OpenIDEO is an open innovation platform. Join our global community to solve big challenges for social good. Sign Up / Login or Learn more

Personalized and Holistic Healing of Fractures - ErgoRehab

Complete recovery of muscle/bone/movement after fractures using a holistic approach and advanced movement analytics.

Photo of Aleck Alexopoulos
1 2

Written by

What challenges or opportunities are you trying to address within the problem? (200 characters or less)

Challenge is to improve healing in a patient-centric manner by deep movement analytics that will improve remineralization and decrease risk of fractures.

The ErgoRehab proposal consists of software based on deep-tech algorithms for evaluation of how a movement is performed. These tools have been validated for healthy athletes and implemented for personalized training and provided 25% more benefits compared to best practices. 

The ErgoRehab software has two key inputs.
The first inputs are generated from a milder version of the movement evaluation tests implemented for athletes. Three groups of tests are employed focusing on dynamic movement, static endurance, dynamic endurance / recovery. Movement algorithms take the test results and provide movement metrics that completely characterize how a resistance is moved and these are employed as inputs to the ErgoRehab software.  
The second key input to the ErgoRehab software has to do with bone mineral density. Aside from the average BMD and the T-score a metric related to spatial variation of the BMD is employed. In the first iteration of the ErgoRehab software the TBS score from TBS iNsight is used.
With these data the ErgoRehab software generates assessments of unbalanced movement and weak points which together with the TBS score can provide an imporved estimate on fracture risk and recommendations for physical therapy modifications. 

The underlying principle is that proper movement patterns lead to more uniform stress on the bone and therefore more uniform remineralization and healing. Also, risk of fracture is not just a function of average BMD but also bone microstructure - this is well known in the literature. Finally, it is hypothesized that osteopenia and microstructural non-uniformities can indirectly affect movement by various protective mechanisms (musculoskeletal and/or neuromuscular). 

ErgoRehab could be employed during the recovery stage, post-fracture, to provide a more personalized and patient-centric recovery experience. 

We have participated in the preparation of two recent EU Horizon2020 proposals that were related to rehabilitation (hand injuries and exoskeletons for hip injuries) where our contribution was deep monitoring of patients during the recovery period and providing more intelligent input data for the AI systems involved. We are currently investigating the implementation in rehabilitation applications mostly as a means for in-depth monitoring or recovery.

With our advanced movement evaluation and advanced algorithms we anticipate the following:

1. more effective healing of both bone and muscle and movement functional capability (i.e., recovery of an increased % of previous capability).

2. more efficient healing in terms of time and necessary resources.

3. fewer problems long-term, e.g., pain or re-injuries.

Important to note that our algorithms are based on first-principles without getting lost in joint-by-joint biomechanics. As such, we do not need any data training period to train an AI as we immediately know what the data mean.
Consequently, we can proceed to a pilot study very fast.

However, in order to connect to other sources of data, e.g., TBS and long-term outcomes, a ML approach would be beneficial and is considered a part of "version 2" or ErgoRehab.




Who is your target end user and why will they be interested? (650 characters or less)

First adopters will be rehabilitation clinics via their directors, doctors, and therapists. After we have demonstrated the benefit in terms of decreased re-injuries, improved patient experience, and decreased costs we may seek support from a Health Insurance Company.

How is your idea scaleable? (650 characters or less)

The ErgoRehab movement tests can be easily taught to physicians and caregivers. The software for analysis of the movement tests can be provided as a service. The ErgoRehab system becomes increasingly accurate and powerful with the accumulation and utilization of data from multiple people with osteoporosis with different types of fractures. In fact version 2 of ErgoRehab will include a Machine Learning module which will connect BMD data with movement data pre- and post- therapy but also with long-term outcomes. The ML module will increase the scalability dramatically and provide improved predictions.

What do/will you measure to know if your solution worked? (500 characters or less)

* More uniform re-mineralization after rehabilitation. * Reduced risk of re-fracture (long-term outcome). * Complete recovery of functional movement (as identified by ErgoRehab evaluation metrics) More specifically in a pilot study one would compare BMD (T-score and TBS) as well as the movement metrics pre- and post- therapy of two groups of patients: one group would be the control and the other would employ suggestions for PT modifications as provided by ErgoRehab software. We would then also follow long-term (1 to 5 years) for assessment of fracture risk and other problems.

What is the current stage of development of your idea?

  • Prototype: We have done some small tests or experiments with prospective users to continue developing the idea.

If you were to become a Top Idea, would you want to actively participate in piloting your idea?

  • I want my idea piloted, and I prefer to do my own piloting in collaboration with the health system and with assistance from the Challenge partner

Company / Organization Name, if applicable (140 characters or less)

ErgoRehab is a tentative Company name. Will be incorporated if funded. ErgoRehab utilizes modified movement algorithms from ErgoSensePro.

Website (if applicable)

http://www.linkedin.com/in/aleckalexopoulos

Tell us about yourself or your team (500 characters or less)

Chemical and Biomedical Engineer (PhD Purdue PostDoc MIT). Research Scientist w 25+ yrs experience. Fascinated with movement, musculoskeletal system, and wellness. Expertise in physiology and disease simulations. Currently at CERTH in Greece and collaborating with several Medical Doctors in the area of Thessaloniki. I have a startup, ErgoSensePro, incorporated in the US (MA) which has provided the movement algorithms to ErgoRehab. I would be very interested in performing a pilot study locally and then a more extensive study in the US.

Location (50 characters)

Thessaloniki, Greece. 1m/yr I stay in Boston.

What is your legal / organizational structure?

  • We are individuals
  • We are a formal part of a University or Research Institution
  • We are a For-Profit Startup or Startup Social Enterprise

Innovator/Organizational Characteristics

  • Work closely with people from the Medical community in all types of rehabilitation problems.

How did you hear about the Challenge?

  • OpenIDEO announcement email
  • OpenIDEO social media

Why are you participating in this Challenge?

I am very interested in osteoporosis as it was a problem with my grandparents. I am looking for applications of the movement algorithms of ErgoSensePro as part of holistic movement solutions. This is driven by scientific curiosity but also a deep desire to improve the lives of people with health issues.

How does your idea help more people who have had a first fracture either 1) discover they have osteoporosis or 2) access/navigate care?

1) In the first version, ErgoRehab will focus more on providing better rehab and fuller recovery avoiding future fractures. As data is gathered and the correlation between BMD, density gradients, and movement patterns becomes clearer through Machine Learning tools (possibly classification and recurring NN) the possibility exists to diagnose abnormal BMD via movement patterns - potentially an early osteoporosis detection. If we can reach this point we can provide an online tool for the physician to use on patient examination or even a simpler version for patients to use by conducting movement tests at home - possibly even via mobile phone videos of ErgoRehab movement tests. 2) ErgoRehab provides diagnostic services to the PCP. With the accumulation of data, ML techniques will provide more detailed directions to the PCP, PT, but also to the patient.

How is your idea new in the world or how does it build on existing interventions?

ErgoRehab is NEW as it is based on first-prinicples movement algorithms developed initially for the evaluation and training of healthy athletes (from the startup ErgoSensePro). The tools and algorithms require only minor modifications to accommodate patients. To this end, the ErgoRehab evaluation tests are a "softer" version of those for healthy athletes as indicated in the solution prototype (slide 7). ErgoRehab employs a metric of nonuniformity of BMD. Recent software products for analysis of DXA images provide such measures (e.g. TBS iNsight). At first, these will be integrated as is, e.g., TBS value, and only later may be modified into more suitable forms, e.g., BMDV, bone mineral density variance. Finally, ErgoRehab will include Machine Learning algorithms at a later date once sufficient data has been gathered. ML approaches will correlate movement evaluation metrics to BMD, BMD-variance, therapy results, and possibly long-term outcomes (e.g., second fractures).

Please upload your journey map. Be sure your journey map shows when your user is introduced to the idea and when/how they access it, and illustrates which moments in the Challenge Journey Map your journey map touches.

ErgoRehab journeymap - focuses primarily on the PCP. Red numbers refer to the slides of the prototype (see below). Journeymap refers to the immediately implementable idea. Additional or improved metrics of BMD variation could be included. At a later date, with sufficient data, a Machine Learning approach can be introduced with many additional capabilities. For example, much more accurate fracture risk estimates and perhaps the capability of osteoporosis diagnosis just from movement tests

Who did you test your idea with, what did you learn, and how did you evolve your concept?

The original movement algorithms of ErgoSensePro have been tested and validated with amateur athletes. The tests were conducted under controlled conditions at a University in Greece and revealed +25% extra benefits compared to best practices over a 4week training period. Interestingly one of the subjects was recovering from an injury (not a fracture) and experienced +70% extra benefits. From this we learned the following: 1. The combination of deep movement evaluation and personalized training provides significant benefits (to athletes). 2. The execution of the evaluation tests and use of wearables were straight forward enough for students to conduct unsupervised after only a single day of training. 3. The manual entry of data gathered from the training sessions into the algorithms was not too cumbersome. After these tests, and the indication that this approach can be applied for rehabilitation I started investigating the problems and needs in the world of rehabilitation and not just for athletes. It became clear that many steps of the healthcare procedure from primary treatment to rehab to post-rehab care are too generic and not sufficiently personalized. Since then I have participated in two recent EU research proposals in the area of rehabilitation: one on hand injuries and the other on the use of exoskeletons for rehab post-hip-surgery. Engineers and Doctors readily understand and appreciate the need for more detailed and deeper movement analytics.

(Optional) Share documentation of your solution prototyping and testing, such as photos.

Slide 1 is an overview of the solution prototype. Slides 2-14 are annotated slides from a powerpoint. At https://www.youtube.com/watch?v=PSbd68mgG-0 : video demo of the validated prototype for athletes. The ErgoRehab version (i.e., slide07) is much simpler and consists only of mild "softer" movement tests (see Videos 1,2,3) Note that we can add a separate PT-facing interface and even a patient-facing interface. Here we have just added a feedback slide for the patient (slide 14)

Please upload your Business Model Canvas

BMC is for the initial version of ErgoRehab. Later versions which will include data-based ML algorithms will be able to offer much more in terms of osteoporosis identification and prediction of fracture likelihood and will have a different BMC mostly in terms of value proposition, customersj and revenue streams.

Please upload your team video.

ErgoRehab is in the early development stage is really is a single-person team. However, there is support from all directions which must be noted. There are the advisors from ErgoSensePro, Thanos Yiagopoulos (CTO Momentive) and Michael Balitsaris-Fortier (President Sylipsis) who have extensive experience in business and healthcare. There is Eleftherios Tsiridis who I will "recruit" as an advisor for this project if it goes forward. Björn Rust from the OpenIdeo Network has been a big help

Attachments (1)

1 comment

Join the conversation:

Comment
Photo of Manisha Laroia
Team

Hi Aleck Alexopoulos 
Thank you for sharing your solution in the Ideas Phase of the Healthy Bones Challenge.

A checklist for your reference. Please make sure your idea does the following:
1) Clearly define the problem with respect to Osteoporosis
2) Connects to at least one opportunity area
3) States how & when user accesses the solution
4) Tells the story

Please make any last minute tweaks you wish to, asap. Like adding IMAGES or changes in text.
The DEADLINE for idea submission is Wednesday July 3rd, 2019 5pm PST.

Let me know if you need anything.
All the best for the next phase of the challenge.

Manisha
OpenIDEO Challenge Team