Data Analytics and Science for Health Research2021-01-27T13:27:46+01:00

Data Analytics and Science for Health Research

In the field of medical research, extremely large data sets must often be evaluated and meaningfully linked. Artificial Intelligence supports data analytics and facilitates the rapid discovery of correlations in order to gain new insights for possible diagnoses and treatments. The goal is to improve the evaluation so that reliable statements can be made and abnormalities in the data can be better identified. Data analytics and data science can thus help to advance research, and thus new medical discoveries.


Use Case: AI supports the diagnosis and treatment of neuromuscular diseases

In a research project with the Neuropaediatrics Department of the University Hospital Essen, the Leibniz Institute for Analytical Sciences (ISAS) and the MVZ Institute for Clinical Genetics in Bonn, data analytics and data science applications are to be used for the first time to optimize health research in the field of neuromuscular diseases. The aim of the joint project is to improve the diagnosis and treatment of diseases by analyzing patient data using a special algorithm.

Currently, costly and complex genetic tests and their accurate interpretation are necessary for a reliable diagnosis. Therefore, faster diagnostic procedures are to be developed by means of simpler protein tests, which would then often prevent lengthy diagnoses and thus enable a suitable therapy to be initiated more quickly. For the evaluation of the test results, INFORM DataLab has developed a special algorithm that is designed to detect certain correlations in the data and thus reliably predict which form of neuromuscular disease a patient is suffering from.

0Terabyte Data Volume
0Project partners
0Million € Subsidy Amount
“With INFORM DataLab as our partner, we have a data science expert on board who understands how to successfully transfer findings from data into practice. In the project, we were able to determine which proteins in combination with specific information from DNA analysis lead to a specific genetic defect. Accordingly, in the future it will be possible to directly predict the affected gene. This is important to be able to better interpret the genetic findings that are collected. Prediction algorithms such as those developed by INFORM DataLab will help to determine the causative genetic defect. In this way, patients can go into genetic counselling as quickly as possible with the knowledge of the responsible gene. Accordingly, the ‘diagnostic odyssey’ that patients often undergo can be prevented in the long term. We often treat patients for whom it can take ten or twelve years to solve the case.”

Dr. Andreas Roos, Neuropaediatrics University Hospital Essen

The Pillars of Data Science Readiness

Success stories about the benefits of machine learning and data science prompt companies from all industries to adopt some level of automated data analysis for themselves. In doing so they often encounter problems early on, or, even worse, late into the process. In this article I will give you an overview of the main pillars of Data Science readiness, as well as how you can achieve them. Data Availability No matter the method or goal, the basis for any machine [...]

Go to Top