presented more sensitivity to ICB therapy. By contrast, OS patients with higher OS-scores revealed more sensitivity to certain drugs. Furthermore, critical genes, RHBDL2 and CGREF1 from the model, were significantly higher expressed in OS cell lines. Our study identified the clusters and signature based on OXS, which would lay the foundation for molecular experimental research, disease prevention and treatment of OS.

Beyond MIPI: Harnessing Machine Learning and Histological Subtype for Enhanced MCL Prognostication of Survival

Introduction Mantle cell lymphoma (MCL) presents challenges due to its aggressive nature and dismal treatment outcomes. The Mantle Cell Lymphoma International Prognostic Index (MIPI) score is valuable for risk stratification, but it may not fully capture the complexity of MCL biology. To address this, we explored innovative data-driven methods based on machine learning to augment the MIPI score. By integrating clinical and histological data with advanced algorithms, this study aimed to enhance risk assessment in MCL. Improved prognostication of survival could facilitate the design of risk-tailored therapeutic approaches, directing more aggressive treatments to high-risk patients, ultimately leading to personalized and precise management. Methods The following patient-level variables were retrieved: age, gender, Ann-Arbor stage (I-II vs III-IV), Bulky disease, extranodal disease, histopathological variant (classic vs pleomorphic/blastoid lymphoma), and Ki67+ cells. The MIPI score was used to categorize patients into low, intermediate, and high-risk groups. Employing random survival forests, we developed a novel risk score by integrating clinical and histological data. Missing variables were imputed using a random forests algorithm. Harrel's concordance indexes (c-indexes) were used to evaluate model's accuracy. Results We assembled a real-world database of 231 MCL patients from 6 Spanish tertiary hospitals (Jan 2000-Dec 2021), and another cohort for validation from another Spanish tertiary hospital (N=44). Median age at diagnosis was 64 years in both cohorts. Median follow-up was 6.28 y and 8.67 y in the training and test sets, and median overall survival (OS) was 11.48 y and 5.61 y. According to the MIPI score, 44% and 38% of patients were of high risk in the training and validation sets; 26% and 39% were of intermediate risk, and 30% & 23% were of low risk. The c-index of the MIPI groups for the prediction of OS was 0.716 and 0.684 in the training and validation sets, respectively. Then, a random survival forest algorithm was used to derive a new risk score in the training set. The first model contained all the available variables mentioned previously. This 8-variable model achieved a cross-validated c-index of 0.764 in the training set. A variable reduction technique was implemented to remove those variables that provided less independent prognostic value. A simplified model was developed, which contained the following variables by order of importance: histological subtype, MIPI-derived groups, age at diagnosis and Ann-Arbor stage. This model outperformed the conventional MIPI grouping strategy, achieving c-indexes of 0.764 and 0.775 in the training and validation sets, respectively ( Figure 1). Conclusion This study showcases the potential of a novel machine learning model in MCL prognostication beyond the traditional MIPI score, utilizing easily accessible clinical information. The inclusion of histological subtype, MIPI score, age at diagnosis, and Ann-Arbor stage as robust independent prognostic factors improves risk prediction accuracy. Future research may further refine the model and explore additional variables to continue optimizing prognostication and treatment strategies for MCL patients.

Machine Learning Techniques for Analyzing Survival Data of Breast Cancer Patients in Baghdad

The Machine learning methods, which are one of the most important branches of promising artificial intelligence, have great importance in all sciences such as engineering, medical, and also recently involved widely in statistical sciences and its various branches, including analysis of survival, as it can be considered a new branch used to estimate the survival and was parallel with parametric, nonparametric and semi-parametric methods that are widely used to estimate survival in statistical research. In this paper, the estimate of survival based on medical images of patients with breast cancer who receive their treatment in Iraqi hospitals was discussed. Three algorithms for feature extraction were explained: The first principal component algorithm, The second kernel principal component algorithm, and The last is the faster ICA algorithm. Then the important features extracted in the three algorithms for features extraction will be entered into machine learning algorithms: The first K nearest neighbor algorithm, The second survival tree algorithm (or regression tree), and the last random survival forests algorithm.
 Two criteria for comparing the best models to estimate survival have relied on the MSE and the C-Index. The best model for estimating and predicting survival is the use of the fastest ICA algorithm with the random survival forest algorithm that gave the lowest amount to MSE and the highest value to the C-Index. Accordingly, we recommend doctors and medical professionals in Iraq adopt this model to estimate survival for patients with breast cancer.

Development and validation of a machine learning model to predict imminent new vertebral fractures after vertebral augmentation

BackgroundAccurately predicting the occurrence of imminent new vertebral fractures (NVFs) in patients with osteoporotic vertebral compression fractures (OVCFs) undergoing vertebral augmentation (VA) is challenging with yet no effective approach. This study aim to examine a machine learning model based on radiomics signature and clinical factors in predicting imminent new vertebral fractures after vertebral augmentation.MethodsA total of 235 eligible patients with OVCFs who underwent VA procedures were recruited from two independent institutions and categorized into three groups, including training set (n = 138), internal validation set (n = 59), and external validation set (n = 38). In the training set, radiomics features were computationally retrieved from L1 or adjacent vertebral body (T12 or L2) on T1-w MRI images, and a radiomics signature was constructed using the least absolute shrinkage and selection operator algorithm (LASSO). Predictive radiomics signature and clinical factors were fitted into two final prediction models using the random survival forest (RSF) algorithm or COX proportional hazard (CPH) analysis. Independent internal and external validation sets were used to validate the prediction models.ResultsThe two prediction models were integrated with radiomics signature and intravertebral cleft (IVC). The RSF model with C-indices of 0.763, 0.773, and 0.731 and time-dependent AUC (2 years) of 0.855, 0.907, and 0.839 (p < 0.001 for all) was found to be better predictive than the CPH model in training, internal and external validation sets. The RSF model provided better calibration, larger net benefits (determined by decision curve analysis), and lower prediction error (time-dependent brier score of 0.156, 0.151, and 0.146, respectively) than the CPH model.ConclusionsThe integrated RSF model showed the potential to predict imminent NVFs following vertebral augmentation, which will aid in postoperative follow-up and treatment.

Study on the prediction model of atherosclerotic cardiovascular disease in the rural Xinjiang population based on survival analysis

PurposeWith the increase in aging and cardiovascular risk factors, the morbidity and mortality of atherosclerotic cardiovascular disease (ASCVD), represented by ischemic heart disease and stroke, continue to rise in China. For better prevention and intervention, relevant guidelines recommend using predictive models for early detection of ASCVD high-risk groups. Therefore, this study aims to establish a population ASCVD prediction model in rural areas of Xinjiang using survival analysis.MethodsBaseline cohort data were collected from September to December 2016 and followed up till June 2022. A total of 7975 residents (4054 males and 3920 females) aged 30–74 years were included in the analysis. The data set was divided according to different genders, and the training and test sets ratio was 7:3 for different genders. A Cox regression, Lasso-Cox regression, and random survival forest (RSF) model were established in the training set. The model parameters were determined by cross-validation and parameter tuning and then verified in the training set. Traditional ASCVD prediction models (Framingham and China-PAR models) were constructed in the test set. Different models' discrimination and calibration degrees were compared to find the optimal prediction model for this population according to different genders and further analyze the risk factors of ASCVD.ResultsAfter 5.79 years of follow-up, 873 ASCVD events with a cumulative incidence of 10.19% were found (7.57% in men and 14.44% in women). By comparing the discrimination and calibration degrees of each model, the RSF showed the best prediction performance in males and females (male: Area Under Curve (AUC) 0.791 (95%CI 0.767,0.813), C statistic 0.780 (95%CI 0.730,0.829), Brier Score (BS):0.060, female: AUC 0.759 (95%CI 0.734,0.783) C statistic was 0.737 (95%CI 0.702,0.771), BS:0.110). Age, systolic blood pressure (SBP), apolipoprotein B (APOB), Visceral Adiposity Index (VAI), hip circumference (HC), and plasma arteriosclerosis index (AIP) are important predictors of ASCVD in the rural population of Xinjiang.ConclusionThe performance of the ASCVD prediction model based on the RSF algorithm is better than that based on Cox regression, Lasso-Cox, and the traditional ASCVD prediction model in the rural population of Xinjiang.

Application of machine learning algorithms in electronic medical records to predict amputation-free survival after first revascularization in patients with peripheral artery disease

BackgroundThis study aimed to apply eight machine learning algorithms to develop the optimal model to predict amputation-free survival (AFS) after first revascularization in patients with peripheral artery disease (PAD). MethodsAmong 2130 patients from 2011 to 2020, 1260 patients who underwent revascularization were randomly assigned to training set and validation set in an 8:2 ratio. 67 clinical parameters were analyzed by lasso regression analysis. Logistic regression, gradient boosting machine, random forest, decision tree, eXtreme gradient boosting, neural network, Cox regression, and random survival forest (RSF) were applied to develop prediction models. The optimal model was compared with GermanVasc score in testing set comprising patients from 2010. ResultsThe postoperative 1/3/5-year AFS were 90%, 79.4%, and 74.1%. Age (HR:1.035, 95%CI: 1.015–1.056), atrial fibrillation (HR:2.257, 95%CI: 1.193–4.271), cardiac ejection fraction (HR:0.064, 95%CI: 0.009–0.413), Rutherford grade ≥ 5 (HR:1.899, 95%CI: 1.296–2.782), creatinine (HR:1.03, 95%CI: 1.02–1.04), surgery duration (HR:1.03, 95%CI: 1.01–1.05), and fibrinogen (HR:1.292, 95%CI: 1.098–1.521) were independent risk factors. The optimal model was developed by RSF algorithm, with 1/3/5-year AUCs in training set of 0.866 (95% CI:0.819–0.912), 0.854 (95% CI:0.811–0.896), 0.844 (95% CI:0.793–0.894), in validation set of 0.741 (95% CI:0.580–0.902), 0.768 (95% CI:0.654–0.882), 0.836 (95% CI:0.719–0.953), and in testing set of 0.821 (95%CI: 0.711–0.931), 0.802 (95%CI: 0.684–0.919), 0.798 (95%CI: 0.657–0.939). The c-index of the model outperformed GermanVasc Score (0.788 vs 0.730). A dynamic nomogram was published on shinyapp (https://wyy2023.shinyapps.io/amputation/). ConclusionThe optimal prediction model for AFS after first revascularization in patients with PAD was developed by RSF algorithm, which exhibited outstanding prediction performance.

Integrated multiomics analyses unveil the implication of a costimulatory molecule score on tumor aggressiveness and immune evasion in breast cancer: A large-scale study through over 8,000 patients

BackgroundAlthough immunotherapy has revolutionised cancer management, reliable genomic biomarkers for identifying eligible patient subpopulations are lacking. Costimulatory molecules play a crucial role in mounting anti-tumour responses, and clinical trials targeting these novel biomarkers are underway. However, whether these molecules can determine tumour aggressiveness and the risk of tumour evasion in breast cancer (BC) remains largely unknown. MethodsThe whole-tissue transcriptomic data of 8236 patients with BC from 15 independent cohorts were extracted. An integrated scoring system named ‘costimulatory molecule score’ (CMS) was constructed and sufficient validated using least absolute shrinkage and selection operator regression (1000 iterations) and the random survival forest algorithm (1000 trees). The correlation among CMSs, cancer genotypes and clinicopathological characteristics was examined. Extensive multiomics and immunogenomic analyses were performed to investigate and verify the association among CMSs, enriched pathways, potential intrinsic and extrinsic immune escape mechanisms, immunotherapy response and therapeutic options. ResultsThe predictive role of CMS model that relies on expression pattern of merely 5 costimulatory genes for prognosis is almost universally applicable to BC patients in a platform-independent manner. Through internal and external in silico validation, high CMS was characterized by favorable genotypes but decreased tumor immunogenicity, activation of stroma, immune-suppressive states and potential immunotherapeutic resistance. Similar results were observed in a real-world immunotherapy cohort and Pan-Cancer analysis. ConclusionThis comprehensive characterization indicates CMS model may be complemented for predicting tumor aggressiveness and immune evasion in BC patients, underlining the future clinical potential for further exploration of resistance mechanisms and optimization of immunotherapeutic strategies.

Abstract 5577: Detection of RAS mutations in colorectal cancer patients using DNA from extracellular vesicles

Abstract Introduction: Precision medicine is becoming increasingly important in cancer treatment, and liquid biopsy (LB) is a core technique. Circulating tumor DNA (ctDNA) is the main target for LB; however, in some patients, its sensitivity is inadequate. Detection of post-operative ctDNA, called Minimal Residual Disease (MRD), indicates cancer recurrence; however, some patients experience recurrent disease without being MRD-positive. To improve sensitivity of ctDNA detection, we focused on exosomes, small vesicles of endosomal origin that contain DNA (exoDNA) derived from cells, including cancer cells. In this study, we assayed KRAS mutations in patients with colorectal cancer using exoDNA, and analyzed the utility of biomarkers in prognosis, using a machine learning algorithm. Materials and Methods: Patients who underwent curative surgery for colorectal cancer from November 2018 to December 2020 were recruited prospectively. Blood samples were obtained before surgery, and ctDNA was extracted from 1 mL of plasma. Exosomes were isolated from this plasma, followed by exoDNA extraction. KRAS mutations in ctDNA and exoDNA were analyzed using droplet digital PCR. The Random Survival Forest (RSF) algorithm was used for variable importance analysis. Results: 300 patients (123 with KRAS mutation and 177 without) were included. The median patient age was 71 years (range: 35 - 91). Concentrations of exoDNA were significantly higher in Stage IV patients compared to patients at other stages (p &amp;lt; 0.01). Numbers of exosomes did not differ by stage. KRAS mutations were detected in exoDNA of 56 patients (45.5%) and in ctDNA of 28 patients with KRAS mutation in their tumors (22.7%, p&amp;lt;0.001). Sensitivity of exoDNA was higher than that of ctDNA in Stage II/III patients with KRAS mutations (Stage II; 33.3% vs 14.2%, p=0.02, Stage III 46.7% vs 13.3%, p=0.001). However, sensitivity of cfDNA was almost equal to that of exoDNA in stage IV patients (53.8% vs 50.0%, p = 0.78). Surprisingly, in patients without KRAS mutations in their tumors, KRAS mutations were detected in exoDNA of 24 patients (13.5%) and in ctDNA of one patient (0.5%). Of 103 stage III patients, 31 (30.1%) experienced recurrence. The RSF algorithm showed that the exoDNA concentration is the most important risk factor for recurrence, followed by a lack of adjuvant chemotherapy. Conclusion: Sensitivity of KRAS mutation detection using exoDNA is excellent. Additionally, the concentration of exoDNA appears to be a superior predictor for recurrence of Stage II/III colorectal cancer after curative surgery. Citation Format: Sho Kuriyama, Takeshi Yamada, Hiromichi Sonoda, Seiichi Shinji, Akihisa Matsuda, Kazuhide Yonaga, Takuma Iwai, Kohki Takeda, Koji Ueda, Toshimitsu Miyasaka, Shintaro Kanaka, Hiroshi Yoshida. Detection of RAS mutations in colorectal cancer patients using DNA from extracellular vesicles. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 5577.

Development and validation of machine learning models for predicting prognosis and guiding individualized postoperative chemotherapy: A real-world study of distal cholangiocarcinoma.

Distal cholangiocarcinoma (dCCA), originating from the common bile duct, is greatly associated with a dismal prognosis. A series of different studies based on cancer classification have been developed, aimed to optimize therapy and predict and improve prognosis. In this study, we explored and compared several novel machine learning models that might lead to an improvement in prediction accuracy and treatment options for patients with dCCA. In this study, 169 patients with dCCA were recruited and randomly divided into the training cohort (n = 118) and the validation cohort (n = 51), and their medical records were reviewed, including survival outcomes, laboratory values, treatment strategies, pathological results, and demographic information. Variables identified as independently associated with the primary outcome by least absolute shrinkage and selection operator (LASSO) regression, the random survival forest (RSF) algorithm, and univariate and multivariate Cox regression analyses were introduced to establish the following different machine learning models and canonical regression model: support vector machine (SVM), SurvivalTree, Coxboost, RSF, DeepSurv, and Cox proportional hazards (CoxPH). We measured and compared the performance of models using the receiver operating characteristic (ROC) curve, integrated Brier score (IBS), and concordance index (C-index) following cross-validation. The machine learning model with the best performance was screened out and compared with the TNM Classification using ROC, IBS, and C-index. Finally, patients were stratified based on the model with the best performance to assess whether they benefited from postoperative chemotherapy through the log-rank test. Among medical features, five variables, including tumor differentiation, T-stage, lymph node metastasis (LNM), albumin-to-fibrinogen ratio (AFR), and carbohydrate antigen 19-9 (CA19-9), were used to develop machine learning models. In the training cohort and the validation cohort, C-index achieved 0.763 vs. 0.686 (SVM), 0.749 vs. 0.692 (SurvivalTree), 0.747 vs. 0.690 (Coxboost), 0.745 vs. 0.690 (RSF), 0.746 vs. 0.711 (DeepSurv), and 0.724 vs. 0.701 (CoxPH), respectively. The DeepSurv model (0.823 vs. 0.754) had the highest mean area under the ROC curve (AUC) than other models, including SVM (0.819 vs. 0.736), SurvivalTree (0.814 vs. 0.737), Coxboost (0.816 vs. 0.734), RSF (0.813 vs. 0.730), and CoxPH (0.788 vs. 0.753). The IBS of the DeepSurv model (0.132 vs. 0.147) was lower than that of SurvivalTree (0.135 vs. 0.236), Coxboost (0.141 vs. 0.207), RSF (0.140 vs. 0.225), and CoxPH (0.145 vs. 0.196). Results of the calibration chart and decision curve analysis (DCA) also demonstrated that DeepSurv had a satisfactory predictive performance. In addition, the performance of the DeepSurv model was better than that of the TNM Classification in C-index, mean AUC, and IBS (0.746 vs. 0.598, 0.823 vs. 0.613, and 0.132 vs. 0.186, respectively) in the training cohort. Patients were stratified and divided into high- and low-risk groups based on the DeepSurv model. In the training cohort, patients in the high-risk group would not benefit from postoperative chemotherapy (p = 0.519). In the low-risk group, patients receiving postoperative chemotherapy might have a better prognosis (p = 0.035). In this study, the DeepSurv model was good at predicting prognosis and risk stratification to guide treatment options. AFR level might be a potential prognostic factor for dCCA. For the low-risk group in the DeepSurv model, patients might benefit from postoperative chemotherapy.

Prognostic impact of examined lymph-node count for patients with esophageal cancer: development and validation prediction model

Esophageal cancer (EC) is a malignant tumor with high mortality. We aimed to find the optimal examined lymph node (ELN) count threshold and develop a model to predict survival of patients after radical esophagectomy. Two cohorts were analyzed: the training cohort which included 734 EC patients from the Chinese registry and the external testing cohort which included 3208 EC patients from the Surveillance, Epidemiology, and End Results (SEER) registry. Cox proportional hazards regression analysis was used to determine the prognostic value of ELNs. The cut-off point of the ELNs count was determined using R-statistical software. The prediction model was developed using random survival forest (RSF) algorithm. Higher ELNs count was significantly associated with better survival in both cohorts (training cohort: HR = 0.98, CI = 0.97–0.99, P < 0.01; testing cohort: HR = 0.98, CI = 0.98–0.99, P < 0.01) and the cut-off point was 18 (training cohort: P < 0.01; testing cohort: P < 0.01). We developed the RSF model with high prediction accuracy (AUC: training cohort: 87.5; testing cohort: 79.3) and low Brier Score (training cohort: 0.122; testing cohort: 0.152). The ELNs count beyond 18 is associated with better overall survival. The RSF model has preferable clinical capability in terms of individual prognosis assessment in patients after radical esophagectomy.

Prognostic Impact and Landscape of Mitochondrial DNA Variants in Myelodysplastic Syndromes Undergoing Allogenic Hematopoietic Cell Transplantation

Background: Myelodysplastic syndromes (MDS) are a heterogenous group of clonal hematopoietic cell disorders characterized by blood cytopenias and a tendency to progress to acute myeloid leukemia. Despite treatment advances, allogeneic hematopoietic stem-cell transplantation (allo-HCT) remains the only potentially curative therapy for MDS. However, mortality after allo-HCT is high due to disease relapse and transplant-related complications. Current prognostic tools defining MDS risk groups, such as the International Prognostic Scoring System (IPSS) and the revised IPSS (IPSS-R), are used to predict posttransplant outcomes for clinical decision-making. A major limitation of these scoring systems is a failure to account for variables other than clinical and hematologic parameters. Comprehensive genomic analyses have shown that mutations in specific genes (e.g., TP53, TET2, and DNMT3A) could inform prognostic stratification of MDS undergoing allo-HCT. However, most studies of MDS genome have focused on mutations occurring in the nuclear genome and ignored the mitochondrial genome. The current study aims to characterize mitochondrial genomic landscape of MDS and identify mitochondrial DNA (mtDNA) genetic variants prognostic for post allo-HCT outcomes in MDS. Methods: We performed whole genome sequencing (WGS) on whole-blood samples obtained before allo-HCT from 494 patients with MDS who were enrolled in the Center for International Blood and Marrow Transplant Research (CIBMTR) between 2014 and 2018. Mitochondrial genome sequences were extracted from the WGS data and aligned to the mtDNA reference genome (Revised Cambridge Reference Sequence, rCRS) by GSNAP. Putative mtDNA variants, including single nucleotide variants (SNV) and indels, were identified by parsing the SAM CIGAR string. Pathogenicity prediction was conducted for mtDNA variants in the protein-coding genes, MT-tRNAs and MT-rRNAs using different databases. We evaluated the impact of mtDNA variants on the overall survival (OS) and relapse with adjustment for MDS- and HCT-related factors. A random survival forest algorithm was applied to evaluate the prognostic performance of models that include mtDNA variants alone and combined with MDS- and HCT-related clinical factors. Results: The patients in the cohort have a median age of 67 years, 36.4% had poor/very poor Revised International Prognostic Scores (IPSS-R), and 26% received myeloablative conditioning regimens. On average, the sequencing depth of the mitochondrial genome was 14,596× (213× - 17,070×), and the average coverage was 99.90% (99.89% - 100%). A total of 2,666 mtDNA variants are identified, including 411 potential pathogenic variants. Mitochondrial control region (also known as D-Loop) was the most frequently mutated region in our cohort and the most frequently mutated protein-coding gene was MT-ND5 (16%). MDS patients with higher number of mitochondrial mutations (continuous variable) had significantly worse OS (hazard ratio, HR, 1.11; 95% CI, 1.01-1.22; P = 0.029) and higher risk of relapse (HR, 1.13; 95% CI, 1.00-1.27; P = 0.049) than patients with lower number of mutations. Gene-based analysis yielded significant associations with OS for MT-CYB (P = 1.04×10-3), MT-ND2 (P = 3.06×10-3) and MT-ND4 (P = 1.41×10-3) variants after Bonferroni correction (P < 0.05/16=3.13×10-3) (Table 1). Four mtDNA genes were significantly associated with relapse, including MT-CYB (P = 7.03×10-4), MT-ND2 (P = 5.92×10-4), MT-ND5 (P = 1.91×10-3) and MT-tRNA (P = 1.99×10-4). (Table 1). To investigate whether mtDNA variants could improve the prognostic stratification of MDS patients receiving allo-HCT, we fitted random survival forest models with and without inclusion of mtDNA variants in the models. The model based only on mtDNA genes had a c-index of 0.58 to predict OS, which was slightly higher than the IPSS-R (c-index = 0.48) and clinical model (IPSS-R plus MDS type and pre-transplantation treatments, c-index = 0.57). Adding mtDNA genes improved the predictive performance of the model, with c-index increased from 0.48 to 0.63 for the IPSS-R model and from 0.57 to 0.66 for the clinical model (Figure 1). Similar results were observed for the models in predicting relapse (Figure 1). Conclusions: There may be clinical utility of mtDNA variants to predict allo-HCT outcomes in combination with more standard clinical parameters. Figure 1View largeDownload PPTFigure 1View largeDownload PPT Close modal