Clinician-driven automated classification of limb fractures from free-text radiology reports

The aim of this research is to report initial experimental results and evaluation of a clinician-driven automated method that can address the issue of misdiagnosis from unstructured radiology reports. Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to disperse information resources and vast amounts of manual processing of unstructured information, a point-of-care accurate diagnosis is often difficult. A rule-based method that considers the occurrence of clinician specified keywords related to radiological findings was developed to identify limb abnormalities, such as fractures. A dataset containing 99 narrative reports of radiological findings was sourced from a tertiary hospital. The rule-based method achieved an F-measure of 0.80 and an accuracy of 0.80. While our method achieves promising performance, a number of avenues for improvement were identified using advanced natural language processing (NLP) techniques.

Is intent-aware expected reciprocal rank sufficient to evaluate diversity?

In this paper we define two models of users that require diversity in search results; these models are theoretically grounded in the notion of intrinsic and extrinsic diversity. We then examine Intent-Aware Expected Reciprocal Rank (ERR-IA), one of the official measures used to assess diversity in TREC 2011-12, with respect to the proposed user models. By analyzing ranking preferences as expressed by the user models and those estimated by ERR-IA, we investigate whether ERR-IA assesses document rankings according to the requirements of the diversity retrieval task expressed by the two models. Empirical results demonstrate that ERR-IA neglects query-intents coverage by attributing excessive importance to redundant relevant documents. ERR-IA behavior is contrary to the user models that require measures to first assess diversity through the coverage of intents, and then assess the redundancy of relevant intents. Furthermore, diversity should be considered separately from document relevance and the documents positions in the ranking.

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.

Creation of a new evaluation benchmark for information retrieval targeting patient information needs

Searching for health advice on the web is becoming increasingly common. Because of the great importance of this activity for patients and clinicians and the effect that incorrect information may have on health outcomes, it is critical to present relevant and valuable information to a searcher. Previous evaluation campaigns on health information retrieval (IR) have provided benchmarks that have been widely used to improve health IR and record these improvements. However, in general these benchmarks have targeted the specialised information needs of physicians and other healthcare workers. In this paper, we describe the development of a new collection for evaluation of effectiveness in IR seeking to satisfy the health information needs of patients. Our methodology features a novel way to create statements of patients’ information needs using realistic short queries associated with patient discharge summaries, which provide details of patient disorders. We adopt a scenario where the patient then creates a query to seek information relating to these disorders. Thus, discharge summaries provide us with a means to create contextually driven search statements, since they may include details on the stage of the disease, family history etc. The collection will be used for the first time as part of the ShARe/-CLEF 2013 eHealth Evaluation Lab, which focuses on natural language processing and IR for clinical care.

Combining word semantics within complex Hilbert space for information retrieval

Complex numbers are a fundamental aspect of the mathematical formalism of quantum physics. Quantum-like models developed outside physics often overlooked the role of complex numbers. Specifically, previous models in Information Retrieval (IR) ignored complex numbers. We argue that to advance the use of quantum models of IR, one has to lift the constraint of real-valued representations of the information space, and package more information within the representation by means of complex numbers. As a first attempt, we propose a complex-valued representation for IR, which explicitly uses complex valued Hilbert spaces, and thus where terms, documents and queries are represented as complex-valued vectors. The proposal consists of integrating distributional semantics evidence within the real component of a term vector; whereas, ontological information is encoded in the imaginary component. Our proposal has the merit of lifting the role of complex numbers from a computational byproduct of the model to the very mathematical texture that unifies different levels of semantic information. An empirical instantiation of our proposal is tested in the TREC Medical Record task of retrieving cohorts for clinical studies.

Overview of the ShARe/CLEF eHealth Evaluation Lab 2013

Discharge summaries and other free-text reports in healthcare transfer information between working shifts and geographic locations. Patients are likely to have difficulties in understanding their content, because of their medical jargon, non-standard abbreviations,and ward-specific idioms. This paper reports on an evaluation lab with an aim to support the continuum of care by developing methods and resources that make clinical reports in English easier to understand for patients, and which helps them in finding information related to their condition.

Towards a visually enhanced medical search engine

This paper presents the prototype of an information retrieval system for medical records that utilises visualisation techniques, namely word clouds and timelines. The system simplifies and assists information seeking tasks within the medical domain. Access to patient medical information can be time consuming as it requires practitioners to review a large number of electronic medical records to find relevant information. Presenting a summary of the content of a medical document by means of a word cloud may permit information seekers to decide upon the relevance of a document to their information need in a simple and time effective manner. We extend this intuition, by mapping word clouds of electronic medical records onto a timeline, to provide temporal information to the user. This allows exploring word clouds in the context of a patient’s medical history. To enhance the presentation of word clouds, we also provide the means for calculating aggregations and differences between patient’s word clouds.

Automatic classification of free-text radiology reports to identify limb fractures using machine learning and the SNOMED CT ontology

Objective To develop and evaluate machine learning techniques that identify limb fractures and other abnormalities (e.g. dislocations) from radiology reports. Materials and Methods 99 free-text reports of limb radiology examinations were acquired from an Australian public hospital. Two clinicians were employed to identify fractures and abnormalities from the reports; a third senior clinician resolved disagreements. These assessors found that, of the 99 reports, 48 referred to fractures or abnormalities of limb structures. Automated methods were then used to extract features from these reports that could be useful for their automatic classification. The Naive Bayes classification algorithm and two implementations of the support vector machine algorithm were formally evaluated using cross-fold validation over the 99 reports. Result Results show that the Naive Bayes classifier accurately identifies fractures and other abnormalities from the radiology reports. These results were achieved when extracting stemmed token bigram and negation features, as well as using these features in combination with SNOMED CT concepts related to abnormalities and disorders. The latter feature has not been used in previous works that attempted classifying free-text radiology reports. Discussion Automated classification methods have proven effective at identifying fractures and other abnormalities from radiology reports (F-Measure up to 92.31%). Key to the success of these techniques are features such as stemmed token bigrams, negations, and SNOMED CT concepts associated with morphologic abnormalities and disorders. Conclusion This investigation shows early promising results and future work will further validate and strengthen the proposed approaches.

ShARe/CLEF eHealth Evaluation Lab 2013, Task 3: Information retrieval to address patients' questions when reading clinical reports

This paper presents the results of task 3 of the ShARe/CLEF eHealth Evaluation Lab 2013. This evaluation lab focuses on improving access to medical information on the web. The task objective was to investigate the effect of using additional information such as the discharge summaries and external resources such as medical ontologies on the IR effectiveness. The participants were allowed to submit up to seven runs, one mandatory run using no additional information or external resources, and three each using or not using discharge summaries.

Producing while consuming: Social interaction around photos shared within private group

User-generated content plays a pivotal role in the current social media. The main focus, however, has been on the explicitly generated user content such as photos, videos and status updates on different social networking sites. In this paper, we explore the potential of implicitly generated user content, based on users’ online consumption behaviors. It is technically feasible to record users’ consumption behaviors on mobile devices and share that with relevant people. Mobile devices with such capabilities could enrich social interactions around the consumed content, but it may also threaten users’ privacy. To understand the potentials of this design direction we created and evaluated a low-fidelity prototype intended for photo sharing within private groups. Our prototype incorporates two design concepts, namely, FingerPrint and MoodPhotos that leverage users’ consumption history and emotional responses. In this paper, we report user values and user acceptance of this prototype from three participatory design workshops.

Practices surrounding children's photos in homes

New parents cherish photos of their children. In their homes one can observe a varied set of arrangements of their young ones' photos. We studied eight families with young children to learn about their practices related to photos. We provide preliminary results from the field study and elaborate on three interesting themes that came out very strongly from our data: physical platforms; family dynamics and values; and creative uses of photos. These themes provide an insight into families' perceived values for photo curating, displaying and experiencing them over a longer period. We provide future directions for supporting practices surrounding children's photos.

Vibrational spectroscopic study of the sulphate mineral glaucocerinite (Zn,Cu)10Al6(SO4)3(OH)32⋅18H2O – a natural layered double hydroxide

We have studied the molecular structure of the mineral glaucocerinite (Zn,Cu)5Al3(SO4)1.5(OH)16�9(H2O) using a combination of Raman and infrared spectroscopy. The mineral is one of the hydrotalcite supergroup of natural layered double hydroxides. The Raman spectrum is characterised by an intense Raman band at 982 cm�1 with a low intensity band at 1083 cm�1. These bands are attributed to the sulphate symmetric and antisymmetric stretching mode. The infrared spectrum is quite broad with a peak at 1020 cm�1. A series of Raman bands at 546, 584, 602, 625 and 651 cm�1 are assigned to the m4 (SO4)2� bending modes. The observation of multiple bands provides evidence for the reduction in symmetry of the sulphate anion from Td to C2v or even lower symmetry. The Raman band at 762 cm�1 is attributed to a hydroxyl deformation mode associated with AlOH units. Vibrational spectroscopy enables aspects of the molecular structure of glaucocerinite to be determined.

De-Identification of health records using Anonym: Effectiveness and robustness across datasets

Objective Evaluate the effectiveness and robustness of Anonym, a tool for de-identifying free-text health records based on conditional random fields classifiers informed by linguistic and lexical features, as well as features extracted by pattern matching techniques. De-identification of personal health information in electronic health records is essential for the sharing and secondary usage of clinical data. De-identification tools that adapt to different sources of clinical data are attractive as they would require minimal intervention to guarantee high effectiveness. Methods and Materials The effectiveness and robustness of Anonym are evaluated across multiple datasets, including the widely adopted Integrating Biology and the Bedside (i2b2) dataset, used for evaluation in a de-identification challenge. The datasets used here vary in type of health records, source of data, and their quality, with one of the datasets containing optical character recognition errors. Results Anonym identifies and removes up to 96.6% of personal health identifiers (recall) with a precision of up to 98.2% on the i2b2 dataset, outperforming the best system proposed in the i2b2 challenge. The effectiveness of Anonym across datasets is found to depend on the amount of information available for training. Conclusion Findings show that Anonym compares to the best approach from the 2006 i2b2 shared task. It is easy to retrain Anonym with new datasets; if retrained, the system is robust to variations of training size, data type and quality in presence of sufficient training data.

Crowdsourcing interactions : using crowdsourcing for evaluating interactive information retrieval systems

In the field of information retrieval (IR), researchers and practitioners are often faced with a demand for valid approaches to evaluate the performance of retrieval systems. The Cranfield experiment paradigm has been dominant for the in-vitro evaluation of IR systems. Alternative to this paradigm, laboratory-based user studies have been widely used to evaluate interactive information retrieval (IIR) systems, and at the same time investigate users’ information searching behaviours. Major drawbacks of laboratory-based user studies for evaluating IIR systems include the high monetary and temporal costs involved in setting up and running those experiments, the lack of heterogeneity amongst the user population and the limited scale of the experiments, which usually involve a relatively restricted set of users. In this paper, we propose an alternative experimental methodology to laboratory-based user studies. Our novel experimental methodology uses a crowdsourcing platform as a means of engaging study participants. Through crowdsourcing, our experimental methodology can capture user interactions and searching behaviours at a lower cost, with more data, and within a shorter period than traditional laboratory-based user studies, and therefore can be used to assess the performances of IIR systems. In this article, we show the characteristic differences of our approach with respect to traditional IIR experimental and evaluation procedures. We also perform a use case study comparing crowdsourcing-based evaluation with laboratory-based evaluation of IIR systems, which can serve as a tutorial for setting up crowdsourcing-based IIR evaluations.