Random Survival Forest Research Articles

Recurrence of Hepatocellular Carcinoma in Patients with Low Albumin-Bilirubin Grade in TACE Combined with Ablation: A Random Forest Cox Predictive Model.

The aim of our study was to investigate the relationship between albumin-bilirubin (ALBI) grade and recurrence in patients who underwent TACE sequential ablation. We developed and validated a nomogram to predict low levels of ALBI patients' recurrence. A total of 880 patients undergoing TACE combined ablation at Beijing Youan Hospital from January 2014 to December 2021 were retrospectively enrolled, including 415 patients with L-ALBI (≤-2.6) and 465 patients with high levels (>-2.6) of ALBI (H-ALBI). L-ALBI patients were randomized in a 7:3 ratio into the training cohort (N=289) and validation cohort (N=126). Multivariate Cox regression followed by random survival forest was carried out to identify independent risk factors for prediction nomogram construction. An examination of nomogram accuracy was performed using the C-index, receiver operating characteristic (ROC), calibration curves, and decision curve analysis (DCA) curves. According to the nomogram, the patients were divided into low-risk, intermediate-risk, and high-risk groups. Kaplan-Meier (KM) curves were applied to compare the difference in recurrence-free survival (RFS) among the three groups. The median RFS in L-ALBI patients was significantly longer than the H-ALBI patients (40.8m vs 20.1m, HR:1.71, 95% CI:1.44-2.04, P<0.0001). The nomogram was composed of five variables, such as age, Barcelona Clinic Liver Cancer (BCLC) stage, globulin, gamma-glutamyl transferase to lymphocyte ratio (GLR), and international normalized ratio (INR). The C-index (0.722 and 0.731) and 1-, 3-, and 5-year AUCs (0.725, 0.803, 0.870, and 0.764, 0.816, 0.798) of the training and validation cohorts proved the good predictive performance of the nomogram. Calibration curves and DCA curves demonstrated good consistency and good clinical utility. There were significant differences in RFS between the low-risk, intermediate-risk, and high-risk groups (P<0.0001). L-ALBI Patients who underwent TACE combined ablation had better recurrence-free survival than patients with H-ALBI. The nomogram developed and validated in our study had good predictive ability in recurrence for L-ALBI patients.

Dendritic cell-related hub genes in head-and-neck squamous cell carcinoma: implications for prognosis and immunotherapy.

In the context of head-and-neck squamous cell carcinoma (HNSCC), dendritic cells (DCs) assume pivotal responsibilities, acting as architects of antigen presentation and conductors of immune checkpoint modulation. In this study, we aimed to identify hub genes associated with DCs in HNSCC and explore their prognostic significance and implications for immunotherapy. Integrated clinical datasets from The Cancer Genome Atlas (TCGA)-HNSCC and GSE65858 cohorts underwent meticulous analysis. Employing weighted gene co-expression network analysis (WGCNA), we delineated candidate genes pertinent to DCs. Through the application of random survival forest and least absolute shrinkage and selection operator (LASSO) Cox's regression, we derived key genes of significance. Lisa (epigenetic Landscape In Silico deletion Analysis and the second descendent of MARGE) highlighted transcription factors, with Dual-luciferase assays confirming their regulatory role. Furthermore, immunotherapeutic sensitivity was assessed utilizing the Tumor Immune Dysfunction and Exclusion online tool. This study illuminated the functional intricacies of HNSCC DC subsets to tailor innovative therapeutic strategies. We leveraged clinical data from the TCGA-HNSCC and GSE65858 cohorts. We subjected the data to advanced analysis, including WGCNA, which revealed 222 DC-related candidate genes. Following this, a discerning approach utilizing random survival forest analysis and LASSO Cox's regression unveiled seven genes associated with the prognostic impact of DCs, notably ACP2 and CPVL, associated with poor overall survival. Differential gene expression analysis between ACP2 + and ACP2 - DC cells revealed 208 differential expressed genes. Lisa analysis identified the top five significant transcription factors as STAT1, SPI1, SMAD1, CEBPB, and IRF1. The correlation between STAT1 and ACP2 was confirmed through quantitative reverse transcription polymerase chain reaction (qRT-PCR) and Dual-luciferase assays in HEK293T cells. Additionally, TP53 and FAT1 mutations were more common in high-risk DC subgroups. Importantly, the sensitivity to immunotherapy differed among the risk clusters. The low-risk cohorts were anticipated to exhibit favorable responses to immunotherapy, marked by heightened expressions of immune system-related markers. In contrast, the high-risk group displayed augmented proportions of immunosuppressive cells, suggesting a less conducive environment for immunotherapeutic interventions. Our research may yield a robust DC-based prognostic system for HNSCC; this will aid personalized treatment and improve clinical outcomes as the battle against this challenging cancer continues.

Survival Prognostication in Patients with Differentiated Thyroid Cancer and Distant Metastases: A SEER Population-Based Study.

Background: For patients with thyroid cancer, distant metastasis is a significant predictor of poor outcome. Since distant metastasis occurs in less than 10% of patients with differentiated thyroid cancer, correlates of survival in this vulnerable patient population remain understudied. This study aimed to identify prognostic groups among patients with differentiated thyroid cancer and distant metastases and to determine the role of, and interactions between, patient and tumor characteristics in determining survival. Methods: We identified adult patients diagnosed with differentiated thyroid cancer with distant metastases from the U.S. SEER-17 cancer registry (2010-2019). Analyses were performed using Cox proportional hazards regression, survival trees, and random survival forest. Relative importance of patient and tumor factors important for disease-specific and overall survival was assessed based on the random survival forest analyses. Results: Cohort consisted of 2411 patients with differentiated thyroid cancer with distant metastases followed for a median of 62 months. Most common histopathologic subtype (86.0%) was papillary thyroid cancer, and the most common sites of distant metastasis were the lungs (33.7%) and bone (18.9%). Cox proportional hazards model illustrated significant associations between survival and the following: patient age (p < 0.001), tumor size (p < 0.01), and site of distant metastasis (p < 0.05). Survival tree analyses identified three distinct prognostic groups based on disease-specific survival (DSS) (5-year survival of the prognostic groups was 92%, 64%, and 41%; p < 0.001) and four distinct prognostic groups based on overall survival (OS) (5-year survival of the prognostic groups was 96%, 84%, 57%, and 31%; p < 0.001). The first split in the survival trees for DSS and OS was by age at diagnosis (≤57 years vs. ≥58 years) with subsequent splits based on presence/absence of lung metastases, tumor size (≤4 cm vs. >4 cm), and patient age. A total of 558 patients (23.1%) died from thyroid cancer, and 757 patients (31.4%) died from all causes during the study period. Conclusions: This study identifies distinct prognostic groups for patients with differentiated thyroid cancer with distant metastases and highlights the importance of patient age, lung metastases, and tumor size for determining both disease-specific and overall survival. These findings inform risk stratification and treatment decision-making in this understudied patient population.

Poster 387: Application of Survival Machine Learning Methodology to Predict Time-Dependent Risk of Revision ACLR Graft Failure in the MARS Cohort

Objectives: Previous machine learning (ML) analysis has shown that a novel ML model built using the Multicenter Anterior Cruciate Ligament (ACL) Revision Study (MARS) cohort data can predict graft failure at 6 years postoperatively as a binary outcome with moderate ability. However, binary classification does not consider the time-to-event component of graft failure as an outcome. In contrast, survival models can factor the time-to-event component of an outcome, incorporate time-dependent variables, and appropriately process censored data to deliver more clinically meaningful outcome predictions. While the previous binary classifier can provide information about whether the primary outcome graft failure will occur at 6 years, survival analysis models are able to provide information on when graft failure occurs (for example, within 2, 4, or 6 years). Therefore, this study sought to apply ML survival analysis methodology to the MARS cohort data to produce a model that can most accurately estimate the probability of revision ACL reconstruction (rACLR) graft failure within 2, 4, and 6 years postoperatively, and identify factors that impact probability estimates at each of these time horizons. Methods: rACLR patients were prospectively recruited by the MARS group. Preoperative radiographs, surgeon-reported intraoperative findings, and 2 and 6-year follow-up data on patient-reported outcomes (PROs), subsequent knee surgeries, and graft failure were obtained. ML models including Cox Proportional Hazards (CoxPH), XGBoost Survival Embeddings (XGBoost), Random Survival Forest (RSF), Extra Survival Tree (EST), and CoxBoost, were built to predict the probability of graft failure within 2, 4, and 6 years postoperatively. Validated performance metrics and feature importance measures were used to evaluate model performance. Results: The cohort included 1142 patients, of which 4.8% (n = 55) experienced documented graft failure during the 6-year postoperative period. CoxBoost demonstrated the highest discriminative power across all studied time points (Timepoint: Time Dependent C-index | 2-year: 0.725 ± 0.127 | 4-year: 0.669 ± 0.057 | 6-year: 0.645 ± 0.054), with well-calibrated scores (Timepoint: Time dependent Brier Score | 2-year: 0.023 ± 0.012 | 4-year: 0.035 ± 0.010 | 6-year: 0.046 ± 0.012) as listed in Table 1 and Table 2 respectively. Based on the Kaplan Meier survival plot, the survival probability (probability of not tearing the ACL graft) at 2, 4, 6 years was 0.977, 0.965, and 0.954 respectively. Within the context of the predictive models, features deemed important for CoxBoost differed from those deemed important for CoxPH predictive ability. Conclusions: Survival machine learning models can predict the risk of rACLR graft failure up to 6 years postoperatively, with the most robust predictions at the 2-year postoperative timepoint. While external validation with further combined registry datasets is required, this present study builds on prior ML analyses towards the development of a bedside calculator for rACLR outcome prediction and risk stratification.

Novel machine learning algorithm in risk prediction model for pan-cancer risk: application in a large prospective cohort

ObjectiveTo develop and validate machine-learning models that predict the risk of pan-cancer incidence using demographic, questionnaire and routine health check-up data in a large Asian population.Methods and analysisThis study is...

Machine learning identifies prognostic subtypes of the tumor microenvironment of NSCLC

The tumor microenvironment (TME) plays a fundamental role in tumorigenesis, tumor progression, and anti-cancer immunity potential of emerging cancer therapeutics. Understanding inter-patient TME heterogeneity, however, remains a challenge to efficient drug development. This article applies recent advances in machine learning (ML) for survival analysis to a retrospective study of NSCLC patients who received definitive surgical resection and immune pathology following surgery. ML methods are compared for their effectiveness in identifying prognostic subtypes. Six survival models, including Cox regression and five survival machine learning methods, were calibrated and applied to predict survival for NSCLC patients based on PD-L1 expression, CD3 expression, and ten baseline patient characteristics. Prognostic subregions of the biomarker space are delineated for each method using synthetic patient data augmentation and compared between models for overall survival concordance. A total of 423 NSCLC patients (46% female; median age [inter quantile range]: 67 [60–73]) treated with definite surgical resection were included in the study. And 219 (52%) patients experienced events during the observation period consisting of a maximum follow-up of 10 years and median follow up 78 months. The random survival forest (RSF) achieved the highest predictive accuracy, with a C-index of 0.84. The resultant biomarker subtypes demonstrate that patients with high PD-L1 expression combined with low CD3 counts experience higher risk of death within five-years of surgical resection.

The survival prediction of advanced colorectal cancer received neoadjuvant therapy—a study of SEER database

PurposeThe aim of study was to screen factors associated with the overall survival of colorectal cancer patients with lymph nodes metastasis who received neoadjuvant therapy and construct a nomogram model.MethodsAll enrolled subjects of the SEER database were randomly assigned to the training and testing group in a ratio of 3:2. The patients of Tangdu Hospital were seemed as validation group. Univariate cox regression analysis, lasso regression and random forest survival were used to screen variables related to the survival of advanced CRC patients received neoadjuvant therapy in the training group. Area under curves were adopted to evaluate the 1,3,5-year prediction value of the optimal model in three cohorts. Calibration curves were drawn to observe the prediction accuracy of the nomogram model. Decision curve analysis was used to assess the potential clinical value of the nomogram model.ResultsA total of 1833 subjects were enrolled in this study. After random allocation, 1055 cases of the SEER database served as the training group, 704 cases as the testing group and 74 patients from our center as the external validation group. Variables were screened by univariate cox regression used to construct a nomogram survival prediction model, including M, age, chemotherapy, CEA, perineural invasion, tumor size, LODDS, liver metastasis and radiation. The AUCs of the model for predicting 1-year OS in the training group, testing and validation group were 0.765 (0.703,0.827), 0.772 (0.697,0.847) and 0.742 (0.601,0.883), predicting 3-year OS were 0.761 (0.725,0.780), 0.742 (0.699,0.785), 0.733 (0.560,0.905) and 5-year OS were 0.742 (0.711,0.773), 0.746 (0.709,0.783), 0.838 (0.670,0.980), respectively. The calibration curves showed the difference between prediction probability of the model and the actual survival was not significant in three cohorts and the decision curve analysis revealed the practice clinical application value. And the prediction value of model was better for young CRC than older CRC patients.ConclusionA nomogram model including LODDS for the prognosis of advanced CRC received neoadjuvant therapy was constructed and verified based on the SEER database and single center practice. The accuracy and potential clinical application value of the model performed well, and the model had better predictive value for EOCRC than LOCRC.

Evolution of serious and life-threatening COVID-19 pneumonia as the SARS-CoV-2 pandemic progressed: an observational study of mortality to 60 days after admission to a 15-hospital US health system

ObjectiveIn order to predict at hospital admission the prognosis of patients with serious and life-threatening COVID-19 pneumonia, we sought to understand the clinical characteristics of hospitalised patients at admission as...

Alterations in genes involved in glycolysis and hypoxia affect the prognosis of pancreatic cancer

PurposeTo construct a prognostic model for pancreatic cancer based on glycolytic and hypoxic metabolic subtypes. To analyze the biological characteristics of these subtypes and explore potential therapeutic options. MethodsWe obtained mRNA, simple nucleotide variation (SNP), and clinical data for pancreatic cancer from The Cancer Genome Atlas (TCGA). Patients were classified into four metabolic subtypes. We focused on glycolysis and hypoxia subtypes. Single-sample gene set enrichment analysis (ssGSEA) assessed immune cell infiltration. We evaluated the effects of immunotherapy and chemotherapy on these subtypes. Cox regression and random survival forest algorithms were used to build a prognostic model. Validation was performed using data from the International Cancer Genome Consortium (ICGC) and ArrayExpress database. ResultsWe identified four subtypes. Kaplan-Meier survival analysis showed the glycolytic subtype had the longest survival, while the hypoxic subtype had the shortest. The glycolytic subtype exhibited higher immune cell infiltration. Immunotherapy and chemotherapy appeared more beneficial for the glycolytic subtype. KRAS mutations were more frequent in the hypoxic subtype. Our prognostic model indicated a worse prognosis for high-risk groups, validated by external data. ConclusionThe glycolytic metabolic subtype of pancreatic cancer is associated with longer survival and better response to chemotherapy and immunotherapy compared to the hypoxic subtype.

A machine learning and drug repurposing approach to target ferroptosis in colorectal cancer stratified by sex and KRAS.

The landscape of sex differences in Colorectal Cancer (CRC) has not been well characterized with respect to the mechanisms of action for oncogenes such as KRAS. However, our recent study showed that tumors from male patients with KRAS mutations have decreased iron-dependent cell death called ferroptosis. Building on these findings, we further examined ferroptosis in CRC, considering both sex of the patient and KRAS mutations, using public databases and our in-house CRC tumor cohort. Through subsampling inference and variable importance analysis (VIMP), we identified significant differences in gene expression between KRAS mutant and wild type tumors from male patients. These genes suppress (e.g., SLC7A11 ) or drive (e.g., SLC1A5 ) ferroptosis, and these findings were further validated with Gaussian mixed models. Furthermore, we explored the prognostic value of ferroptosis regulating genes and discovered sex- and KRAS-specific differences at both the transcriptional and metabolic levels by random survival forest with backward elimination algorithm (RSF-BE). Of note, genes and metabolites involved in arginine synthesis and glutathione metabolism were uniquely associated with prognosis in tumors from males with KRAS mutations. Additionally, drug repurposing is becoming popular due to the high costs, attrition rates, and slow pace of new drug development, offering a way to treat common and rare diseases more efficiently. Furthermore, increasing evidence has shown that ferroptosis inhibition or induction can improve drug sensitivity or overcome chemotherapy drug resistance. Therefore, we investigated the correlation between gene expression, metabolite levels, and drug sensitivity across all CRC primary tumor cell lines using data from the Genomics of Drug Sensitivity in Cancer (GDSC) resource. We observed that ferroptosis suppressor genes such as DHODH , GCH1 , and AIFM2 in KRAS mutant CRC cell lines were resistant to cisplatin and paclitaxel, underscoring why these drugs are not effective for these patients. The comprehensive map generated here provides valuable biological insights for future investigations, and the findings are supported by rigorous analysis of large-scale publicly available data and our in-house cohort. The study also emphasizes the potential application of VIMP, Gaussian mixed models, and RSF-BE models in the multi-omics research community. In conclusion, this comprehensive approach opens doors for leveraging precision molecular feature analysis and drug repurposing possibilities in KRAS mutant CRC.

Prediction of prognosis in patients with systemic sclerosis based on a machine-learning model.

The clinical manifestations of systemic sclerosis (SSc) are highly variable, resulting in varied outcomes and complications. Diverse fibrosis of the skin and internal organs, vasculopathy, and dysregulated immune system lead to poor and varied prognoses in patients with SSc subtypes. Therefore, this study aimed to develop a personalized tool for predicting the prognosis of patients with SSc. A cohort of 517 patients with SSc were recruited between January 2009 and November 2021 at Xijing Hospital in China, and 266 patients completed the follow-up and performed in the survival analysis. Risk factors for death were identified using Cox survival analysis and random survival forest-based machine-learning methods separately. The consistency index, area under the curve (AUC), and integrated Brier scores were used to compare the predictive performance of the different prognostic models. The results of Cox-based multivariate regression analysis suggested that pulmonary arterial hypertension, digital ulcer, and Modified Rodnan Skin Score (mRSS) were independent risk factors for poor prognosis in patients with SSc and significant risk factors in random survival forest (RSF) surveys. A nomogram was plotted to evaluate the prognostic risk to facilitate clinical assessment; the RSF model had better predictive performance than the Cox model, with 3- and 5-year AUCs of 0.74 and 0.78, respectively. Machine-learning models can help us better understand the prognosis of patients with SSc and comprehensively evaluate the clinical characteristics of each individual. The early identification of the characteristics of high-risk patients can improve the prognosis of those with SSc. Key Points • Regarding predictive performance, the random survival forest model was more effective than the Cox model and had unique advantages in analyzing nonlinear effects and variable importance. • Machine learning using the simple clinical features of patients with systemic sclerosis (SSc) to predict mortality can guide attending physicians, and the early identification of high-risk patients with SSc and referral to experts will assist rheumatologists in monitoring and management planning.

Deep learning models for predicting the survival of patients with medulloblastoma based on a surveillance, epidemiology, and end results analysis

Medulloblastoma is a malignant neuroepithelial tumor of the central nervous system. Accurate prediction of prognosis is essential for therapeutic decisions in medulloblastoma patients. We analyzed data from 2,322 medulloblastoma patients using the SEER database and randomly divided the dataset into training and testing datasets in a 7:3 ratio. We chose three models to build, one based on neural networks (DeepSurv), one based on ensemble learning that Random Survival Forest (RSF), and a typical Cox Proportional-hazards (CoxPH) model. The DeepSurv model outperformed the RSF and classic CoxPH models with C-indexes of 0.751 and 0.763 for the training and test datasets. Additionally, the DeepSurv model showed better accuracy in predicting 1-, 3-, and 5-year survival rates (AUC: 0.767–0.793). Therefore, our prediction model based on deep learning algorithms can more accurately predict the survival rate and survival period of medulloblastoma compared to other models.

Scoring System for Predicting the Risk of Liver Cancer among Diabetes Patients: A Random Survival Forest-Guided Approach.

Most liver cancer scoring systems focus on patients with preexisting liver diseases such as chronic viral hepatitis or liver cirrhosis. Patients with diabetes are at higher risk of developing liver cancer than the general population. However, liver cancer scoring systems for patients in the absence of liver diseases or those with diabetes remain rare. This study aims to develop a risk scoring system for liver cancer prediction among diabetes patients and a sub-model among diabetes patients without cirrhosis/chronic viral hepatitis. A retrospective cohort study was performed using electronic health records of Hong Kong. Patients who received diabetes care in general outpatient clinics between 2010 and 2019 without cancer history were included and followed up until December 2019. The outcome was diagnosis of liver cancer during follow-up. A risk scoring system was developed by applying random survival forest in variable selection, and Cox regression in weight assignment. The liver cancer incidence was 0.92 per 1000 person-years. Patients who developed liver cancer (n = 1995) and those who remained free of cancer (n = 1969) during follow-up (median: 6.2 years) were selected for model building. In the final time-to-event scoring system, presence of chronic hepatitis B/C, alanine aminotransferase, age, presence of cirrhosis, and sex were included as predictors. The concordance index was 0.706 (95%CI: 0.676-0.741). In the sub-model for patients without cirrhosis/chronic viral hepatitis, alanine aminotransferase, age, triglycerides, and sex were selected as predictors. The proposed scoring system may provide a parsimonious score for liver cancer risk prediction among diabetes patients.

DeepAFT: A nonlinear accelerated failure time model with artificial neural network.

The Cox regression model or accelerated failure time regression models are often used for describing the relationship between survival outcomes and potential explanatory variables. These models assume the studied covariates are connected to the survival time or its distribution or their transformations through a function of a linear regression form. In this article, we propose nonparametric, nonlinear algorithms (deepAFT methods) based on deep artificial neural networks to model survival outcome data in the broad distribution family of accelerated failure time models. The proposed methods predict survival outcomes directly and tackle the problem of censoring via an imputation algorithm as well as re-weighting and transformation techniques based on the inverse probabilities of censoring. Through extensive simulation studies, we confirm that the proposed deepAFT methods achieve accurate predictions. They outperform the existing regression models in prediction accuracy, while being flexible and robust in modeling covariate effects of various nonlinear forms. Their prediction performance is comparable to other established deep learning methods such as deepSurv and random survival forest methods. Even though the direct output is the expected survival time, the proposed AFT methods also provide predictions for distributional functions such as the cumulative hazard and survival functions without additional learning efforts. For situations where the popular Cox regression model may not be appropriate, the deepAFT methods provide useful and effective alternatives, as shown in simulations, and demonstrated in applications to a lymphoma clinical trial study.

MSR83 Predicting Optimal Treatment Regimen to Improve Outcomes of Patients With CLL/SLL Using Random Survival Forest

MSR83 Predicting Optimal Treatment Regimen to Improve Outcomes of Patients With CLL/SLL Using Random Survival Forest

MSR49 Long-Term Survival Prediction in Early Breast Cancer: A Machine Learning Approach With Random Survival Forest

MSR49 Long-Term Survival Prediction in Early Breast Cancer: A Machine Learning Approach With Random Survival Forest

Deep learning models for predicting the survival of patients with hepatocellular carcinoma based on a surveillance, epidemiology, and end results (SEER) database analysis

Hepatocellular carcinoma (HCC) is a common malignancy with poor survival and requires long-term follow-up. Hence, we collected information on patients with Primary Hepatocellular Carcinoma in the United States from the Surveillance, Epidemiology, and EndResults (SEER) database. We used this information to establish a deep learning with a multilayer neural network (the NMTLR model) for predicting the survival rate of patients with Primary Hepatocellular Carcinoma. HCC patients pathologically diagnosed between January 2011 and December 2015 in the SEER (Surveillance, Epidemiology, and End Results) database of the National Cancer Institute of the United States were selected as study subjects. We utilized two deep learning-based algorithms (DeepSurv and Neural Multi-Task Logistic Regression [NMTLR]) and a machine learning-based algorithm (Random Survival Forest [RSF]) for model training. A multivariable Cox Proportional Hazards (CoxPH) model was also constructed for comparison. The dataset was randomly divided into a training set and a test set in a 7:3 ratio. The training dataset underwent hyperparameter tuning through 1000 iterations of random search and fivefold cross-validation. Model performance was assessed using the concordance index (C-index), Brier score, and Integrated Brier Score (IBS). The accuracy of predicting 1-year, 3-year, and 5-year survival rates was evaluated using Receiver Operating Characteristic (ROC) curves, calibration plots, and Area Under the Curve (AUC). The primary outcomes were the 1-year, 3-year, and 5-year overall survival rates. Models were developed using DeepSurv, NMTLR, RSF, and Cox Proportional Hazards regression. Model differentiation was evaluated using the C-index, calibration with concordance plots, and risk stratification capability with the log-rank test. The study included 2197 HCC patients, randomly divided into a training cohort (70%, n = 1537) and a testing cohort (30%, n = 660). Clinical characteristics between the two cohorts showed no significant statistical difference (p > 0.05). The deep learning models outperformed both RSF and CoxPH models, with C-indices of 0.735 (NMTLR) and 0.731 (DeepSurv) in the test dataset. The NMTLR model demonstrated enhanced accuracy and well-calibrated survival estimates, achieving an Area Under the Curve (AUC) of 0.824 for 1-year survival predictions, 0.813 for 3-year, and 0.803 for 5-year survival rates. This model's superior calibration and discriminative ability enhance its utility for clinical prognostication in Primary Hepatocellular Carcinoma. We deployed the NMTLR model as a web application for clinical practice. The NMTLR model have potential advantages over traditional linear models in prognostic assessment and treatment recommendations. This novel analytical approach may provide reliable information on individual survival and treatment recommendations for patients with primary liver cancer.

Differential Diagnosis of Prostate Cancer Grade to Augment Clinical Diagnosis Based on Classifier Models with Tuned Hyperparameters.

We developed a novel machine-learning algorithm to augment the clinical diagnosis of prostate cancer utilizing first and second-order texture analysis metrics in a novel application of machine-learning radiomics analysis. We successfully discriminated between significant prostate cancers versus non-tumor regions and provided accurate prediction between Gleason score cohorts with statistical sensitivity of 0.82, 0.81 and 0.91 in three separate pathology classifications. Tumor heterogeneity and prediction of the Gleason score were quantified using two feature selection approaches and two separate classifiers with tuned hyperparameters. There was a total of 71 patients analyzed in this study. Multiparametric MRI, incorporating T2WI and ADC maps, were used to derive radiomics features. Recursive feature elimination (RFE), the least absolute shrinkage and selection operator (LASSO), and two classification approaches, incorporating a support vector machine (SVM) (with randomized search) and random forest (RF) (with grid search), were utilized to differentiate between non-tumor regions and significant cancer while also predicting the Gleason score. In T2WI images, the RFE feature selection approach combined with RF and SVM classifiers outperformed LASSO with SVM and RF classifiers. The best performance was achieved by combining LASSO and SVM into a model that used both T2WI and ADC images. This model had an area under the curve (AUC) of 0.91. Radiomic features computed from ADC and T2WI images were used to predict three groups of Gleason score using two kinds of feature selection methods (RFE and LASSO), RF and SVM classifier models with tuned hyperparameters. Using combined sequences (T2WI and ADC map images) and combined radiomics (1st and GLCM features), LASSO, with a feature selection method with RF, was able to predict G3 with the highest sensitivity at a level AUC of 0.92. To predict G3 for single sequence (T2WI images) using GLCM features, LASSO with SVM achieved the highest sensitivity with an AUC of 0.92.

Comparative evaluation of outcomes amongst different radiosurgery management paradigms for patients with large brain metastasis.

This study compares four management paradigms for large brain metastasis (LMB): fractionated SRS (FSRS), staged SRS (SSRS), resection and postoperative-FSRS (postop-FSRS) or preoperative-SRS (preop-SRS). Patients with LBM (≥ 2 cm) between July 2017 and January 2022 at a single tertiary institution were evaluated. Primary endpoints were local failure (LF), radiation necrosis (RN), leptomeningeal disease (LMD), a composite of these variables, and distant intracranial failure (DIF). Gray's test compared cumulative incidence, treating death as a competing risk with a random survival forests (RSF) machine-learning model also used to evaluate the data. 183 patients were treated to 234 LBMs: 31.6% for postop-FSRS, 28.2% for SSRS, 20.1% for FSRS, and 20.1% for preop-SRS. The overall 1-year composite endpoint rates were comparable (21 vs 20%) between nonoperative and operative strategies, but 1-year RN rate was 8 vs 4% (p = 0.012), 1-year overall survival (OS) was 48 vs. 69% (p = 0.001), and 1-year LMD rate was 5 vs 10% (p = 0.052). There were differences in the 1-year RN rates (7% FSRS, 3% postop-FSRS, 5% preop-SRS, 10% SSRS, p = 0.037). With RSF analysis, the out-of-bag error rate for the composite endpoint was 47%, with identified top-risk factors including widespread extracranial disease, > 5 total lesions, and breast cancer histology. This is the first study to conduct a head-to-head retrospective comparison of four SRS methods, addressing the lack of randomized data in LBM literature amongst treatment paradigms. Despite patient characteristic trends, no significant differences were found in LF, composite endpoint, and DIF rates between non-operative and operative approaches.

Fracture risk prediction in postmenopausal women with traditional and machine learning models in a nationwide, prospective cohort study in Switzerland with validation in the UK Biobank.

Fracture prediction is essential in managing patients with osteoporosis and is an integral component of many fracture prevention guidelines. We aimed to identify the most relevant clinical fracture risk factors in contemporary populations by training and validating short- and long-term fracture risk prediction models in 2 cohorts. We used traditional and machine learning survival models to predict risks of vertebral, hip, and any fractures on the basis of clinical risk factors, T-scores, and treatment history among participants in a nationwide Swiss Osteoporosis Registry (N = 5944 postmenopausal women, median follow-up of 4.1yr between January 2015 and October 2022; a total of 1190 fractures during follow-up). The independent validation cohort comprised 5474 postmenopausal women from the UK Biobank with 290 incident fractures during follow-up. Uno's C-index and the time-dependent area under the receiver operating characteristics curve were calculated to evaluate the performance of different machine learning models (Random survival forest and eXtreme Gradient Boosting). In the independent validation set, the C-index was 0.74 [0.58, 0.86] for vertebral fractures, 0.83 [0.7, 0.94] for hip fractures, and 0.63 [0.58, 0.69] for any fractures at year 2, and these values further increased for longer estimations of up to 7yr. In comparison, the 10-yr fracture probability calculated with FRAX Switzerland was 0.60 [0.55, 0.64] for major osteoporotic fractures and 0.62 [0.49, 0.74] for hip fractures. The most important variables identified with Shapley additive explanations values were age, T-scores, and prior fractures, while number of falls was an important predictor of hip fractures. Performances of both traditional and machine learning models showed similar C-indices. We conclude that fracture risk can be improved by including the lumbar spine T-score, trabecular bone score, numbers of falls and recent fractures, and treatment information has a significant impact on fracture prediction.