Medical mining is a broad research area, where mining methods are applied to solve problems of diagnostics and treatment, as well as for the understanding of disease progression. Medical mining encompasses learning on hospital records (for decision support in diagnosis and treatment), learning on healthcare-associated data, and learning on epidemiological data.
Current cooperations and research tasks of the KMD Lab on medical mining include:
Medical Mining I: Treatment prediction, phenotyping in medical research
Data Mining in Tinnitus Research
Together with the Tinnitus Center - Charité University Medicine Berlin, we develop data mining methods to identify significant subgroups and their determining factors concering severity of tinnitus, its comorbidities and therapy effects. Therefore, we use a high-dimensional dataset comprising various information of patients with chronic tinnitus on tinnitus distress, somatic complaints, psychological comorbidities, psycho-social risk factors, health-related quality of life and socio-demographics. The main goal is to derive subgroup-specific therapy hypoteses and models which afterwards can be realized, empirically validated and eventually disseminated.
Publications for Tinnitus Research: here
Data Mining for Immunfitness
Data Mining in Experiments
We cooperate with the Institute of Community Medicine, University Medicine Greifswald
Cooperation with Leibniz Institute of Neurobiology Magdeburg
Together with the Leibniz Institute of Neurobiology Magdeburg, we analyze experiments on human learning. We also cooperate in the context of the studies profile "Learning Systems" of the bachelor degree Informatik.
Data Mining in Epidemiological Studies
We cooperate with the Institute of Community Medicine, University Medicine Greifswald, on the identification of risk factors and predictive factors for hepatic steatosis. In this cooperation, we study longitudinal data from the cohorts SHIP and SHIP-TREND (Study of Health in Pomerania). We develop methods for learning on high-dimensional, timestamped, multi-relational data. We address challenges of object dissimilarity, data skew and of missing information (due to changes in the recording protocol).
Within the Faculty of Computer Science, we work together with the Visualization Lab (Bernhard Preim) on medical mining and visual analytics for the analysis of the population studies' data of Univ Greifswald. Our joint emphasis is on building easily interpretable patterns.
Cooperation with VisLab
We cooperate with the Visualization Lab of the Faculty of Computer Science on the classification of tumor lesions, using DCE-MR images. We develop methods for building regions/clusters inside each lesion, characterizing them on malignancy and using them to assess the malignancy of the tumor as a whole.
Cooperation with CTB
We cooperate with the Center of Biomedical Technology (CTB) and the Univ. Polytecnica de Madrid on "Data Mining and Stream Mining for Epidemiological Studies on the Human Brain" (StreaMED). We develop methods for modeling disease progression and understanding the impact of treatments.
Selected aspects of the KMD research on Medical Mining are partially funded by the project OSCAR (German Research Foundation, 2017-2019).
Data Mining in Diabetology Research
Together with the Diabetology clinic of the University of Magdeburg, we work on the analysis of plantar pressure and temperature patterns for patients with diabetic foot syndrome and we investigate the potential of intelligent wearables.
Together with University Ulm, Center of Research and Technology Hellas (Greece), Univeristy Medicine Regensburg and Donau University (Austria), we work on platforms for patient empowerment. In the EU JOINT ACTION CHRODIS+, September 2017 - November 2020, we work in Task 7.3 on pilots for the implementation of mHealth tools for fostering quality of care of patients with chronic diseases.
Data Mining in Tinnitus Research
UNITI’s overall aim is to deliver a predictive computational model based on existing and longitudinal data attempting to address the question which treatment approach is optimal for a specific patient based on specific parameters. Clinical, epidemiological, medical, genetic and audiological data, including signals reflecting ear-brain communication, will be analysed from existing databases. Predictive factors for different patient groups will be extracted and their prognostic relevance will be tested in a randomized controlled trial (RCT) in which different groups of patients will undergo a combination of therapies targeting the auditory and central nervous systems.
Together with University Medicine Regensburg, University Ulm and Donau University (Austria), we study the disease profiles and evolution of patients with the chronical, presently incurable disease tinnitus. The KMD group develops methods for the analysis of patients undergoing ambulatory hospital treatment, methods to understand the Ecological Momentary Assessments of patients interacting with the mobile app Track Your Tinnitus, and methods to understand discusions on treatments in the social platform TinnitusTalk (in cooperation with the platform owner TinnitusHub). Starting in summer 2017, we are involved in the ESIT Network of Excellence. More information on the cooperation can be found here.
Publications for ESIT: here