Survival Models Research Articles

Clinical predictive models for recurrence and survival in treated laryngeal and hypopharyngeal cancer: a systematic review and meta-analysis

BackgroundThe limitations of the traditional TNM system have spurred interest in multivariable models for personalized prognostication in laryngeal and hypopharyngeal cancers (LSCC/HPSCC). However, the performance of these models depends on the quality of data and modelling methodology, affecting their potential for clinical adoption. This systematic review and meta-analysis (SR-MA) evaluated clinical predictive models (CPMs) for recurrence and survival in treated LSCC/HPSCC. We assessed models’ characteristics and methodologies, as well as performance, risk of bias (RoB), and applicability.MethodsLiterature searches were conducted in MEDLINE (OVID), Embase (OVID) and IEEE databases from January 2005 to November 2023. The search algorithm used comprehensive text word and index term combinations without language or publication type restrictions. Independent reviewers screened titles and abstracts using a predefined Population, Index, Comparator, Outcomes, Timing and Setting (PICOTS) framework. We included externally validated (EV) multivariable models, with at least one clinical predictor, that provided recurrence or survival predictions. The SR-MA followed PRISMA reporting guidelines, and PROBAST framework for RoB assessment. Model discrimination was assessed using C-index/AUC, and was presented for all models using forest plots. MA was only performed for models that were externally validated in two or more cohorts, using random-effects model. The main outcomes were model discrimination and calibration measures for survival (OS) and/or local recurrence (LR) prediction. All measures and assessments were preplanned prior to data collection.ResultsThe SR-MA identified 11 models, reported in 16 studies. Seven models for OS showed good discrimination on development, with only one excelling (C-index >0.9), and three had weak or poor discrimination. Inclusion of a radiomics score as a model parameter achieved relatively better performance. Most models had poor generalisability, demonstrated by worse discrimination performance on EV, but they still outperformed the TNM system. Only two models met the criteria for MA, with pooled EV AUCs 0.73 (95% CI 0.71-0.76) and 0.67 (95% CI 0.6-0.74). RoB was high for all models, particularly in the analysis domain.ConclusionsThis review highlighted the shortcomings of currently available models, while emphasizing the need for rigorous independent evaluations. Despite the proliferation of models, most exhibited methodological limitations and bias. Currently, no models can confidently be recommended for routine clinical use.Systematic review registrationhttps://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42021248762, identifier CRD42021248762.

Development and application of a predictive model for survival and drug therapy based on COVID-19-related lncRNAs in non-small cell lung cancer.

Numerous studies have substantiated the pivotal role of long non-coding RNAs (lncRNAs) in the progression of non-small cell lung cancer (NSCLC) and the prognosis of afflicted patients. Notably, individuals with NSCLC may exhibit heightened vulnerability to the novel coronavirus disease (COVID-19), resulting in a more unfavorable prognosis subsequent to infection. Nevertheless, the impact of COVID-19-related lncRNAs on NSCLC remains unexplored. The aim of our study was to develop an innovative model that leverages COVID-19-related lncRNAs to optimize the prognosis of NSCLC patients. Pertinent genes and patient data were procured from reputable databases, including TCGA, Finngen, and RGD. Through co-expression analysis, we identified lncRNAs associated with COVID-19. Subsequently, we employed univariate, LASSO, and multivariate COX regression techniques to construct a risk model based on these COVID-19-related lncRNAs. The validity of the risk model was assessed using KM analysis, PCA, and ROC. Furthermore, functional enrichment analysis was conducted to elucidate the functional pathways linked to the identified lncRNAs. Lastly, we performed TME analysis and predicted the drug sensitivity of the model. Based on risk scores, patients were categorized into high- and low-risk subgroups, revealing distinct clinicopathological factors, immune pathways, and chemotherapy sensitivity between the subgroups. Four COVID-19-related lncRNAs (AL161431.1, AC079949.1, AC123595.1, and AC108136.1) were identified as potential candidates for constructing prognostic prediction models for NSCLC. We also observed a positive correlation between risk score and MDSC, exclusion, and CAF. Additionally, two immune pathways associated with high-risk and low-risk subgroups were identified. Our findings further support the association between COVID-19 infection and neuroactive ligand-receptor interaction, as well as steroid metabolism in NSCLC. Moreover, we identified several highly sensitive chemotherapy drugs for NSCLC treatment. The developed model holds significant value in predicting the prognosis of NSCLC patients and guiding treatment decisions.

Effects of initial peritoneal dialysis prescription on clinical outcomes in Japanese peritoneal dialysis patients: a cohort study

Effects of the initial peritoneal dialysis (PD) prescription on clinical outcomes are unknown in Japan. We conducted a cohort study using data from Peritoneal Dialysis Outcomes and Practice Patterns Study. The patients were divided into two groups by the volume of the initial PD prescription (≤ 4 L/day or > 4 L/day). Cause-specific Cox proportional hazards survival models were used to model the association between different PD prescriptions and the clinical outcomes. The outcomes included transfer to HD, mortality, the composite of mortality and transfer to HD, peritonitis, hospitalization, and the patient-reported outcomes (PROs). Of the 342 patients, 98 were prescribed ≤ 4 L/day, and 244 were prescribed > 4 L/day. Patients prescribed ≤ 4 L/day were older with a lower percentage being male, had more cardiovascular and cerebrovascular disease but lower diabetes prevalence, were more likely to be receiving CAPD, used more assisted PD, and had lower BMI and mean serum creatinine levels. There were no significant differences between groups in terms of transfer to HD, mortality, transfer to HD or mortality, hospitalization, incidence of peritonitis, and PROs. Patients with initial PD prescriptions of ≤ 4 L/day compared to > 4 L/day had similar clinical outcomes. This practice may provide health economic benefits in Japan.

Cytokine profiles as predictors of HIV incidence using machine learning survival models and statistical interpretable techniques

HIV remains a critical global health issue, with an estimated 39.9 million people living with the virus worldwide by the end of 2023 (according to WHO). Although the epidemic’s impact varies significantly across regions, Africa remains the most affected. In the past decade, considerable efforts have focused on developing preventive measures, such as vaccines and pre-exposure prophylaxis, to combat sexually transmitted HIV. Recently, cytokine profiles have gained attention as potential predictors of HIV incidence due to their involvement in immune regulation and inflammation, presenting new opportunities to enhance preventative strategies. However, the high-dimensional, time-varying nature of cytokine data collected in clinical research, presents challenges for traditional statistical methods like the Cox proportional hazards (PH) model to effectively analyze survival data related to HIV. Machine learning (ML) survival models offer a robust alternative, especially for addressing the limitations of the PH model’s assumptions. In this study, we applied survival support vector machine (SSVM) and random survival forest (RSF) models using changes or means in cytokine levels as predictors to assess their association with HIV incidence, evaluate variable importance, measure predictive accuracy using the concordance index (C-index) and integrated Brier score (IBS) and interpret the model’s predictions using Shapley additive explanations (SHAP) values. Our results indicated that RSFs models outperformed SSVMs models, with the difference covariate model performing better than the mean covariate model. The highest C-index for SSVM was 0.7180 under the difference covariate model, while for RSF, it reached 0.8801 under the difference covariate model using the log-rank split rule. Key cytokines identified as positive predictors of HIV incidence included TNF-A, BASIC-FGF, IL-5, MCP-3, and EOTAXIN, while 29 cytokines were negative predictors. Baseline factors such as condom use frequency, treatment status, number of partners, and sexual activity also emerged as significant predictors. This study underscored the potential of cytokine profiles for predicting HIV incidence and highlighted the advantages of RSFs models in analyzing high-dimensional, time-varying data over SSVMs. It further through ablation studies emphasized the importance of selecting key features within mean and difference based covariate models to achieve an optimal balance between model complexity and predictive accuracy.

From seedlings to adults: Linking survival and leaf functional traits over ontogeny

AbstractAs long‐lived tropical trees grow into the multi‐layered canopy and face different environmental conditions, the relationships between leaf traits and whole‐plant survival can vary over ontogeny. We tested the strength and direction of the relationships between leaf traits and long‐term survival data across life stages for woody species from a subtropical forest in Puerto Rico. Trait–survival relationships were largely consistent across ontogeny with conservative traits leading to higher survival rates. The stage‐specific relationship R2 increased by up to one order of magnitude compared to studies not considering ontogenetic trait variations. Stage‐specific traits were significant predictors of their corresponding stage‐specific survival: Seedlings traits were better predictors of seedling survival than adult traits, and adult traits were better predictors of maximum adult survival than seedling traits. Our results suggest that stage‐specific leaf traits reflect different strategies over ontogeny and can substantially improve predictability of survival models in tropical forests.

Deep Multiple Instance Learning Model to Predict Outcome of Pancreatic Cancer Following Surgery

Background/Objectives: Pancreatic ductal adenocarcinoma (PDAC) is a cancer with very poor prognosis despite early surgical management. To date, only clinical variables are used to predict outcome for decision-making about adjuvant therapy. We sought to generate a deep learning approach based on hematoxylin and eosin (H&E) or hematoxylin, eosin and saffron (HES) whole slides to predict patients’ outcome, compare these new entities with known molecular subtypes and question their biological significance; Methods: We used as a training set a retrospective private cohort of 206 patients treated by surgery for PDAC cancer and a validation cohort of 166 non-metastatic patients from The Cancer Genome Atlas (TCGA) PDAC project. We estimated a multi-instance learning survival model to predict relapse in the training set and evaluated its performance in the validation set. RNAseq and exome data from the TCGA PDAC database were used to describe the transcriptomic and genomic features associated with deep learning classification; Results: Based on the estimation of an attention-based multi-instance learning survival model, we identified two groups of patients with a distinct prognosis. There was a significant difference in progression-free survival (PFS) between these two groups in the training set (hazard ratio HR = 0.72 [0.54;0.96]; p = 0.03) and in the validation set (HR = 0.63 [0.42;0.94]; p = 0.01). Transcriptomic and genomic features revealed that the poor prognosis group was associated with a squamous phenotype. Conclusions: Our study demonstrates that deep learning could be used to predict PDAC prognosis and offer assistance in better choosing adjuvant treatment.

An Evaluation of an Algorithm for the Selection of Flexible Survival Models for Cancer Immunotherapies: Pass or Fail?

Accurately extrapolating survival beyond trial follow-up is essential in a health technology assessment where model choice often substantially impacts estimates of clinical and cost effectiveness. Evidence suggests standard parametric models often provide poor fits to long-term data from immuno-oncology trials. Palmer et al. developed an algorithm to aid the selection of more flexible survival models for these interventions. We assess the usability of the algorithm, identify areas for improvement and evaluate whether it effectively identifies models capable of accurate extrapolation. We applied the Palmer algorithm to the CheckMate-649 trial, which investigated nivolumab plus chemotherapy versus chemotherapy alone in patients with gastroesophageal adenocarcinoma. We evaluated the algorithm's performance by comparing survival estimates from identified models using the 12-month data cut to survival observed in the 48-month data cut. The Palmer algorithm offers a systematic procedure for model selection, encouraging detailed analyses and ensuring that crucial stages in the selection process are not overlooked. In our study, a range of models were identified as potentially appropriate for extrapolating survival, but only flexible parametric non-mixture cure models provided extrapolations that were plausible and accurately predicted subsequently observed survival. The algorithm could be improved with minor additions around the specification of hazard plots and setting out plausibility criteria. The Palmer algorithm provides a systematic framework for identifying suitable survival models, and for defining plausibility criteria for extrapolation validity. Using the algorithm ensures that model selection is based on explicit justification and evidence, which could reduce discordance in health technology appraisals.

Development, Validation, and Clinical Utility of Electronic Patient-Reported Outcome Measure-Enhanced Prediction Models for Overall Survival in Patients With Advanced Non-Small Cell Lung Cancer Receiving Immunotherapy.

Electronic patient-reported outcome measures (ePROMs) are increasingly collected routinely in clinical practice and may be prognostic for survival in adults with advanced non-small cell lung cancer (NSCLC) in addition to clinical data. This study developed ePROM-enhanced models for predicting 1-year overall survival in patients with advanced NSCLC at the start of immunotherapy. This is a single-center study using consecutive patients from a tertiary cancer hospital in England. Using Cox proportional hazards models, we developed one clinical factor-only model and three ePROM-enhanced models, each including one of the following factors: quality of life (as measured by EuroQoL five-dimension five-level utility score) and overall symptom burden and number of moderate-to-severe symptoms (as measured by patient-reported version of Common Terminology Criteria for Adverse Events). Predictive performance was evaluated and compared through bootstrapping internal validation, and clinical utility was determined via decision curve analysis. The clinical factor-only model contained age, histology, performance status, and neutrophile-to-lymphocyte ratio. While calibration was similar between the clinical factor-only and ePROM-enhanced models, the latter showed improved discrimination by 0.020 (95% CI, 0.011 to 0.024), 0.024 (95% CI, 0.016 to 0.031), and 0.024 (95% CI, 0.014 to 0.029) when enhanced with ePROMs on quality of life, overall symptom burden, and number of moderate-to-severe symptoms, respectively. If care decisions are to be made at risk thresholds between 25% and 75%, the ePROM-enhanced models led to higher net benefit than the clinical factor-only model and the default strategies of intervention for all and intervention for none. The ePROM-enhanced models outperformed the clinical factor-only model in predicting 1-year overall survival for patients with advanced NSCLC receiving immunotherapy and showed potential clinical utility for informing decisions in this population. Future studies should focus on validating the models in external data sets.

Lack of Hierarchical Survival Prognosis in AJCC Staging for Colon and Rectal Cancer—Implications for Future Summary Stage Classification

BackgroundCurrent staging for colorectal cancer utilizing the American Joint Committee on Cancer (AJCC) TNM framework groups disease based on extent and provides important prognostic information. Ideally, increasing summary stage should reflect worse prognosis (hierarchical logic). We evaluated survival as a function of stage within the 8th edition AJCC staging system for colorectal cancer. MethodsPatients with non-metastatic primary colorectal cancer diagnosed 2010-2016 were identified from the National Cancer Database. Survival curves were used to determine whether staging was hierarchical for colorectal cancer. Multivariable modeling was used to identify relative contributions of variables (z-score) to overall survival, and hazard ratio (HR)-based groupings were constructed. ResultsAmong 270,584 colon and 53,846 rectal cancer patients, AJCC summary staging was non-hierarchical (e.g. HR IIC=2.92, HR IIIA=0.85-1.31). Multivariable analysis demonstrated that high T category (T4a, T4b) confers the greatest mortality risk (colon: T4a HR 2.76, T4b HR 3.04; rectum: T4a HR 3.29, T4b HR 3.73), while high T category as well as high N category (colon: T4a z=66.9, T4b z=64.6, N2b z=55.7; rectum: T4b z=31.1, N2b z=25.1) contributed substantially to the survival model. Arranging T and N groupings by HR and subsequent organizing them using HR-based groupings resulted in hierarchical organization of these groupings. ConclusionsCurrent AJCC summary stage groups for patients with stage I-III colorectal cancer are non-hierarchical. High T category has a greater impact on survival than N category for early N disease, while high N category is more important for early T disease. This results in paradoxically better observed survival with some stage III cancer subgroups compared to stage II subgroups. An organizational framework based on HR groupings is hierarchical and provides more accurate prognostic information.MicroAbstract: Current staging for colorectal cancer utilizing the TNM framework groups disease based on extent and provides important prognostic information. Ideally, increasing summary stage should reflect worse prognosis (i.e. hierarchical staging groups). However, upon analyzing data from the National Cancer Database, current AJCC 8th edition summary stage groups for patients with stage I-III colorectal cancer were found to be non-hierarchical. This results in paradoxically better observed survival with some stage III cancer subgroups compared to stage II subgroups. An organizational framework based on HR groupings is hierarchical and provides more accurate prognostic information.

The influence of cardiac substructure dose on survival in a large lung cancer stereotactic radiotherapy cohort using a robust personalized contour analysis

Background/Purpose: Radiation-induced cardiac toxicity in lung cancer patients has received increased attention since RTOG 0617. However, large cohort studies with accurate cardiac substructure (CS) contours are lacking, limiting our understanding of the potential influence of individual CSs. Here, we analyse the correlation between CS dose and overall survival (OS) while accounting for deep learning (DL) contouring uncertainty, a/b uncertainty and different modelling approaches. Materials/Methods: This single institution, retrospective cohort study includes 730 patients (early-stage tumours (I or II). All treated: 2009–2019), who received stereotactic body radiotherapy (≥5 Gy per fraction). A DL model was trained on 70 manually contoured patients to create 12 cardio-vascular structures. Structures with median dice score above 0.8 and mean surface distance (MSD) <2 mm during testing, were further analysed. Patientspecific CS dose was used to find the correlation between CS dose and OS with elastic net and random survival forest models (with and without confounding clinical factors). The influence of delineation-induced dose uncertainty on OS was investigated by expanding/contracting the DL-created contours using the MSD ± 2 standard deviations. Results: Eight CS contours met the required performance level. The left atrium (LA) mean dose was significant for OS and an LA mean dose of 3.3 Gy (in EQD2) was found as a significant dose stratum. Conclusion: Explicitly accounting for input parameter uncertainty in lung cancer survival modelling was crucial in robustly identifying critical CS dose parameters. Using this robust methodology, LA mean dose was revealed as the most influential CS dose parameter.

Histotripsy of the Proximal Ureter and Renal Pelvis: Evaluation of Urothelial Injury in a Porcine Survival Model

Histotripsy of the Proximal Ureter and Renal Pelvis: Evaluation of Urothelial Injury in a Porcine Survival Model

Individualized Prediction for Risk of Recurrence in Stage I/II Melanoma Patients With Negative Sentinel Lymph Node.

Despite the favorable prognosis of AJCC stage I/II melanoma patients, up to 20%-30% will develop metastases. Our objective is to predict long-term risk (probability) of recurrence in early-stage melanoma patients. A Risk Score to predict long-term recurrence was developed using Cox regression based on 2668 patients. Five clinicopathological risk factors were included. The association of the Risk Score with the risk of recurrence was evaluated using parametric models (exponential, Weibull, and Gompertz models) and compared to the Cox model using the Akaike information criterion. The discrimination of the model was measured by time-dependent ROC analyses. A calibration curve was used to evaluate the agreement between predicted and observed recurrence probabilities. The bootstrap adjusted C-index was 0.76 (95% CI, 0.74-0.79) overall and 0.87 (0.83-0.90) and 0.82 (0.78-0.85) at one and two years, respectively, and then remained above 0.70 up to 20 years. The Gompertz model for prediction of survival from the Risk Score showed the best performance and displayed good agreement with the Kaplan-Meier curves. The calibration curve of the Gompertz model showed a good agreement between predicted and observed 2-, 5-, and 10-year risk of recurrence. Population-level analysis demonstrated a significant association of Risk Score with risk of recurrence, with 10-year risks of recurrence of 4.5%, 13.0%, and 33.7% in the first, second, and third tertiles, respectively. We developed a Risk Score to predict long-term risk of recurrence for early-stage melanoma patients. A Gompertz survival model fit to the Risk Score allows for individualized prediction of time-dependent recurrence risk.

Cross-Validatory Z-Residual for Diagnosing Shared Frailty Models

Accurate model performance assessment in survival analysis is imperative for robust predictions and informed decision-making. Traditional residual diagnostic tools like martingale and deviance residuals lack a well-characterized reference distribution for censored regression, making numerical statistical tests based on these residuals challenging. Recently, the introduction of Z-residuals for diagnosing survival models addresses this limitation. However, concerns arise from conventional methods that use the entire dataset for both model parameter estimation and residual assessment, which may cause optimistic biases. This article introduces cross-validatory Z-residuals as an innovative approach to address these limitations. Employing a cross-validation (CV) framework, the method systematically partitions the dataset into training and testing sets to reduce the optimistic bias. Our simulation studies demonstrate that, for goodness-of-fit tests and outlier detection, cross-validatory Z-residuals are significantly more powerful (e.g., power increased from 0.2 to 0.6). and more discriminative (e.g., AUC increased from 0.58 to 0.85) than Z-residuals without CV. We also compare the performance of Z-residuals with and without CV in identifying outliers in a real application that models the recurrence time of kidney infection patients. Our findings suggest that cross-validatory Z-residuals can identify outliers, which Z-residuals without CV fail to identify. The CV Z-residual is a more powerful tool than the No-CV Z-residual for checking survival models, particularly in goodness-of-fit tests and outlier detection. We have published a generic function, which is collected in an R package called Zresidual, for computing CV Z-residual for the output of the widely used survival R package.

Association between education level and disability progression in patients with multiple sclerosis in France.

Studies have reported an association between socioeconomic status and disability progression in multiple sclerosis (MS), but findings using the pre-MS individual socioeconomic status are missing. The objective was to investigate the association between education level and disability progression. All Observatoire Français de la Sclérose en Plaques (OFSEP) patients with MS clinical onset over 1960-2014, and aged ⩾25 years at MS onset were included. Education level was classified into four categories from low (primary/secondary school) to very high (master/doctoral degree). Time from MS onset to EDSS 4.0 was studied using flexible parametric survival models adjusted for age, period, and center, and stratified by phenotype (relapsing multiple sclerosis (RMS) and primary progressive multiple sclerosis (PPMS)) and sex. A total of 11,586 patients were included (women/men ratio = 2.5; age = 36.7 ± 8.6 years; follow-up duration 16.7 ± 9.3 years; 86.4% RMS). For women with RMS, the risk of reaching the outcome at 5 years was inversely associated with the education level (Hazard Ratio medium: 0.74 (0.63-0.87), high: 0.51 (0.43-0.62), very high: 0.39 (0.30-0.50) vs low). Results were similar for men. In PPMS, the risk was significantly different between the extreme groups (very high vs low) for women (0.45 (0.28-0.75)) and men (0.54 (0.32-0.91)), but no gradient was evident. Our study showed a strong association between education level and disability progression, regardless of sex and phenotype.

Validation of two predictive models for survival in anaplastic thyroid cancer (ATC)

BackgroundThe prognosis of patients with anaplastic thyroid cancer (ATC) remains dismal. A small portion of patients experience longterm survival and need to be identified before treatment allocation. Survival scores may guide clinicians making more informed decisions about treatment options and improve the understanding of patients’ prognosis. The aim of this study was to validate two prognostic scores using an independent dataset to analyze which prognostic index is superior in discriminating survival.MethodsThirty-four patients with histologically confirmed ATC diagnosed between January 2009 and December 2019 were consecutively treated at our department and evaluated. Next generation sequencing was performed in 7 (21%) patients, but no druggable mutation was found. 50% of all patients received surgery and 56% were treated with chemoradiotherapy. The median radiation dose in equivalent dose in 2 Gy fractions (EQD2) was 50 Gy (SD:21 Gy). The study compared the discrimination of the Sugitani Prognostic Index (SPI) and the Marchand-Crety Prognostic Score (MCPS) using concordance statistics, area under the receiver-operating characteristics curve (AUC), net reclassification index, and integrated discrimination improvement for 6-month survival.ResultsThe median survival of the entire cohort was 5 months (range: 1-133). The AUC for 6-month survival was 0.85 (95% confidence interval [CI]:0.72–0.97) for SPI and 0.69 (95% CI: 0.56–0.83) for MCPS (p < 0.0001). Using the net reclassification index (NRI), 73% of patients were correctly reclassified using SPI instead of MCPS for 6-month survival (p = 0.0237).ConclusionThe SPI was more accurate than the MCPS to determine patients’ life expectancies and should be recommended for clinical guidance and treatment allocation. In the last decade, comprehensive genetic profiling of actionable mutations in ATC has become vital to guide targeted therapy.

Predicting the time to get back to work using statistical models and machine learning approaches

BackgroundWhether machine learning approaches are superior to classical statistical models for survival analyses, especially in the case of lack of proportionality, is unknown.ObjectivesTo compare model performance and predictive accuracy of classic regressions and machine learning approaches using data from the Inspiring Families programme.MethodsThe Inspiring Families programme aims to support members of families with complex issues to return to work. We explored predictors of time to return to work with proportional hazards (Semi-Parametric Cox in Stata) and (Flexible Parametric Parmar-Royston in Stata) against the Survival penalised regression with Elastic Net penalty (scikit-survival), (conditional) Survival Forest algorithm (pySurvival), and (kernel) Survival Support Vector Machine (pySurvival).ResultsAt baseline we obtained data on 61 binary variables from all 3161 participants. No model appeared superior, with a low predictive power (concordance index between 0.51 and 0.61). The median time for finding the first job was about 254 days. The top five contributing variables were ‘family issues and additional barriers’, ‘restriction of hours’, ‘available CV’, ‘self-employment considered’ and ‘education’. The Harrell’s Concordance index was range from 0.60 (Cox model) to 0.71 (Random Survival Forest) suggesting a better fit for the machine learning approaches. However, the comparison for predicting median time on a selected scenario based showed only minor differences.ConclusionImplementing a series of survival models with and without proportional hazards background provides a useful insight as well as better interpretation of the coefficients affected by non-linearities. However, that better fit does not translate to substantially higher predictive power and accuracy from using machine learning approaches. Further tuning of the machine learning algorithms may provide improved results.

Blood methylation biomarkers are associated with diabetic kidney disease progression in type 1 diabetes.

DNA methylation differences are associated with kidney function and diabetic kidney disease (DKD), but prospective studies are scarce. Therefore, we aimed to study DNA methylation in a prospective setting in the Finnish Diabetic Nephropathy Study type 1 diabetes (T1D) cohort. We analysed baseline blood sample-derived DNA methylation (Illumina's EPIC array) of 403 individuals with normal albumin excretion rate (early progression group) and 373 individuals with severe albuminuria (late progression group) and followed-up their DKD progression defined as decrease in eGFR to <60 mL/min/1.73m 2 (early DKD progression group; median follow-up 13.1 years) or end-stage kidney disease (ESKD) (late DKD progression group; median follow-up 8.4 years). We conducted two epigenome-wide association studies (EWASs) on DKD progression and sought methylation quantitative trait loci (meQTLs) for the lead CpGs to estimate genetic contribution. Altogether, 14 methylation sites were associated with DKD progression ( P <9.4×10 -8 ). Methylation at cg01730944 near CDKN1C and at other CpGs associated with early DKD progression were not correlated with baseline eGFR, whereas late progression CpGs were strongly associated. Importantly, 13 of 14 CpGs could be linked to a gene showing differential expression in DKD or chronic kidney disease. Higher methylation at the lead CpG cg17944885, a frequent finding in eGFR EWASs, was associated with ESKD risk (HR [95% CI] = 2.15 [1.79, 2.58]). Additionally, we replicated meQTLs for cg17944885 and identified ten novel meQTL variants for other CpGs. Furthermore, survival models including the significant CpG sites showed increased predictive performance on top of clinical risk factors. Our EWAS on early DKD progression identified a podocyte-specific CDKN1C locus. EWAS on late progression proposed novel CpGs for ESKD risk and confirmed previously known sites for kidney function. Since DNA methylation signals could improve disease course prediction, a combination of blood-derived methylation sites could serve as a potential prognostic biomarker.

A comparative analysis of transformed indolent lymphomas and de novo diffuse large B-cell lymphoma: a population-based cohort study

Histologic transformation (HT) of indolent non-Hodgkin lymphoma (iNHL) to diffuse large B-cell lymphoma (DLBCL) carries a poor prognosis. Using the Surveillance, Epidemiology, and End Results-17 database, we conducted a population-based study of adult patients with transformed follicular lymphoma (t-FL), marginal zone lymphoma (t-MZL), lymphoplasmacytic lymphoma/Waldenström macroglobulinemia (t-LPL/WM), and de novo DLBCL. Primary outcome was relative survival (RS), and secondary outcomes included overall survival (OS) and lymphoma-specific survival (LSS). Outcomes were modeled using flexible parametric survival models, while multivariable modeling was used to compare RS, OS, and LSS. The incidence of HT was highest in splenic MZL (SMZL, 6.78%) and lowest in extranodal MZL (EMZL, 1.62%). Median follow-up times were similar for patients with de novo DLBCL and transformed indolent lymphomas. The 5-year RS and OS were longer in de novo DLBCL compared to all other transformed iNHL subtypes (68 versus 59%, respectively). For t-FL, early transformation (within 2 years of diagnosis, Hazard ratio [HR] = 1.34) and prior treatment (HR = 1.89) were associated with inferior survival. This association was not observed in other transformed lymphoma subtypes. This is the first comparative study to show that the outcomes of t-LPL/WM were inferior compared to de novo DLBCL and highlights the need to incorporate early experimental therapies in patients with t-FL with early transformation and receipt of prior chemotherapy.

Cost-effectiveness analysis of immune checkpoint inhibitors combined with targeted therapy and chemotherapy for HPV/HIV-related cervical cancer.

To systematically assess the cost-effectiveness of immune checkpoint inhibitors compared to the current standard therapy for human papillomavirus (HPV) and human immunodeficiency virus (HIV)-related cervical cancer. A partitioned survival model spanning a 20-year period was created to evaluate the cost and effectiveness of atezolizumab combined with bevacizumab and chemotherapy (ABC), and pembrolizumab combined with bevacizumab and chemotherapy (PBC) vs bevacizumab combined with chemotherapy (BC), based on clinical data from the BEATcc and KEYNOTE-826 trials. Royston-Parmar models were used for survival estimation. Costs and health state utilities were sourced from existing literature and publicly accessible databases. Cumulative costs (in US dollars), life years, quality-adjusted life years (QALYs), and incremental cost-effectiveness ratios (ICERs) were measured and compared. The evaluation was from the US healthcare payer perspective, with the willingness-to-pay threshold set at $100,000 to $150,000. Deterministic sensitivity analysis (DSA), probabilistic sensitivity analysis (PSA), and scenario analyses were conducted. The base-case analysis showed QALYs of 2.05 for BC, 3.18 for PBC, and 2.85 for ABC. PBC increased life-years by 1.76 and ABC by 1.18, with PBC showing the highest effectiveness. Total costs were $272,377 for BC, $715,472 for ABC, and $694,239 for PBC; severe adverse event (SAE) costs were $6189 for BC, $7603.31 for ABC, and $13,640 for PBC, indicating BC had the lowest SAE costs. The ICERs compared to BC were $372,151/QALY for PBC and $553,995/QALY for ABC. Given that the willingness-to-pay threshold was $100,000 to $150,000/QALY, both PBC and ABC exceed this threshold and were not considered cost-effective. BC had the lowest QALYs and the lowest costs, making it the least expensive option and the most cost-effective choice. DSA results indicated that drug prices and utility values were the main factors affecting cost-effectiveness. PSA confirmed BC as the most cost-effective option within a willingness-to-pay threshold of $0 to $300,000, primarily because it was the least costly. Immune checkpoint inhibitors significantly improve survival benefits for patients. However, their addition is costly and unlikely to be cost-effective for HPV/HIV-related metastatic cervical cancer.

Isatuximab-dexamethasone-pomalidomide combination effects on serum M protein and PFS in myeloma: Development of a joint model using phase I/II data.

This study aimed at leveraging data from phase I/II clinical trials to build a nonlinear joint model of serum M-protein kinetics and progression-free survival (PFS) accounting for the effects of isatuximab (Isa), pomalidomide (Pom), and dexamethasone (Dex) in patients with relapsed and/or refractory multiple myeloma. Serum M-protein levels and PFS data from 203 evaluable patients, included either in a phase I/II study (n = 173) or in a phase I study (n = 30), were used to build the model. First, we independently developed a longitudinal model and a PFS model. Then, we linked them in a nonlinear joint model by selecting the link function that best captured the association between serum M-protein kinetics and PFS. A Claret tumor growth-inhibition model accounting for the additive effects of Isa, with an Emax function, Pom, and Dex on serum M-protein elimination was selected to describe serum M-protein kinetics. PFS was best described with a log-logistic model and associations with baseline beta-2 microglobulin level, age, and coadministration of Dex were identified. The instantaneous change in serum M-protein level was found to be associated with PFS in the final joint model. Using model simulations, we retrospectively supported the Isa 10 mg/kg weekly for 4 weeks, then biweekly (QW/Q2W) dosing regimen of the ICARIA-MM phase III pivotal study, and validated it using the same phase III pivotal study data.