Summary
- Profile Type
- Technology offer
- POD Reference
- TOCZ20250204031
- Term of Validity
- 5 February 2025 - 5 February 2026
- Company's Country
- Czechia
- Type of partnership
- Commercial agreement with technical assistance
- Targeted Countries
- All countries
Contact the EEN partner nearest to you for more information.
Find my local partner
General information
- Short Summary
- A Czech university hospital has developed novel system for monitoring the quality of gait in patients with neurological gait disorders, consisting of a wireless rechargeable wearable sensor the size of a smartwatch and a trained AI/ML computational module that can run on a paired mobile phone, tablet or computer. This device suggests immediate level of gait quality through disorder type and classification assessment. Searching for company - co‑development partner.
- Full Description
-
Multiple sclerosis (MS) is the most common cause of neurological disability in young and middle-aged people. MS has a physical, psychological and financial impact on patients and their families.
Up to 85 % of patients with MS identify gait disorders as a major problem. The ability to monitor the development of the disorder over time is highly valued diagnostic measure. Falling because of old age, neurological disorders, movement disorders and injuries can be predicted by the assessment of change in gait quality.
Gait quality monitoring system processes signals from a dedicated sensor unit through a set of unique AI/ML algorithms and delivers information for the patient and/or neurologist/physician and/or family member with the relevant level of detail for the target user.
The system can detect a gait disorder, assess the overall gait quality in real time while walking providing immediate feedback to the user or the physician in the first step. Subsequently, in the second step (further processing) the system identifies a number of different gait disorders, their extent and severity and probable cause of the disorder. The system helps to monitor the development of diseases and disorders of gait and aim to improve the quality of gait.
In both cases, the evaluation is performed using machine learning modules. Both steps show relatively great robustness of the approach used and the relative simplicity of computer performance, especially in the near future.
For general use the first step processing can warn patients or elderly people on the probability of falling. The system is now being tested on diagnostic tasks for several neurological disorders in three relevant practical scenarios performed by neurologists in outpatient offices. Current state of the technical design of the prototype is outlined in Technical specification. - Advantages and Innovations
-
Easy to Use - simple, easy to use, yet reliable and robust diagnostics.
Automatic Evaluation – no expert needed for daily use of a patient and may provide a decision support for expert physician (neurologists) at the same time.
Normal Activity Use – no laboratory assessment distortion, but real world (normal activity view).
One Sensor – no multiple joint sensors and expensive SW/HW needed, just one sensor unit well positioned. - Technical Specification or Expertise Sought
-
Current state of the technical design of the prototype:
Specific hardware for the measurement and data acquisition system using commercially available sensor unit has been developed. The target solution to be certified as MD should consist of a set of microcomputer and custom-made sensor unit (with full manufacturer‘s control over design, quality, HW and SW and firmware) - this part will be up to the application partner to develop and fine tune and design-freeze for certification. This part will include commercially available high sensitivity sensors (accelerometers, gyroscopes, magnetometers), complemented with wireless connectivity e.g. BLE, a suitably rugged and waterproof housing, charging and battery components and with built-in basic data pre-processing and filtering (Kalman filter). For prototyping, e.g. WITMOTION WT901BLECL5.0 are used, which have optimal weight and dimensional parameters.
The microcomputer part can take many forms - depending on the specific use-case: it should allow continuous wireless connection with the sensor unit and perform optimized data processing from the sensor unit using static pre-trained neural networks and display the outputs in a suitable format and graphics and store the results of previous measurements for intra-individual comparative patient evaluation in time or a data export feature.
Depending on the specific use-case, this may be a regular laptop or an average mid-range mobile phone or tablet. Thus, the second part of the system will technically include a computer program or mobile application for a mobile phone or tablet, which can run on widly available HW and usual operating systems, or can run on dedicated closed HW. To give an idea of the necessary performance requirements - the system was successfully tested using, amongst others, a Raspberry Pi 4 microcomputer with 8 GB RAM using unoptimised computer programs in high-level prototyping languages (Python). There is therefore a large space for targeted optimisation by compiling and converting to production low-level programming languages (C). - Stage of Development
- Available for demonstration
- Sustainable Development Goals
- Goal 3: Good Health and Well-being
- IPR status
- Secret know-how
Partner Sought
- Expected Role of a Partner
-
University Hospital is searching for co-development partner to complete the invention and commercialize it under a licence. Research and development support will be provided. The technology is intended to be brought to the market as a:
1. Non-MD/Diag. device – wearable “fall prediction”
2. Diagnostic – wearable – good/bad gait indicator
3. Diagnostic – wearable + mobile/tablet - gait disorder type and severity analyser and classifier. - Type and Size of Partner
- SME 50 - 249
- SME 11-49
- Big company
- SME <=10
- Type of partnership
- Commercial agreement with technical assistance
Dissemination
- Technology keywords
- 06001005 - Diagnostics, Diagnosis
- 06001020 - Physiotherapy, Orthopaedic Technology
- 06001013 - Medical Technology / Biomedical Engineering
- Market keywords
- 05004005 - Diagnostic equipment
- 05001007 - Other diagnostic
- 05004001 - Electromedical and medical equipment
- Sector Groups Involved
- Health
- Targeted countries
- All countries