Search

Objective To determine the effects of using unstructured clinical text in machine learning (ML) for prediction, early detection, and identification of sepsis. Materials and methods PubMed, Scopus, ACM DL, dblp, and IEEE Xplore databases were searched. Articles utilizing clinical text for ML or natural language processing (NLP) to detect, identify, recognize, diagnose, or predict the onset, development, progress, or prognosis of systemic inflammatory response syndrome, sepsis, severe sepsis, or septic shock were included. Sepsis definition, dataset, types of data, ML models, NLP techniques, and evaluation metrics were extracted. Results The clinical text used in models include narrative notes written by nurses, physicians, and specialists in varying situations. This is often combined with common structured data such as demographics, vital signs, laboratory data, and medications. Area under the receiver operating characteristic curve (AUC) comparison of ML methods showed that utilizing both text and structured data predicts sepsis earlier and more accurately than structured data alone. No meta-analysis was performed because of incomparable measurements among the 9 included studies. Discussion Studies focused on sepsis identification or early detection before onset; no studies used patient histories beyond the current episode of care to predict sepsis. Sepsis definition affects reporting methods, outcomes, and results. Many methods rely on continuous vital sign measurements in intensive care, making them not easily transferable to general ward units. Conclusions Approaches were heterogeneous, but studies showed that utilizing both unstructured text and structured data in ML can improve identification and early detection of sepsis.

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.

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.

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.

There are a variety of authoring tools and methods for producing computer-interpretable clinical guideline (CIG). This work is a review of the evaluation of tools and methods currently in use to author CIGs. The aim of this paper is to present the results of a literature review on the evaluation criteria. Both controlled database search and a subsequent snowballing were used to identify relevant literature. The evaluation criteria and evaluation methods of CIG-related themes were manually identified in the found literature. Based on the 32 relevant papers found, 68 evaluation criteria were identified which were then classified into ten themes. We identified the most and least frequently mentioned areas of concern in evaluation which indicate areas that have been neglected in system evaluation.

Representation of clinical guidelines in a computer interpretable format is an active area of research. Various methods and tools have been proposed which have been evaluated based on different evaluation criteria. The evaluation results in the literature and their lessons learnt can be a valuable learning resource in order to redesign and improve the tools. Therefore, this research investigates the lessons learnt from the evaluation studies. Broad search in literature together with a purposeful snowball method were performed to identify the related papers that report any type of evaluation or comparison. We reviewed and analysed the lessons learnt from the evaluation results and classified them into 17 themes which reflect the suggestion concerns. The results indicate that the lessons learnt are more focused on tool functionalities, integration, sharing and maintenance domain. We provide suggestions for the area which had less attention.

We present an initial version of the Core Clinical Protocol Ontology (C2PO). C2PO is an application ontology being developed for the semantic markup of clinical guidelines within the Evicare project. Evicare's goals are to learn more about the actual use of guidelines in the context of clinical care and develop systems to support physicians in answering their clinical questions. The initial implementation of C2PO includes definitions for clinical guideline recommendations, and the process of recommending. We followed a realist approach to ontology design. Design methodology for C2PO, including methods for class selection, is discussed. A collection of guidelines has been manually marked-up and a demonstration system developed in which specific clinical queries will retrieve relevant ranked recommendations. C2PO forms the basis for a lightweight approach to clinical decision support that uses a text-based representation. A future objective is to expand the system to support semantic search of normative medical texts including health records, order sets, and process descriptions.