“Development of a probabilistic network for clinical pathways based on patient cohort characteristics, outcome-indicators and clinical workflow analysis to create artificial patients with prostatic adenocarcinoma”
Principal Investigator
Name
Andrea Riedel
Degrees
Master of Science
Institution
Institute for general practitioners
Position Title
master's degree candidate
Email
About this CDAS Project
Study
PLCO
(Learn more about this study)
Project ID
PLCO-535
Initial CDAS Request Approval
Oct 8, 2019
Title
“Development of a probabilistic network for clinical pathways based on patient cohort characteristics, outcome-indicators and clinical workflow analysis to create artificial patients with prostatic adenocarcinoma”
Summary
Due to the constant development in medicine, there is a wide range of diagnostic and therapeutic options for various diseases. How can technical progress in digitalization help to incorporate various individual patient information into the treatment decision? Can the interplay between clinical decision support and evidence-based patient stratification guidelines be technically implemented?
The main focus of the work is the generation of a probabilistic network in order to subsequently generate artificial prostate cancer patient data. This network, which is based on current study data, should enable a classification of realistic patients. The classification is based on their characteristics, guideline adherence or deviation of the treatment as well as the resulting outcome indicators.
The main focus of the work is the generation of a probabilistic network in order to subsequently generate artificial prostate cancer patient data. This network, which is based on current study data, should enable a classification of realistic patients. The classification is based on their characteristics, guideline adherence or deviation of the treatment as well as the resulting outcome indicators.
Aims
- main aim: generation of a probabilitic network for the creation of artifical prostate cancer patient data
- classification of realistic patients
- classification based on characteristics, guidelin adherence, deviation of the treatment, resulting, outcome indicators
Collaborators
Andrea Riedel (master's degree candidate)
Universitätsklinikum Erlangen
Allgemeinmedizinisches Institut
Universitätsstr. 29
91054 Erlangen