A survival tree method for the analysis of discrete event times in clinical and epidemiological studies

2015 ◽  
Vol 35 (5) ◽  
pp. 734-751 ◽  
Author(s):  
Matthias Schmid ◽  
Helmut Küchenhoff ◽  
Achim Hoerauf ◽  
Gerhard Tutz
Keyword(s):  
Discrete Event ◽  
Epidemiological Studies ◽  
Event Times ◽  
Survival Tree ◽  
Tree Method

Risk Factors for Recurrence After Lung Cancer Resection as Estimated Using the Survival Tree Method

CHEST Journal ◽  
2013 ◽  
Vol 144 (4) ◽  
pp. 1238-1244 ◽  
Author(s):  
Shigeki Sawada ◽  
Natsumi Yamashita ◽  
Hiroshi Suehisa ◽  
Motohiro Yamashita
Keyword(s):  
Risk Factors ◽  
Lung Cancer ◽  
Cancer Resection ◽  
Risk Factors For Recurrence ◽  
Survival Tree ◽  
Tree Method

scholarly journals Multiscale representation of simulated time

SIMULATION ◽  
2017 ◽  
Vol 94 (6) ◽  
pp. 519-558 ◽  
Author(s):  
Rhys Goldstein ◽  
Azam Khan ◽  
Olivier Dalle ◽  
Gabriel Wainer
Keyword(s):  
Multiscale Modeling ◽  
Discrete Event ◽  
Limited Range ◽  
System Specification ◽  
Data Types ◽  
Rounding Errors ◽  
Time Representation ◽  
Event Simulation ◽  
Precision Level ◽  
Event Times

To better support multiscale modeling and simulation, we present a multiscale time representation consisting of data types, data structures, and algorithms that collectively support the recording of past events and scheduling of future events in a discrete event simulation. Our approach addresses the drawbacks of conventional time representations: limited range in the case of 32- or 64-bit fixed-point time values; problematic rounding errors in the case of floating-point numbers; and the lack of a universally acceptable precision level in the case of brute force approaches. The proposed representation provides both extensive range and fine resolution in the timing of events, yet it stores and manipulates the majority of event times as standard 64-bit numbers. When adopted for simulation purposes, the representation allows a domain expert to choose a precision level for his/her model. This time precision is honored by the simulator even when the model is integrated with other models of vastly different time scales. Making use of C++11 programming language features and the Discrete Event System Specification formalism, we implemented a simulator to test the time representation and inform a discussion on its implications for collaborative multiscale modeling efforts.

scholarly journals An ensemble method for interval-censored time-to-event data

Biostatistics ◽  
2019 ◽  
Author(s):  
Weichi Yao ◽  
Halina Frydman ◽  
Jeffrey S Simonoff
Keyword(s):  
Censored Data ◽  
Cox Model ◽  
Conditional Inference ◽  
Interval Censored Data ◽  
Time To Event ◽  
Data Set ◽  
Interval Censored ◽  
Survival Tree ◽  
True Relationship ◽  
Tree Method

Summary Interval-censored data analysis is important in biomedical statistics for any type of time-to-event response where the time of response is not known exactly, but rather only known to occur between two assessment times. Many clinical trials and longitudinal studies generate interval-censored data; one common example occurs in medical studies that entail periodic follow-up. In this article, we propose a survival forest method for interval-censored data based on the conditional inference framework. We describe how this framework can be adapted to the situation of interval-censored data. We show that the tuning parameters have a non-negligible effect on the survival forest performance and guidance is provided on how to tune the parameters in a data-dependent way to improve the overall performance of the method. Using Monte Carlo simulations, we find that the proposed survival forest is at least as effective as a survival tree method when the underlying model has a tree structure, performs similarly to an interval-censored Cox proportional hazards model fit when the true relationship is linear, and outperforms the survival tree method and Cox model when the true relationship is nonlinear. We illustrate the application of the method on a tooth emergence data set.

Suicidal Behavior in German Adolescents

2015 ◽  
Vol 43 (1) ◽  
pp. 39-45 ◽  
Author(s):  
Joana Straub ◽  
Ferdinand Keller ◽  
Nina Sproeber ◽  
Michael G. Koelch ◽  
Paul L. Plener
Keyword(s):  
Suicidal Behavior ◽  
Suicide Attempts ◽  
Depression Scale ◽  
Epidemiological Studies ◽  
Present Sample ◽  
Manic Symptoms ◽  
Symptoms Of Depression ◽  
Adolescent Sample ◽  
History Of ◽  
Sum Scores

Objective: Research in adults has identified an association between bipolar disorder and suicidal behavior. This relationship, however, has been insufficiently investigated in adolescents to date. Methods: 1,117 adolescents from 13 German schools (mean age = 14.83, SD = .63; 52.7% females) completed an extended German version of the Center for Epidemiological Studies Depression Scale (CES-D), which assesses depressive and manic symptoms during the last week, as well as the Self-Harm Behavior Questionnaire (SHBQ) for the assessment of lifetime suicidal behavior. Results: In the present sample 39.4% of the girls and 23.1% of the boys reported lifetime suicidal thoughts and 7.1% of the girls as well as 3.9% of the boys a lifetime history of suicide attempts. 18.7% of the adolescent sample revealed elevated symptoms of depression and 9% elevated levels of mania symptoms. Elevated sum scores of depression and mania were associated with a higher number of suicidal ideations and suicide attempts. A block-wise regression analysis revealed that sum scores of depression and mania predicted suicidal ideations best. Concerning suicide attempts, the best predictors were age as well as depression and mania sum scores. Conclusions: Suicidal behavior was reported more often when adolescents demonstrate symptoms of mania as well as symptoms of depression than when they demonstrate only depressive symptoms. The presence of bipolar symptoms in adolescents should alert clinicians to the heightened possibility of suicidal behavior.

Zur Anwendung der CES-D bei älteren Menschen: Dimensionsstruktur und Meßartefakte

Diagnostica ◽  
2000 ◽  
Vol 46 (1) ◽  
pp. 29-37 ◽  
Author(s):  
Herbert Matschinger ◽  
Astrid Schork ◽  
Steffi G. Riedel-Heller ◽  
Matthias C. Angermeyer
Keyword(s):  
Mental State ◽  
Latent Class ◽  
Mini Mental State Examination ◽  
Depression Scale ◽  
Epidemiological Studies ◽  
Partial Credit ◽  
Examination Score ◽  
State Examination

Zusammenfassung. Beim Einsatz der Center for Epidemiological Studies Depression Scale (CES-D) stellt sich das Problem der Dimensionalität des Instruments, dessen Lösung durch die Konfundierung eines Teilkonstruktes (“Wohlbefinden”) mit Besonderheiten der Itemformulierung Schwierigkeiten bereitet, da Antwortartefakte zu erwarten sind. Dimensionsstruktur und Eignung der CES-D zur Erfassung der Depression bei älteren Menschen wurden an einer Stichprobe von 663 über 75-jährigen Teilnehmern der “Leipziger Langzeitstudie in der Altenbevölkerung” untersucht. Da sich die Annahme der Gültigkeit eines partial-credit-Rasch-Modells sowohl für die Gesamtstichprobe als auch für eine Teilpopulation als zu restriktiv erwies, wurde ein 3- bzw. 4-Klassen-latent-class-Modell für geordnete Kategorien berechnet und die 4-Klassen-Lösung als den Daten angemessen interpretiert: Drei Klassen zeigten sich im Sinne des Konstrukts “Depression” geordnet, eine Klasse enthielt jene Respondenten, deren Antwortmuster auf ein Antwortartefakt hinwiesen. In dieser Befragtenklasse wird der Depressionsgrad offensichtlich überschätzt. Zusammenhänge mit Alter und Mini-Mental-State-Examination-Score werden dargestellt. Nach unseren Ergebnissen muß die CES-D in einer Altenbevölkerung mit Vorsicht eingesetzt werden, der Summenscore sollte nicht verwendet werden.

Epidemiological Trends in Attempted Suicide in Adolescents and Young Adults Between 1996 and 2004

Crisis ◽  
2009 ◽  
Vol 30 (3) ◽  
pp. 115-119 ◽  
Author(s):  
Stephanie De Munck ◽  
Gwendolyn Portzky ◽  
Kees Van Heeringen
Keyword(s):  
Young Adults ◽  
Attempted Suicide ◽  
Suicide Attempts ◽  
Epidemiological Studies ◽  
Adolescents And Young Adults ◽  
University Hospital ◽  
International Studies ◽  
Suicide Attempters ◽  
Increased Risk ◽  
Epidemiological Trends

Background: Notwithstanding the epidemiological studies indicating an increased risk of attempted suicide among adolescents and young adults, there is a scarcity of international studies that examine long-term epidemiological trends in rates and characteristics of this vulnerable group. Aims: This article describes the results of a 9-year monitoring study of suicide attempts in adolescents and young adults referred to the Accident and Emergency Department of the Gent University Hospital (Belgium). Methods: Between January 1996 and December 2004, trends, sociodemographic, and methodrelated characteristics of suicide attempts were assessed by a psychiatrist on data sheets. Results: Attempted suicide rates declined from 1996 to 2001 and then rose until 2004, but did not exceed previous rates. During the 9 years of monitoring, there was a preponderance of female suicide attempters, except for 1997. Rates of attempts and of fatal suicide were negatively correlated. Significantly more males than females deliberately injured themselves. Younger attempters, especially females, significantly more often poisoned themselves with analgesics. In nearly one in five attempts, alcohol was used in combination with other methods, and alcohol intake was more commonly observed in older suicide attempters. Nearly half of the adolescents were identified as repeaters. Conclusions: The results of this study warrant further monitoring of trends and characteristics of young suicide attempters.

Family-, Media-, and School-Related Risk Factors of Video Game Addiction

2013 ◽  
Vol 25 (3) ◽  
pp. 118-128 ◽  
Author(s):  
Florian Rehbein ◽  
Dirk Baier
Keyword(s):  
Risk Factors ◽  
Video Game ◽  
Age Groups ◽  
Well Being ◽  
Epidemiological Studies ◽  
Prevention Measures ◽  
School Life ◽  
Video Game Addiction ◽  
Effective Prevention ◽  
Game Addiction

In recent years, a variety of epidemiological studies have provided empirical data on the prevalence of video game addiction (GA) in different age groups. However, few studies investigated the causes of GA and could explain why video game playing as a widespread phenomenon leads to a comparatively small percentage of addicted players. Additionally, the existing longitudinal studies mainly consider psychological trait variables and neglect the possible explanatory value of predictors in socialization regarding media availability, media use, and family and everyday school life. In this paper, the results of a two-wave longitudinal study comprising a sample of students from Grades 4 to 9 (N = 406) are presented. The data show that 15-year-old video game addicts had already exhibited a number of specific risk factors at the age of 10. Students from single-parent families seem to be particularly at risk, as are students with low experienced school well-being and with a weaker social integration in class. The data also indicate that problematic use of video games in childhood increases the risk of GA in adolescence. Male students are especially vulnerable for developing GA. The results of this study are an important contribution to understanding risk factors for GA in adolescents, thereby laying the groundwork for effective prevention measures.

Sign in / Sign up

Export Citation Format

Share Document