QuDoc - Machine Learning Diagnostics

Problem

Traditionally, diagnosing a patient with patient-reported symptoms is based on an umbrella approach which results in an umbrella diagnosis and treatment. This method is flawed and fails to achieve intended effects due to lack of individual variability from complexity of human biology. It leaves out 7,000 rare diseases affecting over 400 million patients worldwide. 

Solution

QuDoc is a precision based approach for health care. Anyone in the world can have access to a user friendly mobile interface with assessment of risk factors of rare diseases. User inputs data on recent symptoms, birth and gender, residence and travelling, lifestyle details, genetic exams, family tree, allergies information, and disease history. As the data about rare diseases increase due to the high rate of progression in the life sciences, QuDoc is able to integrate all of the risk factors and produce a reliable probability of an individual developing a rare disease. 

Today, there are more than 7,000 rare diseases affecting over 400 million people worldwide. People who have a rare disease often find themselves misunderstood and underserved by health care systems. An estimated four in ten patients with rare disease experience initial misdiagnoses–often resulting in unnecessary harm, frustration, expense, and disease progression. Some estimates indicate these patients may wait nearly five years and see an average of seven different health care providers before their condition is accurately diagnosed.

Traditionally, diagnosing a patient’s condition has been based heavily on the umbrella approach, which is based basically on the patient-reported symptoms, resulting in an umbrella diagnosis and treatment that frequently fails to achieve their intended effects due to individual variability. To exemplify that, just in Europe these failures are responsible for up to 200,000 people deaths each year. In addition, this classical approach is tremendously time consuming and expensive. Precision medicine aims to allow tailor prevention and treatment with an individual approach. Due to the complexity of human biology, individualized medicine requires taking into account aspects that go well beyond standard medical care. In fact, medical care only has a relative contribution of 10 to 20 percent to outcomes; health-related behaviors, socioeconomic factors, and environmental aspects account for the other 80 to 90 percent. The main role of precision medicine is identifying and explaining relationships among interventions and treatments on the one hand—and outcomes on the other— in order to provide the next-best medical action at the individual level. These can leave us for more accurate, earlier and more granular results. With that in mind, how to collect and work with that amount of relevant data needed in a quantum computing model system to help to optimize the medicine approach on day-a-day use.

The necessity for more personalized medicine, is currently very apparent as the stress on doctors increase, and the amount of information to consider about a disease have become numerous. This project aims to help with decreasing the burden on the health care system and providing more reliable care.

That’s where the QuDoc comes in. It is a precision based approach for health care platform, which with a user friendly interface can collect a large amount of relevant data from our patiences. Assessment of risk factors of cervical factors to produce a risk probability of developing the disease connected to a user app. Input data like recent symptoms, birth and gender, residence and travelling, lifestyle details, genetic exams, family tree, allergies information, and disease history. As the data about diseases increase due to the high rate of progression in the life sciences, we would be able to integrate all of the risk factors and produce a reliable probability of an individual developing a rare disease.

Targeting Rare Diseases Pain Points

Precision medicine diagnosing patients with personalized healthcare. The goal is to make a difference in lives of patients with rare diseases who are systemically excluded from the traditional umbrella approach on healthcare. 

Targeting Rare Diseases Pain Points

Precision medicine diagnosing patients with personalized healthcare. The goal is to make a difference in lives of patients with rare diseases who are systemically excluded from the traditional umbrella approach on healthcare. 

Drug discovery and computer aided drug targets for rare diseases 

• Use raw dataset provided to identify new promising targets, drugs, or drug combinations, biomarkers that could be used for prevention, diagnosis, or prognosis. Integrate data with external datasets to find common traits or a potential new way to intervene in rare disease progression on a quantum computing platform.

Create Personalized Analytical tools 

QuDoc is an easy-to-use patient-facing tool or application that links to the existing rare disease patient registry and allows users to regularly track and share a range of symptoms/challenges with their doctors

• Create an application to interactively analyze the rare disease data patient registry or other open medical data using machine learning or other cutting-edge computational methods to help guide researchers and clinicians to a discovery

Identify Rare Disease Genetic modifiers

• QuDoc quantum computing models used for drug discovery to identify genetic modifiers or predictors of major clinical morbidity. There a link between neurological manifestations in and similar manifestations in other genetic disorders and these patterns can be found using genetic modifiers that could cause high tumor burden in some patients, high level of pain, severe forms of autisms, or learning disabilities
• Molecular Genetics of Nervous System Dysfunction and Neurobehavioral: Common causes, mechanisms, relevant cell types and neurotransmitters that contribute to neurological and neurocognitive issues in rare disease syndromes and finding collective data-driven insights from genotype/phenotype correlations
• Decoding and Detecting Metabolic Signatures: Using quantum machine learning to find a  unifying mechanism for metabolism in rare diseases like RASopathies where individuals often have complicated medicine regimens and effects of treatments are unpredictable. The potential for differences in drug metabolism with super-metabolizers and perception of pain threshold are relevant when it comes to drug prescription that is with only available with precision personalized healthcare. 

Improve Rare Disease Community

• 

  Neurocognitive and behavioral issues are among the greatest challenges for caregivers of those with rare diseases. Common example includes a genetic mutation that can lead some to be autistic or non-verbal. When they are in pain it is difficult for them to express the level of pain to their caregivers so that the necessary care can be provided. 

• Overcoming Barriers and Communicating Needs: Barriers to referrals and barriers to access to specialized neuropsychiatric or mental health practitioners that understand rare diseases. For parents, it is difficult to know why a child is upset, whether they are responding to physical pain, emotional pain, hunger, sensory issues, attention issues, etc. QuDoc is trying to improve communication and access to providers equipped with relevant resources based on medical data 
• Help rare disease patients with the large amount of information on their disease with newly diagnosed patients turn to their mobile phones as their first source of information. The overwhelming amount of information, social networks, and ad-hoc websites are difficult to navigate and could lead to misinformation for patients and caregivers. Sometimes the information is there but difficult to grasp, the language is not layperson enough and we want to create a user friendly version to help mitigate this problem.  The entire experience could become extra difficult for patients with learning disabilities.

Incentivize data-sharing in Rare disease research

• Collaboration and open data are important to advancing healthcare research for rare disease like NF, RASopathies, PTEN, and Desmoid tumor that share a lot of molecular pathways with cancer, but their features are very unique and complex. Rare disease data are scarce and not easy to access. Scientific data is key to designing new experiments, validating results, and advancing research and quantum computing and machine learning is the solution. 
• Rare disease patients are usually more willing to share their data and personal records and contribute to research as it further advances the field. QuDoc uses blockchain encryption with IPFS for privacy and security of medical data.

Track quality of life in rare disease patients

How do we know we are improving QOL in our patients? QuDoc will be collecting biometric data evidence to demonstrate that therapy or a treatment is producing its effects and benefiting the patient. 

1. Electronic health records (EHRs)
2. Medical claims and billing
3. Product and disease registries
4. Patient-generated data 

In 2020, the total global pharmaceutical market size was valued at about $1.27 trillion U.S. dollars. The global pharmaceuticals market is expected to grow from $1228.45 billion in 2020 to $1250.24 billion in 2021 at a compound annual growth rate (CAGR) of 1.8%. The Rare Disease Market accounted for US$ 161.4 billion in 2020 and is estimated to be US$ 547.5 billion by 2030. There are more than 7,000 rare diseases affecting over 400 million people worldwide. People who have a rare disease often find themselves misunderstood and underserved by health care systems. 

Currently, there is a technical architecture in consideration. Open sourced software is hosted on Github for QuDoc. It is at Level 3 because research the state-of-the-art quantum algorithms has been done by reading papers and attending seminars. This includes analytical studies and laboratory studies to physically validate the analytical quantum machine learning risk factor predictions of the technology. 

• Q-munity Hack-Q-Thon where QuDoc won 1st place
• Quantum Valley Investments Pitch Competition semi-finalist
• Blockchain Robonomics Hackathon v0
• The Girls in Tech 2021 Virtual Hackathon

Funding from MIT Solve's Horizon Prize would help with the minimal viable product research and development. 

BioTechnology Drug Discovery:

Drug discovery and simulations of quantum objects predict in a matter of hours the properties, structure, and reactivity of such substances—an advance that could revolutionize drug development. Each optimization cycle is expensive and time consuming. Developing new drugs and chemicals is such a lengthy process - take 10 years, cost millions of dollars, and has a high failure cost. From medical datasets provided to identify new promising targets, drugs, or drug combinations, rare disease biomarkers used for prevention, diagnosis, or prognosis. Integrate data with external datasets to find common traits or a potential new way to intervene in rare disease progression. Data analytics and the identification of drug and targets for rare disease with integration with CPU and GPUs on the cloud for high performance computing with NVIDIA. 

Quantum Machine Learning:

QuDoc is innovative because it offers a new approach to medical diagnostics.The use of traditional machine learning has helped the progression of precision medicine but is coming to its limit as the number of health related variables increase. We can use quantum computing to aid this cause, and emphasize the interplay of health risk factors in the progression of disease.  Computationally intensive calculations where quantum computers perform multiple complex calculations with multiple variables simultaneously, exponentially accelerating the training of such AI systems on large rare disease datasets. It is an improvement in functionality, cost or performance over an existing technology/process that is considered state-of-the-art or the current industry best practice.

That’s where the QuDoc comes in. It is a precision based approach for health care platform, which with a user friendly interface can collect a large amount of relevant data from our patiences. Assessment of risk factors of cervical factors to produce a risk probability of developing the disease connected to a user app. Input data like recent symptoms, birth and gender, residence and travelling, lifestyle details, genetic exams, family tree, allergies information, and disease history. As the data about diseases increase due to the high rate of progression in the life sciences, we would be able to integrate all of the risk factors and produce a reliable probability of an individual developing a disease.

Computer vision with three tensorflow models medical diagnosis and automated pill box and fall detection these features allow those with visual impairments to use their smart devices to navigate around their homes and will enhance the sight seniors already have. Computer Vision with Tensorflow.js with an automated pillbox fall detection, visual impairment aid, and remote medical diagnostics. Natural language processing with Tensorflow JS and Open AI's GPT3 - speech recognition, text to command, voice activation, and a chatbot to combat social isolation. Hardware is also attached to an audio sensor allowing for natural language processing capabilities liketext to command and a chat bot feature with voice activation powered by GPT3.

Blockchain medical data with IPFS encryption - allows for data privacy and endpoint security. Considerations made for cybersecurity, compliance, connectivity while leveraging cloud technologies.

https://devpost.com/software/q...

https://devpost.com/software/m...

https://devpost.com/software/m...

QuDoc uses blockchain technology to solve this coupled with quantum computing encryption. Most of today’s online-account passwords and secure transactions and communications are protected through encryption algorithms such as RSA problem is known as prime factorization, since encryption is built around the manipulation of large prime numbers Shor’s algorithm. In the world of quantum – everything is down to a number or a possibility. It is important to take controlled risks as higher risk leads to higher rewards.

Blockchain technology to store patient profiles within block ledgers to securely store all historical data about a patient like examinations, medical procedures, lab tests, and medications anywhere with the patient's permission. QuDoc is built on top of blockchain for a secure way to transfer and centralize patient data to allow access to patient data for all certifies healthcare institutions and patients. Using blockchain encryption for data privacy and point security in order to protect personal identities online. Medical data remains secure and authentic, maintaining data integrity and a chain of trust with considerations made for the following:

• Prohibitive Production Costs

• Lack of needed technical talent 

• Uncertain Data Security

• Lack of understanding of QML technology, capabilities, or limitations by investors, and the public

• Perceived High costs with cooling technology

• Security concerns especially with national security and encryption (RSA hacking and Shor's algorithm)
  

I believe the time, money, and effort associated with these risks will be worth it because the return on investment for helping those with rare diseases will outweight these risks. 

There are more than 7,000 rare diseases affecting over 400 million people worldwide. People who have a rare disease often find themselves misunderstood and underserved by health care systems. An estimated four in ten patients with rare disease experience initial misdiagnoses–often resulting in unnecessary harm, frustration, expense, and disease progression. Some estimates indicate these patients may wait nearly five years and see an average of seven different health care providers before their condition is accurately diagnosed.

Ensure healthy lives and promote well-being for all at all ages

https://sdgs.un.org/goals/goal...

https://sdgs.un.org/goals/goal...

Assessment factors could include: number of jobs created, number of high-paying jobs, project-related revenue growth, etc. 

3

Strong technical background of team from computer science, physics, and biotechnology grad students.

Factors including populations who experience systematic, economic, or geographic barriers in terms of access to software and tech solutions for healthcare. As the software scales, it is important to make diversity, equity, and inclusion considerations with groups research design, implementation, and outcomes. This will ensure gender equity and the inclusion of other marginalized groups research design, implementation, and outcomes:

• Female-led with a diverse representation in the founding team. We are dedicated to increasing the representation in STEM research. Collect sex disaggregated statistics, with gender-sensitive baseline 
• Youth STEM outreach programs to encourage young people from underrepresented communities to be interested in artificial intelligence and support development of a young class of future scientists through training and financing
• Scale up and replicate successful programs to raise access to quality healthcare for everyone everywhere, including community-based programs like rare disease outreach; and advocacy for greater government allocation to healthcare interventions by strengthening partnerships, cooperatives and unions to promote collaboration for rare diagnostic community
• Prioritize a DEI workforce which strives for equity, and respects, accepts and values difference by requiring all incoming employees to participate in DEI training session - Develop and manage review committee, made up of multi-disciplinary experts
• Monitor surveys that include demographic information about users 
• Mentor and teach historically underrepresented groups with inclusive lesson plans inclusive of Indigenous education leaders to deliver proactive community-based outreach. Reduce barriers for Indigenous communities and financial obstacles faced by low-income by offering free software
• Research how rare diseases will affect researching inequalities and/or underserved populations

No however we proactively reached out to those with rare diseases when developing the application. 

The Horizon Prize, powered by MIT Solve, seeks technology-based solutions that use data to help rare disease patients get the right care faster and more accurately. QuDoc leverages big data and analytics to improve the detection and diagnosis of rare diseases using quantum machine learning. 

Collaboration between patients and doctors in the rare disease field and address the unjust and disproportionate burden of rare diseases faced by disinvested communities and historically underrepresented identity groups. 

Can use Symptom Logging to log their day-to-

day health and share it with anyone, using any

application of their choice, be it Mail or Instant Messaging. Increases the number of people exposed to rare diseases making diagnostics more assessable.

They'll share personal experiences and guide patients in support groups that, in turn, will help others on a similar journey. In addition to imparting symptom logging and risk assessment services, provides Machine Learning-based diagnosis and personalized reports. Addresses the needs of a rare disease patient and responsibilities of a caregiver.

Promote community and connection among rare disease patients and their advocates and Unlock collaboration among patients, scientists, and health care providers to improve patient outcomes. 

Experts have an option to create a new post in the Collaborate forum to share their recent findings, look for research partners or just to share their opinions. It serves a dedicated chat and discussion panel for each post in the section. Doctors can easily integrate QuDoc into their workflow for the following: Primary care doctors Pediatricians Family medicine General practitioners Resident doctors Medical students. 

Financial Support:

•Develop decentralized database where any rare disease researcher can upload data.

•Rare disease care plans and campaigns.

•Have all content reviewed and certified by a medical team rare specialists.

•Include whole body MRI tumors with different sites, sizes and shapes. 

•Recommend individual plan of action.

•More precise treatments and best outcomes.

•Add better classical data processing.

•Include health diagnosis and medicine recommendations.

•Increase efficiency of code.

•Add privacy considerations for medical data.

•Include gene data from GEO and SNLP databases.

•

Biotech business model 

Health legal laws with biometric data