Machine Learning in
Public Health
In the midst of the COVID-19 global pandemic, it is clear that issues of community, interdependence, environment and other multi-sectoral factors outside of the hospital are critical with respect to our health and well-being. In this first Machine Learning in Public Health Workshop at NeurIPS, we aim to explore the role of machine learning with respect to these important topics.
In the midst of the COVID-19 global pandemic, it is clear that issues of community, interdependence, environment and other multi-sectoral factors outside of the hospital are critical with respect to our health and well-being. In this first Machine Learning in Public Health Workshop at NeurIPS, we aim to explore the role of machine learning with respect to these important topics.
Submissions are due Oct. 2 2020 midnight, AoE. Submit here: https://cmt3.research.microsoft.com/MLPH2020
Submissions are due Oct. 2 2020 midnight, AoE. Submit here: https://cmt3.research.microsoft.com/MLPH2020
Examples of topics that are out of scope for us but would be appropriate for the ML4H workshop include applying existing ML to a COVID clinical treatment prediction problem. Whereas, creating a method to model the effect of population-level interventions in a certain location would be more appropriate for our workshop given the population and outside hospital focus.
Examples of topics that are out of scope for us but would be appropriate for the ML4H workshop include applying existing ML to a COVID clinical treatment prediction problem. Whereas, creating a method to model the effect of population-level interventions in a certain location would be more appropriate for our workshop given the population and outside hospital focus.
*Workshop Date: Saturday December 12, 2020
*Workshop Date: Saturday December 12, 2020
**We were very happy to see communities across machine learning and public health come together. Please see the Accepted Papers page for Paper award info!**
**We were very happy to see communities across machine learning and public health come together. Please see the Accepted Papers page for Paper award info!**
Public health and population health refer to the study of daily life factors and prevention efforts, and their effects on the health of populations. Much of the data that is traditionally used in machine learning and health problems are really about our interactions with the health care system, and this workshop aims to balance this with machine learning work using data on the non-medical conditions that shape our health. There are many machine learning opportunities specific to these data and how they are used to assess and understand health and disease, that differ from healthcare specific data and tasks (e.g. the data is often unstructured, must be captured across the life-course, in different environments, etc.) This is pertinent for both infectious diseases such as COVID-19 and non-communicable diseases such as diabetes, stroke, etc. Indeed, this workshop topic is especially timely given the COVID outbreak, protests regarding racism, and associated interest in exploring relevance of machine learning to questions around disease incidence, prevention and mitigation related to both of these and their synergy. These questions require the use of data from outside of healthcare, as well as considerations of how machine learning can augment work in epidemiology and biostatistics. Key themes of the workshop and submissions are expected regarding:
Public health and population health refer to the study of daily life factors and prevention efforts, and their effects on the health of populations. Much of the data that is traditionally used in machine learning and health problems are really about our interactions with the health care system, and this workshop aims to balance this with machine learning work using data on the non-medical conditions that shape our health. There are many machine learning opportunities specific to these data and how they are used to assess and understand health and disease, that differ from healthcare specific data and tasks (e.g. the data is often unstructured, must be captured across the life-course, in different environments, etc.) This is pertinent for both infectious diseases such as COVID-19 and non-communicable diseases such as diabetes, stroke, etc. Indeed, this workshop topic is especially timely given the COVID outbreak, protests regarding racism, and associated interest in exploring relevance of machine learning to questions around disease incidence, prevention and mitigation related to both of these and their synergy. These questions require the use of data from outside of healthcare, as well as considerations of how machine learning can augment work in epidemiology and biostatistics. Key themes of the workshop and submissions are expected regarding:
• Data: data collection and algorithms designed for the challenges of real-world data that capture features shaping our health, collection and feature generation from Internet (e.g. social media), mobile (e.g. mHealth), environmental or other outside-clinic datasets, privacy and security challenges related to public health data and tasks, ascertainment of data to measure and define factors related to health disparities
• Data: data collection and algorithms designed for the challenges of real-world data that capture features shaping our health, collection and feature generation from Internet (e.g. social media), mobile (e.g. mHealth), environmental or other outside-clinic datasets, privacy and security challenges related to public health data and tasks, ascertainment of data to measure and define factors related to health disparities
• Methods: Methods for combining non-clinical and clinical data for public and population health applications, algorithms for public health goals, modeling multi-sectoral data with respect to health outcomes, model transport across contexts and domains, algorithmic fairness and causal inference in public health settings
• Methods: Methods for combining non-clinical and clinical data for public and population health applications, algorithms for public health goals, modeling multi-sectoral data with respect to health outcomes, model transport across contexts and domains, algorithmic fairness and causal inference in public health settings
• Policy and Implementation: ML approaches for mitigating disparities, identifying methodological assumptions that fail in public health settings, human and ML interaction in the public health context
• Policy and Implementation: ML approaches for mitigating disparities, identifying methodological assumptions that fail in public health settings, human and ML interaction in the public health context
• Health Topics: ML integration in infectious disease models, improving non-communicable disease surveillance and prediction using ML, health equity
• Health Topics: ML integration in infectious disease models, improving non-communicable disease surveillance and prediction using ML, health equity
We are grateful for support from The Rockefeller Foundation
We are grateful for support from The Rockefeller Foundation