As a rehabilitation scientist working for the startup Lindera, Sophie Rabe knows why a smartphone, artificial intelligence (AI), and a 3D model can be very valuable when it comes to fall prevention.
Ms. Rabe, you research fall prevention and the risk of falls. How can digital innovations improve the effectiveness of fall prevention programs?
Sophie Rabe: Assessing the risk of falls is a complex task. A multitude of risk factors must be analyzed separately. One important factor is gait analysis, which can indicate an increased fall risk. What’s more, the task also requires an analysis of several other factors such as medication, comorbidities, as well as visual and hearing impairments. Subsequently, the right fall prevention measures must be chosen and recommended from a multitude of separate risk factors. Presently, a fall risk assessment is often subjective and paper-based. Moreover, the process is very time-consuming and relies on the knowledge of experienced nurses.
Scientific studies show that a multi-attribute fall risk assessment, as well as the resulting preventive measures, most notably lead to a fall risk reduction. However, due to the current nursing shortage, the benefits of fall prevention are still underutilized.
Our Lindera Mobility Test is the first of its kind that analyzes the 3D image of the gait pattern based on medical standards with the help of a simple smartphone camera. We use AI to digitally interpret the diagnostic awareness and knowledge of the physician and the nursing staff. Other risk factors can also be digitally captured and standardized. Having said that, the planning of prevention measures and their implementation are also of vital importance. Digital data documentation allows the fast creation of personalized prevention plans.
Fall prevention measures often imply the training of physical abilities. The effectiveness of such measures can be objectively assessed via a smartphone-based mobility test. This documents therapeutic success more comprehensibly and results in an improved adherence to recommended measures. What’s more, the analysis of large datasets could also more accurately predict the likelihood of falls and the personalization of fall prevention interventions, which could ultimately lead to a more needs-based approach to patient care in this setting.
What are the current trends in fall risks/fall prevention?
Rabe: There are presently a variety of sensor-based solutions that can reliably detect fall-related events and subsequently initiate the appropriate actions. That being said, in my opinion, the prevention of falls is paramount to maintaining the quality of life, independence and self-determination of the elderly as they age.
Another key issue is the reduction of the enormous economic costs generated by falls and fractures. It is estimated that hip fractures incur 2.77 billion euros of direct costs annually in Germany, not including long-term costs and non-medical expenses. That’s the reason why prevention approaches should be increasingly promoted as part of the digitization of health care.
Several digital fall prevention solutions analyze the mobility of older adults in terms of their fall risk. They require the adjustment of sensors on the body for an analysis. Meanwhile, time-saving solutions that can be easily integrated into daily health care routines and that optimize existing fall prevention processes will predominantly win out in the future. That being said, in addition to assessing the fall risk, these types of products must also offer strategies for personalized and effective prevention.
