AMA With Dr Marcus Tan, Co-Founder, and Dr Dumitrel Loghin, Tech Lead of MediLOT
*We will like to express our gratitude to Crypto Daku for hosting the AMA session*
Dear MediLOT Community,
An AMA was hosted by popular crypto-influencer Crypto Daku, in his community channel on 12th June 2019. We were glad to see active participation by the community and the quality of questions raised.
Here’s what MediLOT’s Co-Founder, Dr Marcus, and Tech Lead, Dr Loghin, had to say during the AMA.
Note: This AMA has been edited for clarity.
AMA With Dr Marcus Tan, Co-Founder, and Dr Dumitrel Loghin, Tech Lead of MediLOT
*We will like to express our gratitude to Crypto Daku for hosting the AMA session*
Dear MediLOT Community,
An AMA was hosted by popular crypto-influencer Crypto Daku, in his community channel on 12th June 2019. We were glad to see active participation by the community and the quality of questions raised.
Here’s what MediLOT’s Co-Founder, Dr Marcus, and Tech Lead, Dr Loghin, had to say during the AMA.
Note: This AMA has been edited for clarity.
Q: To kick things off, can you provide a brief introduction about yourself and an overview of your role within the project?
Dr Marcus: I’m a medical doctor, and also one of the co-founders of MediLOT — in my work I serve as a link between MediLOT and healthcare institutions and also provide a clinical viewpoint on the different challenges that we face. It is an exciting time for MediLOT now with many partnerships and developments coming up and we can’t wait to share them all with you guys.
Dr Loghin: Hi, I am the tech lead at MediLOT. Together with co-founder Professor Ooi Beng Chin, Dr Cai Qingchao and Dr Andreea Costea, we are responsible for the distributed systems, including blockchain and backend services. I am also the architect of the PoC and testnet.
Q: How do you ensure that the data of patients remained secured within your platform?
Dr Marcus: Patients ultimately control access permissions to their own health data — no developers or subscribers can have access to it unless granted by the patient himself. Any data that is shared is also anonymised. The Singapore government has a national data privacy law in place (Personal Data Protection Act, similar to Europe’s GDPR) to safeguard all forms of personal and health data and MediLOT is compliant with that.
We are also not storing the entire data records (e.g. EHR) on the blockchain, but rather a secure hash of that data (which acts as a pointer in the hospital’s database).
Q: Will the project implement any privacy protocol to secure privacy? Also, how do you ensure that the data provided to third party providers in your ecosystem be kept safe?
Dr Loghin: We are using multiple methods to ensure privacy and data protection. By data we mean EHR data. First, this data resides in hospital’s database, and does not leave it in raw format. Second, sensitive fields, such as Identification Number, Addresses, etc. are anonymized when sent to AI model inference. Third, we run the analytics part in a secure sandbox which uses state-of-the-art privacy preserving techniques. Our team of Data Privacy and Security research scientists including Associate Professor Xiao Xiaokui and Dr Dinh Tien Tuan Anh will do our very best to ensure data privacy.
Q: How does MediLOT work with current EHR systems? Does MediLOT plan to have their own database?
Dr Marcus: MediLOT will need to be integrated with current EHR systems as they are very heterogenous. At the database level we can convert standard SQL databases etc to our own or we can choose to integrate at a higher level if institutions choose to retain their own database.
Q: What does Forkbase offer?
Dr Loghin: Forkbase is a git-like database for huge datasets. It offers fine-grain access control and uses hash pointers to ensure data immutability.
Q: How different is MediLOT from other healthcare projects?
Dr Marcus: MediLOT is one of the few distributed systems projects with artificial intelligence (AI) and analytics overlays already developed and integrated into the blockchain and database layers by our team of AI and Data Analytics research scientists led by co-founder Professor Zhang Meihui. Prof Zhang is a Professor at the Beijing Institute of Technology and a winner of prestigious China’s Young Scholar Thousand Talents Program in 2018. Our team members also have extensive publications and references in the space. Business wise we have partnerships with large healthcare institutions in SG and China and we look to leverage on that.
Q: Can you elaborate on the token metrics?
Dr Marcus:
Total initial circulating tokens at listing: 162,330,872 or 162m
Token price: $0.017475 (same for all rounds)
Hardcap = US$7.5m
Strategic Seed Round = US$954K (Closed in June 2018, 1 year ago)
Presale Round = US$5m (Ongoing)
IEO Raise (Exchange to announce on 13 June 2019) = US$1.5m
Bonus for Seed Round = 20%
Bonus for Presale Round = 10%
Bonus for IEO = 0%
Vesting for Seed & Presale:
20% on listing
20% 1 mth after listing
20% 2 mth after listing
40% 3 mth after listing (distribution includes bonus; all tokens to be distributed 3 mths after listing)
Q: Who will have access to patient’s data?
Dr Marcus: Only authorised providers and institutions will be allowed to access the patients’ data, and only with the patients’ permission. This allows the patients to have control over who can view or access their data.
Q: Why is Forkbase preferred to Cloud Storage?
Dr Loghin: Forkbase can work on top of cloud storage, but it offers some advantages compared to other cloud storage services. Some of these services are there in other systems, but none, to the best of my knowledge, offers all services that we need. These include: ease of branching and merging for ease-of-use, deduplication for storage efficiency, data immutability, fine grain access control.
Q: How does Hyperledger++ helps?
Dr Loghin: Hyperledger++ improves the scalability of Hyperledger by at least one order of magnitude. Our experiments show that HL++ scales to over 3,000 TPS on 1,000 cloud nodes distributed all over the world. In contrast, HL does not scale beyond 16 nodes, not even in a local cluster.
Q: Sensitive patients’ data be in encrypted form or just simply hidden/blurred/anonymized?
Dr Loghin: Such data will be anonymized such that they cannot be inferred. Moreover, all data transfers will be encrypted, from hospital’s base to the sandbox.
Q: Will people be keen to share their private data especially medical records are known to be sensitive?
Dr Marcus: Patients will only share their data if it can be anonymised and if they are incentivised enough to do so, otherwise many will not want to! The key lies in what we can offer the patient and also the sense that what they contribute is meaningful to others/society.
Q: The team will raise funds via an ICO or IEO?
Dr Marcus: We are finalising an IEO with an exciting and reputable exchange and will announce it as soon as we are able to. Keep your eyes peeled!
Q: What incentives will the project provide to increase adoption rate?
Dr Marcus: To reach out to potential users we have to offer them value. For contributing data, patients get rewarded in LOT.
One of our onboarding approaches is to offer patients a customised health analysis/report that they can get for free if they wish to use the platform — this will not include advanced analytics, which can be separately accessed via tokens. A very simple example of this would be individualised meal advice for patients who want to upload their meals onto the platform — they can currently test this out using our app http://www.foodlg.com/
Q: What is Apache Singa?
Dr Loghin: Apache Singa is a deep learning framework that supports training and inference, developed by us in NUS and incubating under Apache. It is similar to tensorflow, caffe, pytorch, etc
Q: What will be the reason for mass adoption in the future?
Dr Marcus: This is a big question! But I could say that as a believer in DLT/blockchain technology — we all look forward to a world whereas a patient you can be sure that healthcare professionals/hospitals/researchers are accountable towards your health data. Also, the integration of AI and the beginning of truly personalised medicine as a result of leveraging large amounts of population wide health data. MediLOT is a small step towards that :)
We also work closely with our institutional/ corporate partners to drive individual user adoption: Research organisations, insurance companies, pharmaceutical companies and healthcare organisations who want access to aggregate amounts of large, clean datasets will transact through our token to have access to such datasets — part of this will then go to the people who have contributed such data. Currently, some of our technologies are being used in NUHS (National University Hospital of Singapore) with clinical data. We aim to have large scale adoption in the next 2–3 years.
Q: Along with current developments, what other product features can we expect in the future?
Dr Marcus: We aim for a broad-based ecosystem that allows a large range of products to be built on it. Thinking of health analytics applications such as cardiovascular risk calculators, dietary/lifestyle customisation and advice, even wearables integration. There are many possibilities, but we will have to focus on a few and start from there.
Q: Investors usually avoid healthcare projects due to poor ROIs, how will MediLOT be different?
Dr Marcus: First of all, the project is formulated and executed by a Singapore-based team with solid experience in medicine, tech and business development. The core members are from the blockchain and healthcare spheres.
The research done by MediLOT’s team of professors has been cited in many reputable publications.
Backed by equity investor SG Innovate, the Singapore Government Venture Capital Fund, MediLot has a monopoly in Singapore, having already partnered with National University Hospital (the largest medical research institution in Singapore). More contracts with other Singapore hospitals will be announced. The team has also secured a foothold in the fast-growing China healthcare market.
We will work closely with our institutional/ corporate partners to drive individual user adoption: Research organisations, insurance companies, pharmaceutical companies and healthcare organisations who want access to aggregate amounts of large, clean datasets will transact through our token to have access to such datasets — part of this will then go to the people who have contributed such data. Currently, some of our technologies are being used in NUHS (National University Hospital of SIngapore) with clinical data. We aim to have large scale adoption in the next 2–3 years.
Q: How will you be limiting the information shared with third party providers?
Dr Marcus: The data shared with 3rd parties will be anonymised and only accessible in a sandbox (GEMINI) and yes it will be closely monitored and vetted. We are looking at institutional access mainly, and not to anyone who signs up :)
Q: What are the security layers in Gemini?
Dr Loghin: GEMINI will be running in a sandbox, on data with anonymized fields. Users will not interact with the layers in GEMINI, but rather with the entire system, with input and output. For output, we employ technique to make sure the users do not embedded raw data in model parameters.
Q: If a patient is in coma, who can access his data without his consent?
Dr Marcus: Good question. Right now we allow a patient to authorise 2 trusted persons (usually family members) to have access to override when he is unconscious. Otherwise, 2 nominated senior doctors in the hospital may also override — this is in line with existing practices for patients who are incapable of consent. All decisions have to be made in the best interests of the patient.
Q: How is MediLOT comparable to Solve Care?
Dr Marcus:
Solve Care and MediLOT are complementary.
Solve Care’s platform is designed to simplify access to care, reduce administrative steps and burden, simplify and speed up payments to healthcare providers globally using Blockchain technology. Solve Care utilizes blockchain technology to reduce the enormous global clinical and IT system costs associated with our current healthcare system.
MediLOT is a dual blockchain-based Electronic Health Records platform that allows individual patients to grant healthcare providers, research institutions and pharmaceuticals access to their encrypted medical data by indicating the storage location. This is a highly secure solution which adheres to GDPR and other stringent data privacy regulations. Patients will be incentivized and empowered to permit the usage of their data to facilitate research, such as the research to create new drugs and treatments for cancers.
Hence, we will explore the possibility of partnering Solve Care in future and potentially share our business development network.
Q: What is the main factor you consider to be that will allow this project to be a success during this bear market?
Dr Marcus: Well there are many factors but we believe that having one of the strongest tech teams in the space with a proven track records, the existing strong partnerships we have, and also solid backing from both Govt owned funds and a vibrant community are all crucial to making this a success. This AMA, along with many others is an example of that :)
Q: How valuable are patients’ data, and how do you plan to monetize it ethically?
Dr Marcus: Nice! Health data is immensely valuable — and patients/institutions are free to voluntarily offer it — as in research trials/surveys etc. Pharmaceutical companies pay millions, even billions for trials and studies to collect health data, that should give you an indication.
Q: What are your plans for pushing your product to new markets like USA, Canada, Europe? Have you already signed some agreements?
Dr Marcus: Great question. Our initial focus is Asia/China, but we are open to further expansion. The issue with USA is that they have very strict regulatory requirements, and this is same for EU. HIPAA compliance/ compliance with other regulations will be a huge task for any organisation aiming to break into the US market.
Q: What’s a realistic timeframe for the SDK? Can you provide clarification on what platforms and features the SDK would support?
Dr Loghin: Good question! We are going to provide an SDK for AI model developers which is going to be released publicly. We have an SDK for hospital’s interfacing, which is not going to be public. For the public SDK related to AI, we are planning to release a beta version with our testnet, Q4 this year.
About MediLOT
MediLOT is a dual blockchain-based Electronic Health Records platform that allows individual patients to grant healthcare providers, research institutions and pharmaceuticals access to their encrypted medical data by indicating the storage location. This is a highly secure solution which adheres to GDPR and other stringent data privacy regulations. Patients will be incentivized and empowered to permit the usage of their data to facilitate research. For more information, pls visit:
Whitepaper: https://medilot.com/wp/wp-content/uploads/2018/06/white-paper-en.pdf
Summary: https://medilot.com/wp/wp-content/uploads/2018/06/summary-en.pdf
Intro Video: https://youtu.be/DbyOi53OhSU
POC Video: https://youtu.be/tW7iS9rp_ac
