Exploring potential barriers in equitable access to pediatric diagnostic imaging using machine learning.

In this work, we examine magnetic resonance imaging (MRI) and ultrasound (US) appointments at the Diagnostic Imaging (DI) department of a pediatric hospital to discover possible relationships between selected patient features and no-show or long waiting room time endpoints. The chosen features include age, sex, income, distance from the hospital, percentage of non-English speakers in a postal code, percentage of single caregivers in a postal code, appointment time slot (morning, afternoon, evening), and day of the week (Monday to Sunday). We trained univariate Logistic Regression (LR) models using the training sets and identified predictive (significant) features that remained significant in the test sets. We also implemented multivariate Random Forest (RF) models to predict the endpoints. We achieved Area Under the Receiver Operating Characteristic Curve (AUC) of 0.82 and 0.73 for predicting no-show and long waiting room time endpoints, respectively. The univariate LR analysis on DI appointments uncovered the effect of the time of appointment during the day/week, and patients' demographics such as income and the number of caregivers on the no-shows and long waiting room time endpoints. For predicting no-show, we found age, time slot, and percentage of single caregiver to be the most critical contributors. Age, distance, and percentage of non-English speakers were the most important features for our long waiting room time prediction models. We found no sex discrimination among the scheduled pediatric DI appointments. Nonetheless, inequities based on patient features such as low income and language barrier did exist.

Framingham ten-year general cardiovascular disease risk: agreement between BMI-based and cholesterol-based estimates in a South Asian convenience sample.

The goal of this analysis was to determine the agreement between body mass index-based and cholesterol-based ten-year Framingham general cardiovascular disease risk scores among a convenience sample of 773 South Asian Canadian adults attending community-based screening clinics. Scores were calculated using age, systolic blood pressure, antihypertensive use, current smoking, diabetes, and total cholesterol and high density lipoprotein (for cholesterol-based risk) or height and weight (for body mass index-based risk). Mean risk score differences (body mass index-based risk minus cholesterol-based risk) were estimated using paired t-tests. Bland-Altman plots were used to assess agreement between scores. Finally, agreement across risk categories (low [<10%], moderate [10% to <20%], high [> = 20%]) was examined using the kappa statistic. Average agreement between the two risk scores was quite good overall (mean differences of 0.6% for men and 0.5% for women), but increased to about 3% among participants 60-74 years of age. However, Bland-Altman plots revealed that the differences between the two scores and the variability of the differences increased with increasing average 10-year risk. In terms of clinical importance, the limits of agreement were reasonable for women < 60 years (95% confidence interval: -3.2% to 3.1%), but of concern for women 60-74 years (95% confidence interval: -6.0% to 12.3%), men < 60 years (95% confidence interval: -7.1% to 7.3%) and men 6-074 years (95% confidence interval: -13.8% to 18.8%). Agreement across categories was moderate for most sex and age groups examined (kappa values: 0.51 for women < 60 years, 0.50 for women 60-74 years, 0.65 for men < 60 years), except for men 60-74 years, where agreement was only fair (kappa = 0.26). In light of these disagreements, evaluation of a participant's change in cardiovascular disease risk over time will necessitate use of the same risk score (i.e., either body mass index-based or cholesterol-based) at all screening sessions.

From office tools to community supports: The need for infrastructure to address the social determinants of health in paediatric practice.

Previous research has highlighted the importance of addressing the social determinants of health to improve child health outcomes. However, significant barriers exist that limit the paediatrician's ability to properly address these issues. Barriers include a lack of clinical time, resources, training and education with regard to the social determinants of health; awareness of community resources; and case-management capacity. General practice recommendations to help the health care provider link patients to the community are insufficient. The objective of the current article was to present options for improving the link between the office and the community, using screening questions incorporating physician-based tools that link community resources. Simple interventions, such as routine referral to early-year centres and selected referral to public health home-visiting programs, may help to address populations with the greatest needs.

Des recherches antérieures ont fait ressortir l'importance de tenir compte des déterminants sociaux de la santé pour améliorer la santé des enfants. Cependant, des obstacles importants empêchent les pédiatres de bien se pencher sur la question, incluant le manque de temps clinique, de ressources, de formation et d'enseignement sur les déterminants de la santé, la connaissance des ressources communautaires et la capacité de gestion des cas. Les recommandations faites en pratique générale pour aider le dispensateur de soins à orienter les patients vers des ressources communautaires ne suffisent pas. Le présent article vise à présenter des moyens de faire de meilleurs liens entre le cabinet et la communauté, à l'aide de questions de dépistage intégrant des outils médicaux qui dirigent les patients vers des ressources communautaires. Des interventions simples, telles que l'orientation systématique vers des centres de la petite enfance et l'orientation sélective vers des programmes de visite à domicile par la santé publique, peuvent contribuer à servir les populations qui ont les besoins les plus criants.

Enhancing cultural competence for improved access to quality care.

The Hospital for Sick Children (SickKids) is situated in one of the most diverse cities in the world. This is reflected in the patient population it serves. In 2009, the hospital embarked on a quality improvement initiative to address the existing evidence base on health disparities and to enhance health equity through cultural competence programming. The goal was to achieve optimal health outcomes for all patients and families, with a particular focus on new immigrant and other vulnerable populations. Evaluation results indicate changes in clinical practice as a result of this initiative and increased patient satisfaction with regard to staff members' level of cultural sensitivity. This article provides an overview of this hospital-wide initiative, as well as the evaluation methods and outcomes. Based on a needs assessment, we developed an institutionally meaningful curriculum with SickKids' values of family-centred care, patient safety and service excellence embedded in the program. Educational sessions were delivered to clinical and non-clinical hospital staff, focusing on health disparities, the case for culturally competent care and practical tools for healthcare practitioners. Organizational change strategies, including the use of champions as change agents and role models, were used to embed cultural competence as integral to family-centred care at SickKids.