Semantic search and inferencing in health informatics

Consider a person searching electronic health records, a search for the term ‘cracked skull’ should return documents that contain the term ‘cranium fracture’. A information retrieval systems is required that matches concepts, not just keywords. Further more, determining relevance of a query to a document requires inference – its not simply matching concepts. For example a document containing ‘dialysis machine’ should align with a query for ‘kidney disease’. Collectively we describe this problem as the ‘semantic gap’ – the difference between the raw medical data and the way a human interprets it. This paper presents an approach to semantic search of health records by combining two previous approaches: an ontological approach using the SNOMED CT medical ontology; and a distributional approach using semantic space vector space models. Our approach will be applied to a specific problem in health informatics: the matching of electronic patient records to clinical trials.

Rule-based approach for identifying assertions in clinical free-text data

A rule-based approach for classifying previously identified medical concepts in the clinical free text into an assertion category is presented. There are six different categories of assertions for the task: Present, Absent, Possible, Conditional, Hypothetical and Not associated with the patient. The assertion classification algorithms were largely based on extending the popular NegEx and Context algorithms. In addition, a health based clinical terminology called SNOMED CT and other publicly available dictionaries were used to classify assertions, which did not fit the NegEx/Context model. The data for this task includes discharge summaries from Partners HealthCare and from Beth Israel Deaconess Medical Centre, as well as discharge summaries and progress notes from University of Pittsburgh Medical Centre. The set consists of 349 discharge reports, each with pairs of ground truth concept and assertion files for system development, and 477 reports for evaluation. The system’s performance on the evaluation data set was 0.83, 0.83 and 0.83 for recall, precision and F1-measure, respectively. Although the rule-based system shows promise, further improvements can be made by incorporating machine learning approaches.

Towards semantic search and inference in electronic medical records : an approach using concept-based information retrieval

Background This paper presents a novel approach to searching electronic medical records that is based on concept matching rather than keyword matching. Aim The concept-based approach is intended to overcome specific challenges we identified in searching medical records. Method Queries and documents were transformed from their term-based originals into medical concepts as defined by the SNOMED-CT ontology. Results Evaluation on a real-world collection of medical records showed our concept-based approach outperformed a keyword baseline by 25% in Mean Average Precision. Conclusion The concept-based approach provides a framework for further development of inference based search systems for dealing with medical data.

AEHRC & QUT at TREC 2011 Medical Track : a concept-based information retrieval approach

The Australian e-Health Research Centre and Queensland University of Technology recently participated in the TREC 2011 Medical Records Track. This paper reports on our methods, results and experience using a concept-based information retrieval approach. Our concept-based approach is intended to overcome specific challenges we identify in searching medical records. Queries and documents are transformed from their term-based originals into medical concepts as de ned by the SNOMED-CT ontology. Results show our concept-based approach performed above the median in all three performance metrics: bref (+12%), R-prec (+18%) and Prec@10 (+6%).

Exploiting medical hierarchies for concept-based information retrieval

Search technologies are critical to enable clinical sta to rapidly and e ectively access patient information contained in free-text medical records. Medical search is challenging as terms in the query are often general but those in rel- evant documents are very speci c, leading to granularity mismatch. In this paper we propose to tackle granularity mismatch by exploiting subsumption relationships de ned in formal medical domain knowledge resources. In symbolic reasoning, a subsumption (or `is-a') relationship is a parent-child rela- tionship where one concept is a subset of another concept. Subsumed concepts are included in the retrieval function. In addition, we investigate a number of initial methods for combining weights of query concepts and those of subsumed concepts. Subsumption relationships were found to provide strong indication of relevant information; their inclusion in retrieval functions yields performance improvements. This result motivates the development of formal models of rela- tionships between medical concepts for retrieval purposes.

Graph-based concept weighting for medical information retrieval

This paper presents a graph-based method to weight medical concepts in documents for the purposes of information retrieval. Medical concepts are extracted from free-text documents using a state-of-the-art technique that maps n-grams to concepts from the SNOMED CT medical ontology. In our graph-based concept representation, concepts are vertices in a graph built from a document, edges represent associations between concepts. This representation naturally captures dependencies between concepts, an important requirement for interpreting medical text, and a feature lacking in bag-of-words representations. We apply existing graph-based term weighting methods to weight medical concepts. Using concepts rather than terms addresses vocabulary mismatch as well as encapsulates terms belonging to a single medical entity into a single concept. In addition, we further extend previous graph-based approaches by injecting domain knowledge that estimates the importance of a concept within the global medical domain. Retrieval experiments on the TREC Medical Records collection show our method outperforms both term and concept baselines. More generally, this work provides a means of integrating background knowledge contained in medical ontologies into data-driven information retrieval approaches.

Identify disorders in health records using Conditional Random Fields and Metamap: AEHRC at ShARe/CLEF 2013 eHealth Evaluation Lab Task 1

The Australian e-Health Research Centre (AEHRC) recently participated in the ShARe/CLEF eHealth Evaluation Lab Task 1. The goal of this task is to individuate mentions of disorders in free-text electronic health records and map disorders to SNOMED CT concepts in the UMLS metathesaurus. This paper details our participation to this ShARe/CLEF task. Our approaches are based on using the clinical natural language processing tool Metamap and Conditional Random Fields (CRF) to individuate mentions of disorders and then to map those to SNOMED CT concepts. Empirical results obtained on the 2013 ShARe/CLEF task highlight that our instance of Metamap (after ltering irrelevant semantic types), although achieving a high level of precision, is only able to identify a small amount of disorders (about 21% to 28%) from free-text health records. On the other hand, the addition of the CRF models allows for a much higher recall (57% to 79%) of disorders from free-text, without sensible detriment in precision. When evaluating the accuracy of the mapping of disorders to SNOMED CT concepts in the UMLS, we observe that the mapping obtained by our ltered instance of Metamap delivers state-of-the-art e ectiveness if only spans individuated by our system are considered (`relaxed' accuracy).

Classification of pathology reports for cancer registry notifications

Objective: To develop a system for the automatic classification of pathology reports for Cancer Registry notifications. Method: A two pass approach is proposed to classify whether pathology reports are cancer notifiable or not. The first pass queries pathology HL7 messages for known report types that are received by the Queensland Cancer Registry (QCR), while the second pass aims to analyse the free text reports and identify those that are cancer notifiable. Cancer Registry business rules, natural language processing and symbolic reasoning using the SNOMED CT ontology were adopted in the system. Results: The system was developed on a corpus of 500 histology and cytology reports (with 47% notifiable reports) and evaluated on an independent set of 479 reports (with 52% notifiable reports). Results show that the system can reliably classify cancer notifiable reports with a sensitivity, specificity, and positive predicted value (PPV) of 0.99, 0.95, and 0.95, respectively for the development set, and 0.98, 0.96, and 0.96 for the evaluation set. High sensitivity can be achieved at a slight expense in specificity and PPV. Conclusion: The system demonstrates how medical free-text processing enables the classification of cancer notifiable pathology reports with high reliability for potential use by Cancer Registries and pathology laboratories.

Towards a smart cancer registry

Aims Pathology notification for a Cancer Registry is regarded as the most valid information for the confirmation of a diagnosis of cancer. In view of the importance of pathology data, an automatic medical text analysis system (Medtex) is being developed to perform electronic Cancer Registry data extraction and coding of important clinical information embedded within pathology reports. Methods The system automatically scans HL7 messages received from a Queensland pathology information system and analyses the reports for terms and concepts relevant to a cancer notification. A multitude of data items for cancer notification such as primary site, histological type, stage, and other synoptic data are classified by the system. The underlying extraction and classification technology is based on SNOMED CT1 2. The Queensland Cancer Registry business rules3 and International Classification of Diseases – Oncology – Version 34 have been incorporated. Results The cancer notification services show that the classification of notifiable reports can be achieved with sensitivities of 98% and specificities of 96%5, while the coding of cancer notification items such as basis of diagnosis, histological type and grade, primary site and laterality can be extracted with an overall accuracy of 80%6. In the case of lung cancer staging, the automated stages produced were accurate enough for the purposes of population level research and indicative staging prior to multi-disciplinary team meetings2 7. Medtex also allows for detailed tumour stream synoptic reporting8. Conclusions Medtex demonstrates how medical free-text processing could enable the automation of some Cancer Registry processes. Over 70% of Cancer Registry coding resources are devoted to information acquisition. The development of a clinical decision support system to unlock information from medical free-text could significantly reduce costs arising from duplicated processes and enable improved decision support, enhancing efficiency and timeliness of cancer information for Cancer Registries.

Classification of cancer-related death certificates using machine learning

Background Cancer monitoring and prevention relies on the critical aspect of timely notification of cancer cases. However, the abstraction and classification of cancer from the free-text of pathology reports and other relevant documents, such as death certificates, exist as complex and time-consuming activities. Aims In this paper, approaches for the automatic detection of notifiable cancer cases as the cause of death from free-text death certificates supplied to Cancer Registries are investigated. Method A number of machine learning classifiers were studied. Features were extracted using natural language techniques and the Medtex toolkit. The numerous features encompassed stemmed words, bi-grams, and concepts from the SNOMED CT medical terminology. The baseline consisted of a keyword spotter using keywords extracted from the long description of ICD-10 cancer related codes. Results Death certificates with notifiable cancer listed as the cause of death can be effectively identified with the methods studied in this paper. A Support Vector Machine (SVM) classifier achieved best performance with an overall F-measure of 0.9866 when evaluated on a set of 5,000 free-text death certificates using the token stem feature set. The SNOMED CT concept plus token stem feature set reached the lowest variance (0.0032) and false negative rate (0.0297) while achieving an F-measure of 0.9864. The SVM classifier accounts for the first 18 of the top 40 evaluated runs, and entails the most robust classifier with a variance of 0.001141, half the variance of the other classifiers. Conclusion The selection of features significantly produced the most influences on the performance of the classifiers, although the type of classifier employed also affects performance. In contrast, the feature weighting schema created a negligible effect on performance. Specifically, it is found that stemmed tokens with or without SNOMED CT concepts create the most effective feature when combined with an SVM classifier.

A method for matching patients to advanced prostate cancer clinical trials

Objective: To illustrate a new method for simplifying patient recruitment for advanced prostate cancer clinical trials using natural language processing techniques. Background: The identification of eligible participants for clinical trials is a critical factor to increase patient recruitment rates and an important issue for discovery of new treatment interventions. The current practice of identifying eligible participants is highly constrained due to manual processing of disparate sources of unstructured patient data. Informatics-based approaches can simplify the complex task of evaluating patient’s eligibility for clinical trials. We show that an ontology-based approach can address the challenge of matching patients to suitable clinical trials. Methods: The free-text descriptions of clinical trial criteria as well as patient data were analysed. A set of common inclusion and exclusion criteria was identified through consultations with expert clinical trial coordinators. A research prototype was developed using Unstructured Information Management Architecture (UIMA) that identified SNOMED CT concepts in the patient data and clinical trial description. The SNOMED CT concepts model the standard clinical terminology that can be used to represent and evaluate patient’s inclusion/exclusion criteria for the clinical trial. Results: Our experimental research prototype describes a semi-automated method for filtering patient records using common clinical trial criteria. Our method simplified the patient recruitment process. The discussion with clinical trial coordinators showed that the efficiency in patient recruitment process measured in terms of information processing time could be improved by 25%. Conclusion: An UIMA-based approach can resolve complexities in patient recruitment for advanced prostate cancer clinical trials.

Automatic ICD-10 classification of cancers from free-text death certificates

Objective Death certificates provide an invaluable source for cancer mortality statistics; however, this value can only be realised if accurate, quantitative data can be extracted from certificates – an aim hampered by both the volume and variable nature of certificates written in natural language. This paper proposes an automatic classification system for identifying cancer related causes of death from death certificates. Methods Detailed features, including terms, n-grams and SNOMED CT concepts were extracted from a collection of 447,336 death certificates. These features were used to train Support Vector Machine classifiers (one classifier for each cancer type). The classifiers were deployed in a cascaded architecture: the first level identified the presence of cancer (i.e., binary cancer/nocancer) and the second level identified the type of cancer (according to the ICD-10 classification system). A held-out test set was used to evaluate the effectiveness of the classifiers according to precision, recall and F-measure. In addition, detailed feature analysis was performed to reveal the characteristics of a successful cancer classification model. Results The system was highly effective at identifying cancer as the underlying cause of death (F-measure 0.94). The system was also effective at determining the type of cancer for common cancers (F-measure 0.7). Rare cancers, for which there was little training data, were difficult to classify accurately (F-measure 0.12). Factors influencing performance were the amount of training data and certain ambiguous cancers (e.g., those in the stomach region). The feature analysis revealed a combination of features were important for cancer type classification, with SNOMED CT concept and oncology specific morphology features proving the most valuable. Conclusion The system proposed in this study provides automatic identification and characterisation of cancers from large collections of free-text death certificates. This allows organisations such as Cancer Registries to monitor and report on cancer mortality in a timely and accurate manner. In addition, the methods and findings are generally applicable beyond cancer classification and to other sources of medical text besides death certificates.

Phylogeography and non-invasive landscape genetics of the European pine marten ("martes martes" L. 1758) : insights into ancient and contemporary processes shaping genetic variation

283 p. : graf., map.