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.

Mental health disorders often develop during childhood and adolescence, causing long term and debilitating impacts at individual and societal levels. Local, early, and precise assessment and evidence-based treatment are key to achieve positive mental health outcomes and to avoid long-term care. Technological advancements, such as computerized Clinical Decision Support Systems (CDSSs), can support practitioners in providing evidence-based care. While previous studies have found CDSS implementation helps to improve aspects of medical care, evidence is limited on its use for child and adolescent mental health care. This paper presents challenges and opportunities for adapting CDSS design and implementation to child and adolescent mental health services (CAMHS). To highlight the complexity of incorporating CDSSs within local CAMHS, we have structured the paper around four components to consider before designing and implementing the CDSS: supporting collaboration among multiple stakeholders involved in care; optimally using health data; accounting for comorbidities; and addressing the temporality of patient care. The proposed perspective is presented within the context of the child and adolescent mental health services in Norway and an ongoing Norwegian innovative research project, the Individualized Digital DEcision Assist System (IDDEAS), for child and adolescent mental health disorders. Attention deficit hyperactivity disorder (ADHD) among children and adolescents serves as the case example. The integration of IDDEAS in Norway intends to yield significantly improved outcomes for children and adolescents with enduring mental health disorders, and ultimately serve as an educational opportunity for future international approaches to such CDSS design and implementation. Copyright © 2020 Røst, Clausen, Nytrø, Koposov, Leventhal, Westbye, Bakken, Flygel, Koochakpour and Skokauskas. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

Background Nearly half of all mental health disorders develop prior to the age of 15. Early assessments, diagnosis, and treatment are critical to shortening single episodes of care, reducing possible comorbidity and long-term disability. In Norway, approximately 20% of all children and adolescents are experiencing mental health problems. To address this, health officials in Norway have called for the integration of innovative approaches. A clinical decision support system (CDSS) is an innovative, computer-based program that provides health professionals with clinical decision support as they care for patients. CDSS use standardized clinical guidelines and big data to provide guidance and recommendations to clinicians in real-time. IDDEAS (Individualised Digital DEcision Assist System) is a CDSS for diagnosis and treatment of child and adolescent mental health disorders. The aim of IDDEAS is to enhance quality, competency, and efficiency in child and adolescent mental health services (CAMHS). Methods/design IDDEAS is a mixed-methods innovation and research project, which consists of four stages: 1) Assessment of Needs and Preparation of IDDEAS; 2) The Development of IDDEAS CDSS Model; 3) The Evaluation of the IDDEAS CDSS; and, 4) Implementation & Dissemination. Both qualitative and quantitative methods will be used for the evaluation of IDDEAS CDSS model. Child and adolescent psychologists and psychiatrists (n = 30) will evaluate the IDDEAS` usability, acceptability and relevance for diagnosis and treatment of attention-deficit/hyperactivity disorder. Discussion The IDDEAS CDSS model is the first guidelines and data-driven CDSS to improve efficiency of diagnosis and treatment of child and adolescent mental health disorders in Norway. Ultimately, IDDEAS will help to improve patient health outcomes and prevent long-term adverse outcomes by providing each patient with evidence-based, customized clinical care. © The Author(s). 2020 Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. 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 in a credit line to the data.

Loss of consciousness, so-called syncope, is a commonly occurring symptom associated with worse prognosis for a number of heart-related diseases. We present a comparison of methods for a diagnosis classification task in Norwegian clinical notes, targeting syncope, i.e. fainting cases. We find that an often neglected baseline with keyword matching constitutes a rather strong basis, but more advanced methods do offer some improvement in classification performance, especially a convolutional neural network model. The developed pipeline is planned to be used for quantifying unregistered syncope cases in Norway.

Psychiatric disorders are amongst the most prevalent and impairing conditions in childhood and adolescence. Unfortunately, it is well known that general practitioners (GPs) and other frontline health providers (i.e., child protection workers, public health nurses, and pediatricians) are not adequately trained to address these ubiquitous problems (Braddick et al. Child and Adolescent mental health in Europe: infrastructures, policy and programmes, European Communities, 2009; Levav et al. Eur Child Adolesc Psychiatry 13:395-401, 2004). Advances in technology may offer a solution to this problem with clinical decision support systems (CDSS) that are designed to help professionals make sound clinical decisions in real time. This paper offers a systematic review of currently available CDSS for child and adolescent mental health disorders prepared according to the PRISMA-Protocols (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols). Applying strict eligibility criteria, the identified studies (n = 5048) were screened. Ten studies, describing eight original clinical decision support systems for child and adolescent psychiatric disorders, fulfilled inclusion criteria. Based on this systematic review, there appears to be a need for a new, readily available CDSS for child neuropsychiatric disorder which promotes evidence-based, best practices, while enabling consideration of national variation in practices by leveraging data-reuse to generate predictions regarding treatment outcome, addressing a broader cluster of clinical disorders, and targeting frontline practice environments.

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.

Great advances in molecular biology, genetics and imaging serve to enhance the desire to develop multi-level and multi-scale models for "personalized medicine" but they remain very challenging for high prevalence, high impact childhood onset neuropsychiatric disorders. We currently have the capacity to develop innovative, effective and efficient clinical decision support models, while also creating the opportunities for rapidly incorporating multi-scale, multi-level data as they become available in the very near future. Sensitive to these complex issues, this paper discusses how these existing resources can be used to develop state-of-the-art clinical decision support models that will improve patient care and reduce costs in primary care and specialist settings in the present while creating a mechanism for adding biomarker and other data as it emerges. The new clinical decision support system for child and adolescent mental disorders needs to integrate existing heterogeneous, geographically distinct, current and historical patient-specific and population-specific data in order to generate new information and models for clinic decision support at the level of the individual patient, using the already available informatics frameworks.

How can we use information visualization to support retrospective, exploratory analysis of collections of histories for patients admitted to acute care? This paper describes a novel design for visual cohort identification and exploration. We have developed a tool that integrates multiple, heterogeneous clinical data sources and allows alignment, querying and abstraction in a common workbench. This paper presents results from two projects and a review of related work in the field of information visualization including both presentation and interactive navigation of the information. We have developed an interactive prototype and present the visualization aspect of this prototype and a brief demonstration of its use in a research project with a large cohort of patients. The prototype represents and reasons with patient events in different OWL-formalizations according to the perspective and use: One for integration and alignment of patient records and observations; Another for visual presentation of individual or cohort trajectories. Health researchers have successfully analyzed large cohorts (over 100,000 individuals) using the tool. We have also used the tool to produce interactive personal health time-lines (for more than 10,000 individuals) on the web. Utility, usability and effect have been tested extensively and the results so far are promising. We envision that clinicians who want to learn more about groups of patients and their treatment processes will find the tool valuable. In addition, we believe that the visualization can be useful to researchers looking at data to be statistically evaluated, in order to discover new hypotheses or get ideas for the best analysis strategies. Our main conclusion is that the tool is usable, but it can be challenging to use for large data sets. Postprint version. © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, 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 components of this work in other works.

Advanced information systems have great potential for supporting clinicians in their patient-centered work. In order to meet the specific information and communication needs of healthcare professionals during a wide range of situations, there is an increased focus on developing context-aware user interfaces for pervasive health information systems. However, the high information and communication intensity, the nature of clinical work, and the complexity of healthcare organizations make the system design process, and especially the requirements engineering (RE) phase, particularly challenging.This thesis addresses how structured observation can be used as a technique for elicitation and analysis of requirements for mobile electronic patient record (EPR) systems. The thesis explores how important properties of clinical situations can be captured through observation of actors, processes, and systems.The contributions of the thesis consist of two main components:• An iteratively developed method for structured, focused observation and analysis of clinicians’ information and communication behaviour• Exploration of how the observational data can be analyzed with varying foci and perspectives, and how the results of the processed data may be used as input to the requirements engineering processThe approach has been developed and refined during several observational studies performed in different hospital wards. The development process and the observational studies are presented in the eight papers which constitute the main part of this thesis.Medical students are found to be particularly suited for performing the observations due to their domain knowledge and natural presence as apprentices in hospital wards. As future users of the information systems they can also function as mediators between the end users and the system developers, both during the data collection and the analysis phases of the studies.The recorded observational data consists of sequences of events or communicative acts. When analyzing the data, it is possible to produce patient, process, or actor trajectories. In the thesis it is suggested how this can be used to inform implementation of clinical guidelines. Examples of how communicative patterns of actors and roles can be visualized and directions for how this can be used in the RE process are also given.

This work describes the use of clinical guidelines in public health care for decision support in a primary care record system. The clinical guidelines were used for decision support in primary care in order to improve the quality of electronic referrals to a hospital. Guidelines were developed by the specialists at the hospital, but the design and the development of the system was done in collaboration with general practitioners working in primary care. This paper sums up the findings from a study six months after the introduction of the decision support system, and is based on interviews with users in primary care. The work processes differed between the practices; General practitioners who wrote the referrals after the patient had left the office did not find the system as useful as the ones who wrote them when the patient was present. The general practitioners were reluctant to use guidelines that resulted in an additional workload in terms of providing the hospital with more information than before, but found the system useful as a support for assuring that they made the right clinical decisions. The guidelines were also seen as useful as a support for refusing to refer the patient to specialized care.

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.

Objectives In this paper we present a method for processing and presentation of data recorded through structured observation of clinicians’ information and communication activities. The activities are encoded as sequences of distinctive speech acts, and resulting profiles of communicative behaviour are visualized in radar graphs. Example profiles resulting from the analysis of three clinicians’ communicative behaviour during pre-rounds meetings and medication activities are given. Methods The communicative acts profiles are based on empirical data from an observational study performed at a Norwegian university hospital. A fifth-year medical student spent 20 days in two different hospital wards, following one physician at a time in daily, patient-centred work. The observer recorded the clinicians’ information and communication activities during several ward situations such as pre-rounds meetings, ward rounds, and patient discharge. The data was recorded by means of an observation form consisting of a mixture of codes and free-text fields. The recorded data was post-processed by associating each event with one predefined communicative act, and resulting profiles for three individual physicians in different situations have been created as radar graphs. Results/conclusion The approach is an efficient and useful means for studying clinicians’ information and communication patterns in hospital wards. The method can be used to illustrate variations among individual clinicians in similar situations and to compare profiles of different roles or hospital wards. Given proper validation, the approach may serve as an important tool to inform the design of new clinical information systems.