Machine learning to predict myocardial injury and death after non-cardiac surgery

Myocardial injury due to ischaemia within 30 days of non-cardiac surgery is prognostically relevant. We aimed to determine the discrimination, calibration, accuracy, sensitivity and specificity of single-layer and multiple-layer neural networks for myocardial injury and death within 30 postoperative days. We analysed data from 24,589 participants in the Vascular Events in Non-cardiac Surgery Patients Cohort Evaluation study. Validation was performed on a randomly selected subset of the study population. Discrimination for myocardial injury by single-layer vs. multiple-layer models generated areas (95%CI) under the receiver operating characteristic curve of: 0.70 (0.69–0.72) vs. 0.71 (0.70–0.73) with variables available before surgical referral, p < 0.001; 0.73 (0.72–0.75) vs. 0.75 (0.74–0.76) with additional variables available on admission, but before surgery, p < 0.001; and 0.76 (0.75–0.77) vs. 0.77 (0.76–0.78) with the addition of subsequent variables, p < 0.001. Discrimination for death by single-layer vs. multiple-layer models generated areas (95%CI) under the receiver operating characteristic curve of: 0.71 (0.66–0.76) vs. 0.74 (0.71–0.77) with variables available before surgical referral, p = 0.04; 0.78 (0.73–0.82) vs. 0.83 (0.79–0.86) with additional variables available on admission but before surgery, p = 0.01; and 0.87 (0.83–0.89) vs. 0.87 (0.85–0.90) with the addition of subsequent variables, p = 0.52. The accuracy of the multiple-layer model for myocardial injury and death with all variables was 70% and 89%, respectively.     

Genetic modification of scAAV‐equine‐BMP‐2 transduced bone‐marrow‐derived mesenchymal stem cells before and after cryopreservation: An “off‐the‐shelf” option for fracture repair

Optimizing the environment of complex bone healing and improving treatment of catastrophic bone fractures and segmental bone defects remains an unmet clinical need both human and equine veterinary medical orthopaedics. The objective of this study was to determine whether scAAV‐equine‐BMP‐2 transduced cells would induce osteogenesis in equine bone marrow derived mesenchymal stem cells (BMDMSCs) in vitro, and if these cells could be cryopreserved in an effort to osteogenically prime them as an “off‐the‐shelf” gene therapeutic approach for fracture repair. Our study found that transgene expression is altered by cell expansion, as would be expected by a transduction resulting in episomal transgene expression, and that osteoinductive levels could still be achieved 5 days after recovery, and protein expression would continue up to 14 days after transduction. This is the first evidence that cryopreservation of genetically modified BMDMSCs would not alter the osteoinductive potential or clinical use of allogeneic donor cells in cases of equine fracture repair. © 2018 Orthopaedic Research Society. Published by Wiley Periodicals, Inc. J Orthop Res 37:1310–1317, 2019.     

Evaluation of validity of the STOP-BANG questionnaire in major elective noncardiac surgery

Background

The STOP-BANG questionnaire screens for obstructive sleep apnoea (OSA) in surgical patients. In prior research, the association of STOP-BANG scores with comorbidities and outcomes was inconsistent. The objective of this study was to evaluate the validity of the STOP-BANG score.

Evaluating alcohol and marijuana use among emerging adult males via analysis of text messages

Background: Advances in social technologies offer new tools for large scale data collection and analysis of peer influence and social networks on substance use attitudes and behaviors. Objective: The objective of this study was to determine if text message content can predict alcohol and marijuana use attitudes and behaviors. Methods: Text messages from 91 males ages 18–25 were monitored over a period of 6 months and examined for content related to alcohol and marijuana. Self-report data indicating alcohol and marijuana use attitudes and behaviors were used to determine relationships between text message content, social network structure, and substance use attitudes and behaviors. Results: In total, 23,173 text messages were analyzed with 166 text messages including alcohol related terms and 195 text messages including drug related terms. Individuals who sent text messages related to alcohol use were more likely to have problem alcohol use and positive attitudes toward alcohol use, and individuals who sent text messages related to marijuana use reported higher frequency of marijuana use and more positive attitudes toward marijuana use. Individuals with multiple daily marijuana use were in positions that had less control over network structure. Conclusions: The results of this study indicate that monitoring text message content and social network structure among emerging adult males can potentially predict alcohol and marijuana use attitudes and behaviors. Text message content analysis is a novel technique increasing our understanding of the role of peer influence and social network on substance use attitudes and behaviors.