Presentation at AI morning in April 13th at Tampere University of Technology Kampusklubi.
"AI Morning in April 13th experiments with a new distinctive concept and remixes together machine learning and analytics in the two verticals of healthcare and industry! There is a huge common ground in diagnostics of people and machines, and the same algorithms can be used in both. The presenters from healthcare and industry keynote a conversational networking forum in theme: 'Health: analytics'."
See http://www.aiaamu.fi/
1. What we have done from user’s perspective
2. How we have done it
3. What it means to bring analytics into healthcare products
“experiences in building a medical device software product and integrating analytics to said product”
stroke is a global problem;
we focused on the secondary prevention
patients currently fall to basic health care and come back if a stroke re-occurs -> costly, ineffective, high personal cost
co-developed with HUS, the 2nd largest hospital in western hemisphere; HUS dept. Neurology ranked #1 in the world.
we provided RPM solution for detecting atrial fibrillation and high bp
end-to-end solution with sensors, gateway, cloud+analytics, clinician app
results were excellent: patient interventions, 4.6/5 satisfaction, willingness to commercialize
On a very high level, we have a pipelines and microservices architecture; we aimed at building a common platform that is then specialized for each medical solution. Our main challenge has been how to create multiple medical solutions out of same platform.
Integrating analytics component. At Labs, we developed algorithms with Matlab and Python for e.g. RRI, signal quality, and generic arrhythmias. We integrated 3rd party analytics components for several arrhythmias because we needed algorithms with clinical proof.
The platform architecture is designed to support the requirements; and it is documented according to medical compliancy requirements.
- Build a product offering to enable remote patient monitoring both in the hospital ward and in home environment.- Focus on clinical, medical-grade monitoring – as opposed to consumer-oriented wellness measurement and preventive health monitoring.- Remotely view the essential vital signs of the monitored patients, with minimal setup or intervention required from medical personnel.- Vital sign measurements are expected to include Electrocardiography (ECG), Heart Rate (HR), RR Interval (RRI), Heart Rate Variability (HRV), Blood Oxygenation (SpO2), Respiration Rate, patient posture/movement, temperature and Blood Pressure.- In addition, we will provide alert and annotation support based on real-time and (later) offline analytics capabilities.
For example, If the system is used by healthcare professinals to monitor/diagnose hypertension, it is a medical device and FDA regulations apply.
Kts. EU Medical Device Directive määritelmä
Recap
- Nokia does meaningful work in Tampere with Javascript