Predicting chronic wasting disease in white-tailed deer at the county scale using machine learning.

Continued spread of chronic wasting disease (CWD) through wild cervid herds negatively impacts populations, erodes wildlife conservation, drains resource dollars, and challenges wildlife management agencies. Risk factors for CWD have been investigated at state scales, but a regional model to predict locations of new infections can guide increasingly efficient surveillance efforts. We predicted CWD incidence by county using CWD surveillance data depicting white-tailed deer (Odocoileus virginianus) in 16 eastern and midwestern US states. We predicted the binary outcome of CWD-status using four machine learning models, utilized five-fold cross-validation and grid search to pinpoint the best model, then compared model predictions against the subsequent year of surveillance data. Cross validation revealed that the Light Boosting Gradient model was the most reliable predictor given the regional data. The predictive model could be helpful for surveillance planning. Predictions of false positives emphasize areas that warrant targeted CWD surveillance because of similar conditions with counties known to harbor CWD. However, disagreements in positives and negatives between the CWD Prediction Web App predictions and the on-the-ground surveillance data one year later underscore the need for state wildlife agency professionals to use a layered modeling approach to ensure robust surveillance planning. The CWD Prediction Web App is at https://cwd-predict.streamlit.app/ .

Evaluation of Right Ventricular Myocardial Mechanics Using Velocity Vector Imaging of Cardiac MRI Cine Images in Transposition of the Great Arteries Following Atrial and Arterial Switch Operations.

OBJECTIVE: The aim of the study was to determine right and left ventricle deformation parameters in patients with transposition of the great arteries who had undergone atrial or arterial switch procedures. SETTING: Patients with transposition are born with a systemic right ventricle. Historically, the atrial switch operation, in which the right ventricle remains the systemic ventricle, was performed. These patients have increased rates of morbidity and mortality. We used cardiac MRI with Velocity Vector Imaging analysis to characterize and compare ventricular myocardial deformation in patients who had an atrial switch or arterial switch operation. DESIGN: Patients with a history of these procedures, who had a clinically ordered cardiac MRI were included in the study. Consecutive 20 patients (75% male, 28.7 ± 1.8 years) who underwent atrial switch operation and 20 patients (60% male, 17.7 ± 1.9 years) who underwent arterial switch operation were included in the study. Four chamber and short-axis cine images were used to determine longitudinal and circumferential strain and strain rate using Vector Velocity Imaging software. RESULTS: Compared with the arterial switch group, the atrial switch group had decreased right ventricular ejection fraction and increased end-diastolic and end-systolic volumes, and no difference in left ventricular ejection fraction and volumes. The atrial switch group had decreased longitudinal and circumferential strain and strain rate. When compared with normal controls multiple strain parameters in the atrial switch group were reduced. CONCLUSIONS: Myocardial deformation analysis of transposition patients reveals a reduction of right ventricular function and decreased longitudinal and circumferential strain parameters in patients with an atrial switch operation compared with those with arterial switch operation. A better understanding of the mechanisms of right ventricle failure in transposition of great arteries may lead to improved therapies and adaptation.

Methods for data mining from large multinational surveillance studies.

Traditionally, large surveillance studies have been analyzed by the use of the MICs at which 90% of isolates tested are inhibited (MIC(90)s), MIC(50)s, frequency distributions, and percent susceptibility. In the past, these approaches have proved satisfactory for the monitoring of resistance. From these traditional uses, one can readily detect an increase in MICs for organism and drug combinations. Now that large surveillance studies have been conducted for a number of years and databases have grown to include a large number of datum points, new approaches to the extraction of useful information from these studies are needed. The present study proposes approaches, including the use of antibiotypes, principal components analysis, phylogenetics, and population genetic analysis, to the evaluation of data from large multinational surveillance studies. Application of these types of analyses can be used to describe genetic diversity, analyze changes in susceptibility patterns over time, and possibly, shed light on the origins and evolution of antimicrobial resistance. As global surveillance studies become more common and new questions concerning the evolution of resistance are raised, innovative approaches to analysis of the data will increase in importance.