Development, Evaluation, and Multisite Deployment of a Machine Learning Decision Tree Algorithm To Optimize Urinalysis Parameters for Predicting Urine Culture Positivity.

PittUDT, a recursive partitioning decision tree algorithm for predicting urine culture (UC) positivity based on macroscopic and microscopic urinalysis (UA) parameters, was developed in support of a broader system-wide diagnostic stewardship initiative to increase appropriateness of UC testing. Reflex algorithm training utilized results from 19,511 paired UA and UC cases (26.8% UC positive); the average patient age was 57.4 years, and 70% of samples were from female patients. Receiver operating characteristic (ROC) analysis identified urine white blood cells (WBCs), leukocyte esterase, and bacteria as the best predictors of UC positivity, with areas under the ROC curve of 0.79, 0.78, and 0.77, respectively. Using the held-out test data set (9,773 cases; 26.3% UC positive), the PittUDT algorithm met the prespecified target of a negative predictive value above 90% and resulted in a 30 to 60% total negative proportion (true-negative plus false-negative predictions). These data show that a supervised rule-based machine learning algorithm trained on paired UA and UC data has adequate predictive ability for triaging urine specimens by identifying low-risk urine specimens, which are unlikely to grow pathogenic organisms, with a false-negative proportion under 5%. The decision tree approach also generates human-readable rules that can be easily implemented across multiple hospital sites and settings. Our work demonstrates how a data-driven approach can be used to optimize UA parameters for predicting UC positivity in a reflex protocol, with the intent of improving antimicrobial stewardship and UC utilization, a potential avenue for cost savings.

Regulatory Decision Making in Canada-Exploring New Frontiers in Patient Involvement.

Recent legislative amendments aim to enhance the transparency of the regulatory review processes about drugs, and provide public information about Health Canada's review decisions. There is also growing recognition of the value, with respect to regulatory benefit-risk assessment, of information that could be gathered from patients-the direct users of these products. Patients can provide unique insights into practical aspects of living with their disease and its treatments-as well as gaps in treatment needs. An enhanced understanding of patients' experiences and perspectives can contribute directly to better-informed decision making about these products by regulators. Health Canada is currently exploring and examining the most effective ways to collect and consider patient input in the evaluation of therapeutic products. As part of this process, Health Canada is assessing the suitability of other existing models through environmental scans, discussions with other health authorities, and pilot projects. Lessons learned from these models can inform best practices and opportunities for patient involvement when designing a model to meet Canada's needs and context. Health Canada launched a Patient Involvement Pilot Project in 2014 to simulate how input from patients, their caregivers, health care professionals, and patient groups could be collected and incorporated in the drug submission review process. This ongoing experience and continuous learning will define better how to incorporate patient input into benefit-risk assessment and regulatory decision making throughout the life cycle of therapeutic products in Canada.

Mini-MEND: an obesity prevention initiative in a children's centre.

Student health visitors led a Mini-MEND project for families with young children as part of their public health nursing course. The project gave a framework for the students and staff members from the children's centre to stimulate an awareness of health needs and facilitate health enhancing activities in terms of healthy eating and parenting. Reflection on the initiative identified application of the principles of health visiting and the domains of specialist community public health nursing, yet the pressures of current health visiting workloads mean that having developed public health skills to use with groups and communities, they may not be used by newly-qualified health visitors.

French registry of cases of type I acute aortic dissection admitted to a cardiac rehabilitation center after surgery.

BACKGROUND: After surgery for type I acute aortic dissection, the aorta remains partly dissected. This new population of patients is now referred to cardiac rehabilitation centers (CRCs). The feasibility of subsequent physical exercise is unknown. METHODS: Thirty-three consecutive patients (aged 55.1+/-9.3 years) were included in a prospective registry with clinical and radiological follow-up for 1 year after admission to a CRC. Twenty-six patients had undergone standard training sessions with exercise on a bicycle ergometer. Physical training programs included calisthenics, respiratory physiotherapy, walking, and cycling. Seven patients did not perform standard exercise training sessions but only walking and respiratory physiotherapy. RESULTS: For trained patients, the sessions (18+/-10) were carried out at 11.3+/-1.5 on the Borg scale ('light'), with blood pressure monitoring on exercise (<160 mmHg in 75% of patients). Maximum workload during exercise test (bicycle ergometer, 10 watts/min) increased from 62.7+/-11.8 to 91.6+/-16.5 watts (P=0.002). We identified three complications in two patients requiring further thoracic aorta surgery during follow-up. There was also one case of aortic valve replacement after 5 months and three cases of peripheral ischemia. No deaths, cerebral vascular accidents, or myocardial infarctions were recorded. Ten of the 19 patients of working age were able to return to work. CONCLUSION: Physical training of moderate intensity seems feasible and beneficial in postsurgical type I aortic dissection patients.