Using neural networks to support high-quality evidence mapping.

BACKGROUND: The Living Evidence Map Project at the Norwegian Institute of Public Health (NIPH) gives an updated overview of research results and publications. As part of NIPH's mandate to inform evidence-based infection prevention, control and treatment, a large group of experts are continously monitoring, assessing, coding and summarising new COVID-19 publications. Screening tools, coding practice and workflow are incrementally improved, but remain largely manual. RESULTS: This paper describes how deep learning methods have been employed to learn classification and coding from the steadily growing NIPH COVID-19 dashboard data, so as to aid manual classification, screening and preprocessing of the rapidly growing influx of new papers on the subject. Our main objective is to make manual screening scalable through semi-automation, while ensuring high-quality Evidence Map content. CONCLUSIONS: We report early results on classifying publication topic and type from titles and abstracts, showing that even simple neural network architectures and text representations can yield acceptable performance.

Evaluation of a Hyperlinked Consumer Health Dictionary for reading EHR notes.

In this paper, we report on a pilot study conducted to test the usefulness and understandability of definitions in a Consumer Health Dictionary (IVS-CHD). Our two main goals for this study were to evaluate functionality of the dictionary when embedded in electronic health records (EHR) and determine the methodology for our larger-scale project to iteratively develop the IVS-CHD. The hyperlinked IVS-CHD was made available to thoracic surgery patients reading their own EHR. We asked patients to rate definitions on two 5-level Likert items measuring perceived usefulness and understandability. We also captured the terms that patients wanted defined, but that were not included in the IVS-CHD. Preliminary results indicate the types of problems that must be avoided when creating definitions, for example, that patients prefer detailed explanations that include medical outcomes, and that do not use "unfamiliar" terms they must also look up. We also have gained insight into the types of terms that patients want defined from their EHR notes, especially certain abbreviations. Patients further commented on the experience of reading EHR notes directly from the same system used by healthcare personnel and the help strategy of linking the contents to a hyperlinked dictionary.

Why do people want a paper copy of their electronic patient record?

Changes have recently been passed in the Norwegian legislation, allowing for more exchange of patient information between health personnel. These legal changes came as a result of a long and still ongoing debate concerning the potential conflict between confidentiality issues and patient safety as health care is getting more fragmented. At the same time, an increasing number of patients now make use of their legal right to access their patient record. In this paper, we shed light on some of the reasons why patients request a copy of their record. We report the preliminary results from an interview study in which seventeen patients who have asked for a copy of their patient record following a hospital stay have been interviewed. In our interview study, securing transmission of information between health care workers is one of the main reasons for requesting a copy of the record. We will discuss how this finding might contribute to the ongoing debate.

User-specific perspectives on ontologies.

Ontologies are more and more used in clinical informatics in different settings and supporting different functionalities. Most experts see the role of ontologies as operating in a black box and being invisible for the end-user. With respect to some of the systems that have recently been developed this is only partly possible. Therefore, we provide a methodology to create an end-user perspective on a clinical ontology. This will foster participation of the clinical expert in both ontology exploitation and ontology maintenance. This methodology does not only provide the basis for a better integration of the experts into the ontology-based system, but it can be used to support patient empowerment by helping the patient to understand the content that is stored and partake in its management.

Patients reading their health records - what emotional factors are involved?

In many countries, an increasing number of patients now make use of their legal right to access their health record. In this paper we shed light on the role of emotional factors involved when patients read their record. We report the preliminary results from an interview study in which eight patients who have asked for a copy of their electronic health record following a hospital stay have been interviewed. Our results show that distrust is an important emotional factor involved in asking for record access. When reading the record, several patients also discovered discrepancies between verbal communication and the written documentation, which causes irritation and resentment. Patients' reactions were due to health personnel's lack of openness in direct communication with them. We conclude that health personnel should be prepared to go more into the role as discussion partners with patients to show that their concerns are taken seriously, and that more should be done to avoid documentation errors due to weaknesses in documentation routines.

Personal health notes: lessons learned.

The health care system is characterized by fragmentation and specialization which challenge the possibility for patients to be well-informed about and involved in their health care. The present study contributes to an in-depth understanding of how we can use patients' own personal health notes to learn about the health care information system and patients' experience of multiple encounters. The personal health note shows different aspects of the health care labyrinths considering the inconsistency as well as discontinuity of the information.

Seeing the whole picture: integrated pre-surgery reports with PreOptique.

BACKGROUND: Information technology has transformed the way healthcare is conducted. There is a deluge of patient data dispersed in different systems that are commonly not interoperable. As a result, access to patient data has become a major bottleneck for healthcare professionals that struggle to find the relevant information in a timely way and without missing critical clinical information. RESULTS: We implemented PreOptique, a novel hybrid semantic and text-based system that was commissioned by a large hospital in Norway for providing integrated access to patient health records scattered over several databases and document repositories. We use ontology-based data access (OBDA) for the seamless integration of the structured databases at the hospital through the Optique platform. We employ text analysis techniques to extract vital sign measures and clinical findings from patient documents. PreOptique was developed and deployed at the hospital. This solution demonstrates how OBDA technology can provide integrated data access to disparate structured sources in healthcare, without requiring the replacement of existing databases. Unstructured clinical texts are also mined to extract patient findings, while the graphical user interface (GUI) provides a single access point that hides the underlying complexity of the system. We ran a usability study with 5 target users, obtaining a system usability score (SUS) of 86.0. Further, participants in the study stressed the simplicity of the GUI and the integration of data sources enabled by the system. CONCLUSIONS: This pilot study showcases the use of OBDA technology and text analysis to enable the integration of patient data for supporting clinical surgery operations. PreOptique is usable and can be easily employed by medical personnel to find patient data in a timely way.

Children's contributions to designing a communication tool for children with cancer.

In this paper, we describe the roles played as well as contributions made by child participants in the design of an innovative communication tool for children with cancer. SISOM is a handheld, portable computer application with a graphical user interface that is meant to: (1) help children with cancer communicate their symptoms / problems in a child-friendly, age-adjusted manner; and (2) assist clinicians in addressing children's experienced symptoms and problems in patient care. Unlike other applications for children, the purpose of SISOM is not to provide information to ill children but to elicit personal information from them. Thus the application has a unique set of design issues. Healthy and ill children played an important role in different stages in the design process. They made significant contributions to the graphical design of the system's interface; selection of understandable, child-friendly terms used by the system to describe symptoms; iconic and graphical representations; and its usability. We describe the participatory design methods we used that included children and share important insights from this collaborative design process.

Text characteristics of clinical reports and their implications for the readability of personal health records.

Through personal health record applications (PHR), consumers are gaining access to their electronic health records (EHR). A new challenge is to make the content of these records comprehensible to consumers. To address this challenge, we analyzed the text unit length, syntactic and semantic characteristics of three sets of health texts: clinical reports from EHR, known difficult materials and easy-to-read materials. Our findings suggest that EHR texts are more different from easy texts and more similar to difficult texts in terms of syntactic and semantic characteristics, and EHR texts are more similar to easy texts and different from difficult texts in regard to text unit length features. Since commonly used readability formulas focus more on text unit length characteristics, this study points to the need to tackle syntactic and semantic issues in the effort to measure and improve PHR readability.

Semantic representation of consumer questions and physician answers.

The aim of this study was to identify the underlying semantics of health consumers' questions and physicians' answers in order to analyze the semantic patterns within these texts. We manually identified semantic relationships within question-answer pairs from Ask-the-Doctor Web sites. Identification of the semantic relationship instances within the texts was based on the relationship classes and structure of the Unified Medical Language System (UMLS) Semantic Network. We calculated the frequency of occurrence of each semantic relationship class, and conceptual graphs were generated, joining concepts together through the semantic relationships identified. We then analyzed whether representations of physician's answers exactly matched the form of the question representations. Lastly, we examined characteristics of the answer conceptual graphs. We identified 97 semantic relationship instances in the questions and 334 instances in the answers. The most frequently identified semantic relationship in both questions and answers was brings_about (causal). We found that the semantic relationship propositions identified in answers that most frequently contain a concept also expressed in the question were: brings_about, isa, co_occurs_with, diagnoses, and treats. Using extracted semantic relationships from real-life questions and answers can produce a valuable analysis of the characteristics of these texts. This can lead to clues for creating semantic-based retrieval techniques that guide users to further information. For example, we determined that both consumers and physicians often express causative relationships and these play a key role in leading to further related concepts.

Mapping nurses' natural language to oncology patients' symptom expressions.

Systems that integrate information from both the patients and health professionals require bi-directional term translation. We manually extracted nursing terms from 25 randomly selected cancer patients' charts that expressed symptoms and mapped these to a set of patient-oriented symptoms from a cancer support system. We found that 40% of the nursing terms were synonyms of patient expressions that could be mapped directly; however 38% of the nursing terms required a map to more than one patient expression. In this study, we gained an understanding of the link between nursing and patient language that is needed for future system development.

Children as design partners in the development of a support system for children with cancer.

Children with cancer experience many symptoms and problems that often remain unreported and untreated. We therefore, developed PedsChoice, a support system for pediatric cancer symptom assessment and management to provide children with a "voice," and assist nurses and physicians to better address children's symptoms and problems in patient care. We used participatory design techniques where healthy children joined our design team. During this process we explored the role s healthy children can appropriately play to inform the design of a system for children with cancer and their contributions and limitations as participants in the design process. We found that healthy children can contribute considerably in the role as testers, informers and to some extent as partners. Children have very creative design ideas that can considerably improve the software. However, system development for seriously ill children also requires psychological and pedagogical insights and design and usability expertise. This limits the role children can play as full design partners.

Computer-Interpretable Clinical Guidelines: A Review and Analysis of Evaluation Criteria for Authoring Methods.

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.

Helping healthcare consumers understand: an "interpretive layer" for finding and making sense of medical information.

Healthcare consumers need to find, comprehend, and interpret health information before making informed decisions. Recent work by others and our own work suggest that mis-matches in representations of health information used by consumers and professionals occur at different levels of knowledge representation, such as terminology (i.e., form or surface structure and concept or meaning) and semantic relation-ships. A challenge for consumer health informatics research is to devise a comprehensive strategy to bridge the gap between consumer understanding and biomedical knowledge at all levels. We propose a framework to inform the design of an "interpretive layer" to "mediate" between lay (illness model) and professional (disease model) perspectives, at all levels. In our view, the goal is to assist consumers in identifying terms to describe their needs, finding and understanding relevant information, and applying that knowledge for informed healthcare decision making.

Clinical documentation as a source of information for patients - possibilities and limitations.

Recent legislation in many countries has given patients the right to access their own patient records. Making health-care professionals' assessments and decisions more transparent by giving patients access to their records is expected to provide patients with useful health information and reduce the power imbalance between patient and provider. We conducted both a mail survey and a face-to-face interview study, including patients who had requested a paper copy of their patient records (EPR), to explore their experiences. For many study participants, a view of their records filled in holes in the oral information they previously received. They had problems understanding parts of what they read, but rarely asked for help. Instead they searched for explanations on the Internet or attempted to understand based on the context. Patients are still afraid of seeming suspicious or displeased if they indicate that they would like to read their records. Health-care organizations should consider actively offering patients the chance to view their clinical documentation to a larger extent than what has been done so far.

The core clinical protocol ontology (C2PO): A realist ontology for representing the recommendations within clinical guidelines.

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.

Lay people's experiences with reading their medical record.

An increasing number of patients now make use of their legal right to read their medical record. We report findings from a study in which we conducted qualitative interviews with 17 Norwegian adult patients about their experiences of requesting a copy of their medical record following a hospital stay. Interviews took place between May, 2008 and April 2009. The analytical process, guided by qualitative content analysis, identified two main themes; "keeping a sense of control" and "not feeling respected as a person". The informants' experiences with reading their own medical record were often connected to their experiences in direct communication with health care professionals during the hospital stay, revealing a delicate interaction between trust and power. The informants were hoping for a more mutual exchange of information and knowledge from which they could benefit in the management of their own health. We conclude that to meet patients' expectations of mutuality, health care professionals in hospitals need to be more conscious about their attitudes and communication skills as well as how they exercise their power to define the patient's situation. At the same time, there should be more focus on how structural changes in the organization of hospitals may have impaired the capacity of health care professionals to meet these expectations. In the future, greater attention should also be paid to information exchange to avoid placing unreasonable responsibility on the patient to compensate for deficits in the health care system.

Rape: when the exam is normal.

In this case report we present the sexual assault of a stuporous victim by a suspect who videotaped their encounter. We review the role of substance use and exam findings and discuss both victim and suspect factors that may lead to a negative examination of the victim.

Designing tailored Internet support to assist cancer patients in illness management.

This paper describes the development and a preliminary usage analysis of a novel Internet-based support system that assists cancer patients in symptom monitoring and disease management. The system, called WebChoice, allows patients to monitor symptoms over time, and provides access to evidence-based self-management options tailored to their reported symptoms as well as a communication area where patients can ask questions to a clinical nurse specialist and exchange experiences with other cancer patients. A currently ongoing randomized clinical trial evaluates effects of WebChoice on patient outcomes. This paper describes essential features of WebChoice, steps we used to design it as user-friendly as possible; and preliminary findings on patients use.

Towards consumer-friendly PHRs: patients' experience with reviewing their health records.

Consumer-friendly Personal Health Records (PHRs) have the potential of providing patients with the basis for taking an active role in their healthcare. However, few studies focused on the features that make health records comprehensible for lay audiences. This paper presents a survey of patients' experience with reviewing their health records, in order to identify barriers to optimal record use. The data are analyzed via descriptive statistical and thematic analysis. The results point to providers' notes, laboratory test results and radiology reports as the most difficult records sections for lay reviewers. Professional medical terminology, lack of explanations of complex concepts (e.g., lab test ranges) and suboptimal data ordering emerge as the most common comprehension barriers. While most patients today access their records in paper format, electronic PHRs present much more opportunities for providing comprehension support.