— A machine learning-based framework for digital biomarkers discovery, analysis and development

Focus: PHC

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 

Question to be solved

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.

General Background

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.

Data Types & Technologies

  • Physiological signals data (Heart Rate, Sleep, Differential Heart Rate, Accelerometer data, flu biomarkers)
  • mHealth data ( Epros, patient surveys data, pain reports)
  • Predictive Modeling
  • Machine Learning
  • Exploratory data analysis
  • Feature engineering
  • Model explainability tools
  • Data preprocessing and creating preprocessing pipelines

Needed Skills

  • Self starter with R&D mindset, solving complex machine learning problems
  • Experienced programmer in R or Python
  • Experience in building machine learning driven platforms
  • Experience in time series data analysis and advanced machine learning methods
  • Completed a degree in Data Science/ quantitative field


Dr. Kamran Farooq
Senior Data Scientist @ Data Insights Squad, GIS
LinkedIn Profile

Form of Cooperation

Preferred scale: 6- 12 month full time (remote option is also possible) internship

Possible format: Internship, 6-12 months part time is also possible

How to present your idea


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:


  • You confirm that you are the author of the submission and entitled to dispose of rights of use and exploitation of the contents of your submission, and that you have not yet granted any rights of use and exploitation to third parties that would be infringed by your submission;
  • You grant to Roche Diagnostics GmbH the unrestricted, sublicensable and exclusive right  to use and exploit your submission by all means known today or in the future. This includes without limitation the rights to reproduce, distribute, and exhibit your submission, as well as the right to communicate your submission to the public. You also grant to Roche Diagnostics GmbH the right to edit the submission, to translate it, and to create abbreviations and summaries (abstracts); the aforesaid rights to use and exploit also apply to such edited versions, translations, abbreviations and summaries. 
  • Roche Diagnostics GmbH will designate you as the author of the submission, and will recognize and respect your moral rights in the submission.
  • The relationship you enter into by sending this via the submit button is governed by the laws of the Federal Republic of Germany, and the courts of Germany have international jurisdiction for any disputes arising under or in connection with this relationship..


Any problems with the submit button? Please send your submission to healthcare.xplorers@roche.com.


Further information on our privacy policy can be found here.


Any problems with the submit button?
Please send your submission to healthcare.xplorers@roche.com.


Further information on our privacy policy can be found here.