External validation and application of the Diabetes Population Risk Tool (DPoRT) for prediction of type 2 diabetes onset in the US population.

INTRODUCTION: Characterizing diabetes risk in the population is important for population health assessment and diabetes prevention planning. We aimed to externally validate an existing 10-year population risk model for type 2 diabetes in the USA and model the population benefit of diabetes prevention approaches using population survey data. RESEARCH DESIGN AND METHODS: The Diabetes Population Risk Tool (DPoRT), originally derived and validated in Canada, was applied to an external validation cohort of 23 477 adults from the 2009 National Health Interview Survey (NHIS). We assessed predictive performance for discrimination (C-statistic) and calibration plots against observed incident diabetes cases identified from the NHIS 2009-2018 cycles. We applied DPoRT to the 2018 NHIS cohort (n=21 187) to generate 10-year risk prediction estimates and characterize the preventive benefit of three diabetes prevention scenarios: (1) community-wide strategy; (2) high-risk strategy and (3) combined approach. RESULTS: DPoRT demonstrated good discrimination (C-statistic=0.778 (males); 0.787 (females)) and good calibration across the range of risk. We predicted a baseline risk of 10.2% and 21 076 000 new cases of diabetes in the USA from 2018 to 2028. The community-wide strategy and high-risk strategy estimated diabetes risk reductions of 0.2% and 0.3%, respectively. The combined approach estimated a 0.4% risk reduction and 843 000 diabetes cases averted in 10 years. CONCLUSIONS: DPoRT has transportability for predicting population-level diabetes risk in the USA using routinely collected survey data. We demonstrate the model's applicability for population health assessment and diabetes prevention planning. Our modeling predicted that the combination of community-wide and targeted prevention approaches for those at highest risk are needed to reduce diabetes burden in the USA.

Modeling chronic disease risk across equity factors using a population-based prediction model: the Chronic Disease Population Risk Tool (CDPoRT).

BACKGROUND: Predicting chronic disease incidence at a population level can help inform overall future chronic disease burden and opportunities for prevention. This study aimed to estimate the future burden of chronic disease in Ontario, Canada, using a population-level risk prediction algorithm and model interventions for equity-deserving groups who experience barriers to services and resources due to disadvantages and discrimination. METHODS: The validated Chronic Disease Population Risk Tool (CDPoRT) estimates the 10-year risk and incidence of major chronic diseases. CDPoRT was applied to data from the 2017/2018 Canadian Community Health Survey to predict baseline 10-year chronic disease estimates to 2027/2028 in the adult population of Ontario, Canada, and among equity-deserving groups. CDPoRT was used to model prevention scenarios of 2% and 5% risk reductions over 10 years targeting high-risk equity-deserving groups. RESULTS: Baseline chronic disease risk was highest among those with less than secondary school education (37.5%), severe food insecurity (19.5%), low income (21.2%) and extreme workplace stress (15.0%). CDPoRT predicted 1.42 million new chronic disease cases in Ontario from 2017/2018 to 2027/2028. Reducing chronic disease risk by 5% prevented 1500 cases among those with less than secondary school education, prevented 14 900 cases among those with low household income and prevented 2800 cases among food-insecure populations. Large reductions of 57 100 cases were found by applying a 5% risk reduction in individuals with quite a bit workplace stress. CONCLUSION: Considerable reduction in chronic disease cases was predicted across equity-defined scenarios, suggesting the need for prevention strategies that consider upstream determinants affecting chronic disease risk.

A study protocol for a predictive model to assess population-based avoidable hospitalization risk: Avoidable Hospitalization Population Risk Prediction Tool (AvHPoRT).

INTRODUCTION: Avoidable hospitalizations are considered preventable given effective and timely primary care management and are an important indicator of health system performance. The ability to predict avoidable hospitalizations at the population level represents a significant advantage for health system decision-makers that could facilitate proactive intervention for ambulatory care-sensitive conditions (ACSCs). The aim of this study is to develop and validate the Avoidable Hospitalization Population Risk Tool (AvHPoRT) that will predict the 5-year risk of first avoidable hospitalization for seven ACSCs using self-reported, routinely collected population health survey data. METHODS AND ANALYSIS: The derivation cohort will consist of respondents to the first 3 cycles (2000/01, 2003/04, 2005/06) of the Canadian Community Health Survey (CCHS) who are 18-74 years of age at survey administration and a hold-out data set will be used for external validation. Outcome information on avoidable hospitalizations for 5 years following the CCHS interview will be assessed through data linkage to the Discharge Abstract Database (1999/2000-2017/2018) for an estimated sample size of 394,600. Candidate predictor variables will include demographic characteristics, socioeconomic status, self-perceived health measures, health behaviors, chronic conditions, and area-based measures. Sex-specific algorithms will be developed using Weibull accelerated failure time survival models. The model will be validated both using split set cross-validation and external temporal validation split using cycles 2000-2006 compared to 2007-2012. We will assess measures of overall predictive performance (Nagelkerke R2), calibration (calibration plots), and discrimination (Harrell's concordance statistic). Development of the model will be informed by the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD) statement. ETHICS AND DISSEMINATION: This study was approved by the University of Toronto Research Ethics Board. The predictive algorithm and findings from this work will be disseminated at scientific meetings and in peer-reviewed publications.

"Whatever journey you want to take, I'll support you through": a mixed methods evaluation of a peer worker program in the hospital emergency department.

BACKGROUND: People who are unhoused, use substances (drugs and/or alcohol), and who have mental health conditions experience barriers to care access and are frequently confronted with discrimination and stigma in health care settings. The role of Peer Workers in addressing these gaps in a hospital-based context is not well characterized. The aim of this evaluation was to 1) outline the role of Peer Workers in the care of a marginalized populations in the emergency department; 2) characterize the impact of Peer Workers on patient care, and 3) to describe how being employed as a Peer Worker impacts the Peer. METHODS: Through a concurrent mixed methods evaluation, we explore the role of Peer Workers in the care of marginalized populations in the emergency department at two urban hospitals in Toronto, Ontario Canada. We describe the demographic characteristics of patients (n = 555) and the type of supports provided to patients collected through a survey between February and June 2022. Semi-structured, in-depth interviews were completed with Peer Workers (n = 7). Interviews were thematically analyzed using a deductive approach, complemented by an inductive approach to allow new themes to emerge from the data. RESULTS: Support provided to patients primarily consisted of friendly conversations (91.4%), discharge planning (59.6%), tactics to help the patient navigate their emotions/mental wellbeing (57.8%) and sharing their lived experience (50.1%). In over one third (38.9%) of all patient interactions, Peer Workers shared new information about the patient with the health care team (e.g., obtaining patient identification). Five major themes emerged from our interviews with Peer Workers which include: (1) Establishing empathy and building trust between the patient and their care team through self-disclosure; (2) Facilitating a person-centered approach to patient care through trauma-informed listening and accessible language; (3) Support for patient preferences on harm reduction; (4) Peer worker role facilitating self-acceptance and self-defined recovery; and (5) Importance of supports and resources to help Peer Workers navigate the emotional intensity of the emergency department. CONCLUSIONS: The findings add to the literature on Peer Worker programs and how such interventions are designed to best meet the needs of marginalized populations.

Modelling population-level and targeted interventions of weight loss on chronic disease prevention in the Canadian population.

Obesity is a known risk factor for major chronic diseases. Prevention of chronic disease is a top global priority. The study aimed to model scenarios of population-level and targeted weight loss interventions on 10-year projected risk of chronic disease in Canada using a population-level risk prediction algorithm. The validated Chronic Disease Population Risk Tool (CDPoRT) forecasts 10-year risk of chronic disease in the adult population. We applied CDPoRT to the 2013/14 Canadian Community Health Survey to generate prospective chronic disease estimates for adults 20 years and older in Canada (n = 83,220). CDPoRT was used to model the following scenarios: British Columbia's (BC) and Quebec's (QC) provincial population-level weight reduction targets, a population-level intervention that could achieve weight loss, targeted weight loss interventions for overweight and obese groups, and the combination of a population-level and targeted weight loss intervention. We estimated chronic disease risk reductions and number of cases prevented in each scenario compared with the baseline. At baseline, we predicted an 18.4% risk and 4,151,929 new cases of chronic disease in Canada over the 10-year period. Provincial weight loss targets applied to the Canadian population estimated chronic disease reductions of 0.6% (BC) and 0.1% (QC). The population-level intervention estimated a greater reduction in risk (0.2%), compared to the targeted interventions (0.1%). The combined approach estimated a 0.3% reduction in chronic disease risk. Our modelling predicted that population-level approaches that achieve weight loss in combination with targeted weight loss interventions can substantially decrease the chronic disease burden in Canada.

Predictive risk modelling of high resource users under different prescription drug coverage policies in Ontario and Manitoba, Canada.

INTRODUCTION: Studying high resource users (HRUs) across jurisdictions is a challenge due to variation in data availability and health services coverage. In Canada, coverage for pharmaceuticals varies across provinces under a mix of public and private plans, which has implications for ascertaining HRUs. We examined sociodemographic and behavioural predictors of HRUs in the presence of different prescription drug coverages in the provinces of Manitoba and Ontario. METHODS: Linked Canadian Community Health Surveys were used to create two cohorts of respondents from Ontario (n = 58,617, cycles 2005-2008) and Manitoba (n = 10,504, cycles 2007-2010). HRUs (top 5%) were identified by calculating health care utilization 5 years following interview date and computing all costs in the linked administrative databases, with three approaches used to include drug costs: (1) costs paid for by the provincial payer under age-based coverage; (2) costs paid for by the provincial payer under income-based coverage; (3) total costs regardless of the payer (publicly insured, privately insured, and out-of-pocket). Logistic regression estimated the association between sociodemographic, health, and behavioral predictors on HRU risk. RESULTS: The strength of the association between age (≥ 80 vs. <30) and becoming an HRU were attenuated with the inclusion of broader drug data (age based: OR 37.29, CI: 30.08-46.24; income based: OR 27.34, CI: 18.53-40.33; all drug payees: OR 29.08, CI: 19.64-43.08). With broader drug coverage, the association between heavy smokers vs. non-smokers on odds of becoming an HRU strengthened (age based: OR 1.58, CI: 1.32-1.90; income based: OR 2.97, CI: 2.18-4.05; all drug payees: OR 3.12, CI: 2.29-4.25). Across the different drug coverage policies, there was persistence in higher odds of becoming an HRU in low income households vs. high income households and in those with a reported chronic condition vs. no chronic conditions. CONCLUSIONS: The study illustrates that jurisdictional differences in how HRUs are ascertained based on drug coverage policies can influence the relative importance of some behavioural risk factors on HRU status, but most observed associations with health and sociodemographic risk factors were persistent, demonstrating that predictive risk modelling of HRUs can occur effectively across jurisdictions, even with some differences in public drug coverage policies.

Multimorbidity at time of death among persons with type 2 diabetes: a population-based study in Ontario, Canada.

OBJECTIVE: Individuals with Type 2 Diabetes are likely to experience multimorbidity and accumulate multiple chronic conditions over their life. We aimed to identify causes of death and chronic conditions at the time of death in a population-based cohort, and to analyze variations in the presence of diabetes at the time of death overall and across income and immigrant status. RESEARCH DESIGN AND METHODS: We conducted a retrospective cohort study of 2,199,801 adult deaths from 1992 to 2017 in Ontario, Canada. We calculated the proportion of decedents with chronic conditions at time of death and causes of death. The risk of diabetes at the time of death was modeled across sociodemographic variables with a log binomial regression adjusting for sex, age, immigrant status, area-level income. comorbiditiesand time. RESULTS: The leading causes of death in the cohort were cardiovascular and cancer. Decedents with diabetes had a higher prevalence of most chronic conditions than decedents without diabetes, including hypertension, osteo and other arthritis, chronic coronary syndrome, mood disorder, and congestive heart failure. The risk of diabetes at the time of death was 19% higher in immigrants (95%CI 1.18-1.20) and 15% higher in refugees (95%CI 1.12-1.18) compared to long-term residents, and 19% higher in the lowest income quintile (95%CI 1.18-1.20) relative to the highest income quintile, after adjusting for other covariates. CONCLUSIONS: Individuals with diabetes have a greater multimorbidity burden at the time of death, underscoring the importance of multiple chronic disease management among those living with diabetes and further considerations of the social determinants of health.

Experiences and Reported Outcomes of Patients and Caregivers Enrolled in an Integrated Care Program for Thoracic Surgery: A Qualitative Evaluation.

Background: Health care delivery is often poorly coordinated and fragmented. Integrated care (IC) programs represent one solution to improving continuity of care. The aim of this study was to understand experiences and reported outcomes of patients and caregivers in an IC Program that coordinates hospital and home care for thoracic surgery. Methods: A process evaluation was undertaken using qualitative methods. We conducted semi-structured interviews with 10 patients and 8 caregivers who received IC for thoracic surgery and were discharged between June 2019 and April 2020. A phenomenological approach was used to understand and characterize patient and caregiver experiences. Thematic analysis began with a deductive approach complemented by an inductive approach. Results: Four major themes evolved from patient and caregiver interviews, including 1) coordination and timeliness of patient care facilitated by an IC lead; 2) the provision of person-centred care and relational continuity fostered feelings of partnership with patients and caregivers; 3) clear communication and one shared digital record increased informational continuity; and 4) impacts of IC on patient and caregiver outcomes. Conclusions: Patients and caregivers generally reported this IC Program met their health care needs, which may help inform how future IC programs are designed.

Variations in all-cause mortality, premature mortality and cause-specific mortality among persons with diabetes in Ontario, Canada.

INTRODUCTION: Patients with diabetes have a higher risk of mortality compared with the general population. Large population-based studies that quantify variations in mortality risk for patients with diabetes among subgroups in the population are lacking. This study aimed to examine the sociodemographic differences in the risk of all-cause mortality, premature mortality, and cause-specific mortality in persons diagnosed with diabetes. RESEARCH DESIGN AND METHODS: We conducted a population-based cohort study of 1 741 098 adults diagnosed with diabetes between 1994 and 2017 in Ontario, Canada using linked population files, Canadian census, health administrative and death registry databases. We analyzed the association between sociodemographics and other covariates on all-cause mortality and premature mortality using Cox proportional hazards models. A competing risk analysis using Fine-Gray subdistribution hazards models was used to analyze cardiovascular and circular mortality, cancer mortality, respiratory mortality, and mortality from external causes of injury and poisoning. RESULTS: After full adjustment, individuals with diabetes who lived in the lowest income neighborhoods had a 26% (HR 1.26, 95% CI 1.25 to 1.27) increased hazard of all-cause mortality and 44% (HR 1.44, 95% CI 1.42 to 1.46) increased risk of premature mortality, compared with individuals with diabetes living in the highest income neighborhoods. In fully adjusted models, immigrants with diabetes had reduced risk of all-cause mortality (HR 0.46, 95% CI 0.46 to 0.47) and premature mortality (HR 0.40, 95% CI 0.40 to 0.41), compared with long-term residents with diabetes. Similar HRs associated with income and immigrant status were observed for cause-specific mortality, except for cancer mortality, where we observed attenuation in the income gradient among persons with diabetes. CONCLUSIONS: The observed mortality variations suggest a need to address inequality gaps in diabetes care for persons with diabetes living in the lowest income areas.

Predicting hospitalisations related to ambulatory care sensitive conditions with machine learning for population health planning: derivation and validation cohort study.

OBJECTIVE: To predict older adults' risk of avoidable hospitalisation related to ambulatory care sensitive conditions (ACSC) using machine learning applied to administrative health data of Ontario, Canada. DESIGN, SETTING AND PARTICIPANTS: A retrospective cohort study was conducted on a large cohort of all residents covered under a single-payer system in Ontario, Canada over the period of 10 years (2008-2017). The study included 1.85 million Ontario residents between 65 and 74 years old at any time throughout the study period. DATA SOURCES: Administrative health data from Ontario, Canada obtained from the (ICES formely known as the Institute for Clinical Evaluative Sciences Data Repository. MAIN OUTCOME MEASURES: Risk of hospitalisations due to ACSCs 1 year after the observation period. RESULTS: The study used a total of 1 854 116 patients, split into train, validation and test sets. The ACSC incidence rates among the data points were 1.1% for all sets. The final XGBoost model achieved an area under the receiver operating curve of 80.5% and an area under precision-recall curve of 0.093 on the test set, and the predictions were well calibrated, including in key subgroups. When ranking the model predictions, those at the top 5% of risk as predicted by the model captured 37.4% of those presented with an ACSC-related hospitalisation. A variety of features such as the previous number of ambulatory care visits, presence of ACSC-related hospitalisations during the observation window, age, rural residence and prescription of certain medications were contributors to the prediction. Our model was also able to capture the geospatial heterogeneity of ACSC risk in Ontario, and especially the elevated risk in rural and marginalised regions. CONCLUSIONS: This study aimed to predict the 1-year risk of hospitalisation from ambulatory-care sensitive conditions in seniors aged 65-74 years old with a single, large-scale machine learning model. The model shows the potential to inform population health planning and interventions to reduce the burden of ACSC-related hospitalisations.

Forecasting Diabetes Cases Prevented and Cost Savings Associated with Population Increases of Walking in the Greater Toronto and Hamilton Area, Canada.

Promoting adequate levels of physical activity in the population is important for diabetes prevention. However, the scale needed to achieve tangible population benefits is unclear. We aimed to estimate the public health impact of increases in walking as a means of diabetes prevention and health care cost savings attributable to diabetes. We applied the validated Diabetes Population Risk Tool (DPoRT) to the 2015/16 Canadian Community Health Survey for adults aged 18-64, living in the Greater Toronto and Hamilton area, Ontario, Canada. DPoRT was used to generate three population-level scenarios involving increases in walking among individuals with low physical activity levels, low daily step counts and high dependency on non-active forms of travel, compared to a baseline scenario (no change in walking rates). We estimated number of diabetes cases prevented and health care costs saved in each scenario compared with the baseline. Each of the three scenarios predicted a considerable reduction in diabetes and related health care cost savings. In order of impact, the largest population benefits were predicted from targeting populations with low physical activity levels, low daily step counts, and non active transport use. Population increases of walking by 25 min each week was predicted to prevent up to 10.4 thousand diabetes cases and generate CAD 74.4 million in health care cost savings in 10 years. Diabetes reductions and cost savings were projected to be higher if increases of 150 min of walking per week could be achieved at the population-level (up to 54.3 thousand diabetes cases prevented and CAD 386.9 million in health care cost savings). Policy, programming, and community designs that achieve modest increases in population walking could translate to meaningful reductions in the diabetes burden and cost savings to the health care system.

A sub-national real-time epidemiological and vaccination database for the COVID-19 pandemic in Canada.

The COVID-19 pandemic has demonstrated the need for real-time, open-access epidemiological information to inform public health decision-making and outbreak control efforts. In Canada, authority for healthcare delivery primarily lies at the provincial and territorial level; however, at the outset of the pandemic no definitive pan-Canadian COVID-19 datasets were available. The COVID-19 Canada Open Data Working Group was created to fill this crucial data gap. As a team of volunteer contributors, we collect daily COVID-19 data from a variety of governmental and non-governmental sources and curate a line-list of cases and mortality for all provinces and territories of Canada, including information on location, age, sex, travel history, and exposure, where available. We also curate time series of COVID-19 recoveries, testing, and vaccine doses administered and distributed. Data are recorded systematically at a fine sub-national scale, which can be used to support robust understanding of COVID-19 hotspots. We continue to maintain this dataset, and an accompanying online dashboard, to provide a reliable pan-Canadian COVID-19 resource to researchers, journalists, and the general public.

Characterising mental health and addictions and assault-related health care use in the year prior to death: a population-based linked cohort study of homicide victims.

INTRODUCTION: Homicide is an important cause of death for older youth and adult Canadians; however, little is known about health care use prior to death among this population. OBJECTIVES: To characterise health care use for mental health and addictions (MHA) and serious assault (herein referred to assault) one year prior to death among individuals who died by homicide in Ontario, Canada using linked mortality and health care utilisation data. METHODS: We report rates of health care use for MHA and assault in the year prior to death among all individuals 16 years and older in Ontario, Canada, who died by homicide from April 2003 to December 2012 (N = 1,541). Health care use for MHA included inpatient stays, emergency department (ED) visits and outpatient visits, whereas health care use for assault included only hospital-based care (ED visits and inpatient stays). Sociodemographic characteristics and health care utilisation were examined across homicide deaths, stratified by sex. RESULTS: Overall, 28.5% and 5.9% of homicide victims sought MHA and assault care in the year prior to death, respectively. A greater proportion of females accessed care for MHA, whereas a greater proportion of males accessed assault-related health care. Males were more likely to be hospitalised following an ED visit for a MHA or assault related reason, in comparison to females. The most common reason for a MHA hospital visit was for substance-related disorders. We found an increase over time for hospital-based visits for assault prior to death, a trend that was not observed for MHA-related visits. CONCLUSIONS: A large proportion of homicide victims interacted with the health care system for MHA or assault in the year prior to death. An increase in hospital-based visits for assault-related reasons prior to death was observed. These trends may offer insight into avenues for support and prevention for victims of homicide.

Development and Validation of a Machine Learning Model Using Administrative Health Data to Predict Onset of Type 2 Diabetes.

Importance: Systems-level barriers to diabetes care could be improved with population health planning tools that accurately discriminate between high- and low-risk groups to guide investments and targeted interventions. Objective: To develop and validate a population-level machine learning model for predicting type 2 diabetes 5 years before diabetes onset using administrative health data. Design, Setting, and Participants: This decision analytical model study used linked administrative health data from the diverse, single-payer health system in Ontario, Canada, between January 1, 2006, and December 31, 2016. A gradient boosting decision tree model was trained on data from 1 657 395 patients, validated on 243 442 patients, and tested on 236 506 patients. Costs associated with each patient were estimated using a validated costing algorithm. Data were analyzed from January 1, 2006, to December 31, 2016. Exposures: A random sample of 2 137 343 residents of Ontario without type 2 diabetes was obtained at study start time. More than 300 features from data sets capturing demographic information, laboratory measurements, drug benefits, health care system interactions, social determinants of health, and ambulatory care and hospitalization records were compiled over 2-year patient medical histories to generate quarterly predictions. Main Outcomes and Measures: Discrimination was assessed using the area under the receiver operating characteristic curve statistic, and calibration was assessed visually using calibration plots. Feature contribution was assessed with Shapley values. Costs were estimated in 2020 US dollars. Results: This study trained a gradient boosting decision tree model on data from 1 657 395 patients (12 900 257 instances; 6 666 662 women [51.7%]). The developed model achieved a test area under the curve of 80.26 (range, 80.21-80.29), demonstrated good calibration, and was robust to sex, immigration status, area-level marginalization with regard to material deprivation and race/ethnicity, and low contact with the health care system. The top 5% of patients predicted as high risk by the model represented 26% of the total annual diabetes cost in Ontario. Conclusions and Relevance: In this decision analytical model study, a machine learning model approach accurately predicted the incidence of diabetes in the population using routinely collected health administrative data. These results suggest that the model could be used to inform decision-making for population health planning and diabetes prevention.

Estimating Population Benefits of Prevention Approaches Using a Risk Tool: High Resource Users in Ontario, Canada.

BACKGROUND: Healthcare spending is concentrated, with a minority of the population accounting for the majority of healthcare costs. METHODS: The authors modelled the impact of high resource user (HRU) prevention strategies within five years using the validated High Resource User Population Risk Tool. RESULTS: The authors estimated 758,000 new HRUs in Ontario from 2013-2014 to 2018-2019, resulting in $16.20 billion in healthcare costs (Canadian dollars 2016). The prevention approach that had the largest reduction in HRUs was targeting health-risk behaviours. CONCLUSIONS: This study demonstrates the use of a policy tool by decision makers to support prevention approaches that consider the impact on HRUs and estimated healthcare costs.

Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data.

Across jurisdictions, government and health insurance providers hold a large amount of data from patient interactions with the healthcare system. We aimed to develop a machine learning-based model for predicting adverse outcomes due to diabetes complications using administrative health data from the single-payer health system in Ontario, Canada. A Gradient Boosting Decision Tree model was trained on data from 1,029,366 patients, validated on 272,864 patients, and tested on 265,406 patients. Discrimination was assessed using the AUC statistic and calibration was assessed visually using calibration plots overall and across population subgroups. Our model predicting three-year risk of adverse outcomes due to diabetes complications (hyper/hypoglycemia, tissue infection, retinopathy, cardiovascular events, amputation) included 700 features from multiple diverse data sources and had strong discrimination (average test AUC = 77.7, range 77.7-77.9). Through the design and validation of a high-performance model to predict diabetes complications adverse outcomes at the population level, we demonstrate the potential of machine learning and administrative health data to inform health planning and healthcare resource allocation for diabetes management.

A study protocol for a predictive algorithm to assess population-based premature mortality risk: Premature Mortality Population Risk Tool (PreMPoRT).

BACKGROUND: Premature mortality is an important population health indicator used to assess health system functioning and to identify areas in need of health system intervention. Predicting the future incidence of premature mortality in the population can facilitate initiatives that promote equitable health policies and effective delivery of public health services. This study protocol proposes the development and validation of the Premature Mortality Risk Prediction Tool (PreMPoRT) that will predict the incidence of premature mortality using large population-based community health surveys and multivariable modeling approaches. METHODS: PreMPoRT will be developed and validated using various training, validation, and test data sets generated from the six cycles of the Canadian Community Health Survey (CCHS) linked to the Canadian Vital Statistics Database from 2000 to 2017. Population-level risk factor information on demographic characteristics, health behaviors, area level measures, and other health-related factors will be used to develop PreMPoRT and to predict the incidence of premature mortality, defined as death prior to age 75, over a 5-year period. Sex-specific Weibull accelerated failure time models will be developed using a Canadian provincial derivation cohort consisting of approximately 500,000 individuals, with approximately equal proportion of males and females, and about 12,000 events of premature mortality. External validation will be performed using separate linked files (CCHS cycles 2007-2008, 2009-2010, and 2011-2012) from the development cohort (CCHS cycles 2000-2001, 2003-2004, and 2005-2006) to check the robustness of the prediction model. Measures of overall predictive performance (e.g., Nagelkerke's R2), calibration (e.g., calibration plots), and discrimination (e.g., Harrell's concordance statistic) will be assessed, including calibration within defined subgroups of importance to knowledge users and policymakers. DISCUSSION: Using routinely collected risk factor information, we anticipate that PreMPoRT will produce population-based estimates of premature mortality and will be used to inform population strategies for prevention.

External Validation of a Population-Based Prediction Model for High Healthcare Resource Use in Adults.

Predicting high healthcare resource users is important for informing prevention strategies and healthcare decision-making. We aimed to cross-provincially validate the High Resource User Population Risk Tool (HRUPoRT), a predictive model that uses population survey data to estimate 5 year risk of becoming a high healthcare resource user. The model, originally derived and validated in Ontario, Canada, was applied to an external validation cohort. HRUPoRT model predictors included chronic conditions, socio-demographics, and health behavioural risk factors. The cohort consisted of 10,504 adults (≥18 years old) from the Canadian Community Health Survey in Manitoba, Canada (cycles 2007/08 and 2009/10). A person-centred costing algorithm was applied to linked health administrative databases to determine respondents' healthcare utilization over 5 years. Model fit was assessed using the c-statistic for discrimination and calibration plots. In the external validation cohort, HRUPoRT demonstrated strong discrimination (c statistic = 0.83) and was well calibrated across the range of risk. HRUPoRT performed well in an external validation cohort, demonstrating transportability of the model in other jurisdictions. HRUPoRT's use of population survey data enables a health equity focus to assist with decision-making on prevention of high healthcare resource use.

Predicting population health with machine learning: a scoping review.

OBJECTIVE: To determine how machine learning has been applied to prediction applications in population health contexts. Specifically, to describe which outcomes have been studied, the data sources most widely used and whether reporting of machine learning predictive models aligns with established reporting guidelines. DESIGN: A scoping review. DATA SOURCES: MEDLINE, EMBASE, CINAHL, ProQuest, Scopus, Web of Science, Cochrane Library, INSPEC and ACM Digital Library were searched on 18 July 2018. ELIGIBILITY CRITERIA: We included English articles published between 1980 and 2018 that used machine learning to predict population-health-related outcomes. We excluded studies that only used logistic regression or were restricted to a clinical context. DATA EXTRACTION AND SYNTHESIS: We summarised findings extracted from published reports, which included general study characteristics, aspects of model development, reporting of results and model discussion items. RESULTS: Of 22 618 articles found by our search, 231 were included in the review. The USA (n=71, 30.74%) and China (n=40, 17.32%) produced the most studies. Cardiovascular disease (n=22, 9.52%) was the most studied outcome. The median number of observations was 5414 (IQR=16 543.5) and the median number of features was 17 (IQR=31). Health records (n=126, 54.5%) and investigator-generated data (n=86, 37.2%) were the most common data sources. Many studies did not incorporate recommended guidelines on machine learning and predictive modelling. Predictive discrimination was commonly assessed using area under the receiver operator curve (n=98, 42.42%) and calibration was rarely assessed (n=22, 9.52%). CONCLUSIONS: Machine learning applications in population health have concentrated on regions and diseases well represented in traditional data sources, infrequently using big data. Important aspects of model development were under-reported. Greater use of big data and reporting guidelines for predictive modelling could improve machine learning applications in population health. REGISTRATION NUMBER: Registered on the Open Science Framework on 17 July 2018 (available at https://osf.io/rnqe6/).