Keynote: Digital Health Technologies and Their Role in the Development of Precision Rehabilitation Interventions

Over the past two decades, advances in digital health (e.g., wearable and mhealth technologies) have enabled the collection of massive amounts of data in the clinic and in the home and community settings. Wearable sensors have been used to gather movement and physiological data. Ambient sensors and wearable cameras have provided contextual information. Smartphones and tablets have been utilized to collect ePRO's. In parallel, advances in the field of machine learning have made it possible to derive clinically meaningful information from these large datasets. These developments are transforming the field of rehabilitation medicine. In this talk, first, we will review the use of these technologies in the clinic. We will discuss how sensing technology is gradually replacing costly camera-based systems and how combining - by relying on machine learning algorithms - data collected using inexpensive cameras with data collected using sensing technology can lead to highly accurate kinematic data. We will then show how relying on digital health technologies and on machine learning algorithms, researchers have developed approaches suitable to derive accurate estimates of clinical scores via the analysis of sensor data collected during the performance of functional movements. We will then present evidence that these technologies are transforming the way rehabilitation interventions are designed and implemented as they enable tracking how each patient respond to the prescribed therapy, thus enabling precision rehabilitation interventions. Next, we will discuss applications of digital health technologies outside of the clinic. We will show how these technologies can facilitate the process of gathering information about participation (as defined by the International Classification of Functioning, Disability and Health framework developed by the World Health Organization) and about the impact of contextual factors on clinical outcomes. Then, we will review challenges that researchers are facing in deriving reliable metrics from data collected in the home and community settings. We will present examples of approaches aimed to assure that such metrics are accurate and reliable. Furthermore, we will discuss the role of digital health technologies in enabling the implementation of interventions with minimum (in the clinic) or no (in the home) direct supervision by therapists while enabling patient monitoring for safety. Finally, we will discuss how we envision that the field of rehabilitation will evolve in the next decade as digital health technologies are integrated in clinical practice.

Automated summary

Advancements in digital health technologies, such as wearable sensors and mhealth devices, have led to the collection of massive amounts of data in clinical and home settings; Machine learning capabilities have enabled the extraction of clinically meaningful information from these datasets; These technologies are reshaping the field of rehabilitation medicine by enabling more accurate and personalized interventions.