Merlijn Sevenster

Independence-Friendly Logic: A Game-Theoretic Approach

Preface 1. Introduction 2. Game theory 3. First-order logic 4. Independence-friendly (IF) logic 5. Properties of IF logic 6. Expressive power of IF logic 7. Probabilistic IF logic 8. Further topics References Index.

Model-theoretic and Computational Properties of Modal Dependence Logic

We study the basic modal language extended by an operator dep. If pi are propositional atoms, then dep(p1,…,pn−1;pn) expresses, intuitively, that pn only depends on p1,…,pn−1. The resulting language was baptized ‘modal dependence logic’ by Vaananen in his paper Modal Dependence Logic. The current article compares modal dependence logic with basic modal logic in terms of its model-theoretic and computational properties. We show that modal dependence logic is strictly more expressive than modal logic, but that under special conditions modal dependence logic can be translated into basic modal logic.We show that the complexity of modal dependence logic is NEXP-complete.

Generating links to background knowledge: a case study using narrative radiology reports

Automatically annotating texts with background information has recently received much attention. We conduct a case study in automatically generating links from narrative radiology reports to Wikipedia. Such links help users understand the medical terminology and thereby increase the value of the reports. Direct applications of existing automatic link generation systems trained on Wikipedia to our radiology data do not yield satisfactory results. Our analysis reveals that medical phrases are often syntactically regular but semantically complicated, e.g., containing multiple concepts or concepts with multiple modifiers. The latter property is the main reason for the failure of existing systems. Based on this observation, we propose an automatic link generation approach that takes into account these properties. We use a sequential labeling approach with syntactic features for anchor text identification in order to exploit syntactic regularities in medical terminology. We combine this with a sub-anchor based approach to target finding, which is aimed at coping with the complex semantic structure of medical phrases. Empirical results show that the proposed system effectively improves the performance over existing systems.

Automatically Correlating Clinical Findings and Body Locations in Radiology Reports Using MedLEE

In this paper, we describe and evaluate a system that extracts clinical findings and body locations from radiology reports and correlates them. The system uses Medical Language Extraction and Encoding System (MedLEE) to map the reports’ free text to structured semantic representations of their content. A lightweight reasoning engine extracts the clinical findings and body locations from MedLEE’s semantic representation and correlates them. Our study is illustrative for research in which existing natural language processing software is embedded in a larger system. We manually created a standard reference based on a corpus of neuro and breast radiology reports. The standard reference was used to evaluate the precision and recall of the proposed system and its modules. Our results indicate that the precision of our system is considerably better than its recall (82.32–91.37% vs. 35.67–45.91%). We conducted an error analysis and discuss here the practical usability of the system given its recall and precision performance.

Equilibrium semantics of languages of imperfect information

Abstract In this paper, we introduce a new approach to independent quantifiers, as originally introduced in Informational independence as a semantic phenomenon by Hintikka and Sandu (1989) [9] under the header of independence-friendly (IF) languages. Unlike other approaches, which rely heavily on compositional methods, we shall analyze independent quantifiers via equilibriums in strategic games. In this approach, coined equilibrium semantics, the value of an IF sentence on a particular structure is determined by the expected utility of the existential player in any of the game’s equilibriums. This approach was suggested in Henkin quantifiers and complete problems by Blass and Gurevich (1986) [2] but has not been taken up before. We prove that each rational number can be realized by an IF sentence. We also give a lower and upper bound on the expressive power of IF logic under equilibrium semantics.

Improved Efficiency in Clinical Workflow of Reporting Measured Oncology Lesions Via PACS-Integrated Lesion Tracking Tool

OBJECTIVE. Imaging provides evidence for the response to oncology treatment by the serial measurement of reference lesions. Unfortunately, the identification, comparison, measurement, and documentation of several reference lesions can be an inefficient process. We tested the hypothesis that optimized workflow orchestration and tight integration of a lesion tracking tool into the PACS and speech recognition system can result in improvements in oncologic lesion measurement efficiency. SUBJECTS AND METHODS. A lesion management tool tightly integrated into the PACS workflow was developed. We evaluated the effect of the use of the tool on measurement reporting time by means of a prospective time-motion study on 86 body CT examinations with 241 measureable oncologic lesions with four radiologists. RESULTS. Aggregated measurement reporting time per lesion was 11.64 seconds in standard workflow, 16.67 seconds if readers had to register measurements de novo, and 6.36 seconds for each subsequent follow-up study. Differences were statistically significant (p < 0.05) for each reader, except for one difference for one reader. CONCLUSION. Measurement reporting time can be reduced by using a PACS workflow-integrated lesion management tool, especially for patients with multiple follow-up examinations, reversing the onetime efficiency penalty at baseline registration.

Sentence-based classification of free-text breast cancer radiology reports

Radiology reports generally consist of narrative text. It has been envisioned that structured medical content can be leveraged to clinical applications. Text-mining techniques can be utilized to realize this vision. We created a pipeline for automatic sentence classification of narrative breast cancer radiology reports. A corpus of 353 reports and 8166 sentences was annotated with seven sentence classes related to laterality, modality and recommendation. Sentences have been represented by four types of feature sets, characterizing various levels of linguistic complexity and domain knowledge. We conducted an evaluation to find the optimal combination of features and the optimal classification paradigm. The classification accuracy ranges between 92 and 98% for the different classes.

Bridging the Text-Image Gap: a Decision Support Tool for Real-Time PACS Browsing

In this paper, we introduce an ontology-based technology that bridges the gap between MR images on the one hand and knowledge sources on the other hand. The proposed technology allows the user to express interest in a body region by selecting this region on the MR image he or she is viewing with a mouse device. The proposed technology infers the intended body structure from the manual selection and searches the external knowledge source for pertinent information. This technology can be used to bridge the gap between image data in the clinical workflow and (external) knowledge sources that help to assess the case with increased certainty, accuracy, and efficiency. We evaluate an instance of the proposed technology in the neurodomain by means of a user study in which three neuroradiologists participated. The user study shows that the technology has high recall (>95%) when it comes to inferring the intended brain region from the participant’s manual selection. We are confident that this helps to increase the experience of browsing external knowledge sources.

Classifying Measurements in Dictated, Free-Text Radiology Reports

Radiological measurements (e.g., ‘3.2 x 1.4 cm’) are the predominant type of quantitative data in free-text radiology reports. We report on the development and evaluation of a classifier that labels measurement descriptors with the exam they refer to: current and/or prior exam. Our classifier aggregates regular expressions as binary features in a maximum entropy model. It has average F-measure 0.942 on 2,000 annotated instances; the rule-based baseline algorithm has F-measure 0.795. Potential applications and routes for future are discussed.

Identifying Breast Cancer Concepts in SNOMED-CT Using Large Text Corpus

Large medical ontologies can be of great help in building a specialized clinical information system. First step in their use is to identify the subset of concepts which are relevant to the specialty. In this paper we present a method to automatically identify the breast cancer concepts from the SNOMED-CT ontology using large text corpus as source of knowledge. In addition to finding them, the concepts are also assigned relevance values.