Understanding intersectional inequality in access to primary care providers using multilevel analysis of individual heterogeneity and discriminatory accuracy.

BACKGROUND: Despite the Canadian healthcare system's commitment to equity, evidence for disparate access to primary care (PC) providers exists across individual social identities/positions. Intersectionality allows us to reflect the realities of how social power shapes healthcare experiences at an individual's interdependent and intersecting social identities/positions. The objectives of this study were to determine: (1) the extent to which intersections can be used classify those who had/did not have a PC provider; (2) the degree to which each social identity/position contributes to the ability to classify individuals as having a PC provider; and (3) predicted probabilities of having a PC provider for each intersection. METHODS AND FINDINGS: Using national cross-sectional data from 241,445 individuals in Canada aged ≥18, we constructed 320 intersections along the dimensions of gender, age, immigration status, race, and income to examine the outcome of whether one had a PC provider. Multilevel analysis of individual heterogeneity and discriminatory accuracy, a multi-level model using individual-level data, was employed to address intersectional objectives. An intra-class correlation coefficient (ICC) of 23% (95%CI: 21-26%) suggests that these intersections could, to a very good extent, explain individual variation in the outcome, with age playing the largest role. Not all between-intersection variance in this outcome could be explained by additive effects of dimensions (remaining ICC: 6%; 95%CI: 2-16%). The highest intersectional predicted probability existed for established immigrant, older South Asian women with high income. The lowest intersectional predicted probability existed for recently immigrated, young, Black men with low income. CONCLUSIONS: Despite a "universal" healthcare system, our analysis demonstrated a substantial amount of inequity in primary care across intersections of gender, age, immigration status, race, and income.

Understanding data provenance when using electronic medical records for research: Lessons learned from the Deliver Primary Healthcare Information (DELPHI) database.

Introduction: We set out to assess the impact of Choosing Wisely Canada recommendations (2014) on reducing unnecessary health investigations and interventions in primary care across Southwestern Ontario. Methods: We used the Deliver Primary Healthcare Information (DELPHI) database, which stores deidentified electronic medical records (EMR) of nearly 65,000 primary care patients across Southwestern Ontario. When conducting research using EMR data, data provenance (i.e., how the data came to be) should first be established. We first considered DELPHI data provenance in relation to longitudinal analyses, flagging a change in EMR software that occurred during 2012 and 2013. We attempted to link records between EMR databases produced by different software using probabilistic linkage and inspected 10 years of data in the DELPHI database (2009 to 2019) for data quality issues, including comparability over time. Results: We encountered several issues resulting from this change in EMR software. These included limited linkage of records between software without a common identifier; data migration issues that distorted procedure dates; and unusual changes in laboratory test and medication prescription volumes. Conclusion: This study reinforces the necessity of assessing data provenance and quality for new research projects. By understanding data provenance, we can anticipate related data quality issues such as changes in EMR data over time-which represent a growing concern as longitudinal data analyses increase in feasibility and popularity.

Is primary health care ready for artificial intelligence? Stakeholder perspectives: Worth the risk as long as you do it well.

Context: The effective deployment of artificial intelligence (AI) in primary health care requires a match between the AI tools that are being developed and the needs of primary health care practitioners and patients. Currently, the majority of AI development targeted toward potential application in primary care is being conducted without the involvement of these stakeholders. Objective: To identify key issues regarding the use of AI tools in primary health care by exploring the views of primary health care and digital health stakeholders. Study Design: A descriptive qualitative approach was taken in this study. Fourteen in-depth interviews were conducted with primary care and digital health stakeholders. Setting: Province of Ontario, Canada Population studied: Primary health care and digital health stakeholders Outcome Measures: N/A Results: Two main themes emerged from the data analysis: Worth the Risk as Long as You Do It Well; and, Mismatch Between Envisioned Uses and Current Reality. Participants noted that AI could have value if used for specific purposes, for example: supporting care for patients; reducing practitioner burden; analyzing existing evidence; managing patient populations; and, supporting operational efficiencies. Participants identified facilitators of AI being used for these purposes including: use of relevant case studies/success stories with realistic uses of AI highlighted; easy or low risk applications; and, end user involvement. However, barriers to the use of AI included: data quality; digital divide/equity; distrust of AI including security/privacy issues; for-profit motives; need for transparency about how AI works; and, fear about impact on practitioners regarding clinical judgement. Conclusion: AI will continue to become more prominent in primary health care. There is potential for positive impact, however there are many factors that need to be considered regarding the implementation of AI. The findings of this study can help to inform the development and deployment of AI tools in primary health care.

Identifying priorities for artificial intelligence and primary care in ontario: A multi-stakeholder engagement event.

CONTEXT: Artificial intelligence (AI) is increasingly being recognized as having potential importance to primary care (PC). However, there is a gap in our understanding about where to focus efforts related to AI for PC settings, especially given the current COVID-19 pandemic. OBJECTIVE: To identify current priority areas for AI and PC in Ontario, Canada. STUDY DESIGN: Multi-stakeholder engagement event with facilitated small and large group discussions. A nominal group technique process was used to identify and rank challenges in PC that AI may be able to support. Mentimeter software was used to allow real-time, anonymous and independent ranking from all participants. A final list of priority areas for AI and PC, with key considerations, was derived based on ranked items and small group discussion notes. SETTING: Ontario, Canada. POPULATION STUDIED: Digital health and PC stakeholders. OUTCOME MEASURES: N/A. RESULTS: The event included 8 providers, 8 patient advisors, 4 decision makers, 3 digital health stakeholders, and 12 researchers. Nine priority areas for AI and PC were identified and ranked, which can be grouped into those intended to support physician (preventative care and risk profiling, clinical decision support, routine task support), patient (self-management of conditions, increased mental health care capacity and support), or system-level initiatives (administrative staff support, management and synthesis of information sources); and foundational areas that would support work on other priorities (improved communication between PC and AI stakeholders, data sharing and interoperability between providers). Small group discussions identified barriers and facilitators related to the priorities, including data availability, quality, and consent; legal and device certification issues; trust between people and technology; equity and the digital divide; patient centredness and user-centred design; and the need for funding to support collaborative research and pilot testing. Although identified areas do not explicitly mention COVID-19, participants were encouraged to think about what would be feasible and meaningful to accomplish within a few years, including considerations of the COVID-19 pandemic and recovery phases. CONCLUSIONS: A one-day multi-stakeholder event identified priority areas for AI and PC in Ontario. These priorities can serve as guideposts to focus near-term efforts on the planning, development, and evaluation of AI for PC.

Scalable approximate policies for Markov decision process models of hospital elective admissions.

OBJECTIVE: To demonstrate the feasibility of using stochastic simulation methods for the solution of a large-scale Markov decision process model of on-line patient admissions scheduling. METHODS: The problem of admissions scheduling is modeled as a Markov decision process in which the states represent numbers of patients using each of a number of resources. We investigate current state-of-the-art real time planning methods to compute solutions to this Markov decision process. Due to the complexity of the model, traditional model-based planners are limited in scalability since they require an explicit enumeration of the model dynamics. To overcome this challenge, we apply sample-based planners along with efficient simulation techniques that given an initial start state, generate an action on-demand while avoiding portions of the model that are irrelevant to the start state. We also propose a novel variant of a popular sample-based planner that is particularly well suited to the elective admissions problem. RESULTS: Results show that the stochastic simulation methods allow for the problem size to be scaled by a factor of almost 10 in the action space, and exponentially in the state space. We have demonstrated our approach on a problem with 81 actions, four specialities and four treatment patterns, and shown that we can generate solutions that are near-optimal in about 100s. CONCLUSION: Sample-based planners are a viable alternative to state-based planners for large Markov decision process models of elective admissions scheduling.