Multimodal Sensor Systems for Precision Health Enabled by Data Harnessing, Artificial Intelligence, and Learning | 20 556

Opportunity Information: Apply for 20 556

The National Science Foundation (NSF) grant opportunity titled "Multimodal Sensor Systems for Precision Health Enabled by Data Harnessing, Artificial Intelligence, and Learning" (Funding Opportunity Number 20-556) supports high-risk, high-reward research aimed at advancing next-generation sensing technologies for precision health. The core idea is to push beyond single-sensor or single-biomarker approaches by developing multimodal sensor systems that can collect many different kinds of signals at once, interpret them in real time, and translate them into actionable health insights. NSF is specifically interested in work that blends sensing hardware and systems with artificial intelligence (AI), machine learning (ML), and mathematical and statistical (MS) methods for learning, so that large volumes of diverse data can be fused into predictive models that improve diagnosis and enable more individualized treatments.

A central theme of the solicitation is the design of integrated sensor-and-intelligence systems that achieve high accuracy, sensitivity, and selectivity while operating on heterogeneous streams of data. In practice, this means systems that can combine measurements across different sensing modalities (for example, chemical, biological, mechanical, electrophysiological, imaging, or behavioral signals) and use learning-based methods to detect patterns that would be difficult to see with any single modality alone. The opportunity emphasizes "data harnessing" as a key capability, pointing to the need for methods and architectures that can manage, synchronize, and interpret high-volume, high-velocity data in real time rather than only in offline analyses.

NSF highlights the potential for these systems to identify combinations of biomarkers with high confidence. Importantly, the solicitation explicitly includes not only traditional molecular or physiological biomarkers but also kinematic and kinetic indicators, which are movement- and force-related measures often associated with disease progression, disability, rehabilitation outcomes, and functional health status. This framing encourages proposals that connect sensing and analytics to meaningful health endpoints, such as distinguishing disease subtypes, detecting early changes, monitoring response to therapy, or forecasting future risk for individuals, while also recognizing that useful biomarkers may be distributed across multiple signal types and time scales.

From a research standpoint, the solicitation is positioned as a focused call for interdisciplinary foundational advances rather than incremental product development. NSF is looking for novel concepts, innovative methodologies, new theory, algorithms, and enabling technologies that address fundamental scientific and technological challenges at the intersection of sensing, computation, and health. That includes challenges like multimodal data fusion, robust inference under uncertainty, learning with limited labeled clinical data, domain shift across populations and settings, interpretable and trustworthy models, sensor calibration and drift, and system-level constraints such as energy, wearability, usability, and real-time operation. Proposals are expected to span expertise areas and typically require collaboration across fields such as electrical and computer engineering, bioengineering, mechanical systems, computer science, statistics/mathematics, and health-related application domains.

Administratively, this is a discretionary NSF grant program in the Science and Technology and other Research and Development category. It is supported across multiple NSF divisions, including Electrical, Communications and Cyber Systems (ECCS); Chemical, Bioengineering, Environmental and Transport Systems (CBET); Civil, Mechanical and Manufacturing Innovation (CMMI); Information and Intelligent Systems (IIS); and Mathematical Sciences (DMS), reflecting the solicitation's intentionally cross-cutting scope. The opportunity anticipated approximately 10 awards, and the published award ceiling is listed as 0, which typically indicates that a specific cap is not stated in the summary field and applicants should consult the full solicitation for budget expectations and constraints. The original closing date for the referenced cycle was June 8, 2020, and eligibility is described broadly as "Others," with clarification expected in the solicitation's eligibility section.

Overall, the program is best understood as NSF's push to stimulate breakthrough research that couples advanced multimodal sensing with modern AI/ML and rigorous mathematical/statistical learning methods to enable more precise, personalized health assessment and intervention. The intended impact is not only better sensing devices, but complete sensing-to-decision pipelines that can reliably discover and use complex biomarker signatures, operate in real-world conditions, and ultimately support more accurate diagnosis and individualized treatment planning.

• The National Science Foundation in the science and technology and other research and development sector is offering a public funding opportunity titled "Multimodal Sensor Systems for Precision Health Enabled by Data Harnessing, Artificial Intelligence, and Learning" and is now available to receive applicants.
• Interested and eligible applicants and submit their applications by referencing the CFDA number(s): 47.041, 47.049, 47.070.
• This funding opportunity was created on Mar 12, 2020.
• Applicants must submit their applications by Jun 08, 2020. (Agency may still review applications by suitable applicants for the remaining/unused allocated funding in 2026.)
• The number of recipients for this funding is limited to 10 candidate(s).
• Eligible applicants include: Others (see text field entitled Additional Information on Eligibility for clarification).

Apply for 20 556

[Watch] Creating a grant proposal using the step-by-step wizard inside the applicant portal: