HackCoin - Secure Multi-party Computation (MPC) w/ Blockchain for Healthcare Private Data Computational Research

04 AUG LONDON SUMMER EVENTS
Posted at 11:34h in Business by YeY7F385WW 0 Comments
23 Likes
Share

Big-Ben-creative-commons-300x199

HackCoin London 2015 – Barclays Accelerator

Following on from the success of the previous London event at UBS, another hackathon event was organised on the 24th July. Since the previous theme had been explored but no business implementation had been offered by the wider market in the meantime, the same theme was selected. Thus, “Identity and the Blockchain” was focused on by participants.

Transcript

1. Secure Multi-party Computation (MPC) w/ Blockchain for Healthcare Private Data Computational Research • Charles Cai • #FO #FICC: Investment Banking Front Office: FX/Commodities • #ETRM: Energy Trading & Risk Management • #entrepreneur #innovator #disruptor • Twitter: @caidong • #big-data #data-science #MOOC #Mobile#Cloud #UX #IoT • LinkedIn: http://uk.linkedin.com/in/charlescai/en Identity & Privacy Hackathon #HackCoin 24 July 2015
2. Use case: Continuous Patient Monitoring with Wearable Technology • Until now there’s no cure for Parkinson’s disease • New medicine trial is an extremely slow process – and feedbacks from the patients are not frequent at all • Microsoft Band, Fitbit etc can easily help quicken the process • Sensor data can be can be collected from Microsoft Band real-time (up to 64 measurements per second): • Movements: gyroscope, accelerometer, • Bio-metrics: heartbeat, skin temperature, … • To analyze typical Parkinson’s symptoms: tremor and slowed movements – Loss of automatic movements, impaired posture and balance • Along with clinical records of medicine intake • Technology used: Microsoft Band -> Mobile Phone or Raspberry Pi (with Bluetooth) -> Azure
3. Objective: advanced Healthcare Machine Learning / Predictive Platform in the Cloud • By collecting continuous bio-sensor data, we need big storage + advanced machine learning model • Azure EventHub + Streaming Analytics + AzureML provides a sophisticated platform to tackle the big data challenge in Healthcare • Microsoft Band is an IMU (inertial measurement unit) with gyroscope, accelerometer • Advanced sensor fusion to be developed • Classification of wearer activities • sitting, standing, walking, running, sleeping… • Detect pattern of patient symptoms • E.g.: Parkinson’s Disease: • predicting deterioration speed • new trial medicine effectiveness
4. Secure Multi-party Computation: Wikipedia
5. How to run a simple secured MapReduce
6. Apache Spark – with Blockchain integrated
7. Benefits • Legal requirements: e.g. • Privacy-preserving • Auditable – who can access / compute my data • Full + pseudo-anonymous (k-anonymity) • Monetizing opportunity for data contributors (based on computation counters) • Kill-switch: control if he/she wants to participate in the computation • Meeting HIPPA: • Ethereum VM, Esri DB, Solidity (need extension in Smart Contract for private data, a.k.a. Private Contract) + Spark Analytics Computation Engine