Characterization of C-reactive protein in dogs undergoing medial patellar luxation surgery.

C-reactive protein (CRP) is a major acute phase protein used to monitor response to treatment during surgical recovery. Depending on the anatomical problem, surgery type and technique, the level of CRP can change drastically. The aim of this study was to describe the changes in CRP and white blood cell (WBC) levels following surgery for medial patellar luxation in otherwise healthy dogs. Twenty-two dogs completed the study. CRP was measured using a commercially available dry chemistry slide on a commercially available in-clinic analyser. Analyses were performed using the Wilcoxon Rank Sum test and a mixed effects Poisson regression model. A significant change in CRP levels was found between the pre-anesthetic and 24 hr post-surgical timepoint with a median difference of 92.0 mg/dL (P < 0.001). Though a median drop in the CRP value of 13.9 mg/dL was observed between the 24 hr and 48 hr post-surgical time period, the result was not statistically significant (P = 0.456). Similarly, there was a significant increase in WBC between the pre-anesthetic and 24-hr post-surgical time point (P < 0.001) followed by a significant decrease in WBC between the 24 hr and 48-hr post-surgical time points (P = 0.015). In this study population, CRP levels were observed to aid in monitoring of the overall health of the dogs following surgery for medial patellar luxation. The results of this study suggest that both CRP and WBC values significantly increase by 24 hr but where CRP levels remain elevated through 48 hr post-surgery, WBC showed a significant drop between 24 and 48 hr. Further investigation into the length of time for both CRP and WBC to reach basal levels in this particular type of surgery would be of value to monitor recovery from surgery.

Mental Health First Aid in Rural Communities: Appropriateness and Outcomes.

PURPOSE: Mental Health First Aid (MHFA), an early intervention training program for general audiences, has been promoted as a means for improving population-level behavioral health (BH) in rural communities by encouraging treatment-seeking. This study examined MHFA's appropriateness and impacts in rural contexts. METHODS: We used a mixed-methods approach to study MHFA trainings conducted from November 2012 through September 2013 in rural communities across the country. DATA SOURCES: (a) posttraining questionnaires completed by 44,273 MHFA participants at 2,651 rural and urban trainings in 50 US states; (b) administrative data on these trainings; and (c) interviews with 16 key informants who had taught, sponsored, or participated in rural MHFA. Measure of Rurality: Rural-Urban Commuting Area Codes. ANALYSES: Chi-square tests were conducted on questionnaire data. Structural, descriptive, and pattern coding techniques were used to analyze interview data. FINDINGS: MHFA appears aligned with some key rural needs. MHFA may help to reduce unmet need for BH treatment in rural communities by raising awareness of BH issues and mitigating stigma, thereby promoting appropriate treatment-seeking. However, rural infrastructure deficits may limit some communities' ability to meet new demand generated by MHFA. MHFA may help motivate rural communities to develop initiatives for strengthening infrastructure, but additional tools and consultation may be needed. CONCLUSIONS: This study provides preliminary evidence that MHFA holds promise for improving rural BH. MHFA alone cannot compensate for weaknesses in rural BH infrastructure.

Using Machine Learning and Natural Language Processing Algorithms to Automate the Evaluation of Clinical Decision Support in Electronic Medical Record Systems.

INTRODUCTION: As the number of clinical decision support systems (CDSSs) incorporated into electronic medical records (EMRs) increases, so does the need to evaluate their effectiveness. The use of medical record review and similar manual methods for evaluating decision rules is laborious and inefficient. The authors use machine learning and Natural Language Processing (NLP) algorithms to accurately evaluate a clinical decision support rule through an EMR system, and they compare it against manual evaluation. METHODS: Modeled after the EMR system EPIC at Maine Medical Center, we developed a dummy data set containing physician notes in free text for 3,621 artificial patients records undergoing a head computed tomography (CT) scan for mild traumatic brain injury after the incorporation of an electronic best practice approach. We validated the accuracy of the Best Practice Advisories (BPA) using three machine learning algorithms-C-Support Vector Classification (SVC), Decision Tree Classifier (DecisionTreeClassifier), k-nearest neighbors classifier (KNeighborsClassifier)-by comparing their accuracy for adjudicating the occurrence of a mild traumatic brain injury against manual review. We then used the best of the three algorithms to evaluate the effectiveness of the BPA, and we compared the algorithm's evaluation of the BPA to that of manual review. RESULTS: The electronic best practice approach was found to have a sensitivity of 98.8 percent (96.83-100.0), specificity of 10.3 percent, PPV = 7.3 percent, and NPV = 99.2 percent when reviewed manually by abstractors. Though all the machine learning algorithms were observed to have a high level of prediction, the SVC displayed the highest with a sensitivity 93.33 percent (92.49-98.84), specificity of 97.62 percent (96.53-98.38), PPV = 50.00, NPV = 99.83. The SVC algorithm was observed to have a sensitivity of 97.9 percent (94.7-99.86), specificity 10.30 percent, PPV 7.25 percent, and NPV 99.2 percent for evaluating the best practice approach, after accounting for 17 cases (0.66 percent) where the patient records had to be reviewed manually due to the NPL systems inability to capture the proper diagnosis. DISCUSSION: CDSSs incorporated into EMRs can be evaluated in an automatic fashion by using NLP and machine learning techniques.