Skip to main content
 
Stage of development
Prototype developed (see picture) and successfully tested in relevant environment (hospital)

Intellectual property
Priority patent application filed

Intended collaboration
Licencia y/o codesarrollo

Contact
Marc Escamilla
Vice-presidency for Innovation and Transfer
m.escamilla@dicv.csic.es
comercializacion@csic.es

Reference
CSIC/ME/022
Additional information
#Chemistry #Industrial Process

Improved walking analysis method to detect and prevent risk of falling

System to analyze human gait, that generates an accurate analysis adapted to each patient and its characteristics and peculiarities of footfall, being therefore of special interest for prevention and rehabilitation of motor disorders or anomalies.

Market need
Currently, there are multiple commercial systems for biomechanical analysis of human movement, with very diverse purposes (health, physical exercise, digitalization and AI, etc.). Most of these systems have complex algorithms generally designed to optimize movement, and are therefore of limited usefulness when it comes to diagnosing cases with pathological mobility or motor disorders. This means that there is a special interest in having new systems adapted to the detection and prevention of motor disorders, such as foot drop syndrome or hemiparetic gait, among others.

Proposed solution
Our system is specifically designed to detect the accurate gait of the person who uses it, generating a completely personalized walking profile, and through the use of its own software, achieves an analysis of key parameters to detect possible anomalies, risks or injuries, allowing to prevent accidents or falls and to design tailored rehabilitation programs. It is therefore a system of special interest to be used in hospitals, nursing homes, or physiotherapy centers.

Competitive advantages
  • Low cost design and structure without compromising precision in data collection and analysis.
  • Generation of a completely personalized gait profile, since it does not use predictive algorithms like most current commercial solutions.
  • Easy to implement in commercial wearable systems.