La Data Fountain (an OpScientia collaboration) Decentralizing unused medical lab data to better predict and treat human illnesses

Part 1 - Proposal Submission

Name of Project: La Data Fontaine (LaDaFo)

Proposal in one sentence:

A “Data Passport” mobile application that brings research participants and scientists together for secure sharing of personal health and diagnostic lab data to crowdsource research participation, development of diagnostic algorithms, and tracking and preventing disease processes.

Description of the project and what problem is it solving:

The Problem:

There is no easy way for researchers to identify eligible participants, nor for participants to leverage their personal health data to achieve personalized insights. Researchers require large medical datasets from specific populations to develop new treatments, track public health metrics, and provide personalized care for individuals.

Unfortunately, even though individuals generate large amounts of highly valuable medical data during their lifetime of visits, this data remains inert on medical lab servers.

This trove of medical data remains untapped because of privacy concerns, poor interoperability standards, and missing infrastructure for secure data sharing.

Discarded diagnostic medical data can be aggregated to improve healthcare, advance our understanding of disease processes, identify correlations and relationships between symptoms, and provide highly valuable indicators of public health.

The Solution:

We propose a “Data Passport” mobile application that allows researchers to publish quests for participation in scientific studies, and for participants to securely share their personal health data and obtain high quality personalized reports. The Data Passport is powered by a back-end data fountain pipeline that unleashes medical lab data lakes, addresses privacy issues, supports interoperable standards for science data sharing, and connects research participants with scientists.

Digital assets such as aggregated datasets and algorithms for generating personalized health insights are tokenized and access controlled using a private fork of the Ocean market.

Overall, this tech stack 1) closes the loop for the care pathway by providing a safe continued use-case for medical data after diagnosis is made, 2) links researchers with eligible participants to perform scientific research, and 3) empowers participants to own their own data, receive rewards for participation in research, and lastly purchase personalized insights on a decentralized marketplace for A.I algorithms.

Grant Deliverables: (Target deliverables for the funding provided.)

Considering the nature of the project, the first phase grant deliverables will have two forks or stacks. Stack 1 will be the business part of the project and will include deliverables related to business activities and improvement. Stack 2 will be the Tech component of the project and the key deliverables here shall be related to wireframes, UI designs and back-end data models.

The groups of stakeholder for this stack will be bi-caudal and will include data donors and data consumers.

The stakeholders belonging to the data donors group shall be participating diagnostic labs, doctors and patients, whereas the stakeholders in the data consumers group shall be researchers, clinical research companies and tech companies (eg. Opscientia) that want to utilize this data to build tech stacks and algorithms on top of it.

The following gives a gist of the top-level milestones that we have planned:

  • First version of Front-End iOS Wireframe with panels for social login, profile definition, initial tutorial, search and explore, data vaults, and personalized reports.
  • First draft of back-end architecture design for Web3 login, search/claim research quests, and personal data vault management
  • iOS/Android application skeleton with basic features for login, profile creation, and placeholders for content
  • Discussion with at-least one Health organizational entity/ Corporate partner who agree for privacy-based data sharing
  • Develop drafts for smart contracts and engage with community for feed back and improvement

Which category best describes your project?

[x] Build / improve applications or integrations to Ocean

What is the final product?

LaDaFo will be based on Open Science Data Passport and will be an application designed for mobile users, medical diagnostic laboratories, and researchers to securely store and share their personal health data including diagnostic data. In addition to personal health data storage, we will also empower medical labs and researchers to participate in an open data community. We expect that unused medical data, including retrospective diagnostic data sitting idle, may be tapped to generate insights for medical research.

Patients and participating labs will be the core stakeholders and will participate in scientific research, support the development of data insights into their health conditions, and access personalized analytic reports generated by A.I.

The Open Science Passport will be a decentralized platform that will utilize Ocean Protocol to bring scientists, health data analysts, research participants, and diagnostic medical labs together to develop better health outcomes.

Considering the exhaustive nature of the healthcare domain, during the initial phases of the project, LaDaFo will focus on specific uses cases in the healthcare domain.

This focused ‘small use-case approach’ will enable our team to validate the project concepts and improve on it’s pain points.

As a starting point of the project, we are tentatively planning to focus on lab patients who undergo a cardiac profile analysis. These can be both self referral or referral by a cardiologist to assess a series of blood parameters. But this use case will be validated based on the market research (which will include extensive literature review, demographic prevelance and stake holder interviews) which is a part of the roadmap and milestones.

Value add criteria:

Usage of Ocean:

Ocean Protocol will be implemented to control access to published research data, algorithms, and protocols for data collection that comprise quests.

Viability:

We consider the project viability can be graded between medium to high. Initial pre-proposal discussion have been held with select labs about the possibility of establishing partnerships and a network of participating labs. Considering the tech, we will leverage on the prior groundwork already established in the works by the OpScientia community.

The timing of this proposal, i.e., considering the development of data use in medical research, powering data crowdsourcing, demand for secure and transparent data services in the healthcare domain and the ideology of making the patient the owner of the data, makes us highly optimistic and confident that the project viability will be more than ROI>1

Community activeness:

Our advisors are active ambassadors and developers within the Ocean community., We will be able to leverage the community support to drive this project forward with OpScientia serving as a collaborator and official advisor for the project.

Benefit for the Ocean Ecosystem:

At the end of the deliverables, this project and the Open Science Data Passport would be designed for use by anyone in the Ocean Ecosystem. In addition, we also will incorporate careful design considerations by participating in working groups on the Ocean discord. Our team and advisors will be active members of the Ocean community, which will enable peer-to- peer learning, knowledge share and improve data provenance in the field of healthcare,

Funding Requested:
3.000 USD (equivalent in Ocean)

Proposal Wallet Address:
0x057c9a25f1302484Bb34C9CEB6d3BC69Bd319e01

Have you previously received an OceanDAO Grant?

No, this is the first time as a primary lead applicant.

Team Website:
N/A

Twitter Handle:
@arunakiry

Discord Handle:
Arunakiry#1973

Project lead email:
arunehealth@gmail.com

Country of Residence:
Germany

Part 2 - Team

2.1 Core Team

Dr. Arunakiry Natarajan

Role: Digital Health and Medical Informatics Expert and will be center of contact with the various stakeholders of this project.

Relevant Credentials:

GitHub: https://github.com/arunehealth

LinkedIn: https://www.linkedin.com/in/arunakiry-natarajan/

Website: https://arunehealth.wixsite.com/arunakirynatarajan.

Background/Experience: Dr. Arunakiry has a background in healthcare (dentistry) coupled with education and experience in medical informatics and digital health. He has more than 20 years of experience combining both healthcare and digital health and also has more than 3 years experience in development cooperation projects. His global (onsite and or virtual) experience include India, Kyrgyzstan, CAREC countries, Albania, Nepal, South Africa, Ethiopia, Cambodia and Germany.
Currently, he plays an important role as a senior medical informatics expert and engages with different team members and stakeholders for the development of Inter-operable applications using SNOMED and FHIR.

Dr. Sassicoumary Arunakiry

Role: Digital Health and Medical Informatics Expert and will be developing data standards and consensus building with stakeholders.

Relevant Credentials:

LinkedIn: https://www.linkedin.com/in/sassicoumary-arunakiry-742514104/

Background/Experience: Dr. Sassicoumary has a background in healthcare and she is currently pursuing her master thesis as a part of her Masters in Medical Informatics at the Technische Hochschule Deggendorf. She has remained a clinical dentist around 15 years and now engages herself in providing teledentistry services to patients. She has been part of a successful hackathon at Bosch Incubation Harbor in Berlin, Germany.

Mr. Rengarajan Sundararajan

Role: Medical reviewer and quality check in medical and pharmaceutical research.Operations and project management

Relevant Credentials:

LinkedIn:https://www.linkedin.com/in/rengarajansundararajan/

Background/Experience: Mr. Rengarajan has a Masters in Applied Mmicrobiology and has extensive experience in managing multi-million dollar projects across different medical publishers and pharma majors in the USA and Europe.
He has deep expertise in digital transformation and leads automation of medical functions of pharma majors. Currently, he is a lead in the management of a team in the context of reviewing legal and medical standards of pharma and medical research.

2.2 Advisors

OpScientia Team

Shady El Damaty, M.Sc., Ph.D.

Role: Cognitive Neuroscientist, Project Advisor, Opscientia Founder

Relevant Credentials:

Github: https://github.com/seldamat

Website: https://seldamat.github.io 2

Linkedin: https://www.linkedin.com/in/seldamat/

Past Experience: Neuroscientist & Big Data Engineer at Georgetown University

Dr. Prakash Kamaraj

Dr. Prakash is currently a member of the Ocean Ambassador community; outreach ship. He has a technology background in Health data-science and AI products in the MedTech industry.

In addition, he is also a Co-founding member of Deep Medicine Labs, a HealthTech solution in the AI space. He also plays multiple roles as an advisor and Tech product Consultant to multiple MedTech companies.

Relevant Credentials:

LinkedIn: https://www.linkedin.com/in/drprk/

Github: https://github.com/drprk

Recent Web3 experience:

Part 3 - Proposal Details

3.1 Details

Details of the proposal:

Decentralized Data Lakes and Data Fountains

The biggest problem of health care today is two-fold - the first being that health data exists in data silos with central data control, which restricts its effective use in research and development, and the second being, missed opportunities in the secondary use of healthcare data. To address these hiccups, healthcare systems need to shift from the centralized paradigm to decentralized models and identify sources of unused data that can be distilled to develop more insights.

Patient-First Care in the Data Ecosystem

In the healthcare context, there is ambiguity in understanding the data lineage and the role of the data owner. The model we propose will enable equal participation of the various stakeholders in the data ecosystem and will shift the power of the data to the patient.

Joining the Science ‘Quest’ in the Open Science passport

Researchers may publish containerized datasets following standard specifications to Coral, the open science knowledge market forked from Ocean Protocol. This will be preceded by various test and validation and quality control which are an integral part of the Open Science Passport ecosystem.

Developing digital identities for the stakeholders of the project

We will enable the development of digital identity for the stakeholders (partner labs, doctors and patients) and these digital identities will be constructed based on personal data of the entities.

Access and control on data

Our proposal is centered around bringing patients together with researchers to solve scientific challenges while maintaining self-ownership of an individual’s health data. We will design our workflow so that users decide who can access their data. Every request to use data will be maintained by trustless systems that determine whether a data request is valid. Another potential workflow for secure access control is mediation through trusted parties that decide and act on access requests. We will design and detail more access principles as the project matures.

Built-in Data Privacy

Private data is kept encrypted locally on the device. Users can publish their data to claim rewards for completing Science Quests as a part of the Open Science Passport ecosystem. Users control access permissions, allowing them to consent in and out of the project in real time. We will create mechanisms that will only allow aggregation of anonymized versions of the data, never the raw original data.

Personalized Research Reports

Users can obtain personalized data reports, called Cards, by consuming algorithms published on Coral by community scientists. Algorithms are shipped to the data provider, maintaining confidentiality and privacy for the user. Stakeholders will be incentivized to innovate on analytic pipelines to drive consumption of their algorithm and accumulation of rewards.

An Open Science Metaverse

Defined use-case quests, algorithms that generate cards, partner profiles, and user avatars are all stored in a rich graph queried by elastic search that is populated when assets are published.

The linked (knowledge) graph structure of the Open Science Metaverse establishes a new precedent for transparency and Metascience workflows to track contributions, incentivize collaboration, and provide participants with control over their data.

Community Governance

All transactions that occur on the Market that will be facilitated by the Open Science Passport incur a transaction fee that is routed to a community-governed treasury. The Open Science Passport rewards active users with tokens that can be claimed for Cards, staked to earn passive income from Market, or vote on proposals.

3.2 If in Category "Build / improve applications or integration to Ocean"

App will be live at:

passport.opsci.io

Is the software open-source?

Yes. The real model will be Data-as-a-Service built on top of an existing tech stack.

MIT License:

Project software can be found at:

https://github.com/opscientia/passport

3.5 If in Category “Build / improve Ocean core software”:

A Pull Request (PR) will be made to these Ocean components: e.g. Aquarius, Provider etc.

We commit to working with Ocean core developers to merging the PR, following software quality best practices.

3.7 If the project includes software:

Are there any mockups or designs to date? If yes, please share details / links.

Yes

https://miro.com/app/board/o9J_l4WScs4=/?invite_link_id=159892124712

3.9 Project Deliverables - Roadmap

What is the project roadmap?

The project road map has two distinct components - milestones that are related to the technical components of the project and the ones related to the business components.

It should be noted that each of these milestones are not vertically planned milestones but overlap as a series of interrelated landmarks in the project.

Key Milestone 1: Initiate synergies with Opscientia and develop forward the work that is already been done by Opscientia

Key Milestone 2: Develop an wireframes and database models with Opscientia and publish the results on a Medium post and reports in the form of white papers,

Key Milestone 3: Begin conversations with Healthcare entities, to form data-sharing agreements without the data-monetization aspects for a pilot-phase

What are the team’s future plans and intentions? Is there maintenance? Possible extensions to the work?

  • Develop more use cases that can add value to the current use case
  • Interview relevant stakeholders and source user requirements for application design.
  • Develop knowledge graphs that can help understand relationships and interrelations between features and their related indicators
  • Include more stakeholders and partners that can participate and donate data
  • Develop synergies and partnerships with other ongoing projects in the Ocean ecosystem
  • Make the Data Passport interoperable in the future for any enterprise/Ocean ecosystem users.
  • Closely discuss with other ecosystem players to avoid repetition of existing work that’s already been done.
  • Engage with other Data science and AI communities to enable them to build an ML or AI stack on top of the data fountains.

opscientia.eth changed to wallet resolve address: 0x057c9a25f1302484Bb34C9CEB6d3BC69Bd319e01

Hi there,

For transparency, starting R12, all proposals will have to be funded within 2 weeks of winning a grant.

The funding deadline is December 27th 23:59 GMT.

You can read our wiki and how to submit a funding request to learn more.

2 Likes

Dear Team Ocean,

Thanks for giving us a chance to work on our proposal with the extensive ocean network of experts.
We also take a chance to thank all the members who voted our proposal.
I am sure that we will make the best use of this opportunity to validate our proposal and develop a good use case in this project.

1 Like