Emmalin Buajitti

Emmalin Buajitti

Auto-generated profile, based on publicly available information

Emmalin Buajitti

Dalla Lana School of Public Health, University of Toronto , Toronto, ON

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 October 2020 in BMJ Open
Verified
Journal Article
Open access
PDF file
JMJason Denzil Morgenstern
Jason Denzil Morgenstern
EBEmmalin Buajitti
Emmalin Buajitti
MOMeghan O’nEill
Meghan O’nEill
TPThomas Piggott
Thomas Piggott
VGVivek Goel
Vivek Goel
Laura RosellaLaura Rosella
Laura Rosella
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/).

2 April 2020 in PLOS ONE
Verified
Journal Article
Open access
PDF file
EBEmmalin Buajitti
Emmalin Buajitti
JFJohn Frank
John Frank
TWTristan Watson
Tristan Watson
KKKathy Kornas
Kathy Kornas
Laura RosellaLaura Rosella
Laura Rosella
This study aimed to characterize trends in absolute and relative socioeconomic inequalities in adult premature mortality between 1992 and 2017, in the context of declining population-wide mortality rates. We conducted a population-based cohort study of all adult premature deaths in Ontario, Canada using provincial vital statistics data linked to census-based, area-level deprivation indices for socioeconomic status. The cohort included all individuals eligible for Ontario’s single-payer health insurance system at any time between January 1, 1992 and December 31, 2017 with a recorded Ontario place of residence and valid socioeconomic status information (N = 820,370). Deaths between ages 18 and 74 were used to calculate adult premature mortality rates per 1000, stratified by provincial quintile of material deprivation. Relative inequalities were measured using Relative Index of Inequality (RII) measures. Absolute inequalities were estimated using Slope Index of Inequality (SII) measures. All outcome measures were calculated as sex-specific, annual measures for each year from 1992 to 2017. Premature mortality rates declined in all socioeconomic groups between 1992 and 2017. Relative inequalities in premature mortality increased over the same period. Absolute inequalities were mostly stable between 1992 and 2007, but increased dramatically between 2008 and 2017, with larger increases to absolute inequalities seen in females than in males. As in other developed countries, long-term downward trends in all-cause premature mortality in Ontario, Canada have shifted to a plateau pattern in recent years, especially in lower- socioeconomic status subpopulations. Determinants of this may differ by setting. Regular monitoring of mortality by socioeconomic status is the only way that this phenomenon can be detected sensitively and early, for public health attention and possible corrective action.

22 July 2022 in The Journal of Rural Health
Verified
Journal Article
Closed access
EFErik Loewen Friesen
Erik Loewen Friesen
WYWinnie Yu
Winnie Yu
EBEmmalin Buajitti
Emmalin Buajitti
PSPeter Selby
Peter Selby
LRLaura Rosella
Laura Rosella
PKPaul Kurdyak
Paul Kurdyak

12 July 2024 in Research in Health Services & Regions
Verified
Journal Article
Open access
PDF file
AAAliya Allen-Valley
Aliya Allen-Valley
SBShalu Bains
Shalu Bains
KRKaren Rai
Karen Rai
NSNirmal Summan
Nirmal Summan
MEMay Eleid
May Eleid
Laura RosellaLaura Rosella
Laura Rosella
Disparities in healthcare delivery and design are deeply-rooted within healthcare systems globally. Many researchers have developed methods to measure inequity; however, there currently exists no accepted measurement approach implemented consistently across health systems. We applied the model-based Relative Index of Inequality (RII) as a measure of inequity at one of Canada’s largest health systems, Trillium Health Partners, across two service types: planned and outpatient. Our RII estimates suggest that the lowest-SES individuals received planned and outpatient services at rates 2.4 times and 2.5 times lower than the highest-SES individuals, respectively. Across both service types, the largest disparity was for breast cancer screening, where patients from the lowest-SES neighbourhoods were 5.4 times less likely to use this service at THP. These findings further underscore the importance of consistently measuring and monitoring inequities to develop effective strategies to address the health needs of patients from lower SES neighbourhoods. The approach used within this study should be considered for widespread integration into health system reporting metrics.

4 March 2025 in Epidemiology
Verified
Journal Article
Open access
EBEmmalin Buajitti
Emmalin Buajitti
Laura RosellaLaura Rosella
Laura Rosella
Background: Health selection into neighborhoods describes unhealthy people moving disproportionately to lower-income neighborhoods, producing observable socioeconomic gradients sometimes falsely attributed to neighborhood effects on health. We investigated residential mobility outcomes and their relationship to baseline health using population-level data linkages in Ontario, Canada. Methods: We included Canadian Community Health Survey respondents ages 25 to 64 between 2005 and 2014 (n = 93,235). We assessed baseline health using self-reported health and multimorbidity. We captured moves using health administrative data and the Canadian census. We fit multinomial logistic regression models with a six-category residential mobility outcome: (1) nonmovers from low-income neighborhoods; (2) nonmovers from high-income neighborhoods; (3) movers from low-income to low-income; (4) movers from low-income to high-income; (5) movers from high-income to low-income; and (6) movers from high-income to high-income. We adjusted models for the Canadian Community Health Survey cycle, age, sex, household income, immigrant status, and residential instability. Results: Compared with those with very good or excellent health, respondents reporting fair or poor health at baseline had higher odds of moving from low- to low-income neighborhoods (Adjusted odds ratios [aOR] = 1.73; 95% confidence interval [CI] = 1.46, 2.05), moving from high- to low-income (aOR = 1.64; 95% CI = 1.35, 1.98), moving from low- to high-income (aOR = 1.26; 95% CI = 1.04, 1.54), and not moving within low-income (aOR = 1.36; 1.23, 1.51) relative to not moving within high-income. Results were consistent for objective health measures, comparing respondents with at least four chronic conditions to those with one or none. Conclusions: In a large, population-based study, both subjective and objective measures of health had a strong relationship with residential mobility outcomes.

18 July 2026 in American Journal of Epidemiology
Verified
Journal Article
Open access
IGIngrid Giesinger
Ingrid Giesinger
EBEmmalin Buajitti
Emmalin Buajitti
ASArjumand Siddiqi
Arjumand Siddiqi
PSPeter M Smith
Peter M Smith
RKRahul G Krishnan
Rahul G Krishnan
Laura RosellaLaura Rosella
Laura Rosella
Multimorbidity follows a strong social gradient, yet how the co-occurrence of social determinants shapes risk remains poorly understood. Most research examines individual determinants in isolation, potentially obscuring socially patterned subgroups relevant to multimorbidity risk. This study examines the association between multidimensional social exposure profiles (derived from individual- and area-level determinants) and multimorbidity risk. Profiles were derived through unsupervised clustering applied to population-based cohort of Ontario respondents to the Canadian Community Health Survey (2001-2011) and linked area-level Census measures. Chronic disease and subsequent multimorbidity status were identified through linkage to administrative health data until 2022. Sex-stratified Weibull models were used to estimate hazard ratios for the association between multidimensional social exposure and incident multimorbidity. Unsupervised clustering identified six distinct social exposure profiles, with multimorbidity onset differing across profiles and elevated risk observed across multiple patterns of social disadvantage, rather than following a simple graded gradient. In sex-stratified analyses, disadvantage social exposure profiles were associated with an earlier multimorbidity onset among females (adjusted HR: 1.70, 95%CI, 1.18-2.53) and males (adjusted HR: 1.59, 95%CI, 1.20-2.05). These multidimensional social exposure profiles capture population-level social patterning associated with differential multimorbidity risk. These findings have implications for upstream policy aimed at reducing inequities in multimorbidity.