Improving tree survival prediction with forecast combination and disaggregation

2011 ◽  
Vol 41 (10) ◽  
pp. 1928-1935 ◽  
Author(s):  
Xiongqing Zhang ◽  
Yuancai Lei ◽  
Quang V. Cao ◽  
Xinmei Chen ◽  
Xianzhao Liu
Keyword(s):  
Tree Mortality ◽  
Survival Model ◽  
Pinus Tabulaeformis ◽  
Combination Method ◽  
Survival Models ◽  
Survival Prediction ◽  
Forecast Combination ◽  
Data Set ◽  
Tree Survival ◽  
Level Model

The tree mortality model plays an important role in simulating stand dynamic processes. Past work has shown that the disaggregation method was successful in improving tree survival prediction. This method was used in this study to forecast tree survival probability of Chinese pine (Pinus tabulaeformis Carrière) in Beijing. Outputs from the tree survival model were adjusted from either the stand-level model prediction or the combined estimator from the forecast combination method. Our results show that the disaggregation approach improved the performance of tree survival models. We also showed that stand-level prediction played a crucial role in refining outputs from a tree survival model, especially when it is a very simple model. Because the forecast combination method produced better stand-level prediction, we prefer the use of this method in conjunction with the disaggregation approach, even though the performance gain in using the forecast combination method shown for this data set was modest.

scholarly journals Claims-Based Approach to Predict Cause-Specific Survival in Men With Prostate Cancer

2019 ◽  
pp. 1-7 ◽  
Author(s):  
Paul Riviere ◽  
Christopher Tokeshi ◽  
Jiayi Hou ◽  
Vinit Nalawade ◽  
Reith Sarkar ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Claims Data ◽  
Prediction Models ◽  
Survival Model ◽  
Localized Prostate Cancer ◽  
Survival Models ◽  
Accurate Estimation ◽  
Survival Prediction ◽  
Data Set ◽  
Comorbidity Index

PURPOSE Treatment decisions about localized prostate cancer depend on accurate estimation of the patient’s life expectancy. Current cancer and noncancer survival models use a limited number of predefined variables, which could restrict their predictive capability. We explored a technique to create more comprehensive survival prediction models using insurance claims data from a large administrative data set. These data contain substantial information about medical diagnoses and procedures, and thus may provide a broader reflection of each patient’s health. METHODS We identified 57,011 Medicare beneficiaries with localized prostate cancer diagnosed between 2004 and 2009. We constructed separate cancer survival and noncancer survival prediction models using a training data set and assessed performance on a test data set. Potential model inputs included clinical and demographic covariates, and 8,971 distinct insurance claim codes describing comorbid diseases, procedures, surgeries, and diagnostic tests. We used a least absolute shrinkage and selection operator technique to identify predictive variables in the final survival models. Each model’s predictive capacity was compared with existing survival models with a metric of explained randomness (ρ2) ranging from 0 to 1, with 1 indicating an ideal prediction. RESULTS Our noncancer survival model included 143 covariates and had improved survival prediction (ρ2 = 0.60) compared with the Charlson comorbidity index (ρ2 = 0.26) and Elixhauser comorbidity index (ρ2 = 0.26). Our cancer-specific survival model included nine covariates, and had similar survival predictions (ρ2 = 0.71) to the Memorial Sloan Kettering prediction model (ρ2 = 0.68). CONCLUSION Survival prediction models using high-dimensional variable selection techniques applied to claims data show promise, particularly with noncancer survival prediction. After further validation, these analyses could inform clinical decisions for men with prostate cancer.

scholarly journals A method to derive a tree survival model from any existing stand survival model

2019 ◽  
Vol 49 (12) ◽  
pp. 1598-1603 ◽  
Author(s):  
Quang V. Cao
Keyword(s):  
Survival Data ◽  
Survival Model ◽  
Integrated System ◽  
Survival Models ◽  
Tree Level ◽  
Survival Prediction ◽  
Tree Model ◽  
Simple Method ◽  
Individual Tree ◽  
Tree Survival

This study addresses a situation in which a forest manager has been using a whole-stand model that seems to predict well for their stands and now wants to derive an individual-tree model from it to form an integrated system that can perform well at both stand and tree levels. A simple method was developed to derive tree survival models from three existing stand-level survival models. The derived tree survival models were based on the difference between the diameter of a given tree and the diameter at which tree and stand survival probabilities are equal. For stand survival prediction, each stand model performed less adequately than its derived tree model, and one of the derived tree survival models was the best overall. For tree survival prediction, the same derived tree model also performed best overall. Even though only three stand-level survival models were considered in this study, the method presented here should be applicable to any stand survival model. When no tree survival data were available, tree survival models derived from stand survival models ranked lowest in terms of performance but produced acceptable evaluation statistics for predicting tree-level survival.

scholarly journals An integrated system for modeling tree and stand survival

2017 ◽  
Vol 47 (10) ◽  
pp. 1405-1409 ◽  
Author(s):  
Quang V. Cao
Keyword(s):  
Survival Probability ◽  
Mathematical Structure ◽  
Survival Model ◽  
Integrated System ◽  
Survival Models ◽  
Tree Level ◽  
Individual Tree ◽  
Tree Survival ◽  
Different Levels ◽  
Model Approach

Traditionally, separate models have been used to predict the number of trees per unit area (stand-level survival) and the survival probability of an individual tree (tree-level survival) at a certain age. This study investigated the development of integrated systems in which survival models at different levels of resolution are related in a mathematical structure. Two approaches for modeling tree and stand survival were considered: deriving a stand-level survival model from a tree-level survival model (approach 1) and deriving a tree survival model from a stand survival model (approach 2). Both approaches rely on finding a tree diameter that yields a tree survival probability equal to the stand-level survival probability. The tree and stand survival models from either approach are conceptually compatible with each other but not numerically compatible. Parameters of these models can be estimated either sequentially or simultaneously. Results indicated that approach 2, with parameters estimated sequentially (first from the stand survival model and then from the derived tree survival model), performed best in predicting both tree- and stand-level survival. Although disaggregation did not help improve prediction of tree-level survival, this method can be used when numerical consistency between stand and tree survival is desired.

scholarly journals Multiple-Membership Survival Analysis and Its Applications in Organizational Behavior and Management Research

2019 ◽  
pp. 109442811987745
Author(s):  
Hans Tierens ◽  
Nicky Dries ◽  
Mike Smet ◽  
Luc Sels
Keyword(s):  
Organizational Behavior ◽  
Large Scale ◽  
Model Building ◽  
Real Life ◽  
Hierarchical Structures ◽  
Survival Model ◽  
Survival Models ◽  
Data Set ◽  
Potential Applications ◽  
Multiple Membership

Multilevel paradigms have permeated organizational research in recent years, greatly advancing our understanding of organizational behavior and management decisions. Despite the advancements made in multilevel modeling, taking into account complex hierarchical structures in data remains challenging. This is particularly the case for models used for predicting the occurrence and timing of events and decisions—often referred to as survival models. In this study, the authors construct a multilevel survival model that takes into account subjects being nested in multiple environments—known as a multiple-membership structure. Through this article, the authors provide a step-by-step guide to building a multiple-membership survival model, illustrating each step with an application on a real-life, large-scale, archival data set. Easy-to-use R code is provided for each model-building step. The article concludes with an illustration of potential applications of the model to answer alternative research questions in the organizational behavior and management fields.

A tree survival model with application to species of the Great Lakes region

1983 ◽  
Vol 13 (4) ◽  
pp. 601-608 ◽  
Author(s):  
R. G. Buchman ◽  
S. P. Pederson ◽  
N. R. Walters
Keyword(s):  
Great Lakes ◽  
Test Data ◽  
General Model ◽  
Survival Model ◽  
Tree Size ◽  
Great Lakes Region ◽  
Mathematical Form ◽  
Data Set ◽  
Tree Survival ◽  
Slow Growing

The survival model presented relates survival to tree size and vigor. Biological principles establish the general model form. The mathematical descriptor presented follows these biological principles with sufficient flexibility to portray the particular survival behavior of each species. Coefficients are presented for five major Great Lakes species. Although there were thousands of trees available for determining the coefficients for each species, each data set was deficient in large, slow-growing trees. Each set was augmented to guide the model in this range of size and growth. Applying the model to five species demonstrates the flexibility of its mathematical form. The model's performance is well established for the range of conditions underlying the test data.

scholarly journals Bayesian Computational Methods for Sampling from the Posterior Distribution of a Bivariate Survival Model, Based on AMH Copula in the Presence of Right-Censored Data

Entropy ◽  
2018 ◽  
Vol 20 (9) ◽  
pp. 642 ◽  
Author(s):  
Erlandson Saraiva ◽  
Adriano Suzuki ◽  
Luis Milan
Keyword(s):  
Computational Methods ◽  
Posterior Distribution ◽  
Estimation Procedure ◽  
Small Sample ◽  
Survival Model ◽  
Data Set ◽  
Right Censored Data ◽  
Slice Sampling ◽  
Bivariate Survival ◽  
Model Based

In this paper, we study the performance of Bayesian computational methods to estimate the parameters of a bivariate survival model based on the Ali–Mikhail–Haq copula with marginal distributions given by Weibull distributions. The estimation procedure was based on Monte Carlo Markov Chain (MCMC) algorithms. We present three version of the Metropolis–Hastings algorithm: Independent Metropolis–Hastings (IMH), Random Walk Metropolis (RWM) and Metropolis–Hastings with a natural-candidate generating density (MH). Since the creation of a good candidate generating density in IMH and RWM may be difficult, we also describe how to update a parameter of interest using the slice sampling (SS) method. A simulation study was carried out to compare the performances of the IMH, RWM and SS. A comparison was made using the sample root mean square error as an indicator of performance. Results obtained from the simulations show that the SS algorithm is an effective alternative to the IMH and RWM methods when simulating values from the posterior distribution, especially for small sample sizes. We also applied these methods to a real data set.

scholarly journals Joint Modeling of Longitudinal Change and Survival

GeroPsych ◽  
2011 ◽  
Vol 24 (4) ◽  
pp. 177-185 ◽  
Author(s):  
Graciela Muniz Terrera ◽  
Andrea M. Piccinin ◽  
Fiona Matthews ◽  
Scott M. Hofer
Keyword(s):  
Repeated Measures ◽  
Memory Performance ◽  
Joint Modeling ◽  
Disease Diagnosis ◽  
Careful Consideration ◽  
Survival Model ◽  
Longitudinal Change ◽  
Survival Models ◽  
Time Data ◽  
Aging Research

Joint longitudinal-survival models are useful when repeated measures and event time data are available and possibly associated. The application of this joint model in aging research is relatively rare, albeit particularly useful, when there is the potential for nonrandom dropout. In this article we illustrate the method and discuss some issues that may arise when fitting joint models of this type. Using prose recall scores from the Swedish OCTO-Twin Longitudinal Study of Aging, we fitted a joint longitudinal-survival model to investigate the association between risk of mortality and individual differences in rates of change in memory. A model describing change in memory scores as following an accelerating decline trajectory and a Weibull survival model was identified as the best fitting. This model adjusted for random effects representing individual variation in initial memory performance and change in rate of decline as linking terms between the longitudinal and survival models. Memory performance and change in rate of memory decline were significant predictors of proximity to death. Joint longitudinal-survival models permit researchers to gain a better understanding of the association between change functions and risk of particular events, such as disease diagnosis or death. Careful consideration of computational issues may be required because of the complexities of joint modeling methodologies.

scholarly journals Application of a WiFi/Geomagnetic Combined Positioning Method in a Single Access Point Environment

2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Hongbin Pan ◽  
Yang Xiang ◽  
Jian Xiong ◽  
Yifan Zhao ◽  
Ziwei Huang ◽  
...  
Keyword(s):  
Nearest Neighbor ◽  
Detection Method ◽  
Access Point ◽  
Combination Method ◽  
Data Set ◽  
Positioning Accuracy ◽  
Multipath Effects ◽  
Positioning Method ◽  
Fingerprint Database ◽  
Mismatch Rate

Because of the particularity of urban underground pipe corridor environment, the distribution of wireless access points is sparse. It causes great interference to a single WiFi positioning method or geomagnetic method. In order to meet the positioning needs of daily inspection staff, this paper proposes a WiFi/geomagnetic combined positioning method. In this combination method, firstly, the collected WiFi strength data was filtered by outlier detection method. Then, the filtered data set was used to construct the offline fingerprint database. In the following positioning operation, the classical k -nearest neighbor algorithm was firstly used for preliminary positioning. Then, a standard circle was constructed based on the points obtained by the algorithm and the actual coordinate points. The diameter of the standard circle was the error, and the geomagnetic data were used for more accurate positioning in this circle. The method reduced the WiFi mismatch rate caused by multipath effects and improved positioning accuracy. Finally, a positioning accuracy experiment was performed in a single AP distribution environment that simulates a pipe corridor environment. The results proves that the WiFi/geomagnetic combined positioning method proposed in this paper is superior to the traditional WiFi and geomagnetic positioning methods in terms of positioning accuracy.

scholarly journals Explainable Transformer-Based Neural Network forthe Prediction of Survival Outcomes in Non-SmallCell Lung Cancer (NSCLC)

2021 ◽  
Author(s):  
Gustavo Arango ◽  
Elly Kipkogei ◽  
Etai Jacob ◽  
Ioannis Kagiampakis ◽  
Arijit Patra
Keyword(s):  
Immune System ◽  
Precision Medicine ◽  
Cancer Patients ◽  
Patient Survival ◽  
Response To Therapy ◽  
Survival Models ◽  
Attractive Alternative ◽  
Survival Prediction ◽  
Molecular Features ◽  
Clinical Measurements

In this paper, we introduce the Clinical Transformer - a recasting of the widely used transformer architecture as a method for precision medicine to model relations between molecular and clinical measurements, and the survival of cancer patients. Although the emergence of immunotherapy offers a new hope for cancer patients with dramatic and durable responses having been reported, only a subset of patients demonstrate benefit. Such treatments do not directly target the tumor but recruit the patient immune system to fight the disease. Therefore, the response to therapy is more complicated to understand as it is affected by the patients physical condition, immune system fitness and the tumor. As in text, where the semantics of a word is dependent on the context of the sentence it belongs to, in immuno-therapy a biomarker may have limited meaning if measured independent of other clinical or molecular features. Hence, we hypothesize that the transformer-inspired model may potentially enable effective modelling of the semantics of different biomarkers with respect to patient survival time. Herein, we demonstrate that this approach can offer an attractive alternative to the survival models utilized incurrent practices as follows: (1) We formulate an embedding strategy applied to molecular and clinical data obtained from the patients. (2) We propose a customized objective function to predict patient survival. (3) We show the applicability of our proposed method to bioinformatics and precision medicine. Applying the clinical transformer to several immuno-oncology clinical studies, we demonstrate how the clinical transformer outperforms other linear and non-linear methods used in current practice for survival prediction. We also show that when initializing the weights of a domain-specific transformer by the weights of a cross-domain transformer, we further improve the predictions. Lastly, we show how the attention mechanism successfully captures some of the known biology behind these therapies

Sign in / Sign up

Export Citation Format

Share Document