Titel: Real and assumed insights : statistical models and imaging biomarkers for disease characterization of intracranial aneurysms
Autor/-in: Hirsch, Sven
Juchler, Norman
et. al: No
Angaben zur Konferenz: 1. Digital Health Lab Day (Life in Numbers 5), Wädenswil, 3. October 2019
Erscheinungsdatum: 2019
Lizenz (gemäss Verlagsvertrag): Lizenz gemäss Verlagsvertrag
Art der Begutachtung: Keine Angabe
Sprache: Englisch
Fachgebiet (DDC): 005: Computerprogrammierung, Programme und Daten
616: Innere Medizin und Krankheiten
Zusammenfassung: Clinical data science is an emerging discipline, owing to recent developments in the acquisition, storage and processing of large amounts of clinical data. The increasing wealth of data, however, demands for interdisciplinary collaborations, which imposes new challenges. The need for properly dealing with selection biases and establishing balanced databases becomes a key issue to be addressed in the field of digital health. Pre-existing beliefs about the disease sometimes are badly supported by evidence. Wrong assumptions or selection biases, however, will skew the subsequent analyses and mislead the interpretation of results. Subjective or approximate assessments by clinicians, just like missing/censored information about the patients, the data acquisition process or the pathology under examination make data scientific approaches introduce uncertainty about the data to be processed. All this requires robust approaches and very good domain knowledge to avoid false predictions. To successfully reach the clinically relevant statements calls for transparent methods and efficient tools for creating and communicating insights to practitioners. This talk will present some of the experiences made throughout our research on intracranial aneurysms and discuss how we manage these challenges. It will touch the detection of visual biomarkers with machine learning, present an approach to quantifying rather vaguely defined subjective estimations and demonstrate how visualization helps to detect clinical pathways in high dimensional diagnostic data.
Departement: Life Sciences und Facility Management
Organisationseinheit: Institut für Angewandte Simulation (IAS)
Publikationstyp: Konferenz: Sonstiges
URI: https://digitalcollection.zhaw.ch/handle/11475/18565
Publiziert im Rahmen des ZHAW-Projekts: AneuX
Enthalten in den Sammlungen:Publikationen Life Sciences und Facility Management

Dateien zu dieser Ressource:
Es gibt keine Dateien zu dieser Ressource.

Alle Ressourcen in diesem Repository sind urheberrechtlich geschützt, soweit nicht anderweitig angezeigt.