NSF Workshop: Computing challenges in future mobile health systems and applications

I participated in an NSF workshop on Computing Challenges in Future Mobile Health (mHealth) Systems, which was held at the National Institutes of Health in Bethesda, Maryland, on October 29th. The workshop brought together an impressive group of scientists in computing and health research. The full day workshop focused on three key goals:

1. Identify mHealth grand challenges in computing that can lead to transformative advances in health.
2. Identify the major barriers to engaging computing researchers in mHealth.
3. Establish an academic community of mHealth researchers in computing.

There were impressive presentations and discussions throughout the day, touching on different aspects of computing challenges in mHealth research: mHealth Sensing, mHealth Analytics, mHealth Intervention/treatment, and mHealth research community infrastructure and platforms.

I had the chance to present Kitware's experience in developing software and community building tools for the medical imaging and EHR communities. I discussed with the workshop participants how a publicly accessible mHealth database and a robust community infrastructure will foster collaborations between mobile health researchers and computational scientists. As part of this discussion, I highlighted a three-legged approach to building a vibrant mHealth research community.

To create and nurture a vibrant community, a real cultural transformation is required that would value transparency and collaboration. It is essential the community adopt a collaborative science approach that values:

• Data, model/algorithm and software sharing
• Leverage each other's work and avoid reinventing the wheel
• Practice reproducibility
• Disseminate and scale pilot program

A high quality robust community infrastructure is also essential. In order to create a robust infrastructure that is sustainable and effective, however, key technical considerations must be taken into account during the design process such as user-friendly and flexible access, the capability to handle heterogeneous data coming from a wide spectrum of sensors, and a unified API.

In my opinion, the mHealth research community is off to a great start. The fact that the community organized this type of workshop shows its recognition of the issues in nurturing collaborative research.  The concrete steps that are planned are very encouraging, and they will help foster collaborations between mobile health researchers and computing scientists and lead to advances in medicine and improved health care.