Refine
Year of publication
Document Type
- Master's Thesis (20)
- Bachelor Thesis (5)
- Preprint (2)
- Diploma Thesis (1)
Language
- English (28) (remove)
Has Fulltext
- yes (28)
Is part of the Bibliography
- no (28)
Keywords
- Application (3)
- Neuronales Netz (3)
- Bildgebung (2)
- MRI (2)
- Maschinelles Lernen (2)
- Simulation (2)
- Software (2)
- stroke (2)
- web application (2)
- 3D Slicer (1)
Institute
- Medizinische Informatik (14)
- Informatik (13)
Medication reconciliation is defined by the American Society of Health- System Pharmacists (ASHP) and the American Pharmacists Association (AphA) as “the comprehensive evaluation of a patient’s medication regimen any time there is a change in therapy in an effort to avoid medication errors such as omissions, duplications, dosing errors or drug interactions, as well as to observe compliance and adherence patterns “. Medication reconciliation is very important to avoid medication errors but it is also a complex and time-consuming process. Medication histories, i.e. records of prescription, purchase, and refill sequences are considered to be a resource from which conclusions about medication reconciliation can be drawn. However, medication histories spread across diverse paper and electronic media may lack the required accuracy. By employing multiple electronic sources this thesis will evaluate if more accurate medication histories can be collected.
Cytoscape is an open source platform for complex network analysis and visualisation. The Pathway Interaction Database (PID) is a highly structured, curated collection of information about known biomolecular interactions and key cellular processes assembled into signalling pathways. Despite the obvious potential and advantageous usage of both tool (Cytoscape) and information source (PID), there has been no conclusive effort to merge and synergise them. This project aims to make use of the open source characteristics of Cytoscape and optimally visualise the biomolecular interactions found in the PID. This is made possible by the development of a plugin which imports a user-selected pathway file, converts it into a Cytoscape-readable file, and then visualises it. Finally, the user has options to further optimise the pathway by the use of a filter (Barcode – Affymetrix) that removes nodes from the network which are lowly expressed in the Affymetrix microarray data. The user then obtains visual results in a matter of seconds. Additionally, the process of subgraphing nodes through the shortest path method could be applied to the network. This can further assist the user in identifying the molecular pathways of the nodes of interest, a useful feature in network analysis.
Implementation of an interactive pattern mining framework on electronic health record datasets
(2019)
Large collections of electronic patient records contain a broad range of clinical information highly relevant for data analysis. However, they are maintained primarily for patient administration, and automated methods are required to extract valuable knowledge for predictive, preventive, personalized and participatory medicine. Sequential pattern mining is a fundamental task in data mining which can be used to find statistically relevant, non-trivial temporal dependencies of events such as disease comorbidities. This works objective is to use this mining technique to identify disease associations based on ICD-9-CM codes data of the entire Taiwanese population obtained from Taiwan’s National Health Insurance Research Database.
This thesis reports the development and implementation of the Disease Pattern Miner – a pattern mining framework in a medical domain. The framework was designed as a Web application which can be used to run several state-of-the-art sequence mining algorithms on electronic health records, collect and filter the results to reduce the number of patterns to a meaningful size, and visualize the disease associations as an interactive model in a specific population group. This may be crucial to discover new disease associations and offer novel insights to explain disease pathogenesis. A structured evaluation of the data and models are required before medical data-scientist may use this application as a tool for further research to get a better understanding of disease comorbidities.
Ambulant studies are dependent on the behavior and compliance of subjects in their home environment. Especially during interventions on the musculoskeletal system, monitoring physical activity is essential, even for research on nutritional, metabolic, or neuromuscular issues. To support an ambulant study at the German Aerospace Center (DLR), a pattern recognition system for human activity was developed. Everyday activi-ties of static (standing, sitting, lying) and dynamic nature (walking, ascending stairs, descending stairs, jogging) were under consideration. Two tri-axial accelerometers were attached to the hip and parallel to the tibia. Pattern characterizing features from the time domain (mean, standard deviation, absolute maximum) and the frequency domain (main frequencies, spectral entropy, autoregressive coefficients, signal magni-tude area) were extracted. Artificial neural networks (ANN) with a feedforward topology were trained with backpropagation as supervised learning algorithm. An evaluation of the resulting classifier was conducted with 14 subjects completing an activity protocol and a free chosen course of activities. An individual ANN was trained for each subject. Accuracies of 87,99 % and 71,23 % were approached in classifying the activity protocol and the free run, respectively. Reliabilities of 96,49 % and 76,77 % were measured. These performance parameters represent a working ambulant physical activity monitor-ing system.
Alzheimer’s Disease affects millions of people worldwide, but till today, the gold standard
for definitive diagnosis of this disease is a biopsy. Nevertheless, with the progress
of the disease, a volume loss in the Hippocampus can be observed. Therefore, good
segmentation methods are crucial to facilitate quantification of this loss.
The focus of this work is on the development of a Machine Learning algorithm, more
precisely a Generative Adversarial Network, for the automated segmentation of the
human Hippocampus and its substructures in Magnetic Resonance Images. In particular,
the task is to determine if the integration of a pre-trained network that generates
segmentations into a Generative Adversarial Network scheme can improve generated
segmentations. In this context, a segmentation network in form of a U-net corresponds
to the generator. The discriminator is developed separately and merged in a second
step with the generator for combined training.
With a literature review regarding the automated segmentation of the Hippocampus,
current methods in this field and their medical and technological basics were identified.
The datasets were preprocessed to make them suitable for the use in a neural
network. In the training process, the generator was trained first until convergence.
Then, the Generative Adversarial Network including the pre-trained generator was
trained. The outcomes were evaluated via cross-validation in two different datasets
(Kulaga-Yoskovitz and Winterburn). The Generative Adversarial Network scheme
was tested regarding different architectural and training aspects, including the usage
of skip-connections and a combined loss function.
The best results were achieved in the Kulaga-Yoskovitz dataset with a Dice coefficient
of 90.84 % after the combined training of generator and discriminator with a joined
loss function. This improves the current state of the art method in the same task and
dataset with a Dice index of 88.79 % by Romero [Rom17]. Except of two cases in the
Winterburn dataset, the proposed combined method could always improve the Dice
results after the training of only the generator, even though only by a small amount.
There are many drug interactions and to know every single interaction is impossible. In Uganda, a country located in East Africa, patients often do not get a patient information leflaet when a physician prescribes drugs because they only get the drugs without packaging and information inside. Even in developed countries many poeple die because of drug interactions.
This work aims at developing a clinical decision support system for different kinds of drug interactions: 1) drug-drug interaction,
2) drug-food interactions,
3) drug-condition
interactions and
4) drug-disease interactions.
This system must be integrated into an
existing hospital information system called electronic Health Management Information System (eHMIS).
In the first part of this thesis different kinds of clinical decision support systems are described to find out which one is the best for eHMIS. The two different types are knowledge-based and non knowledge-based systems. The second part of this thesis, the data base of eHMIS is extended to have a full
knowledge base for the new module which contains drug-drug interactions, drug-food interactions, drug-disease interactions as well as drug-condition interactions. Therefore new tables were created and filled with data of several data bases with drug interactions. The last part is about designing the clinical decision support system for drug interactions
with the knowledge base of eHMIS, including the implementation considering the integration into the existing system. To know how health professionals in Uganda work
with an electronical health system as well as their other work ows was important. The system now runs in a hospital in Kampala, the capital of Uganda and in a health center level three in Mifumi, a village located in the east of the country.
Every year, hundreds of thousands of patients are affected by treatment failure or adverse drug reactions, many of which could be revented by pharmacogenomic testing. To address these deficiencies in care, clinics require
automated clinical decision support through computer based systems, which provide clinicians with patient-specific ecommendations. The primary knowledge needed for clinical pharmacogneomics is currently being
developed through textual and unstructured guidelines.
In this thesis, it is evaluated whether a web service can annotate clinically relevant genetic variants with guideline information using web services and identify areas of challenge. The proposed tool displays a formal representation of pharmacogenomic guideline information through a web service and existing resources. It enables the annotation of variant call format (VCF) files with clinical guideline information from the Pharmacogenomic Knowledge Base (PharmGKB) and Clinical Pharmacogenetics Implementation Consortium (CPIC).
The applicability of the web service to nnotate clinically relevant variants with pharmacogenomics guideline information is evaluated by translating five guidelines to a web service workflow and executing the process to annotate publically available genomes. The workflow finds genetic variants covered in CPIC guidelines and influenced drugs.
The results show that the web service could be used to annotate in real time clinically relevant variants with up-to-date pharmacogenomics guideline information, although several challenges such as translating variants into star allele nomenclature and the absence of a unique haplotype nomenclature
remain before the clinical implementation of this approach and the use on other drugs.
Medical imaging produces many images every day in clinical routine. Keeping up with the
daily image analysis task and this vast amount of data is quite a challenge for radiologists.
However, these analysis tasks can be automated with well-proven automatic segmentation
methods. Segmentation reviewing of an expert is necessary because learningbased
automatic segmentation methods may not perform well on exceptional image
data. Creating valid segmentations by reviewing them also improve the learning-based
methods.
Combining established standards with modern technologies creates a flexible environment
to efficiently evaluate multiple segmentation algorithm outputs based on different metrics
and visualizations and report these analysis results back to a clinical system environment.
The presented software system can inspect such quantitative results in a fast and intuitive
way, potentially improving the daily repetitive segmentation review and rework of a
research radiologist. The presented system is designed to be integrated into a virtual
distributed computing environment with other systems and analysis methods. Critical
factors for this particular environment are the handling of many patient data and routine
automated analysis with state of the art technology.
First experiments show that the time to review automatic segmentation results can be
roughly divided in half while the confidence of the radiologist is enhanced. The system
is also able to highlight individual slices which are essential for the expert’s review
decision. For this highlighting, different metric scores are compared and evaluated.
Development and validation of a neural network for adaptive gait cycle detection from kinematic data
(2020)
(1) Background: Instrumented gait analysis is a tool for quantification of the different
aspects of the locomotor system. Gait analysis technology has substantially evolved over
the last decade and most modern systems provide real-time capability. The ability to
calculate joint angles with low delays paves the way for new applications such as real-time
movement feedback, like control of functional electrical stimulation in the rehabilitation
of individuals with gait disorders. For any kind of therapeutic application, the timely
determination of different gait phases such as stance or swing is crucial. Gait phases are
usually estimated based on heuristics of joint angles or time points of certain gait events.
Such heuristic approaches often do not work properly in people with gait disorders due to
the greater variability of their pathological gait pattern. To improve the current state-ofthe-
art, this thesis aims to introduce a data-driven approach for real-time determination
of gait phases from kinematic variables based on long short-term memory recurrent neural
networks (LSTM RNNs).
(2) Methods: In this thesis, 56 measurements with gait data of 11 healthy subjects,
13 individuals with incomplete spinal cord injury and 10 stroke survivors with walking
speeds ranging from 0.2 m
s up to 1 m
s were used to train the networks. Each measurement
contained kinematic data from the corresponding subject walking on a treadmill for 90
seconds. Kinematic data was obtained by measuring the positions of reflective markers on
body landmarks (Helen Hayes marker set) with a sample rate of 60Hz. For constructing a
ground truth, gait data was annotated manually by three raters. Two approaches, direct
regression of gait phases and estimation via detection of the gait events Initial Contact
and Final Contact were implemented for evaluation of the performance of LSTM RNNs.
For comparison of performance, the frequently cited coordinate- and velocity-based event
detection approaches of Zeni et al. were used. All aspects of this thesis have been
implemented within MATLAB Version 9.6 using the Deep Learning Toolbox.
(3) Results: The mean time difference between events annotated by the three raters
was −0.07 ± 20.17ms. Correlation coefficients of inter-rater and intra-rater reliability
yielded mainly excellent or perfect results. For detection of gait events, the LSTM RNN
algorithm covered 97.05% of all events within a scope of 50ms. The overall mean time
difference between detected events and ground truth was −11.62 ± 7.01ms. Temporal
differences and deviations were consistently small over different walking speeds and gait
pathologies. Mean time difference to the ground truth was 13.61 ± 17.88ms for the
coordinate-based approach of Zeni et al. and 17.18 ± 15.67ms for the velocity-based
approach. For estimation of gait phases, the gait phase was determined as a percentage.
Mean squared error to the ground truth was 0.95 ± 0.55% for the proposed algorithm
using event detection and 1.50 ± 0.55% for regression. For the approaches of Zeni et al.,
mean squared error was 2.04±1.23% for the coordinate-based approach and 2.24±1.34%
for the velocity-based approach. Regarding mean absolute error to the ground truth, the
proposed algorithm achieved a mean absolute error of 1.95±1.10% using event detection
and one of 7.25 ± 1.45% using regression. Mean absolute error for the coordinate-based
approach of Zeni et al. was 4.08±2.51% and 4.50±2.73% for the velocity-based approach.
(4) Conclusion: The newly introduced LSTM RNN algorithm offers a high recognition
rate of gait events with a small delay. Its performance outperforms several state-of-theart
gait event detection methods while offering the possibility for real-time processing
and high generalization of trained gait patterns. Additionally, the proposed algorithm
is easy to integrate into existing applications and contains parameters that self-adapt
to individuals’ gait behavior to further improve performance. In respect to gait phase
estimation, the performance of the proposed algorithm using event detection is in line
with current wearable state-of-the-art methods. Compared with conventional methods,
performance of direct regression of gait phases is only moderate. Given the results,
LSTM RNNs demonstrate feasibility regarding event detection and are applicable for
many clinical and research applications. They may be not suitable for the estimation
of gait phases via regression. For LSTM RNNs, it can be assumed, that with a more
optimal configuration of the networks, a much higher performance is achieved.
Sudden cardiac arrest is a leading cause of death world wide, with about 100.000 to 150.000 cases each year in Germany alone [Weidringer and Sefrin, 2006]. This means that annually one out of 1000 citizens are affected [Bahr, 2007]. At standard conditions the human brain has a relative low ischemic1 tolerance. Therefore after 3 - 5 minutes without therapy, irreversible damage is to be expected. The rate of survival drops 7% - 10% each minute, without resuscitation [Bahr, 2007]. Since the arrival of the organized emergency medical service usually takes more than 5 minutes after the emergency call [Wahlen et al., 2003, Weisfeldt et al., 2010], the instant and adequate resuscitation by bystanders in this period is of vital importance. The advantage of basic life support2 (BLS) by laymen shows a fourfold higher rate of survival, once resuscitation has begun, until the arrival of the emergency medical service [Bahr, 2007].