Develop machine learning-based framework for digital biomarkers discovery: A generic platform for digital biomarkers development and analysis using patient surveys and wearables data
Apply until December 6, 2021 / Xplorers Camp on December 9, 2021
How could we build a generic framework which could be utilised in digital biomarkers discovery, analysis and prognostic modelling. How to best exploit digital biomarkers and electronic patient reported outcomes/ patient questionnaire data for disease prediction.
Digital health is being rapidly adopted all over the world due to rise in healthcare costs, deteriorating health outcomes, and the growing prevalence and accessibility of mobile health (mHealth) and wearable technology. Data from Biometric Monitoring Technologies (BioMeTs), including mHealth and wearables, can be transformed into digital biomarkers that act as indicators of health outcomes and can be used to diagnose and monitor a number of chronic diseases and conditions. At Roche we are at the forefront of deploying Digital Health strategies to enable utilisation of digital biomarkers and patient surveys data for building preventative care solutions in the area of epidemiology, endometriosis and infectious diseases etc. We collect structured data as part of running clinical trials in various clinical case studies. The data consists of physiological signals, vital signs information along with Epros (electronic patient reported outcomes). These data are collected through wearable devices (Fitbit, Garmin, Empatica_E4 etc.) and other mHealth platforms. The collated data is then used to answer specific clinical questions around symptom onset and prediction of various clinical conditions. We are interested in building a generic machine learning driven platform for digital biomarkers discovery and analysis to build disease-specific prognostic models.
Open source software platform for the development of digital biomarkers
Preferred scale: 6- 12 month full time (remote option is also possible) internship
Possible format: Internship, 6-12 months part time is also possible
Please formulate your ideas on how to tackle this challenge (how to utilise digital biomarkers and EPROs) mhealth data streams. Present a short and concise slide deck (3-6 slides) to elaborate on your proposed solution. Ensure that the proposed solution is driven by state of the art/literature review. One page document with figures to illustrate your concept.
We don’t expect a ready made solution but rather are interested in your methodology design and your approach towards solving the problem. We are looking forward to seeing your ideas and discussing your findings.
By sending this to us via the submit button you agree to the following: