Accelerated Failure Time Research Articles

Inter-cohort shifts in chronic disease, dementia, and mortality

ABSTRACT Previous work using U.S. data has identified generational shifts, reflected in inter-cohort changes, in the incidence and prevalence of diseases in older ages. This study extends previous findings to England by examining similar results in memory complaints, heart conditions, stroke, diabetes, lung disease, and cancer using data from the English Longitudinal Study of Ageing (ELSA). We fit Cox proportional hazard models to the first eight waves (2002–2016) of the ELSA sample (n = 18,528). In addition to exploring shifts in disease incidence we also examine shifts in disease mortality. Both general and sex-related differences are examined. Disease incidence has increased for later-born cohorts in England, replicating similar trends in the U.S. Not all diseases showed differences between men and women, but when differences were identified, women had lower risks for disease. In comparison to the U.S. sample, disease trends in England are more negative (i.e. accelerated failure times) for more recently born cohorts. These results showing increasing incidence of disease among the later-born cohorts suggest the possibility of increased disease burden in coming years.

Time to Cure and Predictive Factors Among Patients with Multi-Drug Resistance Tuberculosis in Puntland, Somalia: A Retrospective Cohort Study

Background: Multi-drug-resistant tuberculosis, also known as MDR-TB, is caused by bacteria that are resistant to the most effective first-line anti-tuberculosis medications, which are rifampicin and isoniazid. MDR-TB is an increasing global concern, and its spread has varying cure times for patients affected. Thus, this study was intended to investigate the median time to cure and identify predictive factors for patients with MDR-TB in Puntland, Somalia. Methods: A retrospective cohort study was carried out at the MDR-TB center in Galkayo, Puntland, Somalia between the years of July 2017 and August 2023. The study utilized data that were collected from the inquiry form and monitoring cards of a randomly selected sample of 130 patients over a 6-year period. The data were entered into Epi-Data version 4.3 and analyzed using R Programming version 4.4.0. Non-parametric methods were used to estimate the median time to cure for patients with MDR-TB. Semi-parametric and parametric models were employed to determine predictive factors that influence the time to cure for MDR-TB patients. The Akaike Information Criteria (AIC) and Bayesian Information Criteria (BIC) of different survival models were compared to select the model that offers the best fit. Results: Out of the total of MDR-TB patients, 109(83.85%) were cured and 21(16.15%) were censored during the follow-up period. The median time to cure from MDR-TB was found to be 619 days which is approximately 20 months. In accordance with the AIC and BIC, the Log-logistic accelerated failure time model was the best fit for the data as compared to the other AFT models. The result of the Log-logistic AFT model revealed that age, sex, disease site, and comorbidities significantly affect the time to cure for MDR-TB. According to this study, older age with MDR-TB patients, male MDR-TB patients, MDR-TB patients with comorbid conditions, and extrapulmonary MDR-TB patients had a longer time to cure than their reference categories. Conclusion: Based on the findings of the study, the median time to cure for patients with MDR-TB in Puntland was found to be 20 months. Sex, disease site, comorbidities and age were predictive factors of time to cure from MDR-TB.

Investigation of Freeway Incident Duration Using Classification and Regression Trees Based on Multisource Data

Targeted contingency measures have proven highly effective at reducing the duration and harm caused by incidents. This study utilized the Classification and Regression Trees (CART) data mining technique to predict and quantify the duration of incidents. To achieve this, multisensor data collected from the Hangzhou freeway in China spanning from 2019 to 2021 was utilized to construct a regression tree with eight levels and 14 leaf nodes. By extracting 14 rules from the tree and establishing contingency measures based on these rules, accurate incident assessment and effective implementation of post-incident emergency plans were achieved. In addition, to more accurately apply the research findings to actual incidents, the CART method was compared with XGBoost, Random Forest (RF), and AFT (accelerated failure time) models. The results indicated that the prediction accuracy of the CART model is better than the other three models. Furthermore, the CART method has strong interpretability. Interactions between explanatory variables, up to seven, are captured in the CART method, rather than merely analyzing the effect of individual variables on the incident duration, aligning more closely with actual incidents. This study has important practical implications for advancing the engineering application of machine learning methods and the analysis of sensor data.

CTNI-26. A PHASE II STUDY OF SACITUZUMAB GOVITECAN IN RECURRENT GLIOBLASTOMA

Abstract BACKGROUND Glioblastoma (GBM) is the most aggressive and common form of primary brain cancer. GBM expresses trophoblast cell-surface antigen 2 (Trop2) which correlates with proliferation rate, microvessel density, histological grade and clinical survival. Sacituzumab Govitecan (SG) is an antibody-drug conjugate targeting Trop2 with a chemotherapy payload, SN-38. This drug has been approved for triple-negative and hormone-receptor positive metastatic breast cancer. METHODS We conducted multi-center (UT Health San Antonio, Cleveland Clinic, Texas Oncology in Austin), open-label, single-arm phase 2 study using a 2-stage adaptive Bayesian design. Patients with recurrent GBM (rGBM), IDH wild-type, following standard-of-care chemoradiation, received SG (10mg/kg IV, days 1 and 8 every 21 days). Patients were assessed by RANO and CTCAE v5. The primary endpoint was PFS of patients on SG as compared to a historical control of lomustine. RESULTS As of interim analysis cutoff, 24 patients have been screened with 20 patients enrolled. The average age was 58.8 years. 65% of patients identified as male. 95% were Caucasian with 20% identifying as Spanish, Hispanic or Latino. Adverse events (AE) include lymphopenia (40%), neutropenia (40%), hypokalemia (35%), elevated alkaline phosphatase (30%), anemia (30%) with most AE being grade ≤ and no grade 5 observed. 4 patients had grade ≥3 neutropenia attributable to SG. 20% had stable disease as best response with the rest being progressive disease. The mean PFS and OS were 7.0 and 2.0 months, respectively. Of 19 evaluable samples, 63% had positive Trop2 expression (H-Score ≥100, mean 123.6±74 [0.6, 269.2]). A post-hoc analysis of OS log survival time vs H-Score (n=19) using an accelerated failure time model showed that survival correlated with H-Score (p=0.0361). CONCLUSIONS In the interim analysis of this study of patients with rGBM, Sacituzumab was found to be well-tolerated. Further study of those patients bearing tumors with elevated H-scores may be warranted.

Data‐driven estimation for multithreshold accelerated failure time model

AbstractThis article develops a novel estimation framework for the multithreshold accelerated failure time model, which has distinct linear forms within different subdomains. One major challenge is to determine the number of threshold effects. We first show the selection consistency of a modified Bayesian information criterion under mild conditions. It is useful sometimes but heavily depends on the penalization magnitude, which usually varies from the model configuration and data distribution. To address this issue, we leverage a cross‐validation criterion alongside an order‐preserved sample‐splitting scheme to yield a consistent estimation. The new criterion is completely data driven without additional parameters and thus robust to model setting and data distributions. The asymptotic properties for the parameter estimates are also carefully established. Additionally, we propose an efficient score‐type test to examine the existence of threshold effects. The new statistic is free of estimating any potential threshold effects and is thus suitable for multithreshold scenarios. Numerical experiments validate the reliable finite‐sample performance of our methodologies, which corroborates the theoretical results.

Accelerated failure time modelling in the analysis of type 2 diabetic patient data

Accelerated failure time modelling in the analysis of type 2 diabetic patient data

Predicting long-term survival among patients with HCC.

Prognosticating survival among patients with HCC and cirrhosis must account for both the tumor burden/stage, as well as the severity of the underlying liver disease. Although there are many staging systems used to guide therapy, they have not been widely adopted to predict patient-level survival after the diagnosis of HCC. We sought to develop a score to predict long-term survival among patients with early- to intermediate-stage HCC using purely objective criteria. Retrospective cohort study among patients with HCC confined to the liver, without major medical comorbidities within the Veterans Health Administration from 2014 to 2023. Tumor data were manually abstracted and combined with clinical and laboratory data to predict 5-year survival from HCC diagnosis using accelerated failure time models. The data were randomly split using a 75:25 ratio for training and validation. Model discrimination and calibration were assessed and compared to other HCC staging systems. The cohort included 1325 patients with confirmed HCC. A risk score using baseline clinical, laboratory, and HCC-related survival had excellent discrimination (integrated AUC: 0.71 in the validation set) and calibration (based on calibration plots and Brier scores). Models had superior performance to the BCLC and ALBI scores and similar performance to the combined BCLC-ALBI score. We developed a risk score using purely objective data to accurately predict long-term survival for patients with HCC. This score, if validated, can be used to prognosticate survival for patients with HCC, and, in the setting of liver transplantation, can be incorporated to consider the net survival benefit of liver transplantation versus other curative options.

Disparities in time to diagnosis of Radiographic Axial Spondyloarthritis.

Radiographic axial spondyloarthritis (r-axSpA) has a 7-year average diagnostic delay. While the impact of sex or gender on time to diagnosis has been evaluated, the role of social determinants of health remains understudied. We assessed whether time from initial clinical documentation of r-axSpA symptoms to r-axSpA diagnosis (diagnostic delay) varies based on sex, race, ethnicity, or the presence of social needs. We studied patients with r-axSpA from a tertiary center from 2000 to 2022. The cohort was built with the Observational Health Data Sciences and Informatics (OHDSI) network. For the primary analysis, we assessed the time from back pain/spinal pain to r-axSpA diagnosis and secondarily, the time to r-axSpA from any other r-axSpA -related condition. To estimate differences in diagnostic delay, we employed a parametric survival model, accelerated failure time. We included 404 patients (mean age 49, 37% female), with 25.5% identifying as Black, 31.1% as other or unknown race and 14.1% as Hispanic. Patients with a documented social need had a 21% increase in time from back pain to r-axSpA diagnosis (95% CI 0.93, 1.56). In patients with any r-axSpA related condition, time to diagnosis increased similarly by 21% (95% CI 0.92, 1.57). Considering an average time to diagnosis of 34 months, a social need increased time to diagnosis by 7 months. This study reveals a trend toward diagnostic delay in r-axSpA related to social need, sex, race, and ethnicity. Future studies should focus on referral strategies to enable prompt diagnosis and optimize care.

Core Concepts in Pharmacoepidemiology: Time-To-Event Analysis Approaches in Pharmacoepidemiology.

This article provides an overview of time-to-event (TTE) analysis in pharmacoepidemiology. The key concept of censoring is reviewed, including right-, left-, interval- and informative censoring. Simple descriptive statistics are explained, including the nonparametric estimation of the TTE distribution as per Kaplan-Meier method, as well as more complex TTE regression approaches, including the parametric Accelerated Failure Time (AFT) model and the semi-parametric Cox Proportional Hazards and Restricted Mean Survival Time (RMST) models. Additional approaches and various TTE model extensions are presented as well. Finally, causal inference for TTE outcomes is addressed. A thorough review of the available concepts and methods outlines the immense variety of available and useful TTE models. There may be underused TTE concepts and methods, which are highlighted to raise awareness for researchers who aim to apply the most appropriate TTE approach for their study. This paper constitutes a modern summary of TTE analysis concepts and methods. A curated list of references is provided.

Relative burden of cancer and noncancer mortality among long-term survivors of differentiated thyroid cancer in the US.

Limited information is available regarding the relative risks of cancer-specific mortality and noncancer-specific mortality among long-term survivors with differentiated thyroid cancer (DTC). In this retrospective study, nationwide data from the Surveillance, Epidemiology, and End Results database (1992-2020) were utilized. The Accelerated Failure Time Model was applied to calculate Survival Time Ratios (TR), with the primary focus on mortality resulting from DTC. The competing risks model was employed to investigate the relative risks of various outcomes in DTC patients with a survival duration of 5 years or more. In our cohort, 279 patients succumbed to DTC, while 748 died from other diseases. Notably, in DTC cohorts, noncancer-specific mortality rates were consistently higher than DTC-specific mortality rates across different age groups and genders. The risk of DTC and noncancer-specific mortality varied based on the TNM stage. With more advanced disease stages, the risk of DTC and other cancer-specific mortality gradually increased. The cumulative mortality from other cancer-specific causes was consistently the lowest. In long-term surviving DTC patients, noncancer-specific mortality outweighed DTC-specific mortality irrespective of age and gender. For stage I and II patients, increased attention should be directed toward noncancer-specific mortality in postoperative follow-ups. Conversely, for stage III and IV patients, greater consideration should be given to DTC-related causes of death. In addition, for stage III and IV DTC patients, the risk of death from other cancers was significantly higher than for stages I and II.

Likelihood-Based Inference of Log-Logistic Accelerated Hazards Regression Models for Cross Hazards Data

ABSTRACT The proportional hazards model and accelerated failure time model are two important classes for analyzing survival data. However, the two models cannot capture time-scaled effects such as crossing hazard or the gradual effect of treatment over time. For the purpose of this detection, accelerated hazards model has been studied. In this paper, we propose the use of log-logistic distribution for the baseline hazard function of the accelerated hazards model which allows for time-dependent group effect. In particular, the log-logistic distribution gives various forms (e.g. non-monotone) of hazard function and also an easy implementation for likelihood-based model fitting due to an explicit form of hazard and survival functions. The likelihood-based estimation procedures of the accelerated hazards models are derived. Our method is demonstrated with two practical data sets, via the procedures of systematic model checking.

Association of triglyceride-glucose index and its combination with obesity indicators in predicting the risk of aortic aneurysm and dissection.

The association between the triglyceride-glucose (TyG) index and its combination with obesity indictors in aortic aneurysm and dissection (AAD) remains unclear. We aimed to investigate the association between TyG and TyG-body mass index (TyG-BMI), TyG-waist circumference (TyG-WC), TyG-waist height ratio (TyG-WHtR) and AAD risk. This study included 387,483 baseline participants from the UK Biobank with complete data on TyG, TyG-BMI, TyG-WC and TyG-WHtR. Cox proportional hazard models evaluated the relationship between these four indicators and the risk of AAD occurrence. Restricted cubic spline (RCS) examined the non-linear relationship between these indicators and AAD risk, while receiver operating characteristic (ROC) curves assessed the predictive value of these four indicators for AAD risk. Over a median follow-up of 13.7 years, 3,041 AAD events were recorded. Multivariate Cox regression analysis indicated that for each standard deviation increase, the risk of AAD occurrence increased by 33% (HR: 1.33, 95%CI: 1.29-1.38), 25% (HR: 1.25, 95%CI: 1.21-1.29), 61% (HR: 1.61, 95%CI: 1.56-1.66) and 44% (HR: 1.44, 95%CI: 1.39-1.49) for TyG, TyG-BMI, TyG-WC and TyG-WHtR, respectively. RCS demonstrated a linear relationship between these indicators and AAD risk, with TyG-WC demonstrating the best performance in predicting AAD occurrence based on ROC curves. The present study, based on a large prospective cohort design, showed that higher TyG index and its combination with obesity indices were significantly associated with the risk of AAD. Moreover, AFT models further showed that elevation of these indicators significantly advanced the onset of AAD. In addition, RCS analyses demonstrated a linear association between these indicators and the risk of AAD, and the TyG-WC showed higher predictive ability for AAD. These findings emphasize the potential application of the TyG index and its combination with obesity indicators in the early identification of AAD.

A semiparametric accelerated failure time-based mixture cure tree

The mixture cure rate model (MCM) is the most widely used model for the analysis of survival data with a cured subgroup. In this context, the most common strategy to model the cure probability is to assume a generalized linear model with a known link function, such as the logit link function. However, the logit model can only capture simple effects of covariates on the cure probability. In this article, we propose a new MCM where the cure probability is modeled using a decision tree-based classifier and the survival distribution of the uncured is modeled using an accelerated failure time structure. To estimate the model parameters, we develop an expectation maximization algorithm. Our simulation study shows that the proposed model performs better in capturing nonlinear classification boundaries when compared to the logit-based MCM and the spline-based MCM. This results in more accurate and precise estimates of the cured probabilities, which in-turn results in improved predictive accuracy of cure. We further show that capturing nonlinear classification boundary also improves the estimation results corresponding to the survival distribution of the uncured subjects. Finally, we apply our proposed model and the EM algorithm to analyze an existing bone marrow transplant data.

Association between periodontitis with the all-cause and cause specific mortality among the population with hyperlipidemia

BackgroundTo explore the association between periodontitis and all-cause as well as cause-specific mortality rates in U.S. adults with hyperlipidemia.MethodsParticipants were extracted from NHANES during 1988–1994, 1999–2004 and 2009–2014 periods. To assess the association between moderate-to-severe periodontitis and mortality rates for both all-cause and cause-specific mortality, hazard ratios (HRs), time ratios (TRs), and their respective 95% confidence intervals (CIs) were calculated using Cox proportional hazards and Weibull accelerated failure time (AFT) models.ResultsOver a median follow-up duration of 11.83 years, 4,623 deaths of 16,848 participants were recorded. Multivariate Cox regression and AFT analyses showed moderate-to-severe periodontitis were associated with an increased risk of all-cause (HR: 1.31, 95% CI: 1.20–1.44, P < 0.001; TR: 0.85, 95% CI: 0.80–0.90, P < 0.001), cardiovascular disease (CVD)-related (HR: 1.36, 95% CI: 1.14–1.63, P = 0.001; TR: 0.83, 95% CI: 0.75–0.92, P < 0.001) and cancer-related mortality ( HR: 1.35, 95% CI: 1.12–1.63, P = 0.002; TR: 0.82, 95% CI: 0.72–0.93, P = 0.002). Meanwhile, there was a significant upward trend in the risk of mortality with increasing severity of periodontitis (P for trend < 0.001).ConclusionsOur study highlights the moderate-to-severe periodontitis is associated with an increased risk of all-cause, CVD-related and cancer-related mortality among U.S. adults with hyperlipidemia. And the mortality risk increasing alongside the severity of periodontitis.

Comparative Study of Cox Proportional Hazard and Accelerated Failure Time Models on Survival of Diabetes Mellitus and Hypertension Patients

Comparative analysis of survival models for hypertension and diabetics carried out in this study. The study compared the performance of Cox Proportional Hazard (CPH) and Accelerated Failure Time (AFT) models with and without random effects in analyzing hypertension and diabetes survival data obtained from General Hospital Keffi and General Hospital Nasarawa for the period of five years (2018-2022). Models evaluated include CPH, AFT (Exponential, Weibull, Log-Logistic) and their corresponding random effect counterparts. The Weibull AFT random effect model outperformed all other models in terms of goodness-of-fit, predictive accuracy and interpretability. This model accounted for individual heterogeneity and clustering effects, providing a more nuanced understanding of risk factors’ impact on survival rates. The Weibull AFT random effects model is the most suitable choice for analyzing hypertension and diabetes survival data, offering improved predictive power and insight into the complex relationships between risk factors and time-to-event outcomes. These findings have significant implications for healthcare professionals, policymakers, and researchers seeking to optimize survival analysis methodologies.

Incumbents’ marketing deterrence strategies and potential entrants’ time-to-entry: evidence from the US airline industry

Purpose The purpose of this study is to investigate how incumbent firms’ marketing deterrence strategies, price-cuts and quality improvement, influence potential entrants’ (PEs) entry timing into incumbents’ markets and examine the moderating role of incumbents’ market-level resources and capabilities (R&amp;Cs). Design/methodology/approach To test the hypotheses, an accelerated failure time model is applied to a rich data set of entry threats between 1997 and 2019 in the US airline industry. Findings The findings show that while quality improvements delay PEs’ entry, price-cuts expedite it. Furthermore, PEs are more likely to be deterred by price-cuts when incumbents possess high market-level R&amp;Cs. However, such R&amp;Cs do not moderate the link between incumbents’ quality improvement and PEs’ entry timing. Research limitations/implications Market entry in this research is conceptualized and defined as a large resource deployment into a market and operationalized as a binary variable. However, PEs might rather choose a minor resource deployment instead to establish a foothold in new markets. It would be fruitful for future research to examine various levels of participation in a new market and examine how the incumbents’ marketing deterrence strategies affect PEs’ entry timing. Doing so would provide us with a deeper understanding of the difference between actual/full market entry and micro/minor market entry. Practical implications This research examines the impact of incumbents’ marketing deterrence strategies in a contingency framework and highlights the crucial role of R&amp;Cs in implementing such deterrence strategies. Doing so provides actionable insights to managers who craft strategies to protect their markets against PEs. Originality/value Previous research illustrates that incumbent firms commonly respond to competitors’ entry threats by cutting prices and improving quality. While antecedents of these deterrence strategies have been extensively investigated, the consequences have yet to be empirically examined.

Modelling of the time to death of breast cancer patients at Hiwot Fana Specialized University Hospital

Breast cancer is the most common cause of cancer death and is a frequently diagnosed cancer among women worldwide. It is becoming a challenging health condition in Ethiopia with a high rate of morbidity and mortality. The main aim of this study was to model the time to death in breast cancer patients at Hiwot Fana Specialized University Hospital. A retrospective cohort study was carried out from April 1st, 2020, to April 1st, 2023, and 296 women were included in the study. We used nonparametric methods and Bayesian accelerated failure time models (with Laplace approximation) to identify risk factors and choose a model fitting breast cancer patient data. Model comparison was performed using the marginal likelihood, deviance information criterion and Watanabe Akaike information criterion. From the total of 296 patients in the study, 56 (18.9%) died. The estimated median survival time was 33 months. The log-rank test showed that age group, stage, alcohol consumption, smoking habit, and comorbidity were potential risk factors associated with the time to death in breast cancer patients at the 5% level of significance. The Bayesian Weibull accelerated failure time model was found to be the best fitted model for predicting the survival time of patients with minimum DIC (520.39) and WAIC (521.59) values. The final Bayesian Weibull AFT model with the integrated nested Laplace approximation estimation technique revealed that age group, stage, alcohol consumption, smoking habit, and comorbidity were significantly associated with the time to death in breast cancer patients. Individuals older than 65 years, with stage IV disease, drinking alcohol, smoking cigarettes and having comorbidities had shortened survival times in patients with breast cancer. Hence, Hiwot Fana Specialized University Hospital and related bodies should work on awareness creation to reduce smoking habits and alcohol use as well as give due attention to elderly and stage IV breast cancer patients during intervention.

Geographically weighted accelerated failure time model for spatial survival data: application to ovarian cancer survival data in New Jersey

BackgroundIn large multiregional cohort studies, survival data is often collected at small geographical levels (such as counties) and aggregated at larger levels, leading to correlated patterns that are associated with location. Traditional studies typically analyze such data globally or locally by region, often neglecting the spatial information inherent in the data, which can introduce bias in effect estimates and potentially reduce statistical power.MethodWe propose a Geographically Weighted Accelerated Failure Time Model for spatial survival data to investigate spatial heterogeneity. We establish a weighting scheme and bandwidth selection based on quasi-likelihood information criteria. Theoretical properties of the proposed estimators are thoroughly examined. To demonstrate the efficacy of the model in various scenarios, we conduct a simulation study with different sample sizes and adherence to the proportional hazards assumption or not. Additionally, we apply the proposed method to analyze ovarian cancer survival data from the Surveillance, Epidemiology, and End Results cancer registry in the state of New Jersey.ResultsOur simulation results indicate that the proposed model exhibits superior performance in terms of four measurements compared to existing methods, including the geographically weighted Cox model, when the proportional hazards assumption is violated. Furthermore, in scenarios where the sample size per location is 20-25, the simulation data failed to fit the local model, while our proposed model still demonstrates satisfactory performance. In the empirical study, we identify clear spatial variations in the effects of all three covariates.ConclusionOur proposed model offers a novel approach to exploring spatial heterogeneity of survival data compared to global and local models, providing an alternative to geographically weighted Cox regression when the proportional hazards assumption is not met. It addresses the issue of certain counties' survival data being unable to fit the model due to limited samples, particularly in the context of rare diseases.

Deep Neural Network-Based Accelerated Failure Time Models Using Rank Loss.

An accelerated failure time (AFT) model assumes a log-linear relationship between failure times and a set of covariates. In contrast to other popular survival models that work on hazard functions, the effects of covariates are directly on failure times, the interpretation of which is intuitive. The semiparametric AFT model that does not specify the error distribution is sufficiently flexible and robust to depart from the distributional assumption. Owing to its desirable features, this class of model has been considered a promising alternative to the popular Cox model in the analysis of censored failure time data. However, in these AFT models, a linear predictor for the mean is typically assumed. Little research has addressed the non-linearity of predictors when modeling the mean. Deep neural networks (DNNs) have received much attention over the past few decades and have achieved remarkable success in a variety of fields. DNNs have a number of notable advantages and have been shown to be particularly useful in addressing non-linearity. Here, we propose applying a DNN to fit AFT models using Gehan-type loss combined with a sub-sampling technique. Finite sample properties of the proposed DNN and rank-based AFT model (DeepR-AFT) were investigated via an extensive simulation study. The DeepR-AFT model showed superior performance over its parametric and semiparametric counterparts when the predictor was nonlinear. For linear predictors, DeepR-AFT performed better when the dimensions of the covariates were large. The superior performance of the proposed DeepR-AFT was demonstrated using three real datasets.

Determinants of Outcomes for Acute Myeloid Leukemia Patients Treated in a Community-Based Specialized Versus Non-Specialized Hospital Setting.

The treatment setting influences acute myeloid leukemia (AML) outcomes. Most cancer patients receive care in the community, yet few studies have evaluated the effectiveness of clinical programs outside of academic or National Cancer Institute (NCI)-designated cancer centers. This was a multi-level, case-controlled study of real-world outcomes for initial AML treatment in a community-based network for 1,391 patients with AML between 2011 and 2018. We benchmarked survival within our network against the Surveillance, Epidemiology, and End Results (SEER) database. Coarsened exact matching was performed against 17,186 chemotherapy-treated patients in the SEER database. Cox proportional and accelerated failure time multivariable modeling were performed to identify patient, disease, therapy and center characteristics associated with the risk of AML mortality. Within the network, 799 patients were treated at six specialized blood cancer centers and 592 at 63 other hospitals. Patients receiving high-intensity induction at specialized centers had improved median survivals of 31 months versus 18 months [P<0.001] at non-specialized centers. Median survivals were 13 for non-specialized centers versus 10 months for SEER [P<0.001], and 18 for the entire network versus 10 months for SEER [P<0.001]. Multivariable modeling showed significant impacts from age (HR = 1.025), high-intensity induction therapy (HR= .695), diagnosis year (HR= .937), neighborhood income (HR = .997; P<0.01), higher acuity (HR = 1.002) and Charlson comorbidity score (HR = 1.117). AML treatment may be effectively delivered in the community hospital setting, with specialized centers producing better outcomes for higher intensity treatments.