Graph + Medical Informatics

Graph-based signal integration for patient diagnosis discovery
http://www.biotconf.org/biot2011/BIOT-2011-EA-Herskovic-Bernstam.pdf

Biomedical information problems are often difficult to
solve with computational techniques. One reason for this
difficulty is that many qualitatively different information
types must be combined to solve the problem. For example,
diagnosing a disease requires that information such as
patient demographics, past medical history, disease
prevalence, and current complaints be integrated in some
rational way. In this paper, we describe an approach that
leverages graphs to integrate several information sources to
“diagnose” a patient record

A three-level graph-based model for the management of hospital information systems.
http://www.ncbi.nlm.nih.gov/pubmed/7476470
Information processing in hospitals, especially in university hospitals, is currently faced with two major issues: low-cost hardware and progress in networking technology leads to a further decentralization of computing capacity, due to the increasing need for information processing in hospitals and due to economic restrictions, it is necessary to use commercial software products. This leads to heterogeneous hospital information systems using a variety of software and hardware products, and to a stronger demand for integrating these products and, in general, for a dedicated methodology for the management of hospital information systems to support patient care and medical research. We present a three-level graph-based model (3LGM) to support the systematic management of hospital information systems. 3LGM can serve as a basis for assessing the quality of information processing in hospitals. 3LGM distinguishes between a procedural level for describing the information procedures (and their information interchange) of a hospital information system and thus its functionality, a logical too level, focusing on application systems and communication links, and a physical tool level with physical subsystems (e.g., computer systems) and data transmission. The examples that are presented have been taken from the Heidelberg University Hospital Information System.

Integrated multimedia electronic patient record and grap
http://perso.telecom-paristech.fr/~bloch/papers/CBM-08.pdf
Current electronic patient record (EPR) implementations do not incorporate medical images, nor structural information extracted from them,
despite images increasing role for diagnosis. This paper presents an integration framework into EPRs of anatomical and pathological knowledge
extracted from segmented magnetic resonance imaging (MRI), applying a graph of representation for anatomical and functional information
for individual patients. Focusing on cerebral tumors examination and patient follow-up, multimedia EPRs were created and evaluated through a
3D navigation application, developed with open-source libraries and standards. Results suggest that the enhanced clinical information scheme
could lead to original changes in the way medical experts utilize image-based information.


A Graph-based Bagging
http://www.cse.iitm.ac.in/CoLISD/Papers/4.pdf
The ensemble technique weights several individual classi ers
and combines them to obtain a composite classi er that outperforms each
of them alone. Despite of this technique has been successfully applied in
many areas, in the literature review we did not nd its application on
networked data. To tackle with this lack, we propose a bagging proce-
dure applied to graph-based classi ers. Our contribution was to develop
a bagging procedure for networked data which either maintains or signif-
icantly improves the performance of the tested relational classi ers. Ad-
ditionally, we investigate the role played by diversity among the several
individual classi ers to explain when the technique can be successfully
applied.

Graph-based learning for information systems
http://gradworks.umi.com/33/52/3352368.html


Design and Evaluation of a Temporal, Graph-based Language for Querying Collections of Patient Histories

Giving clinicians and researchers the ability to easily retrieve and explore relevant fragments of patient histories would greatly facilitate quality assurance, patient follow-up and research on patient treatment processes. Established database query languages are inconvenient for such exploration, and may also be too complex for users with limited backgrounds in informatics. We believe that understandability can be increased in return for a sacrifice of some of the power of expression found in general query languages. In order to design a specialized query language, we have collected and synthesized a tentative list of requirements. Based on these requirements, we have designed and implemented Practice Explorer, a prototype for visual query of collections of patient histories, and evaluated the understandability of its query language by testing with medical students. The results indicate that parts of the language are intuitive enough for users to understand without demonstrations, examples, feedback or assistance. They also provide some lessons for future work in this area.


Graph-based Word Sense Disambiguation of Biomedical Documents
http://bioinformatics.oxfordjournals.org/content/early/2010/10/07/bioinformatics.btq555.full.pdf
Word Sense Disambiguation (WSD), automatically identifying the meaning of ambiguous words in context, is an important stage of text processing. This paper presents a graph-based
approach to WSD in the biomedical domain. The method is unsupervised and does not require any labeled training data. It makes use
of knowledge from the Unified Medical Language System (UMLS)
Metathesaurus which is represented as a graph. A state-of-the-art
algorithm, Personalized PageRank, is used to perform WSD.
Results: When evaluated on the NLM-WSD dataset the algorithm
outperforms other methods that rely on the UMLS Metathesaurus
alone


Graph-Based Shape Analysis for MRI Classification
http://www.igi-global.com/article/international-journal-knowledge-discovery-bioinformatics/62299
Searching for correlations between brain structure and attributes of a person’s intellectual state is a process which may be better done by automation than by human labor. Such an automated system would be capable of performing classification based on the discovered correlation, which would be means of testing how accurate the discovered correlation is. The authors have developed a system which generates a graph-based representation of the shape of the third and lateral ventricles based on a structural MRI, and classifies images represented in this manner. The system is evaluated on accuracy at classifying individuals showing cognitive impairment to Alzheimer’s Disease. Classification accuracy is 74.2% when individuals with CDR 0.5 are included as impaired in a balanced dataset of 166 images, and 79.3% accuracy when differentiating individuals with CDR at least 1.0 and healthy individuals in a balanced dataset of 54 images. Finally, the system is used to classify MR images according to level of education, with 77.2% accuracy differentiating highly-educated individuals from those for whom no higher education is listed, in a balanced dataset of 178 images.


Graph Based Detection of Optic Disc and Fovea in Retinal Images
http://www.inf.unideb.hu/~hajdua/papers/hajduc_2010h.pdf

Diabetic retinopathy (DR) is the damage to the eye's
retina that occurs with long-term diabetes, which can eventually
lead to blindness. Screening programs for DR are being
introduced, however, an important prerequisite for automation is
the accurate localization of the main anatomical features in the
image, notably the optic disc (OD) and the macula. A series of
interesting algorithms have been proposed in the recent past and
the performance is generally good, but each method has
situations, where it fails. This paper presents a novel framework
for automatic detection of optic disc and macula in retinal fundus
images using a combination of different optic disc and macula
detectors represented by a weighted complete graph. A node
pruning procedure removes the worst vertices of the graph by
satisfying predefined geometric constraints and get best possible
detector outputs to be combined using a weighted average. The
extensive tests have shown that combining the predictions of
multiple detectors is more accurate than any of the individual
detectors making up the ensemble.

Power Watershed: A Unifying Graph-Based Optimization Framework
http://www.computer.org/portal/web/csdl/doi/10.1109/TPAMI.2010.200

In this work, we extend a common framework for graph-based image segmentation that includes the graph cuts, random walker, and shortest path optimization algorithms. Viewing an image as a weighted graph, these algorithms can be expressed by means of a common energy function with differing choices of a parameter q acting as an exponent on the differences between neighboring nodes. Introducing a new parameter p that fixes a power for the edge weights allows us to also include the optimal spanning forest algorithm for watershed in this same framework. We then propose a new family of segmentation algorithms that fixes p to produce an optimal spanning forest but varies the power q beyond the usual watershed algorithm, which we term the power watershed. In particular, when q=2, the power watershed leads to a multilabel, scale and contrast invariant, unique global optimum obtained in practice in quasi-linear time. Placing the watershed algorithm in this energy minimization framework also opens new possibilities for using unary terms in traditional watershed segmentation and using watershed to optimize more general models of use in applications beyond image segmentation.


MEDRank: using graph-based concept ranking to index biomedical texts.
http://www.mendeley.com/research/medrank-using-graphbased-concept-ranking-index-biomedical-texts-1/
As the volume of biomedical text increases exponentially, automatic indexing becomes increasingly important. However, existing approaches do not distinguish central (or core) concepts from concepts that were mentioned in passing. We focus on the problem of indexing MEDLINE records, a process that is currently performed by highly trained humans at the National Library of Medicine (NLM). NLM indexers are assisted by a system called the Medical Text Indexer (MTI) that suggests candidate indexing terms.


A semantic graph-based approach to biomedical summarisation
http://dl.acm.org/citation.cfm?id=2016307
Access to the vast body of research literature that is available in biomedicine and related fields may be improved by automatic summarisation. This paper presents a method for summarising biomedical scientific literature that takes into consideration the characteristics of the domain and the type of documents. Methods: To address the problem of identifying salient sentences in biomedical texts, concepts and relations derived from the Unified Medical Language System (UMLS) are arranged to construct a semantic graph that represents the document. A degree-based clustering algorithm is then used to identify different themes or topics within the text. Different heuristics for sentence selection, intended to generate different types of summaries, are tested. A real document case is drawn up to illustrate how the method works. Results: A large-scale evaluation is performed using the recall-oriented understudy for gisting-evaluation (ROUGE) metrics. The results are compared with those achieved by three well-known summarisers (two research prototypes and a commercial application) and two baselines. Our method significantly outperforms all summarisers and baselines. The best of our heuristics achieves an improvement in performance of almost 7.7 percentage units in the ROUGE-1 score over the LexRank summariser (0.7862 versus 0.7302). A qualitative analysis of the summaries also shows that our method succeeds in identifying sentences that cover the main topic of the document and also considers other secondary or ''satellite'' information that might be relevant to the user. Conclusion: The method proposed is proved to be an efficient approach to biomedical literature summarisation, which confirms that the use of concepts rather than terms can be very useful in automatic summarisation, especially when dealing with highly specialised domains.


グラフ構造を用いた時系列関係の発見(9月15日)(<特集>「アクティブマイニング」及び一般)
http://ci.nii.ac.jp/naid/110002664364
医療データを取り扱った知識発見で,最も難しい部分は,不均質に発生する時系列データの扱い方である.本論文では,そのようなデータを取り扱うための,一階述語論理を使った規則発見手法を提案する.提案手法は,時系列データの表現にグラフを採り入れて,そのデータをある規則にしたがって書き換えることで,規則に使われる述語の候補の生成を行う.評価のために,実際の医療データを用いて実験を行い,手法の有効性を示した.

PuReD-MCL: a graph-based PubMed document clustering methodology
http://bioinformatics.oxfordjournals.org/content/24/17/1935.full


A graph-based representation of Gene Expression profiles in DNA microarrays
http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=4675762
This paper proposes a new and very flexible data model, called gene expression graph (GEG), for genes expression analysis and classification. Three features differentiate GEGs from other available microarray data representation structures: (i) the memory occupation of a GEG is independent of the number of samples used to built it; (ii) a GEG more clearly expresses relationships among expressed and non expressed genes in both healthy and diseased tissues experiments; (iii) GEGs allow to easily implement very efficient classifiers. The paper also presents a simple classifier for sample-based classification to show the flexibility and user-friendliness of the proposed data structure.

GOLEM: an interactive graph-based gene-ontology navigation and analysis tool
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC1618863/
The Gene Ontology has become an extremely useful tool for the analysis of genomic data and structuring of biological knowledge. Several excellent software tools for navigating the gene ontology have been developed. However, no existing system provides an interactively expandable graph-based view of the gene ontology hierarchy. Furthermore, most existing tools are web-based or require an Internet connection, will not load local annotations files, and provide either analysis or visualization functionality, but not both.



http://www.biomedcentral.com/1471-2105/8/S9/S4/