• Register Now

Acquisition of evidence-based understanding of human health behavior and exposure to environments forms a central focus of  health research, and a critical prerequisite for effective health policy. The use of mobile devices to study health behavior via cross-linked sensor data and on-device self-reporting and crowdsourcing have been demonstrated to provide  important insights that traditional techniques cannot. However, design, delivery and analysis of mobile data studies requires skills rarely developed in health science training.

This tutorial introduces public health researchers and practitioners to tools, practical skills and the conceptual background required to collect and analyze mobile data on health behavior, and assists participants in getting started in applying such techniques to studies and applications of specific interest to them. This tutorial will include hands-on work with novel and standard tools and techniques.

This event includes both a classroom curriculum (featuring much hands-on work) and an incubator designed to help students build and test out custom study designs, survey instruments (EMAs/eligibility, entry & exit surveys), crowdsourcing mechanisms, and sensor-based data collection mechanisms for their specific study designs and data collection priorities.  Both portions of the event will make heavy use of the widely-used Ethica health smartphone- and wearable-based data collection system.  Together with its progenitor system, this system has been deployed in between 50 and 100 studies.

This workshop is targeted at professionals from a variety of health fields, including health researchers, health administrators, public health workers, health decision makers, and any health professionals or modellers seeking empirical behavioural data.

Dr. Nathaniel D. Osgood

Dr. Nathaniel D. Osgood is a Professor in the Department of Computer Science and Associate Faculty in the Department of Community Health & Epidemiology at the University of Saskatchewan. His research is focused on providing cross-linked simulation, ubiquitous sensing, and machine learning tools to inform understanding of population health trends and health policy tradeoffs. His applications work has addressed challenges in the communicable, zoonotic, environmental, and chronic disease areas.  Dr. Osgood is further the co-creator of two novel mobile sensor-based epidemiological monitoring systems, most recently the Google Android- and iPhone-based iEpi (now Ethica Health) mobile epidemiological monitoring systems.  He has additionally contributed innovations to improve dynamic modeling quality and efficiency, introduced novel techniques hybridizing multiple simulation approaches and simulation models with decision analysis tools, and which leverage such models using data gathered from wireless epidemiological monitoring systems.  Dr. Osgood has led many international courses in simulation modeling and health around the world, and his online videos on the subject attract thousands of views per month.  Prior to joining the U of S faculty, he graduated from MIT with a PhD in Computer Science in 1999, served as a Senior Lecturer at MIT and worked for a number of years in a variety of academic, consulting and industry positions.

Mohammad Hashemian

Mohammad Hashemian is the founder and CEO of Ethica. He holds a B.Sc. in Software Engineering and M.Sc. in Computer Science with the focus on Epidemiology and Public Health. He has been involved in design and rollout of nearly 70 research projects using Ethica since 2015. Prior to founding Ethica, he was Platform Developer on Google Android TV. Together with Nathaniel, Mohammad has co-presented the Ethica platform in workshops across Canada, United States, and Australia.

The course will be staffed with a broad set of graduate-level teaching assistants, who will provide assistance both during the tutorial sessions and during the open times and post-tutorial brainstorming sessions.  To better address the questions of participants from a wide variety of backgrounds, the teaching assistants will be drawn from both health science and technical backgrounds.

Instructors will provide lectures and step-by-step hands-on tutorials on conceptual foundations, mechanics & best practices.  Topics are anticipated to include the following, with details of coverage of these and additional topics depending on participant interests expressed via pre-study surveys.  We will endeavour to record all sessions and make those available with quick turnaround to participants during and following the bootcamp. The below provides only high-level summaries for many items; interested readers should refer to the website for additional detail.

• Behavioural and physiological sensing via smartphones and paired devices (smartwatches, weight scales, etc.)

• On-device questionnaires, crowdsourcing mechanisms

• Case studies from diverse health areas

• Effective study design

  • Recruitment, including discussion of recruitment needs in diverse population types

  • Smartphones as surveillance, smartphones as interventions

  • Securing community buy-in and support

  • Privacy and confidentiality

    • Ensuring operation within ethical research guidelines, and working with Institutional Review Boards/Research Ethics Boards

    • Ensuring security and confidentiality

    • Support for ongoing and retroactive participant opt-out

    • Addressing privacy concerns via retaining data in escrow for contingent use

  • Design of effective survey instruments

    • Size, frequency and participant burden tradeoffs

    • Using contextually triggered instruments:  Opportunities, strengths and risks

    • Supporting, Eligibility, entry, ecological momentary assessments (EMAs), study completion and opt-out questionnaires

    • Capturing skip patterns and conditional questions in survey instruments

    • Using per-question completion timing information

    • Multi-page vs. single page questionnaires

    • Enabling multimedia responses (photos, audio)

  • Supporting informed consent, both remote and in-person

  • Participant incentives

    • Participant access to own data

    • Operating studies with and without incentives

    • Non-monetary incentives

    • Community-based sharing of data

  • Recruiting networks:  Study design, practical and ethical considerations

  • How much data is enough?

  • Different needs in in-patient and population surveillance

  • Budgeting a study:  Cost economics of running smartphone-based studies

  • The data backhaul (WiFi vs. Cell data networks): Impacts on reporting and monitoring timeliness, financial impact on study, tradeoffs across populations.

• Study management and operation

  • Working with participant-owned and study-provided mobile devices, including special needs with low-socioeconomic status populations

  • Retention

  • Monitoring adherence/involvement

  • Database structure and retrieval

  • Routine reporting via website-based analytics

• Cross-leveraging smartphone-collected data with traditional and other electronic data sources

• Data Analysis

  • Systematic characterization of analysis approaches responsive to particular types of research questions

  • Models for sense-making:  Hierarchies of data analysis needs (the data analysis pipeline)

  • Using cross-linked data from multiple smartphone and federated measurement modalities

  • Data cleaning, filtering and conditioning

  • Dealing with missing data

  • Use of smartphone-collected data with biostatistical analysis (e.g., survival, recurrent event, multiple regression, and other analyses)

  • Machine learning-based classification & inference

  • Understanding intervention effects across multiple causal pathways

  • Integration of data with dynamic models

  • Geospatial behavior and GIS

  • Prospects for use of data with behavioral and choice modeling

  • Visualization (Kibana, Tableau, R, and Zeppelin)

  • Tools for large-scale data analysis:  Apache, Kibana, R, Anaconda, & Spark

The “incubator” side of the event will further leverage the extensive experience of the instructor and teaching assistants to provide ongoing advice, guidance, tips and hands-on assistance as participants build, explore, test, and refine their own study designs, survey and crowdsourcing  instruments, sensor data collection mechanisms addressing their surveillance needs. Guided by instructors and interdisciplinary team of TAs, participants will have the opportunity to design a prototype data collection experiment, and to acquire, visualize and analyze the collected data using current tools and techniques.

• Register Now