Identifying Bladder Phenotypes After Spinal Cord Injury With Unsupervised Machine Learning: A New Way to Examine Urinary Symptoms and Quality of Life.

PURPOSE: Patients with spinal cord injuries (SCIs) experience variable urinary symptoms and quality of life (QOL). Our objective was to use machine learning to identify bladder-relevant phenotypes after SCI and assess their association with urinary symptoms and QOL. MATERIALS AND METHODS: We used data from the Neurogenic Bladder Research Group SCI registry. Baseline variables that were previously shown to be associated with bladder symptoms/QOL were included in the machine learning environment. An unsupervised consensus clustering approach (k-prototypes) was used to identify 4 patient clusters. After qualitative review of the clusters, 2 outcomes of interest were assessed: the total Neurogenic Bladder Symptom Score (NBSS) and the NBSS-satisfaction question (QOL). The NBSS and NBSS-satisfaction question at baseline and after 1 year were compared between clusters using analysis of variance and linear regression. RESULTS: Among the 1263 included participants, the 4 identified clusters were termed "female predominant," "high function, low SCI complication," "quadriplegia with bowel/bladder morbidity," and "older, high SCI complication." Using outcome data from baseline, significant differences were observed in the NBSS score, with the female predominant group exhibiting worse bladder symptoms. After 1 year, the overall bladder symptoms (NBSS Total) did not change significantly by cluster; however, the QOL score for the high function, low SCI complication group had more improvement (ß = -0.12, P = .005), while the female predominant group had more deterioration (ß = 0.09, P = .047). CONCLUSIONS: This study demonstrates the utility of machine learning in uncovering bladder-relevant phenotypes among SCI patients. Future research should explore cluster-based targeted strategies to enhance bladder-related outcomes and QOL in SCI.

DRL-GAN: A Hybrid Approach for Binary and Multiclass Network Intrusion Detection.

Our increasingly connected world continues to face an ever-growing number of network-based attacks. An Intrusion Detection System (IDS) is an essential security technology used for detecting these attacks. Although numerous Machine Learning-based IDSs have been proposed for the detection of malicious network traffic, the majority have difficulty properly detecting and classifying the more uncommon attack types. In this paper, we implement a novel hybrid technique using synthetic data produced by a Generative Adversarial Network (GAN) to use as input for training a Deep Reinforcement Learning (DRL) model. Our GAN model is trained on the NSL-KDD dataset, a publicly available collection of labeled network traffic data specifically designed to support the evaluation and benchmarking of IDSs. Ultimately, our findings demonstrate that training the DRL model on synthetic datasets generated by specific GAN models can result in better performance in correctly classifying minority classes over training on the true imbalanced dataset.

Factors Influencing Admission Decisions in Skilled Nursing Facilities: Retrospective Quantitative Study.

BACKGROUND: Occupancy rates within skilled nursing facilities (SNFs) in the United States have reached a record low. Understanding drivers of occupancy, including admission decisions, is critical for assessing the recovery of the long-term care sector as a whole. We provide the first comprehensive analysis of financial, clinical, and operational factors that impact whether a patient referral to an SNF is accepted or denied, using a large health informatics database. OBJECTIVE: Our key objectives were to describe the distribution of referrals sent to SNFs in terms of key referral- and facility-level features; analyze key financial, clinical, and operational variables and their relationship to admission decisions; and identify the key potential reasons behind referral decisions in the context of learning health systems. METHODS: We extracted and cleaned referral data from 627 SNFs from January 2020 to March 2022, including information on SNF daily operations (occupancy and nursing hours), referral-level factors (insurance type and primary diagnosis), and facility-level factors (overall 5-star rating and urban versus rural status). We computed descriptive statistics and applied regression modeling to identify and describe the relationships between these factors and referral decisions, considering them individually and controlling for other factors to understand their impact on the decision-making process. RESULTS: When analyzing daily operation values, no significant relationship between SNF occupancy or nursing hours and referral acceptance was observed (P>.05). By analyzing referral-level factors, we found that the primary diagnosis category and insurance type of the patient were significantly related to referral acceptance (P<.05). Referrals with primary diagnoses within the category "Diseases of the Musculoskeletal System" are least often denied whereas those with diagnoses within the "Mental Illness" category are most often denied (compared with other diagnosis categories). Furthermore, private insurance holders are least often denied whereas "medicaid" holders are most often denied (compared with other insurance types). When analyzing facility-level factors, we found that the overall 5-star rating and urban versus rural status of an SNF are significantly related to referral acceptance (P<.05). We found a positive but nonmonotonic relationship between the 5-star rating and referral acceptance rates, with the highest acceptance rates found among 5-star facilities. In addition, we found that SNFs in urban areas have lower acceptance rates than their rural counterparts. CONCLUSIONS: While many factors may influence a referral acceptance, care challenges associated with individual diagnoses and financial challenges associated with different remuneration types were found to be the strongest drivers. Understanding these drivers is essential in being more intentional in the process of accepting or denying referrals. We have interpreted our results using an adaptive leadership framework and suggested how SNFs can be more purposeful with their decisions while striving to achieve appropriate occupancy levels in ways that meet their goals and patients' needs.

Describing Intersectional Health Outcomes: An Evaluation of Data Analysis Methods.

BACKGROUND: Intersectionality theoretical frameworks have been increasingly incorporated into quantitative research. A range of methods have been applied to describing outcomes and disparities across large numbers of intersections of social identities or positions, with limited evaluation. METHODS: Using data simulated to reflect plausible epidemiologic data scenarios, we evaluated methods for intercategorical intersectional analysis of continuous outcomes, including cross-classification, regression with interactions, multilevel analysis of individual heterogeneity (MAIHDA), and decision-tree methods (classification and regression trees [CART], conditional inference trees [CTree], random forest). The primary outcome was estimation accuracy of intersection-specific means. We applied each method to an illustrative example using National Health and Nutrition Examination Study (NHANES) systolic blood pressure data. RESULTS: When studying high-dimensional intersections at smaller sample sizes, MAIHDA, CTree, and random forest produced more accurate estimates. In large samples, all methods performed similarly except CART, which produced less accurate estimates. For variable selection, CART performed poorly across sample sizes, although random forest performed best. The NHANES example demonstrated that different methods resulted in meaningful differences in systolic blood pressure estimates, highlighting the importance of selecting appropriate methods. CONCLUSIONS: This study evaluates some of a growing toolbox of methods for describing intersectional health outcomes and disparities. We identified more accurate methods for estimating outcomes for high-dimensional intersections across different sample sizes. As estimation is rarely the only objective for epidemiologists, we highlight different outputs each method creates, and suggest the sequential pairing of methods as a strategy for overcoming certain technical challenges.

Is primary health care ready for artificial intelligence? What do primary health care stakeholders say?

BACKGROUND: Effective deployment of AI tools in primary health care requires the engagement of practitioners in the development and testing of these tools, and a match between the resulting AI tools and clinical/system needs in primary health care. To set the stage for these developments, we must gain a more in-depth understanding of the views of practitioners and decision-makers about the use of AI in primary health care. The objective of this study was 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. METHODS: This study utilized a descriptive qualitative approach, including thematic data analysis. Fourteen in-depth interviews were conducted with primary health care and digital health stakeholders in Ontario. NVivo software was utilized in the coding of the interviews. RESULTS: Five main interconnected themes emerged: (1) Mismatch Between Envisioned Uses and Current Reality-denoting the importance of potential applications of AI in primary health care practice, with a recognition of the current reality characterized by a lack of available tools; (2) Mechanics of AI Don't Matter: Just Another Tool in the Toolbox- reflecting an interest in what value AI tools could bring to practice, rather than concern with the mechanics of the AI tools themselves; (3) AI in Practice: A Double-Edged Sword-the possible benefits of AI use in primary health care contrasted with fundamental concern about the possible threats posed by AI in terms of clinical skills and capacity, mistakes, and loss of control; (4) The Non-Starters: A Guarded Stance Regarding AI Adoption in Primary Health Care-broader concerns centred on the ethical, legal, and social implications of AI use in primary health care; and (5) Necessary Elements: Facilitators of AI in Primary Health Care-elements required to support the uptake of AI tools, including co-creation, availability and use of high quality data, and the need for evaluation. CONCLUSION: The use of AI in primary health care may have a positive impact, but many factors need to be considered regarding its implementation. This study may help to inform the development and deployment of AI tools in primary health care.

A Smart Technology Intervention in the Homes of People with Mental Illness and Physical Comorbidities.

Appropriate support in the home may not be readily available for people living in the community with mental illness and physical comorbidities. This mixed-method study evaluated a smart home technology intervention for individuals within this population as well as providing health care providers with health monitoring capabilities. The study recruited 13 participants who were offered a smartphone, a touchscreen monitor, and health devices, including smartwatches, weigh scales, and automated medication dispensers. Healthcare providers were able to track health device data, which were synchronized with the Lawson Integrated DataBase. Participants completed interviews at baseline as well as at 6-month and 12-month follow-ups. Focus groups with participants and care providers were conducted separately at 6-month and 12-month time points. As the sample size was too small for meaningful statistical inference, only descriptive statistics were presented. However, the qualitative analyses revealed improvements in physical and mental health, as well as enhanced communication with care providers and friends/family. Technical difficulties and considerations are addressed. Ethics analyses revealed advancement in equity and fairness, while policy analyses revealed plentiful opportunities for informing policymakers. The economic costs are also discussed. Further studies and technological interventions are recommended to explore and expand upon in-home technologies that can be easily implemented into the living environment.

Patterns of Primary Care Use Prior to a First Diagnosis of Nonaffective Psychotic Disorder in Ontario, Canada: Modèles d'utilisation des soins de première ligne avant un premier diagnostic de trouble psychotique non affectif en Ontario, Canada.

BACKGROUND: Many people experience early signs and symptoms before the onset of psychotic disorder, suggesting that there may be help-seeking prior to first diagnosis. The family physician has been found to play a key role in pathways to care. This study examined patterns of primary care use preceding a first diagnosis of psychotic disorder. METHODS: We used health administrative data from Ontario (Canada) to construct a population-based retrospective cohort. We investigated patterns of primary care use, including frequency and timing of contacts, in the 6 years prior to a first diagnosis of psychosis, relative to a general population comparison group matched on age, sex, geographic area, and index date. We used latent class growth modeling to identify distinct trajectories of primary care service use, and associated factors, preceding the first diagnosis. RESULTS: People with early psychosis contacted primary care over twice as frequently in the 6 years preceding first diagnosis (RR = 2.22; 95% CI, = 2.19 to 2.25), relative to the general population, with a sharp increase in contacts 10 months prior to diagnosis. They had higher contact frequency across nearly all diagnostic codes, including mental health, physical health, and preventative health. We identified 3 distinct service use trajectories: low-, medium-, and high-increasing usage. DISCUSSION: We found elevated patterns of primary care service use prior to first diagnosis of psychotic disorder, suggesting that initiatives to support family physicians in their role on the pathway to care are warranted. Earlier intervention has implications for improved social, educational, and professional development in young people with first-episode psychosis.

Artificial Intelligence and Primary Care Research: A Scoping Review.

PURPOSE: Rapid increases in technology and data motivate the application of artificial intelligence (AI) to primary care, but no comprehensive review exists to guide these efforts. Our objective was to assess the nature and extent of the body of research on AI for primary care. METHODS: We performed a scoping review, searching 11 published or gray literature databases with terms pertaining to AI (eg, machine learning, bayes* network) and primary care (eg, general pract*, nurse). We performed title and abstract and then full-text screening using Covidence. Studies had to involve research, include both AI and primary care, and be published in Eng-lish. We extracted data and summarized studies by 7 attributes: purpose(s); author appointment(s); primary care function(s); intended end user(s); health condition(s); geographic location of data source; and AI subfield(s). RESULTS: Of 5,515 unique documents, 405 met eligibility criteria. The body of research focused on developing or modifying AI methods (66.7%) to support physician diagnostic or treatment recommendations (36.5% and 13.8%), for chronic conditions, using data from higher-income countries. Few studies (14.1%) had even a single author with a primary care appointment. The predominant AI subfields were supervised machine learning (40.0%) and expert systems (22.2%). CONCLUSIONS: Research on AI for primary care is at an early stage of maturity. For the field to progress, more interdisciplinary research teams with end-user engagement and evaluation studies are needed.

Drug interactions and pharmacogenetic factors contribute to variation in apixaban concentration in atrial fibrillation patients in routine care.

Factor Xa-inhibitor apixaban is an oral anticoagulant prescribed in atrial fibrillation (AF) for stroke prevention. Its pharmacokinetic profile is known to be affected by cytochrome P450 (CYP)3A metabolism, while it is also a substrate of the efflux transporters ATP-binding cassette (ABC)B1 (P-glycoprotein) and ABCG2 (breast cancer resistance protein, BCRP). In this study, we assessed the impact of interacting medication and pharmacogenetic variation to better explain apixaban concentration differences among 358 Caucasian AF patients. Genotyping (ABCG2, ABCB1, CYP3A4*22, CYP3A5*3) was performed by TaqMan assays, and apixaban quantified by mass spectrometry. The typical patient was on average 77.2 years old, 85.5 kg, and had a serum creatinine of 103.1 µmol/L. Concomitant amiodarone, an antiarrhythmic agent and moderate CYP3A/ABCB1 inhibitor, the impaired-function variant ABCG2 c.421C > A, and sex predicted higher apixaban concentrations when controlling for age, weight and serum creatinine (multivariate regression; R2 = 0.34). Our findings suggest that amiodarone and ABCG2 genotype contribute to interpatient apixaban variability beyond known clinical factors.

A generalized shapelet-based method for analysis of nanostructured surface imaging.

The determination of quantitative structure-property relations is a vital but challenging task for nanostructured materials research due to the presence of large-scale spatially varying patterns resulting from nanoscale processes such as self-assembly and nano-lithography. Focusing on nanostructured surfaces, recent advances have been made in automated quantification methods for orientational and translational order using shapelet functions, originally developed for analysis of images of galaxies, as a reduced-basis for surface pattern structure. In this work, a method combining shapelet functions and machine learning is developed and applied to a representative set of images of self-assembled surfaces from experimental characterization techniques including scanning electron miscroscopy, atomic force microscopy and transmission electron microscopy. The method is shown to be computationally efficient and able to quantify salient pattern features including deformation, defects, and grain boundaries from a broad range of patterns typical of self-assembly processes.

Development of an EMG-Based Muscle Health Model for Elbow Trauma Patients.

Wearable robotic braces have the potential to improve rehabilitative therapies for patients suffering from musculoskeletal (MSK) conditions. Ideally, a quantitative assessment of health would be incorporated into rehabilitative devices to monitor patient recovery. The purpose of this work is to develop a model to distinguish between the healthy and injured arms of elbow trauma patients based on electromyography (EMG) data. Surface EMG recordings were collected from the healthy and injured limbs of 30 elbow trauma patients while performing 10 upper-limb motions. Forty-two features and five feature sets were extracted from the data. Feature selection was performed to improve the class separation and to reduce the computational complexity of the feature sets. The following classifiers were tested: linear discriminant analysis (LDA), support vector machine (SVM), and random forest (RF). The classifiers were used to distinguish between two levels of health: healthy and injured (50% baseline accuracy rate). Maximum fractal length (MFL), myopulse percentage rate (MYOP), power spectrum ratio (PSR) and spike shape analysis features were identified as the best features for classifying elbow muscle health. A majority vote of the LDA classification models provided a cross-validation accuracy of 82.1%. The work described in this paper indicates that it is possible to discern between healthy and injured limbs of patients with MSK elbow injuries. Further assessment and optimization could improve the consistency and accuracy of the classification models. This work is the first of its kind to identify EMG metrics for muscle health assessment by wearable rehabilitative devices.

CYP2D6 genotype and endoxifen plasma concentration do not predict hot flash severity during tamoxifen therapy.

PURPOSE: Tamoxifen is frequently prescribed to prevent breast cancer recurrence. Tamoxifen is a prodrug and requires bioactivation by CYP2D6. Tamoxifen use is often limited by adverse effects including severe hot flashes. There is paucity of prospectively collected data in terms of CYP2D6 genotype and measured tamoxifen, 4-hydroxytamoxifen and endoxifen concentrations in relation to hot flash severity during tamoxifen therapy. METHODS: We conducted a longitudinal prospective study of breast cancer patients on tamoxifen (n = 410). At each visit, blood samples were collected, and patients completed a standardized hot flash survey (n = 1144) that reflected hot flash severity during the 7 days prior to the visit. Plasma concentrations of tamoxifen, 4-hydroxytamoxifen, and endoxifen were measured using liquid chromatography-tandem mass spectrometry and genotyping was carried out for CYP2D6. A linear mixed-effects regression analysis assessed the association of covariates in relation to the hot flash severity score (HFSS). RESULTS: Median age at first assessment was 50 years with 61.9% of patients considered peri-menopausal. Most patients (92.2%) experienced hot flash symptoms with 51.0% having low HFSS (0-4) and 7.32% experiencing HFSS > 25. Age was significantly associated with hot flash severity, with patients aged 45-59 more likely to have higher HFSS. Neither duration of tamoxifen therapy nor observed tamoxifen, endoxifen and 4-hydroxy tamoxifen plasma concentration predicted hot flash severity. Genetic variation in CYP2D6 or CYP3A4 was not predictive of hot flash severity. CONCLUSIONS: Hot flash severity during tamoxifen therapy can not be accounted for by CYP2D6 genotype or observed plasma concentration of tamoxifen, 4-hydroxytamoxifen, or endoxifen.

Set-valued dynamic treatment regimes for competing outcomes.

Dynamic treatment regimes (DTRs) operationalize the clinical decision process as a sequence of functions, one for each clinical decision, where each function maps up-to-date patient information to a single recommended treatment. Current methods for estimating optimal DTRs, for example Q-learning, require the specification of a single outcome by which the "goodness" of competing dynamic treatment regimes is measured. However, this is an over-simplification of the goal of clinical decision making, which aims to balance several potentially competing outcomes, for example, symptom relief and side-effect burden. When there are competing outcomes and patients do not know or cannot communicate their preferences, formation of a single composite outcome that correctly balances the competing outcomes is not possible. This problem also occurs when patient preferences evolve over time. We propose a method for constructing DTRs that accommodates competing outcomes by recommending sets of treatments at each decision point. Formally, we construct a sequence of set-valued functions that take as input up-to-date patient information and give as output a recommended subset of the possible treatments. For a given patient history, the recommended set of treatments contains all treatments that produce non-inferior outcome vectors. Constructing these set-valued functions requires solving a non-trivial enumeration problem. We offer an exact enumeration algorithm by recasting the problem as a linear mixed integer program. The proposed methods are illustrated using data from the CATIE schizophrenia study.

An app-based ecological momentary assessment of undergraduate student mental Health during the COVID-19 pandemic in Canada (Smart Healthy Campus Version 2.0): Longitudinal study.

This paper presents results from the Smart Healthy Campus 2.0 study/smartphone app, developed and used to collect mental health-related lifestyle data from 86 Canadian undergraduates January-August 2021. Objectives of the study were to 1) address the absence of longitudinal mental health overview and lifestyle-related data from Canadian undergraduate students, and 2) to identify associations between these self-reported mental health overviews (questionnaires) and lifestyle-related measures (from smartphone digital measures). This was a longitudinal repeat measures study conducted over 40 weeks. A 9-item mental health questionnaire was accessible once daily in the app. Two variants of this mental health questionnaire existed; the first was a weekly variant, available each Monday or until a participant responded during the week. The second was a daily variant available after the weekly variant. 6518 digital measure samples and 1722 questionnaire responses were collected. Mixed models were fit for responses to the two questionnaire variants and 12 phone digital measures (e.g. GPS, step counts). The daily questionnaire had positive associations with floors walked, installed apps, and campus proximity, while having negative associations with uptime, and daily calendar events. Daily depression had a positive association with uptime. Daily resilience appeared to have a slight positive association with campus proximity. The weekly questionnaire variant had positive associations with device idling and installed apps, and negative associations with floors walked, calendar events, and campus proximity. Physical activity, weekly, had a negative association with uptime, and a positive association with calendar events and device idling. These lifestyle indicators that associated with student mental health during the COVID-19 pandemic suggest directions for new mental health-related interventions (digital or otherwise) and further efforts in mental health surveillance under comparable circumstances.

Perceptions of Artificial Intelligence Use in Primary Care: A Qualitative Study with Providers and Staff of Ontario Community Health Centres.

PURPOSE: To understand staff and health care providers' views on potential use of artificial intelligence (AI)-driven tools to help care for patients within a primary care setting. METHODS: We conducted a qualitative descriptive study using individual semistructured interviews. As part of province-wide Learning Health Organization, Community Health Centres (CHCs) are a community-governed, team-based delivery model providing primary care for people who experience marginalization in Ontario, Canada. CHC health care providers and staff were invited to participate. Interviews were audio-recorded and transcribed verbatim. We performed a thematic analysis using a team approach. RESULTS: We interviewed 27 participants across 6 CHCs. Participants lacked in-depth knowledge about AI. Trust was essential to acceptance of AI; people need to be receptive to using AI and feel confident that the information is accurate. We identified internal influences of AI acceptance, including ease of use and complementing clinical judgment rather than replacing it. External influences included privacy, liability, and financial considerations. Participants felt AI could improve patient care and help prevent burnout for providers; however, there were concerns about the impact on the patient-provider relationship. CONCLUSIONS: The information gained in this study can be used for future research, development, and integration of AI technology.

Application of a novel index for understanding vascular health following pharmacological intervention in a pre-clinical model of metabolic disease.

While a thorough understanding of microvascular function in health and how it becomes compromised with progression of disease risk is critical for developing effective therapeutic interventions, our ability to accurately assess the beneficial impact of pharmacological interventions to improve outcomes is vital. Here we introduce a novel Vascular Health Index (VHI) that allows for simultaneous assessment of changes to vascular reactivity/endothelial function, vascular wall mechanics and microvessel density within cerebral and skeletal muscle vascular networks with progression of metabolic disease in obese Zucker rats (OZR); under control conditions and following pharmacological interventions of clinical relevance. Outcomes are compared to "healthy" conditions in lean Zucker rats. We detail the calculation of vascular health index, full assessments of validity, and describe progressive changes to vascular health index over the development of metabolic disease in obese Zucker rats. Further, we detail the improvement to cerebral and skeletal muscle vascular health index following chronic treatment of obese Zucker rats with anti-hypertensive (15%-52% for skeletal muscle vascular health index; 12%-48% for cerebral vascular health index; p < 0.05 for both), anti-dyslipidemic (13%-48% for skeletal muscle vascular health index; p < 0.05), anti-diabetic (12%-32% for cerebral vascular health index; p < 0.05) and anti-oxidant/inflammation (41%-64% for skeletal muscle vascular health index; 29%-42% for cerebral vascular health index; p < 0.05 for both) drugs. The results present the effectiveness of mechanistically diverse interventions to improve cerebral or skeletal muscle vascular health index in obese Zucker rats and provide insight into the superiority of some pharmacological agents despite similar effectiveness in terms of impact on intended targets. In addition, we demonstrate the utility of including a wider, more integrative approach to the study of microvasculopathy under settings of elevated disease risk and following pharmacological intervention. A major benefit of integrating vascular health index is an increased understanding of the development, timing and efficacy of interventions through greater insight into integrated microvascular function in combination with individual, higher resolution metrics.

Quantitative methods for descriptive intersectional analysis with binary health outcomes.

Intersectionality recognizes that in the context of sociohistorically shaped structural power relations, an individual's multiple social positions or identities (e.g., gender, ethnicity) can interact to affect health-related outcomes. Despite limited methodological guidance, intersectionality frameworks have increasingly been incorporated into epidemiological studies, both to describe health disparities and to examine their causes. This study aimed to advance methods in intersectional estimation of binary outcomes in descriptive health disparities research through evaluation of 7 potentially intersectional data analysis methods: cross-classification, regression with interactions, multilevel analysis of individual heterogeneity (MAIHDA), and decision trees (CART, CTree, CHAID, random forest). Accuracy of estimated intersection-specific outcome prevalence was evaluated across 192 intersections using simulated data scenarios. For comparison we included a non-intersectional main effects regression. We additionally assessed variable selection performance amongst decision trees. Example analyses using National Health and Nutrition Examination Study data illustrated differences in results between methods. At larger sample sizes, all methods except for CART performed better than non-intersectional main effects regression. In smaller samples, MAIHDA was the most accurate method but showed no advantage over main effects regression, while random forest, cross-classification, and saturated regression were the least accurate, and CTree and CHAID performed moderately well. CART performed poorly for estimation and variable selection. Sensitivity analyses examining the bias-variance tradeoff suggest MAIHDA as the preferred unbiased method for accurate estimation of high-dimensional intersections at smaller sample sizes. Larger sample sizes are more imperative for other methods. Results support the adoption of an intersectional approach to descriptive epidemiology.

Describing a complex primary health care population to support future decision support initiatives.

Introduction: Developing decision support tools using data from a health care organization, to support care within that organization, is a promising paradigm to improve care delivery and population health. Descriptive epidemiology may be a valuable supplement to stakeholder input towards selection of potential initiatives and to inform methodological decisions throughout tool development. We additionally propose that to properly characterize complex populations in large-scale descriptive studies, both simple statistical and machine learning techniques can be useful. Objective: To describe sociodemographic, clinical, and health care use characteristics of primary care clients served by the Alliance for Healthier Communities, which provides team-based primary health care through Community Health Centres (CHCs) across Ontario, Canada. Methods: We used electronic health record data from adult ongoing primary care clients served by CHCs in 2009-2019. We performed traditional table-based summaries for each characteristic; and applied three unsupervised learning techniques to explore patterns of common condition co-occurrence, care provider teams, and care frequency. Results: There were 221,047 eligible clients. Sociodemographics: We described 13 characteristics, stratified by CHC type and client multimorbidity status. Clinical characteristics: Eleven-year prevalence of 24 investigated conditions ranged from 1% (Hepatitis C) to 63% (chronic musculoskeletal problem) with non-uniform risk across the care history; multimorbidity was common (81%) with variable co-occurrence patterns. Health care use characteristics: Most care was provided by physician and nursing providers, with heterogeneous combinations of other provider types. A subset of clients had many issues addressed within single-visits and there was within- and between-client variability in care frequency. In addition to substantive findings, we discuss methodological considerations for future decision support initiatives. Conclusions: We demonstrated the use of methods from statistics and machine learning, applied with an epidemiological lens, to provide an overview of a complex primary care population and lay a foundation for stakeholder engagement and decision support tool development.

Developing a Smart Home Technology Innovation for People With Physical and Mental Health Problems: Considerations and Recommendations.

Smart home technologies present an unprecedented opportunity to improve health and health care by providing greater communication and connectivity with services and care providers and by supporting the daily activities of people managing both mental and physical health problems. Based on our experience from conducting smart technology health studies, including a smart home intervention, we provide guidance on developing and implementing such interventions. First, we describe the need for an overarching principle of security and privacy that must be attended to in all aspects of such a project. We then describe 4 key steps in developing a successful smart home innovation for people with mental and physical health conditions. These include (1) setting up the digital infrastructure, (2) ensuring the components of the system communicate, (3) ensuring that the system is designed for the intended population, and (4) engaging stakeholders. Recommendations on how to approach each of these steps are provided along with suggested literature that addresses additional considerations, guidelines, and equipment selection in more depth.