The proposed project incorporates novel machine learning based methods from a large clinical Magnetic Resonance Imaging (MRI) dataset. These methods incorporate high- and low-level imaging features including intervertebral disc location, shape, and intensity. Moreover, these methods model the disc structure as a Markov chain to enable neighborhood information utilization. In addition to the imaging features, these methods utilize patient meta-data including patient age, height, weight, pain and disability score, patient history, and physical exam findings. The availability of these features provides information for the diagnosis of low back pain. These methods generate unbiased and reproducible interpretation. This technology is capable of providing standardized, unbiased, and reproducible MRI interpretation.
Many people are affected by low back pain and it is the most common reason behind job-related disability. It is a prominent chronic disease that causes major disruption in people's lives. An annual estimate of at least $50 billion is spent in the United States on diagnosis and related rehabilitation of low back pain patients. Moreover, the associated individualized treatment and rehabilitation cost is significant and often requires special pre-approval to undergo treatment from the insurance providers responsible for paying for health care costs. The most common current clinically approved standard for low back pain diagnosis is MRI testing and the diagnostic interpretation of MRIs is highly subjective. All subsequent therapeutic recommendations are based on the subjective report. This technology may be able to provide the MRI interpretation based on a standardized protocol will significantly impact the treatment plan outcome and minimize overtreatment.
Summary: This iCorps grants enabled our team to actively meet with over 100 potential customers to productize our innovation. Based on these customer meetings we fine-tuned our business model to provide a well-founded business plan including: our potential partners, our specific product, our available resources, potential customers, relationship channels, and the revenue stream. Furthermore, we discussed our team formation and roles for each team member have become clearer. Most importantly, we built a complete understanding of our potential product, how it fits within the workflow of the customer, how it saves our customer money, and how it may standardize low back pain treatment recommendation for better patient care. Towards the end of this grant, we developed a proof-of concept demo for our product with a small dataset. Meeting with experts in the healthcare and insurance field provided us with the domain knowledge and expertise for many scenarios that a patient may face when having an episode of low back pain. We learnt of the details surrounding these scenarios. We found that the surgery authorization is most expensive step with the largest likelihood for unnecessary expenditure. Studies have shown that about 20% of the patients that have undergone surgery develop low back failed syndrome. This may cause complete disruption in patient life and hence all subsequent cost including disability compensation and loss for the community that could have been prevented. On the other hand, during this grant, we aimed at fine-tuning our business model. During this period, we were able to study each of the segments on the business model canvas. We explored the various available potential partners locally and nationwide. We found that Proscan Radiology Buffalo PLLC may be a strong and essential partner as they can provide the data and access for patients upon patient consents. Furthermore, upon exploring our value proposition, we concluded that we are saving money for insurance provider by alerting them during the surgery request authorization when this surgery is not needed and, in fact, may cause subsequent losses for the insurance and for the patient. Further investigation on the various customer segments resulted in various potential customers including: healthcare insurance, No-fault and liability insurance providers (auto insurance industry), hospital administration, and state worker disability compensation boards. Other segments on the business model have been investigated including the revenue stream and pay model with flexibility to meet customer needs to attract them for subsequent products that our company will be providing down the road. Our next outcome was the proof of concept demo. We also built an iPAD based app for input and collection of patient information using a standardized clinical patient questionnaire for low back pain. This will enable us collect the required data for validation and testing of our product and attract investors. Specific outcomes: 1- Well-established business model with specific value propositions, specific customer segments for each value proposition, methods to maintain and establish customer relationship, communication and sale channels, specific partners who will provide us with patient access and data after patients' consents. 2- Software tools, iPAD app, to collect patient information and clinicians diagnosis in a standardized form. This enables us to accelerate and standardize information collection. This information is an essential part to train, develop, and validate our product. 3- Proof of concept Demo for potential customers and investors.
