Population Health Decision-Making: Risk Segmentation, Stratification, and Management

2021 ◽  
Author(s):  
Julie L. Mascari ◽  
Anne M. Hewitt
Keyword(s):  
Decision Making ◽  
Population Health ◽  
Health Decision Making ◽  
Health Decision

scholarly journals Use of Machine Learning and Linked Population Health Data to Develop Predictive Risk Algorithms for Population Health Decision-Making

2020 ◽  
Vol 5 (5) ◽  
Author(s):  
Stacey Fisher ◽  
Lief Pagalan ◽  
Mack Hurst ◽  
Meghan O’Neill ◽  
Lori Diemert ◽  
...  
Keyword(s):  
Machine Learning ◽  
Decision Making ◽  
Population Health ◽  
Support Vector ◽  
Learning Methods ◽  
Individual Level ◽  
Health Decision Making ◽  
Machine Learning Methods ◽  
Health Decision ◽  
Predictive Risk

IntroductionData from population health surveys, administrative health records and environmental monitoring are increasingly being linked at the individual level. As these data become available to health researchers, there is an increasing need for methods which can make sense of large, noisy and heterogeneous data and can model complex relationships. Using these data, machine learning methods have the potential to produce population health risk algorithms with better performance than those developed with traditional statistical approaches. Objectives and ApproachThe objective of this work is to explore the use of machine learning methods for the development, validation and implementation of predictive risk algorithms designed specifically for population health planning purposes. Algorithms to predict risk of dementia and avoidable hospitalizations are in development using the Canadian Community Health Survey, geographic sociodemographic information, administrative health care utilization data and vital statistics. Methods being explored include naïve Bayes, gradient boosting, support vector machines and neural networks. ResultsRisk algorithms for population health should generally prioritize calibration over discrimination due to implications for resource allocation decisions. Approaches to minimize the risk of overfitting should be used and reweighting of unbalanced data avoided as it distorts the population-level nature of the data. It is important to be aware of propagating underlying bias in the data or exacerbating existing health inequities, which can be evaluated in part through assessment of calibration across relevant population subgroups. Approaches that consider multi-level data structures are needed to appropriately incorporate neighbourhood-level measures with individual-level information. To maximize population health impact and acceptability, model transparency and interpretability should be prioritized. ConclusionThere is tremendous potential for machine learning approaches to leverage large volumes of linked population data to produce predictive risk algorithms that will inform population health decision-making. Future work will explore use of complex environmental remote sensing and built environment data.

scholarly journals The NCCMT’s dynamic model for evidence-informed public health

2020 ◽  
Vol 30 (Supplement_5) ◽  
Author(s):  
E Clark ◽  
S Neil-Sztramko ◽  
M Dobbins
Keyword(s):  
Public Health ◽  
Decision Making ◽  
Research Evidence ◽  
Decision Makers ◽  
Local Data ◽  
Public Health Decision ◽  
Health Decision Making ◽  
Political Preferences ◽  
Health Decision ◽  
Structured Approach

Abstract Issue It is well accepted that public health decision makers should use the best available research evidence in their decision-making process. However, research evidence alone is insufficient to inform public health decision making. Description of the problem As new challenges to public health emerge, there can be a paucity of high quality research evidence to inform decisions on new topics. Public health decision makers must combine various sources of evidence with their public health expertise to make evidence-informed decisions. The National Collaborating Centre for Methods and Tools (NCCMT) has developed a model which combines research evidence with other critical sources of evidence that can help guide decision makers in evidence-informed decision making. Results The NCCMT's model for evidence-informed public health combines findings from research evidence with local data and context, community and political preferences and actions and evidence on available resources. The model has been widely used across Canada and worldwide, and has been integrated into many public health organizations' decision-making processes. The model is also used for teaching an evidence-informed public health approach in Masters of Public Health programs around the globe. The model provides a structured approach to integrating evidence from several critical sources into public health decision making. Use of the model helps ensure that important research, contextual and preference information is sought and incorporated. Lessons Next steps for the model include development of a tool to facilitate synthesis of evidence across all four domains. Although Indigenous knowledges are relevant for public health decision making and should be considered as part of a complete assessment the current model does not capture Indigenous knowledges. Key messages Decision making in public health requires integrating the best available evidence, including research findings, local data and context, community and political preferences and available resources. The NCCMT’s model for evidence-informed public health provides a structured approach to integrating evidence from several critical sources into public health decision making.

scholarly journals Reproductive Health Decision-Making in Perinatally HIV-Infected Adolescents and Young Adults

2012 ◽  
Vol 17 (5) ◽  
pp. 797-808 ◽  
Author(s):  
Cynthia Fair ◽  
Lori Wiener ◽  
Sima Zadeh ◽  
Jamie Albright ◽  
Claude Ann Mellins ◽  
...  
Keyword(s):  
Decision Making ◽  
Young Adults ◽  
Reproductive Health ◽  
Adolescents And Young Adults ◽  
Health Decision Making ◽  
Health Decision

scholarly journals Contributions in the field of Public Health for decision-making in health

2017 ◽  
Vol 27 (2) ◽  
pp. 128 ◽  
Author(s):  
Luiz Antônio Tavares Neves
Keyword(s):  
Public Health ◽  
Decision Making ◽  
Motor Development ◽  
Growth And Development ◽  
Human Growth ◽  
Public Health Decision ◽  
Health Decision Making ◽  
Scientific World ◽  
Health Decision ◽  
Human Growth And Development

  Brazil has made a wide development and contribution in the field of Public Health. These contributions have maximized public health decision-making, which is a factor of great importance for the maintenance of health of a given population, either in the prevention of disease, as is the case of immunizations or with actions in Health Promotion, improving the quality of life of the affected population. Thus, the Journal of Human Growth and Development has contributed enormously to the dissemination of knowledge, not only in Brazil but also in the world making a major effort with its publications in English which is the preferred language of the modern scientific world. It was evidenced the importance of research in the investigation of better ways to obtain the public health of a given community, bringing discussion of themes that involve aspects of human growth and development such as nutritional aspects, sexuality, motor development, covering situations and diseases as obesity, cerebral palsy, dyslexia and violence. The Journal of Human Growth and Development has maintained the tradition of approaching the different aspects that involve clinical practice for people and for Public Health. 

Sign in / Sign up

Export Citation Format

Share Document