ABSTRACT
Understanding how emerging infectious diseases spread within and between countries is essential to contain future pandemics. Spread to new areas requires connectivity between one or more sources and a suitable local environment, but how these two factors interact at different stages of disease emergence remains largely unknown. Further, no analytical framework exists to examine their roles. Here we develop a dynamic modelling approach for infectious diseases that explicitly models both connectivity via human movement and environmental suitability interactions. We apply it to better understand recently observed (1995-2019) patterns as well as predict past unobserved (1983-2000) and future (2020-2039) spread of dengue in Mexico and Brazil. We find that these models can accurately reconstruct long-term spread pathways, determine historical origins, and identify specific routes of invasion. We find early dengue invasion is more heavily influenced by environmental factors, resulting in patchy non-contiguous spread, while short and long-distance connectivity becomes more important in later stages. Our results have immediate practical applications for forecasting and containing the spread of dengue and emergence of new serotypes. Given current and future trends in human mobility, climate, and zoonotic spillover, understanding the interplay between connectivity and environmental suitability will be increasingly necessary to contain emerging and re-emerging pathogens.
Subject(s)
Dengue , Dengue/epidemiology , Dengue/transmission , Dengue/virology , Humans , Brazil/epidemiology , Mexico/epidemiology , Animals , Dengue Virus/physiology , Communicable Diseases, Emerging/epidemiology , Communicable Diseases, Emerging/virology , Communicable Diseases, Emerging/transmission , Environment , Human Migration , Aedes/virologyABSTRACT
As the frequency of international travel increases, more individuals are at risk of travel-acquired infections (TAIs). In this ecological study of over 170,000 unique tests from Public Health Ontario's laboratory, we reviewed all laboratory-reported cases of malaria, dengue, chikungunya, and enteric fever in Ontario, Canada between 2008-2020 to identify high-resolution geographical clusters for potential targeted pre-travel prevention. Smoothed standardized incidence ratios (SIRs) and 95% posterior credible intervals (CIs) were estimated using a spatial Bayesian hierarchical model. High- and low-incidence areas were described using data from the 2016 Census based on the home forward sortation area of patients testing positive. A second model was used to estimate the association between drivetime to the nearest travel clinic and incidence of TAI within high-incidence areas. There were 6,114 microbiologically confirmed TAIs across Ontario over the study period. There was spatial clustering of TAIs (Moran's I = 0.59, p<0.0001). Compared to low-incidence areas, high-incidence areas had higher proportions of immigrants (p<0.0001), were lower income (p = 0.0027), had higher levels of university education (p<0.0001), and less knowledge of English/French languages (p<0.0001). In the high-incidence Greater Toronto Area (GTA), each minute increase in drive time to the closest travel clinic was associated with a 3% reduction in TAI incidence (95% CI 1-6%). While urban neighbourhoods in the GTA had the highest burden of TAIs, geographic proximity to a travel clinic in the GTA was not associated with an area-level incidence reduction in TAI. This suggests other barriers to seeking and adhering to pre-travel advice.
ABSTRACT
There has been considerable growth in the development of machine learning algorithms for clinical applications. The authors survey recent machine learning models developed with the use of large health administrative databases at ICES and highlight three areas of ongoing development that are particularly important for health system applications.
Subject(s)
Algorithms , Machine Learning , Databases, Factual , HumansABSTRACT
Pediatric intensivists are bombarded with more patient data than ever before. Integration and interpretation of data from patient monitors and the electronic health record (EHR) can be cognitively expensive in a manner that results in delayed or suboptimal medical decision making and patient harm. Machine learning (ML) can be used to facilitate insights from healthcare data and has been successfully applied to pediatric critical care data with that intent. However, many pediatric critical care medicine (PCCM) trainees and clinicians lack an understanding of foundational ML principles. This presents a major problem for the field. We outline the reasons why in this perspective and provide a roadmap for competency-based ML education for PCCM trainees and other stakeholders.
ABSTRACT
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.
Subject(s)
Ambulatory Care Sensitive Conditions , Population Health , Aged , Cohort Studies , Hospitalization , Humans , Machine Learning , Ontario/epidemiology , Retrospective StudiesABSTRACT
Cross-sector partnerships are vital for maintaining resilient health systems; however, few studies have sought to empirically assess the barriers and enablers of effective and responsible partnerships during public health emergencies. Through a qualitative, multiple case study, we analyzed 210 documents and conducted 26 interviews with stakeholders in three real-world partnerships between Canadian health organizations and private technology startups during the COVID-19 pandemic. The three partnerships involved: 1) deploying a virtual care platform to care for COVID-19 patients at one hospital, 2) deploying a secure messaging platform for physicians at another hospital, and 3) using data science to support a public health organization. Our results demonstrate that a public health emergency created time and resource pressures throughout a partnership. Given these constraints, early and sustained alignment on the core problem was critical for success. Moreover, governance processes designed for normal operations, such as procurement, were triaged and streamlined. Social learning, or the process of learning from observing others, offset some time and resource pressures. Social learning took many forms ranging from informal conversations between individuals at peer organisations (e.g., hospital chief information officers) to standing meetings at the local university's city-wide COVID-19 response table. We also found that startups' flexibility and understanding of the local context enabled them to play a highly valuable role in emergency response. However, pandemic fueled "hypergrowth" created risks for startups, such as introducing opportunities for deviation away from their core value proposition. Finally, we found each partnership navigated intense workloads, burnout, and personnel turnover through the pandemic. Strong partnerships required healthy, motivated teams. Visibility into and engagement in partnership governance, belief in partnership impact, and strong emotional intelligence in managers promoted team well-being. Taken together, these findings can help to bridge the theory-to-practice gap and guide effective cross-sector partnerships during public health emergencies.
ABSTRACT
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.
Subject(s)
COVID-19 , Databases, Factual , Vaccination/statistics & numerical data , COVID-19/epidemiology , COVID-19/prevention & control , Canada/epidemiology , Data Collection , Humans , PandemicsABSTRACT
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 1â¯657â¯395 patients, validated on 243â¯442 patients, and tested on 236â¯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 2â¯137â¯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.
Subject(s)
Age of Onset , Algorithms , Decision Making, Computer-Assisted , Diabetes Mellitus, Type 2/diagnosis , Diabetes Mellitus, Type 2/physiopathology , Forecasting/methods , Machine Learning , Risk Assessment/methods , Adolescent , Adult , Aged , Aged, 80 and over , Child , Cohort Studies , Diabetes Mellitus, Type 2/epidemiology , Electronic Health Records/statistics & numerical data , Female , Humans , Incidence , Male , Middle Aged , Ontario/epidemiology , Retrospective Studies , Young AdultABSTRACT
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.
Subject(s)
COVID-19/epidemiology , Disaster Planning/organization & administration , Emergencies/epidemiology , Health Promotion/organization & administration , Public Health Administration/methods , Cooperative Behavior , Humans , Interprofessional Relations , Population Surveillance/methods , Public Health , SARS-CoV-2 , SyndemicABSTRACT
Estimates in a 1989 study indicated that physicians in the United States were unable to reach a diagnosis that accounted for their patient's symptoms in up to 90% of outpatient patient encounters. Many proponents of artificial intelligence (AI) see the current process of moving from clinical data gathering to medical diagnosis as being limited by human analytic capability and expect AI to be a valuable tool to refine this process. The use of AI fundamentally calls into question the extent to which uncertainty in medical decision making is tolerated. Uncertainty is perceived by some as fundamentally undesirable and thus, for them, optimal decision making should be based on minimizing uncertainty. However, uncertainty cannot be reduced to zero; thus, relative uncertainty can be used as a metric to weigh the likelihood of various diagnoses being correct and the appropriateness of treatments. Here, the authors make the argument, using as examples the experiences of 2 AI systems, IBM Watson on Jeopardy and Watson for Oncology, that medical decision making based on relative uncertainty provides a better lens for understanding the application of AI to medicine than one that minimizes uncertainty. This approach to uncertainty has significant implications for how health care leaders consider the benefits and trade-offs of AI-assisted and AI-driven decision tools and ultimately integrate AI into medical practice.
Subject(s)
Artificial Intelligence/standards , Clinical Decision-Making/methods , Decision Making, Computer-Assisted , Diagnosis, Computer-Assisted/methods , Diagnosis, Computer-Assisted/psychology , Physicians/psychology , Uncertainty , Adult , Attitude to Computers , Female , Humans , Male , Middle Aged , United StatesABSTRACT
BACKGROUND: Nonpharmaceutical interventions (NPIs) are the primary tools to mitigate early spread of the coronavirus disease 2019 (COVID-19) pandemic; however, such policies are implemented variably at the federal, provincial or territorial, and municipal levels without centralized documentation. We describe the development of the comprehensive open Canadian Non-Pharmaceutical Intervention (CAN-NPI) data set, which identifies and classifies all NPIs implemented in regions across Canada in response to COVID-19, and provides an accompanying description of geographic and temporal heterogeneity. METHODS: We performed an environmental scan of government websites, news media and verified government social media accounts to identify NPIs implemented in Canada between Jan. 1 and Apr. 19, 2020. The CAN-NPI data set contains information about each intervention's timing, location, type, target population and alignment with a response stringency measure. We conducted descriptive analyses to characterize the temporal and geographic variation in early NPI implementation. RESULTS: We recorded 2517 NPIs grouped in 63 distinct categories during this period. The median date of NPI implementation in Canada was Mar. 24, 2020. Most jurisdictions heightened the stringency of their response following the World Health Organization's global pandemic declaration on Mar. 11, 2020. However, there was variation among provinces or territories in the timing and stringency of NPI implementation, with 8 out of 13 provinces or territories declaring a state of emergency by Mar. 18, and all by Mar. 22, 2020. INTERPRETATION: There was substantial geographic and temporal heterogeneity in NPI implementation across Canada, highlighting the importance of a subnational lens in evaluating the COVID-19 pandemic response. Our comprehensive open-access data set will enable researchers to conduct robust interjurisdictional analyses of NPI impact in curtailing COVID-19 transmission.
Subject(s)
COVID-19/therapy , Pandemics/prevention & control , Social Media/statistics & numerical data , COVID-19/diagnosis , COVID-19/epidemiology , COVID-19/virology , COVID-19 Testing/methods , Canada/epidemiology , Geography , Government , Humans , Infection Control/methods , Pandemics/legislation & jurisprudence , Physical Distancing , Policy , SARS-CoV-2/genetics , Time FactorsABSTRACT
With emerging innovations in artificial intelligence (AI) poised to substantially impact medical practice, interest in training current and future physicians about the technology is growing. Alongside comes the question of what, precisely, should medical students be taught. While competencies for the clinical usage of AI are broadly similar to those for any other novel technology, there are qualitative differences of critical importance to concerns regarding explainability, health equity, and data security. Drawing on experiences at the University of Toronto Faculty of Medicine and MIT Critical Data's "datathons", the authors advocate for a dual-focused approach: combining robust data science-focused additions to baseline health research curricula and extracurricular programs to cultivate leadership in this space.
ABSTRACT
Purpose of review: Machine learning (ML), a branch of artificial intelligence, is influencing all fields in medicine, with an abundance of work describing its application to adult practice. ML in pediatrics is distinctly unique with clinical, technical, and ethical nuances limiting the direct translation of ML tools developed for adults to pediatric populations. To our knowledge, no work has yet focused on outlining the unique considerations that need to be taken into account when designing and implementing ML in pediatrics. Recent findings: The nature of varying developmental stages and the prominence of family-centered care lead to vastly different data-generating processes in pediatrics. Data heterogeneity and a lack of high-quality pediatric databases further complicate ML research. In order to address some of these nuances, we provide a common pipeline for clinicians and computer scientists to use as a foundation for structuring ML projects, and a framework for the translation of a developed model into clinical practice in pediatrics. Throughout these pathways, we also highlight ethical and legal considerations that must be taken into account when working with pediatric populations and data. Summary: Here, we describe a comprehensive outline of special considerations required of ML in pediatrics from project ideation to implementation. We hope this review can serve as a high-level guideline for ML scientists and clinicians alike to identify applications in the pediatric setting, generate effective ML solutions, and subsequently deliver them to patients, families, and providers.