New Risk Scoring System for Predicting 3-month Mortality after Acute Exacerbation of Idiopathic Pulmonary Fibrosis

Acute exacerbation of idiopathic pulmonary fibrosis (AE-IPF) is often fatal. A straightforward staging system for AE-IPF would improve prognostication, guide patient management, and facilitate research. The aim of study is to develop a multidimensional prognostic AE-IPF staging system that uses commonly measured clinical variables. This retrospective study analyzed data from 353 consecutive patients with IPF admitted to our hospital during the period from January 2008 through January 2018. Multivariate analysis of information from a database of 103 recorded AE-IPF cases was used to identify factors associated with 3-month mortality. A clinical prediction model for AE-IPF was developed by using these retrospective data. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic performance of this model. Logistic regression analysis showed that PaO2/FiO2 ratio, diffuse HRCT pattern, and serum C-reactive protein (CRP) were significantly associated with 3-month mortality; thus, PaO2/FiO2 ratio < 250 (P), CRP ≥ 5.5 (C), and diffuse HRCT pattern (radiological) (R) were included in the final model. A model using continuous predictors and a simple point-scoring system (PCR index) was developed. For the PCR index, the area under the ROC curve was 0.7686 (P < 0.0001). The sensitivity of the scoring system was 78.6% and specificity was 67.8%. The PCR index identified four severity grades (0, 1, 2, and 3), which were associated with a 3-month mortality of 7.7%, 29.4%, 54.8%, and 80%, respectively. The present PCR models using commonly measured clinical and radiologic variables predicted 3-month mortality in patients with AE-IPF.

Understanding the Effect of Categorization of a Continuous Predictor with Application to Neuro Oncology

Many Neuro-Oncology studies commonly assess the association between a prognostic factor (predictor) and disease or outcome, such as the association between age and glioma. Predictors can be continuous (e.g., age) or categorical (e.g., race/ethnicity). Effects of categorical predictors are frequently easier to visualize and interpret than effects of continuous variables. This makes it an attractive, and seemingly justifiable, option to subdivide the continuous predictors into categories (e.g., age&lt; 50 years vs. age ≥50 years). However, this approach results in loss of information (and power) compared to the continuous version. This review outlines the use cases for continuous and categorized predictors and provides tips and pitfalls for interpretation of these approaches.

A Machine Learning Approach for Forecasting US Presidential Election

In this paper, we develop and compare two models for forecasting the 2020 U.S. presidential election using multiple linear regressions (MLR) and the Machine Learning method of Extreme Gradient Boosting (xgboost). We predict each state’s Republican vote share using seven continuous predictors from 1976-2016, as well as dummy columns for each state. After computing 95% confidence intervals for each prediction, we determine the candidates’ electoral college probabilities. The xgboost appears to be a very strong predictor, accounting for 98.6% of the variance with a 3.34% root mean square error (RMSE), whereas the MLR only accounts for 71.8% of the variance and leaves an RMSE of 6.35%. We observe that 1) both models predict a Democratic electoral college landslide in the 2020 elections, 2) Georgia, Iowa, Florida, North Carolina, and Ohio are crucial for the Republicans to win, and 3) Extreme Gradient Boosting is an attractive alternative to MLR in election forecasting.

Factors Associated With Postoperative Confusion and Prolonged Hospital Stay Following Deep Brain Stimulation Surgery for Parkinson Disease

BACKGROUND Several patient and disease characteristics are thought to influence DBS outcomes; however, most previous studies have focused on long-term outcomes with only a few addressing immediate postoperative course. OBJECTIVE To evaluate predictors of immediate outcomes (postoperative confusion and length of postoperative hospitalization) following deep brain stimulation surgery (DBS) in Parkinson disease (PD) patients. METHODS We conducted a retrospective study of PD patients who underwent DBS at our institution from 2006 to 2011. We computed the proportion of patients with postoperative confusion and those with postoperative hospitalization longer than 2 d. To look for associations, Fisher's exact tests were used for categorical predictors and logistic regression for continuous predictors. RESULTS We identified 130 patients [71% male, mean age: 63 ± 9.1, mean PD duration: 10.7 ± 5.1]. There were 7 cases of postoperative confusion and 19 of prolonged postoperative hospitalization. Of the 48 patients with tremors, none had postoperative confusion, whereas 10.1% of patients without tremors had confusion (P = .0425). Also, 10.2% of patients with preoperative falls/balance-dysfunction had postoperative confusion, whereas only 1.6% of patients without falls/balance-dysfunction had postoperative confusion (P = .0575). For every one-unit increase in score on the preoperative on-UPDRS III/MDS-UPDRS III score, the odds of having postoperative confusion increased by 10% (P = .0420). The following factors were noninfluential: age, disease duration, dyskinesia, gait freezing, preoperative levodopa-equivalent dose, number of intraoperative microelectrode passes, and laterality/side of surgery. CONCLUSION Absence of tremors and higher preoperative UPDRS III predicted postoperative confusion after DBS in PD patients. Clinicians’ awareness of these predictors can guide their decision making regarding patient selection and surgical planning.

A reformulation of the selection ratio shed light on resource selection functions and leads to a unified framework for habitat selection studies

The selection ratio (SR), i.e. the ratio of proportional use of a habitat over proportional availability of this habitat, has for long been the standard metric of habitat selection analyses. It is easy to compute and directly estimates disproportionate use. Its apparent restriction to habitat selection analyses using categorical predictors led to the development of the resource selection functions (RSF) approach, which has now become the norm.The RSF approach has however led to debates and confusion. For instance, what functional form can be used remains debated, and the concept of relative probability of selection is often misunderstood.I propose a reformulation of the SR demonstrating that it can be estimated in a regression context, and thus even with continuous predictors. This reformulation suggests that RSF can be seen as an intermediate step in the calculation of SR. This reformulation also clarifies some long-standing debates about RSF and data-selection/fitting practices.I further suggest that SR estimates the strength of habitat selection, but that the contribution of selection in determining use, which should be more directly linked to fitness than selection per se, should be estimated by another metric, the selection effect on use (SE). SE could be estimated simply as the difference between proportional use and proportional availability, and can be computed from SR and a density estimation of availability.I conduct a habitat selection analysis of plains zebras to demonstrate the added-value of going beyond RSF scores and using SR estimated in a regression context, and of combining SR and SE.Overall, I highlight the inter-relation between various metrics used to study habitat selection (i.e., SR, other selection indices, RSF scores, marginality). I conclude by proposing that SR and SE can be the unifying metrics of habitat selection, as together they offer a comprehensive view on the strength of habitat selection and its effect on habitat use.