Kathleen Sienko, PhD, is an Arthur F. Thurnau Professor of Mechanical Engineering and a 2019 Precision Health Investigators Award recipient. She has a broad background in engineering, with specific training and expertise in biomechanics, wearable sensors, augmented balance, rehabilitation engineering, design ethnography, and medical device design processes for low-resource settings. Sienko studies human-device interactions that inform the design and development of medical devices and rehabilitation technologies, with a special emphasis on human-centered and inclusive design.

She directs the Sienko Research Group, a multidisciplinary laboratory developing and using novel methodologies to create technological solutions that address pressing societal needs at the intersection of health care and engineering. Many of these technologies aim to mitigate the shortfall in clinical staff faced both in the US and elsewhere by decreasing the need for a “human-in-the-loop” and supporting clinical needs in nonclinical settings (e.g., the home).

In the fall of 2021, Sienko and her colleagues were awarded a three-year National Science Foundation (NSF) award for their project “Automating At-Home Balance Training Using Wearable Sensors.”

Please talk a little about your Precision Health Investigators Award project (“Personalized Data-Driven Balance-Training Instruction and Assessment for Older Adults”), and how it led to additional NSF funding.
The Investigators Award enabled us to collect pilot data to de-risk our NSF submission. We were more competitive for this external grant because of the Precision Health support that we received. Even though NSF doesn’t require pilot data, it was very helpful to have the Precision-Health-funded data and preliminary models in order to develop this proposal.

What is the goal of this research?
The goal of this research is to develop and verify data-driven models capable of 1) remotely assessing balance in users’ homes and 2) recommending balance exercises informed by wearable sensors and observed clinical decision-making that adequately and safely challenge users based on their balance abilities. Declines in balance function drastically impact quality of life and present long-term care challenges. Although effective, balance-training programs require frequent visits to the clinic and/or the supervision of a physical therapist (PT). The costs (and associated travel) are prohibitive for the average patient and increased visits for one-on-one guided training are not scalable.

We will develop models that will capture the iterative, co-adaptive process of expert-patient interaction that evolves over the course of a training program, where the patient adapts their sensorimotor behavior due to the selected training and the PT adapts the training based on patient progress. This research will determine expert-informed, direct measures for inferring patient state, selecting rehabilitation progression paths, and supporting clinical research assessments of other interventions.

With whom are you collaborating on the project?
The investigator team includes Leia Stirling, PhD, Associate Professor of Industrial and Operations Engineering; Xun Huan, PhD, Assistant Professor of Mechanical Engineering; [Precision Health Co-Director] Jenna Wiens, PhD, Associate Professor of Computer Science and Engineering; Lauro Ojeda, MS, Associate Research Scientist, Mechanical Engineering; and Wendy Carender, MPT, Physical Therapist, U-M Health System. Our Precision-Health-funded postdoc Chris DiCesare, PhD, made significant contributions to the proposal. Safa Jabri and Jeremiah Hauth—doctoral candidates in Mechanical Engineering and Graduate Student Research Assistants funded by Precision Health—have been instrumental in collecting and analyzing data and developing the data-driven models.

What are the potential applications of this work, and how will it help people?
This research is the first and necessary step in achieving the long-term goal of creating automated balance training technologies to complement, supplement, and increase access to clinic-quality care. The outcomes of this research have the potential to be adapted to a diverse population of Americans with a wide range of balance and gait impairments including sensory, neurological, and motor disorders.

This work will result in the development of models that integrate heterogeneous clinical and biomechanical data and generate new approaches for modeling expert-patient interactions that are robust to patient differences and co-adaptive between the expert and patient over time.

This work will inform future efforts to develop effective, scalable, at-home balance training solutions for older adults and people with vestibular dysfunction.