To handle the inflation of odds ratios in a retrospective study with a profile penalized log‐likelihood approach

SummaryThe increase in availability of species data sets means that approaches to species distribution modelling that incorporate multiple data sets are in greater demand. Recent methodological developments in this area have led to combined likelihood approaches, in which a log-likelihood comprised of the sum of the log-likelihood components of each data source is maximised. Often, these approaches make use of at least one presence-only data set and use the log-likelihood of an inhomogeneous Poisson point process model in the combined likelihood construction. While these advancements have been shown to improve predictive performance, they do not currently address challenges in presence-only modelling such as checking and correcting for violations of the independence assumption of a Poisson point process model or more general challenges in species distribution modelling such as overfitting.In this paper, we present an extension of the combined likelihood frame-work which accommodates alternative presence-only likelihoods in the presence of spatial dependence as well as lasso-type penalties to account for potential overfitting. We compare the proposed combined penalised likelihood approach to the standard combined likelihood approach via simulation and apply the method to modelling the distribution of the Eurasian lynx in the Jura Mountains in eastern France.The simulations show that the proposed combined penalised likelihood approach has better predictive performance than the standard approach when spatial dependence is present in the data. The lynx analysis shows that the predicted maps vary significantly between the model fitted with the proposed combined penalised approach accounting for spatial dependence and the model fitted with the standard combined likelihood.This work highlights the benefits of careful consideration of the presence-only components of the combined likelihood formulation, and allows greater flexibility and ability to accommodate real datasets.

Download Full-text

The Association Between Age and Prognosis in Patients Under 45 Years of Age With Anti-NMDA Receptor Encephalitis

Frontiers in Neurology ◽

10.3389/fneur.2020.612632 ◽

2020 ◽

Vol 11 ◽

Author(s):

Yueqian Sun ◽

Guoping Ren ◽

Jiechuan Ren ◽

Wei Shan ◽

Xiong Han ◽

...

Keyword(s):

Logistic Regression ◽

Retrospective Study ◽

Nmda Receptor ◽

Confidence Interval ◽

Modified Rankin Scale ◽

Odds Ratios ◽

Nmda Receptor Encephalitis ◽

Aspartate Receptor ◽

Multivariable Logistic Regression ◽

Neurological Prognosis

This study aims to evaluate the association between age and prognosis in patients with anti-N-methyl-D-aspartate receptor encephalitis (anti-NMDARE) under the age of 45 years. A retrospective study was conducted in patients younger than 45 years diagnosed as anti-NMDARE in four hospitals in China. Age at admission was divided into four categories: <15, 15–24, 25–34, 35–45 years. Neurological prognosis was evaluated using modified Rankin Scale. Adjusted multivariable logistic regression was used to analyze the association. The multivariable-adjusted odds ratios (95% confidence interval) of prognosis in anti-NMDARE across the categories of age were as follows: in males, 1.00 (reference), 4.76 (0.39–58.76), 13.50 (0.79–230.40), and 8.81 (0.36–218.39) (P for trend = 0.171); in females, 1.00 (reference), 7.27 (0.36–146.19), 20.08 (1.09–370.39), and 54.41 (1.60–1,849.10) (P for trend = 0.01). We concluded that the increasing age was associated with a poorer prognosis of anti-NMDARE in females but not males.

Download Full-text

Estimating Haplotype Effects on Dichotomous Outcome for Unphased Genotype Data Using a Weighted Penalized Log-Likelihood Approach

Human Heredity ◽

10.1159/000093476 ◽

2006 ◽

Vol 61 (2) ◽

pp. 104-110 ◽

Cited By ~ 13

Author(s):

Olga W. Souverein ◽

Aeilko H. Zwinderman ◽

Michael W.T. Tanck

Keyword(s):

Genotype Data ◽

Dichotomous Outcome ◽

Log Likelihood ◽

Likelihood Approach ◽

Unphased Genotype ◽

Unphased Genotype Data

Download Full-text

Outcomes of Dogs Presented for Cataract Evaluation: A Retrospective Study

Journal of the American Animal Hospital Association ◽

10.5326/0410235 ◽

2005 ◽

Vol 41 (4) ◽

pp. 235-240 ◽

Cited By ~ 21

Author(s):

Elizabeth A. Adkins ◽

Diane V.H. Hendrix

Keyword(s):

Retrospective Study ◽

Cataract Surgery ◽

Retinal Degeneration ◽

Common Reason ◽

Odds Ratios ◽

Cocker Spaniel ◽

University Of Tennessee ◽

Mixed Breed ◽

The University ◽

Purebred Dogs

Two hundred and forty-four dogs were evaluated for cataracts at the University of Tennessee from January 2001 to December 2002. Fifty-four canine breeds were affected. Odds ratios for cataracts were significantly higher for six purebred dogs (including the cocker spaniel, miniature schnauzer, toy poodle, Boston terrier, miniature poodle, and bichon frise) compared with mixed-breed dogs. One hundred fifty-nine dogs did not have cataract surgery. The most common reason for dogs not having surgery was retinal degeneration (n=66).

Download Full-text

Analysis of vasovagal syncope in the blood collection room in patients undergoing phlebotomy

Scientific Reports ◽

10.1038/s41598-020-74265-9 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Akira Yoshimoto ◽

Atsushi Yasumoto ◽

Yuko Kamiichi ◽

Haruna Shibayama ◽

Masaya Sato ◽

...

Keyword(s):

Risk Factors ◽

Retrospective Study ◽

Waiting Time ◽

Large Scale ◽

Vasovagal Syncope ◽

Blood Collection ◽

Odds Ratios ◽

Large Scale Study ◽

Blood Collection Tubes

Abstract Vasovagal syncope (VVS) is well-known to occur in patients undergoing phlebotomy, however, there have been no large-scale studies of the incidence of VVS in the blood collection room. The aim of our present retrospective study was to investigate the conditions of phlebotomy and determine the incidence/factors predisposing to the development of VVS. We investigated 677,956 phlebotomies performed in outpatients in the blood collection room, to explore factors predisposing to the development of VVS. Our analysis revealed an overall incidence of VVS of 0.004% and suggested that use of more than 5 blood collection tubes and a waiting time of more than 15 min were associated with a higher risk of VVS. The odds ratios of these factors were 8.10 (95% CI 3.76–17.50) and 3.69 (95% CI 0.87–15.60), respectively. This is the large-scale study to analyze factors of the development of VVS in the blood collection room, and according to our results, use of a large number of blood collection tubes and a prolonged waiting time for phlebotomy may be risk factors for the development of VVS.

Download Full-text