Search

Background With a motivation of quality assurance, machine learning techniques were trained to classify Norwegian radiology reports of paediatric CT examinations according to their description of abnormal findings. Methods 13.506 reports from CT-scans of children, 1000 reports from CT scan of adults and 1000 reports from X-ray examination of adults were classified as positive or negative by a radiologist, according to the presence of abnormal findings. Inter-rater reliability was evaluated by comparison with a clinician’s classifications of 500 reports. Test–retest reliability of the radiologist was performed on the same 500 reports. A convolutional neural network model (CNN), a bidirectional recurrent neural network model (bi-LSTM) and a support vector machine model (SVM) were trained on a random selection of the children’s data set. Models were evaluated on the remaining CT-children reports and the adult data sets. Results Test–retest reliability: Cohen’s Kappa = 0.86 and F1 = 0.919. Inter-rater reliability: Kappa = 0.80 and F1 = 0.885. Model performances on the Children-CT data were as follows. CNN: (AUC = 0.981, F1 = 0.930), bi-LSTM: (AUC = 0.978, F1 = 0.927), SVM: (AUC = 0.975, F1 = 0.912). On the adult data sets, the models had AUC around 0.95 and F1 around 0.91. Conclusions The models performed close to perfectly on its defined domain, and also performed convincingly on reports pertaining to a different patient group and a different modality. The models were deemed suitable for classifying radiology reports for future quality assurance purposes, where the fraction of the examinations with abnormal findings for different sub-groups of patients is a parameter of interest.

Background The limited availability of clinical texts for Natural Language Processing purposes is hindering the progress of the field. This article investigates the use of synthetic data for the annotation and automated extraction of family history information from Norwegian clinical text. We make use of incrementally developed synthetic clinical text describing patients’ family history relating to cases of cardiac disease and present a general methodology which integrates the synthetically produced clinical statements and annotation guideline development. The resulting synthetic corpus contains 477 sentences and 6030 tokens. In this work we experimentally assess the validity and applicability of the annotated synthetic corpus using machine learning techniques and furthermore evaluate the system trained on synthetic text on a corpus of real clinical text, consisting of de-identified records for patients with genetic heart disease. Results For entity recognition, an SVM trained on synthetic data had class weighted precision, recall and F1-scores of 0.83, 0.81 and 0.82, respectively. For relation extraction precision, recall and F1-scores were 0.74, 0.75 and 0.74. Conclusions A system for extraction of family history information developed on synthetic data generalizes well to real, clinical notes with a small loss of accuracy. The methodology outlined in this paper may be useful in other situations where limited availability of clinical text hinders NLP tasks. Both the annotation guidelines and the annotated synthetic corpus are made freely available and as such constitutes the first publicly available resource of Norwegian clinical text.

Infections caused by central venous catheter (CVC) use is a serious and under-reported problem in healthcare. The CVC is almost ubiquitous in critical care because it enables fast circulatory monitoring and central ad- ministration of medication and nutrition. However, the CVC exposes the patient to a risk of blood-stream infections (BSI). Explicit documentation of normal CVC usage and exposure is sparse and indirect in the health record. For a clinician, CVC presence is simple to infer from record statements about procedures, plans and results related to CVC. In order to capture evidence about CVC-related risk of infections and complications, it is important to develop computerized tools that can estimate individual patient days of CVC exposure retrospectively for large cohorts of patients. Towards that objec- tive, we have developed methods for learning classifiers for statements about CVC-related events occurring in the textual health record. This includes developing and testing an annotation ontology of events and indicators, an- notation guidelines, a gold standard of annotated clinical records selected from a corpus of complete health records for more 800 episodes of care and collecting alternate health register evidence for validation purposes. This paper describes the available data and gold standard, feature selection ap- proaches and our experiments with different classification algorithms. We find that even with limited data it is possible to build reasonably accurate sentence classifiers for the most important events. We also find that mak- ing use of document meta information helps improve classification quality by providing additional context to a sentence. Finally, we outline some strate- gies on using our results for future analysis and reasoning about CVC usage intervals and CVC exposure over individual patient trajectories.

Infections caused by central venous catheter (CVC) use is a serious and under-reported problem. In our research we explore methods of automatically detecting CVC use from clinical documentation for quality improvement and surveillance purposes. This paper describes our initial research on this topic, where we build CVC event classifiers based on an episodes of care corpus and an annotated gold standard. After describing the available data and gold standard we then experiment with different classification algorithms and feature selection approaches. We find that even with limited data it is possible to build reasonably accurate sentence classifiers, at least for the events that are most important to us. We also find that making use of document meta information may help improve classification quality by providing additional context to a sentence. Finally, we outline some strategies on using these preliminary clinical document-centric results as a tool for future analysis and elicitation of CVC usage intervals over full patient histories. © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

In this article, we describe the development of annotation guidelines for family history information in Norwegian clinical text. We make use of incrementally developed synthetic clinical text describing patients’ family history relating to cases of cardiac disease and present a general methodology which integrates the synthetically produced clinical statements and guideline development. We analyze inter-annotator agreement based on the developed guidelines and present results from experiments aimed at evaluating the validity and applicability of the annotated corpus using machine learning techniques. The resulting annotated corpus contains 477 sentences and 6030 tokens. Both the annotation guidelines and the annotated corpus are made freely available and as such constitutes the first publicly available resource of Norwegian clinical text.

Background To improve consistency and streamline development and publication of clinical guidelines (GL), there is a need for appropriate software support. We have found few specific tools for the actual authoring and maintaining of GLs, and correspondingly few analyses or reviews of GL development tool functionality. In order to assist GL developers in selecting and evaluating tools, this study tries to address the perceived gap by pursuing four goals: 1) identifying available tools, 2) reviewing a representative group of tools and their supported functionalities, 3) uncovering themes of features that the studied tools support, and 4) compare the selected tools with respect to the themes. Methods We conducted a literature search using PubMed and Google Scholar in order to find GL development tools (GDT). We also explored tools and Content Management Systems (CMS) used in representative organisations and international communities that develop and maintain GLs. By reading a selected representative group of five GL tool manuals, exploring tools hands-on, we uncovered 8 themes of features. All found tools were compared according to these themes in order to identify the level of functionality they offer to support the GL development and publishing process. In order to limit the scope, tools for designing computer-interpretable/executable GL are excluded. Results After finding 1552 published papers, contacting 7 organizations and international communities, we identified a total of 19 unique tools, of which 5 tools were selected as representative in this paper. We uncovered a total of 8 themes of features according to the identified functionalities that each tool provides. Four features were common among tools: Collaborative authoring process support, user access control, GL repository management, electronic publishing. We found that the GRADE methodology was supported by three of the reviewed tools, while only two tools support annotating GL with MeSH terms. We also identified that monitoring progress, reference management, Managing versions (version control), and Change control (tracking) were often the missing features. Conclusion The results can promote sector discussion and eventual agreement on important tool functionality. It may aid tool and GL developers towards more efficient, and effective, GL authoring. © The Author(s). 2017. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, andreproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link tothe Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver(http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.

We have developed a tool for annotation of electronic health record (ERR) data. Currently we are in the process of manually annotating a corpus of Norwegian general practitioners' ERRs with mainly linguistic information. The purpose of this project is to attain a linguistically annotated corpus of patient histories from general practice. This corpus will be put to future use in medicallanguage processing and information extraction applications. The paper outlines some of our practical experiences from developing such a corpus and, in particular, the effects of semi-automated annotation. We have also dene some preliminary experiments with part-of-speech tagging based on our corpus. The results indicate that relevant training data from the clinical domain gives better results for the tagging task in this domain than training the tagger on a corpus from a more general domain. We are planning to expand the corpus annotations with medical information at a later stage.

Access control is a key feature of healthcare systems. Up until recently most healthcare information systems have been local to a healthcare facility and accessible only to clinicians. Currently there is a move towards making health information more accessible to patients. One example is the Personally Controlled Health Record (PCHR) where the patient is in charge of deciding who gets access to the information. In the PCHR the patient is the administrator of access control. While it certainly is possible to create roles representing people most patients would want to share with, like primary physician, it is also likely, and desirable, to afford the patients a high level of control and freedom to be able to create specialized access policies tailored to their personal wishes. We entitle this personalized access control. In this paper we present a semi-formal model for how we believe personalized access control may be realized. The model draws on and combines properties and concepts of both Role-Based Access Control (RBAC) and Discretionary Access Control (DAC) to achieve the desired properties. Throughout the paper we use the PCHR as a motivating example and to explain our reasoning and practical use of the model.

Reviewing a patient history can be very time consuming, partly because of the large number of consultation notes. Often, most of the notes contain little new information. Tools facilitating this and other tasks could be constructed if we had the ability to automatically detect the novel notes. We propose the use of measures based on text compression, as an approximation of Kolmogorov complexity, for classifying note novelty. We define four compression-based and eight other measures. We evaluate their ability to predict the presence of previously unseen diagnosis codes associated with the notes in patient histories from general practice. The best measures show promising classification ability, which, while not enough to serve alone as a clinical tool, might be useful as part of a system taking more data types into account. The best individual measure was the normalized asymmetric compression distance between the concatenated prior notes and the current note.

The current article investigates the affordances associated with paper out of the motivation that this can help inform design of pervasive and ubiquitous computing solutions for clinical use. In particular, we will focus on paper-based medication charts, and discuss how these artifacts differ from various digital and context-aware solutions both in terms of media properties and functionalities. Based on a comparison of media, we argue that the affordances offered by the paper-based medication charts are not fully transferable to one digital medium, but that a combination of complementary digital media is required.

We present a framework for characterising hospital scenarios involving the patient chart. The paper-based chart is regarded as simple, efficient, and handy for mobile use by patient-care teams. However, the chart is available in only one physical place at a time, and it needs to be manually synchronised with the electronic healthcare record (EHR). The framework presented in this paper has been developed for use in non-participatory, observational studies performed at the University Hospital of Trondheim, conducted as a part of the MOBEL (MOBile ELectronic patient chart) project at NTNU. We have developed the framework iteratively; repeatedly observing groups in the ward, characterising observations in the framework, and changing attributes and outcome values. This paper presents our latest framework, a representative choice of scenarios, and their characterisation. We conclude with a discussion of results so far, the method, and the utility in the development of the MEPC.