https://ecp.ep.liu.se/index.php/shi <p>The SHI conference is an annual scientific event attended by scientist and practitioners working in the field of Health Informatics.</p> Linköping University Electronic Press en-US Scandinavian Conference on Health Informatics 1650-3686 https://ecp.ep.liu.se/index.php/shi/article/view/429 The onset of COVID-19 has the accelerated adoption and diffusion of remote care services to address the challenges of postoperative follow-up and support patients receiving care at home. Despite the great importance of this emerging technological solution, the field is still in its infancy. This paper presents findings based on feedback from an early-stage implementation of digitally enabled remote care in Norway and China, respectively. The same solution has been implemented in the two countries with a particular focus on patients with chronic conditions and postoperative rehabilitation. Hong Li Torbjørg Meum Miria Grisot Copyright (c) 2022 Hong Li, Torbjørg Meum, Miria Grisot https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 2 8 10.3384/ecp187001 https://ecp.ep.liu.se/index.php/shi/article/view/430 Background: The Learning Health System is a concept born from the Institute of Medicine roundtable in 2006 which aims for overcoming the limitations of evidence-based medicine. Since its conception several nations and organizations have actively proposed health policies, research plans, and innovation strategies for its implementation. The effective realization of practices enabling a Learning health system hinge on the availability of Information system functionality and tools. Objective: To describe the EHR functionality that is needed and corresponding indicators for use in evaluation. Methods: Analysis of the content of influential scientific publications on the topic. Results and discussion: The key enabling practices are linked to the life-cycle of biomedical knowledge as well as to knowledge on how to implement evidence-based care. Olga Golburean Ove Lintvedt Espen Sobbakken Nordheim Rune Pedersen Luis Marco-Ruiz Arild Faxvaag Copyright (c) 2022 Olga Golburean, Ove Lintvedt, Espen Sobbakken Nordheim, Rune Pedersen, Luis Marco-Ruiz, Arild Faxvaag https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 9 13 10.3384/ecp187002 https://ecp.ep.liu.se/index.php/shi/article/view/431 The aim was to translate and cross-culturally adapt the original Telehealth Usability Questionnaire (TUQ) into Danish and pre-test the translation on a sample of Danish patients with diabetes who received telemedicine. Participants with diabetes (n = 34) completed the Danish TUQ and participated in semi-structured interviews. The overall internal consistency was 0.857. The internal consistency for the five sub-groups ranged from 0.241 (sub-group four) to 0.857 (sub-group five). The study demonstrates an overall accepted statistical internal consistency compared with the original TUQ, which makes it a reliable tool to assess patients’ perceptions after using a telemedicine service. Clara Bender Marie Germund Nielsen Ole Hejlesen Stine Hangaard Copyright (c) 2022 Clara Bender, Marie Germund Nielsen, Ole Hejlesen, Stine Hangaard https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 14 20 10.3384/ecp187003 https://ecp.ep.liu.se/index.php/shi/article/view/432 In this paper we present a computer vision (CV) based prototype application for knee range of motion analysis. The prototype is built on top of an existing CV pose estimation technique, requiring only one web camera. The aim was to investigate whether it can provide adequate measurement accuracy for rehabilitation purposes. Pilot testing were used to compare the accuracy of the prototype with universal goniometer when measuring range of motion of the knee joint. Our research indicates that sufficient accuracy for range of motion analysis of the knee can potentially be achieved in standing and lying positions by extending the underlying training dataset. Thomas Hellstén Jonny Karlsson Christian Häggblom Jyrki Kettunen Copyright (c) 2022 Thomas Hellstén, Jonny Karlsson, Christian Häggblom, Jyrki Kettunen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 21 25 10.3384/ecp187004 https://ecp.ep.liu.se/index.php/shi/article/view/433 Since 2014, an electronic prescribing system has been piloted for patients receiving medications as multidose drug dispensing; a system commonly used in home care services. In this longitudinal study of 499 patients, we investigate workload at the pharmacies, measured as the number of times pharmacists assess prescriptions. In the 26-week period before the implementation, 17% of the patients got their prescriptions assessed by a pharmacist every 2 weeks, in the 42 weeks after, this increased to 47%. This considerably increases the pharmacy workload, with an estimated additional 602.000 pharmacist assessments every year if all eligible patients get the new prescribing system. Anette Jøsendal Trine Bergmo Copyright (c) 2022 Anette Jøsendal, Trine Bergmo https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 26 32 10.3384/ecp187005 https://ecp.ep.liu.se/index.php/shi/article/view/434 The objective of this narrative review is to provide an overview of the knowledge and gaps in the existing research on digital Antibiotic resistance (ABR) monitoring in Low- and middle-income countries (LMICs). ABR presents a complex threat to global health. One of the key global priorities is to address this challenge through effective monitoring. An analysis of the literature revealed the missing role of IS (Information systems) research in digital ABR monitoring. A thematic analysis of the identified literature on digital interventions for ABR revealed several gaps. This research contributes by providing potential research directions and identifying the role of IS research in ABR. Yogita Thakral Copyright (c) 2022 Yogita Thakral https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 33 40 10.3384/ecp187006 https://ecp.ep.liu.se/index.php/shi/article/view/435 Patient self-management is vital to improved health outcomes for patients with chronic diseases. The objective of this study was to understand the role of wearable sensors in patients’ self-management. A survey encompassing factors related to motivation in mHealth was conducted. Ease of use and sensory accuracy was found most important when choosing a wearable. Manual registration of most health-related information is unpopular, although some exceptions exist. Respondents valued sensor accuracy and easiness in manual registration and usage of mHealth systems. Further research is needed to pinpoint what ease of use exactly is, and how ease of use can be improved. Andre Henriksen Gerit Pfuhl Ashenafi Zebene Woldaregay David-Zacharie Issom Eirik Årsand Keiichi Sato Gunnar Hartvigsen Copyright (c) 2022 Andre Henriksen, Gerit Pfuhl, Ashenafi Zebene Woldaregay, David-Zacharie Issom, Eirik Årsand, Keiichi Sato, Gunnar Hartvigsen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 41 45 10.3384/ecp187007 https://ecp.ep.liu.se/index.php/shi/article/view/436 During cardiac surgery, in addition to their manual work, surgeons need to perceive a large amount of procedural intraoperative data, including information which is not directly visible to them. Therefore, we developed an augmented reality demonstrator that displays alphanumerical data into the loupe of surgical magnifying glasses. Eight cardiac surgeons tested the demonstrator in a skill task that simulates the critical part of a typical surgical procedure while being confronted to vital intraoperative parameters getting critical. The results showed a decrease of missed critical phases and improved response times when using the demonstrator instead of a customary monitor for tracking intraoperative parameters. Artur Liebrecht Roman Bibo Bastian Dewitz Sebastian Kalkhoff Sobhan Moazemi Markus Rollinger Jean-Michel Asfour Klaus-Jürgen Janik Artur Lichtenberg Hug Aubin Falko Schmid Copyright (c) 2022 Artur Liebrecht, Roman Bibo, Bastian Dewitz, Sebastian Kalkhoff, Sobhan Moazemi, Markus Rollinger, Jean-Michel Asfour, Klaus-Jürgen Janik, Artur Lichtenberg, Hug Aubin, Falko Schmid https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 46 51 10.3384/ecp187008 https://ecp.ep.liu.se/index.php/shi/article/view/437 The increased development and use of ubiquitous digital services reinforce the trend where health-related data is generated everywhere. Data usage in different areas introduces different terms for the same or similar concepts. This adds to the confusion of what these terms represent. We aim to provide an overview of concepts and terms used in connection with digital twins and in a healthcare context. Erlend Johannessen André Henriksen Gunnar Hartvigsen Alexander Horsch Eirik Årsand Jonas Johansson Copyright (c) 2022 Erlend Johannessen, André Henriksen, Gunnar Hartvigsen, Alexander Horsch, Eirik Årsand, Jonas Johansson https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 52 58 10.3384/ecp187009 https://ecp.ep.liu.se/index.php/shi/article/view/438 When evaluating the potential of an alternative method to detects physiological changes that occur during hypoglycemia it is important to be aware of the perceived usefulness among potential users [17]. The aim of this study was to explore the perceived usefulness of a contactless monitor for detection of hypoglycemia among people with type 1-diabetes (T1D). Semi-structured interviews (n =8) were conducted after people with T1D used the contactless monitor at home. The interviews were analyzed using a thematic approach. Five overall themes were identified. Overall, the participants reported that the contactless monitor was an acceptable method to detect nocturnal hypoglycemia. Julie Egmose Katrine Holmstrup Sørensen Tanja Fredensborg Holm Ole Hejlesen Morten Hasselstrøm Jensen Stine Hangaard Copyright (c) 2022 Julie Egmose, Katrine Holmstrup Sørensen, Tanja Fredensborg Holm, Ole Hejlesen, Morten Hasselstrøm Jensen, Stine Hangaard https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 59 63 10.3384/ecp187010 https://ecp.ep.liu.se/index.php/shi/article/view/439 Typically, routine prenatal care includes several in-person visits with healthcare professionals by pregnant women, where fetal and maternal assessments are performed. This paper proposes an architectural framework for prenatal care using non-invasive, simple, and low-cost internet of things (IoT) monitoring system. The aim is to design an IoT-based architecture that serves as a fundamental system for self-imperative care in regular pregnancy check-ups in the comfort of the home that offers routine prenatal screening tests. The system provides easy access to care regardless of the location and internet availability. We implemented preliminary architecture with simulated sensor data for blood pressure monitoring. Sarala Ghimire Santiago Martine Martin Gerdes Copyright (c) 2022 Sarala Ghimire, Santiago Martine, Martin Gerdes https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 64 68 10.3384/ecp187011 https://ecp.ep.liu.se/index.php/shi/article/view/440 Digital Patient Contact Technologies (DPCT), including telemedicine solutions and digital tools for text-based communication between patients and physicians, play a significant role in today’s healthcare. Professional identity defines norms, principles, and logic that guide one’s professional actions. Presently, little research is available regarding professional identity changes in the context of DPCT implementations. This work theoretically and empirically illustrates the nature of the possible DPCT’ impact on physicians’ professional identities. To this end, a conceptual framework was constructed, and the interviews with eight physicians operating an asynchronous healthcare-advice chat service (1177 Vårdguiden) in Uppsala, Sweden, were examined. Michal Dolezel Åsa Cajander Copyright (c) 2022 Michal Dolezel, Åsa Cajander https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 69 76 10.3384/ecp187012 https://ecp.ep.liu.se/index.php/shi/article/view/441 Type 2 diabetes mellitus (T2D) and prediabetes prevalence rates are high. Consequences are serious, but current treatment is often not efficient for achieving remission. Remission may be achieved through lifestyle intervention. Frequent follow-up is necessary, and health care personnel (HCP) lack resources, time, and often adequate knowledge. Self-management of T2D can benefit from better use of Information and Communication Technologies (ICT), which may improve patient involvement and follow-up, and can provide new tools for lifestyle change. Virtual follow-up through ICT with HCP may reduce costs and reach more patients. An electronic health (e-health) program for T2D and prediabetes will be developed in collaboration with users, as part of a plan for a large randomized controlled trial (RCT). Tina Rishaug André Henriksen Anne-Marie Aas Gunnar Hartvigsen Kåre Inge Birkeland Eirik Årsand Copyright (c) 2022 Tina Rishaug, André Henriksen, Anne-Marie Aas, Gunnar Hartvigsen, Kåre Inge Birkeland, Eirik Årsand https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 77 81 10.3384/ecp187013 https://ecp.ep.liu.se/index.php/shi/article/view/442 Medical consultations for chronic diseases form an arena to provide information from health personnel to patients. This information is necessary for patients to understand how to deal with the possible lifelong symptoms and needed self-management activities. The amount of patient-generated health data is increasing. Today’s patients gather an increasing amount of personalised health-related information. Meanwhile, the health personnel get more patients to care for and fewer resources. This paper summarises information and communication technologies possibilities for improved diabetes consultations. It aims to inform how the medical consultation for chronic diseases needs to change drastically to meet today and future’s challenges. Pietro Randine John Graham Cooper Gunnar Hartvigsen Eirik Årsand Copyright (c) 2022 Pietro Randine, John Graham Cooper, Gunnar Hartvigsen, Eirik Årsand https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 82 87 10.3384/ecp187014 https://ecp.ep.liu.se/index.php/shi/article/view/443 Many with intellectual disabilities (ID) have difficulties adhering to current physical activity guidelines. The goal of this study was to develop a mobile app for assisting people with ID to be more physically active. We implemented a solution that combines the digital and real world using augmented reality (AR). Eight people working with people with ID (special education teachers, social workers, psychologists, and researchers) tested the app and completed a usability test. Results indicate that a mobile app focusing on everyday life scenarios can have a potential value for the targeted user group, but AR solutions can be challenging. Magnus Stellander André Henriksen Henriette Michalsen Audny Anke Daniel Ursin Santiago Martinez Susanna Pelagatti Keiichi Sato Vebjørn Haugland Erlend Johannessen Juan Carlos Torrado Gunnar Hartvigsen Copyright (c) 2022 Magnus Stellander, André Henriksen, Henriette Michalsen, Audny Anke, Daniel Ursin, Santiago Martinez, Susanna Pelagatti, Keiichi Sato, Vebjørn Haugland, Erlend Johannessen, Juan Carlos Torrado, Gunnar Hartvigsen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 88 91 10.3384/ecp187015 https://ecp.ep.liu.se/index.php/shi/article/view/444 Few papers have described academic/faculty staff’s experiences with co-creation, or partnering with students in cross-disciplinary collaborations. The purpose of this paper is to share challenges and outcomes from two interdisciplinary student–staff co-creations of serious games for use in a Bachelor of Nursing program in Norway. Our experiences are discussed against an evidence-informed model of student–staff co-creation in higher education. Based on the lessons learned from these two projects, we propose ten key points for planning and conducting cross-disciplinary student–staff co-creation of serious games. Hege Mari Johnsen Jannicke Rabben Copyright (c) 2022 Hege Mari Johnsen, Jannicke Rabben https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 92 96 10.3384/ecp187016 https://ecp.ep.liu.se/index.php/shi/article/view/445 The recent pandemic highlighted telemedicine’s potential for continuity of remote diabetes patients’ care. The study objective was to identify diabetes telemedicine services, benefits, and challenges in Norway. We searched for publications on the topic in PubMed, ScienceDirect, CINAHL, and Nora. Most of the included studies (7/15) focused on telemedicine for type 2 diabetes. Telemedicine benefits include improved self-management and cost and time effectiveness. Challenges include organizational and technical issues. To optimize the health system, telemedicine can be used for highly engaged diabetes patients. Creating clear and practical national and organizational telemedicine guidelines for diabetes management could solve the identified challenges. Dillys Larbi Henriette Lauvhaug Nybakke Karianne Lind Eirin Rødseth Elia Gabarron Copyright (c) 2022 Dillys Larbi, Henriette Lauvhaug Nybakke, Karianne Lind, Eirin Rødseth, Elia Gabarron https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 97 102 10.3384/ecp187017 https://ecp.ep.liu.se/index.php/shi/article/view/446 This paper describes the development of an easily applicable web-based IT solution that enhances interactive communication (the interactive communication model) and ensures comprehension in nursing practice. The model seeks to identify knowledge and skills allowing tailored communication and seeks to ensure comprehension and recall between nurses and patients. Results from testing the model shows that it has the potential to enhance self-care in citizens receiving community nursing and creates a basis for a more holistic nursing approach. Lisa Korsbakke Emtekær Hæsum Ole Kristian Hejlesen Copyright (c) 2022 Lisa Korsbakke Emtekær Hæsum, Ole Kristian Hejlesen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 103 110 10.3384/ecp187018 https://ecp.ep.liu.se/index.php/shi/article/view/447 This review provides an overview of the existing research on social media, autism, and physical activity. We searched for publications on PubMed, PsycInfo, Embase, Education source, ERIC, IEEE Xplore, and the proceedings from conferences on health informatics and autism. Eight studies were included in this review. Studies reported mixed results on the link between social media, physical activity, and autism. Technology usage is related to sedentary time. However, physical activity interventions delivered through social media provide several benefits. Further research with stronger designs is needed to increase the knowledge of the role of social media on physical activity and autism. Elia Gabarron André Henriksen Anders Nordahl-Hansen Copyright (c) 2022 Elia Gabarron, André Henriksen, Anders Nordahl-Hansen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 111 117 10.3384/ecp187019 https://ecp.ep.liu.se/index.php/shi/article/view/448 Performing regular physical activity can be challenging. Integrating chatbots with social media platforms and physical activity sensors can potentially increase physical activity. The objective of this study was to identify design preferences for integrating an activity tracker supported chatbot in a social media platform. Norwegian adults (n=120) responded to an ad-hoc online survey. User preferences included adding a step goal feature that can be renewed every week and communicating with the chatbot once per day. Preferences of all types of potential users for a social media chatbot for physical activity should be explored to produce a well-accepted intervention. Dillys Larbi Helle Sandsdalen Elia Gabarron Eirik Årsand André Henriksen Copyright (c) 2022 Dillys Larbi, Helle Sandsdalen, Elia Gabarron, Eirik Årsand, André Henriksen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 118 123 10.3384/ecp187020 https://ecp.ep.liu.se/index.php/shi/article/view/449 The availability of direct-to-consumer genetic testing services and genome sequencing data bring novel opportunities for applications like genomic risk scoring where a polygenic disease risk score is calculated considering the statistical distribution of the disease associated SNPs. Nowadays, various websites are offering polygenic risk score estimations for various complex diseases. However, these services require the upload of the genomic data to their sites, which is a fairly sensitive personal data. Since, genome data uniquely identifies a person, anonymization is not sufficient alone and may become a threat in the long run. A potential solution is the use of cryptographic techniques along this goal. We propose to deploy homomorphic encryption, a technique which enables to do computation in encrypted data, for a web server providing polygenic risk score estimation. We implemented a proof-of-concept software to measure the performance of such a service with current technology. We also developed a GUI which facilitates the usage of homomorphic encryption for non-technical users. We conclude that recently developed homomorphic encryption libraries enable practical privacy-preserving genomic risk scoring services. Homomorphic encryption is becoming a strong alternative for practical secure privacy-preserving personalized medicine applications. Shaedul Islam Hüseyin Demirci Gabriele Lenzini Copyright (c) 2022 Shaedul Islam, Hüseyin Demirci, Gabriele Lenzini https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 124 127 10.3384/ecp187021 https://ecp.ep.liu.se/index.php/shi/article/view/450 An increasing number of citizens with multiple chronic conditions and technological innovations enabling new types of treatments pressure the Danish healthcare sector economically. The solution so far has been increased patient responsibility and the application of digital healthcare solutions. This longitudinal study examines how Danish citizens between 2013-2021 interact with Health Information Technology (HIT) and digital data. Results show that the Danes' use of HIT and digital data has increased over the period. Additionally, the numbers reveal that education, gender, age and chronic conditions influence how HIT and digital health data are used, which is relevant from a health inequity perspective. Jeppe Eriksen Kristina Tornbjerg Eriksen Pernille Bertelsen Copyright (c) 2022 Jeppe Eriksen, Kristina Tornbjerg Eriksen, Pernille Bertelsen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 128 135 10.3384/ecp187022 https://ecp.ep.liu.se/index.php/shi/article/view/451 Social robots interact with human beings and are used for a variety of therapeutic purposes, for example in interaction with children with neurodevelopmental disorders. A key ethical issue related to the application of social robots in these contexts is the idea of normativity, involved in both the design of social robots, i.e., the use of such robots to portray or mimic what is normal and to identify deviant behaviour or development. The article presents the beginnings of a framework for incorporating divergent opinions of normal social functioning, particularly neurodiversity, into the design and application of social robots. Henrik Skaug Sætra Anders Nordahl-Hansen Eduard Fosch-Villaronga Christine Dahl Copyright (c) 2022 Henrik Skaug Sætra, Anders Nordahl-Hansen, Eduard Fosch-Villaronga, Christine Dahl https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 136 140 10.3384/ecp187023 https://ecp.ep.liu.se/index.php/shi/article/view/452 Artificial intelligence based methods, especially machine learning (ML), are increasingly used in healthcare for automatic medical image analysis and clinical decision support systems. Development and validation of ML models involve processing of large volumes of personal data. We analysed regulatory impacts on ML based application development especially from the perspective of privacy protection and usage of ML models as a basis for software under medical device regulation (MDR). We present best practices for ML application development and personal data usage in a use case of predicting elderly individuals’ future need for healthcare and social welfare services. Jaakko Lähteenmäki Juha Pajula Emmi Antikainen Copyright (c) 2022 Jaakko Lähteenmäki, Juha Pajula, Emmi Antikainen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 141 146 10.3384/ecp187024 https://ecp.ep.liu.se/index.php/shi/article/view/453 Depression is one of the most burdensome diseases in the world. A problem that depression presents, is the fact that it is connected with a high rate of unwillingness to seek professional help, and therefore many aspects of depression go unreported, affecting our understanding of it. Nowadays, individuals turn to online platforms for help and support, which creates vast amounts of data. This infodemiological study utilised data from Twitter to identify temporal patterns of behaviours related to depression in Finland. The findings of this study can be used to improve the impact of public health measures in relation to depression. Jonas Tana Bao Cai Leonardo Espinosa-Leal Copyright (c) 2022 Jonas Tana, Bao Cai, Leonardo Espinosa-Leal https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 147 153 10.3384/ecp187025 https://ecp.ep.liu.se/index.php/shi/article/view/454 Nudge principles and techniques can motivate and improve personal health through emerging digital devices, such as activity trackers. Tracking people's health and well-being using such devices have earned widespread interest. These devices can continuously capture and analyze health-related data from individuals and communities in their everyday environment. Providing context-aware nudges can help individuals to self-manage and improve their health. In this study, we discuss how a consumer-based activity tracker can be used to track different variables for physical activity (PA) and how it has the potential to be an important source of data for future smart nudging. Seshathiri Dhanasekaran Anders Andersen Randi Karlsen Anne Håkansson André Henriksen Copyright (c) 2022 Seshathiri Dhanasekaran, Anders Andersen, Randi Karlsen, Anne Håkansson, André Henriksen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 154 158 10.3384/ecp187026 https://ecp.ep.liu.se/index.php/shi/article/view/455 This article explores the collaborative work of maintaining data quality of a major health administrative database as it is carried out by medical secretaries in the role of ‘registration responsible medical secretaries’. The article reports on ongoing socio-technical study of local, on-the-ground data work in 5 Danish hospital departments. We argue the medical secretaries make important and skillful contributions to data quality at department level, including identifying and correcting errors, implementing changes to the coding practice, and maintenance of data input quality at the department level requiring a high level of context sensitivity. Casper Knudsen Pernille Bertelsen Copyright (c) 2022 Casper Knudsen, Pernille Bertelsen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 159 165 10.3384/ecp187027 https://ecp.ep.liu.se/index.php/shi/article/view/456 A computer-assisted coding tool could alleviate the burden on medical staff to assign ICD diagnosis codes to discharge summaries by utilising deep learning models to generate recommendations. However, the opaque nature of deep learning models makes it hard for humans to trust them. In this study, the explainable AI models LIME and SHAP have been applied to the clinical language model SweDeClin-BERT to explain ICD-10 codes assigned to Swedish gastrointestinal discharge summaries. The explanations have been evaluated by eight medical experts, showing a statistically higher significant difference in explainable performance for SHAP compared to LIME. Alexander Dolk Hjalmar Davidsen Hercules Dalianis Thomas Vakili Copyright (c) 2022 Alexander Dolk, Hjalmar Davidsen, Hercules Dalianis, Thomas Vakili https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 166 173 10.3384/ecp187028 https://ecp.ep.liu.se/index.php/shi/article/view/457 Clinical text contains many negated concepts since the physician excludes irrelevant symptoms when reasoning and concluding about the diagnosis. This study investigates the machine interpretation of negated symptoms and diagnoses using a rule-based negation detector and its influence on downstream text classification task. The study focuses on the effect of negated concepts and NegEx preprocessing on classifier performance for predicting ICD-10 gastro surgical codes assigned to discharge summaries. Based on the experiments, NegEx preprocessing resulted in a slight performance improvement for traditional machine learning model (SVM) and had no effect on the performance of the deep learning model KB/BERT. Andrius Budrionis Taridzo Chomutare Therese Olsen Svenning Hercules Dalianis Copyright (c) 2022 Andrius Budrionis, Taridzo Chomutare, Therese Olsen Svenning, Hercules Dalianis https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 174 178 10.3384/ecp187029 https://ecp.ep.liu.se/index.php/shi/article/view/458 We commonly adjust for confounding factors in analytical observational epidemiology to reduce biases that distort the results. Stratification and matching are standard methods for reducing confounder bias. Coarsened exact matching (CEM) is a recent method using stratification to coarsen variables into categorical variables to enable exact matching of exposed and nonexposed subjects. CEM’s standard approach to stratifying variables is histogram binning. However, histogram binning creates strata of uniform widths and does not distinguish between exposed and nonexposed. We present Autostrata, a novel algorithmic approach to stratification producing improved results in CEM and providing more control to the researcher. Jo Inge Arnes Alexander Hapfelmeier Alexander Horsch Copyright (c) 2022 Jo Inge Arnes, Alexander Hapfelmeier, Alexander Horsch https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 179 186 10.3384/ecp187030 https://ecp.ep.liu.se/index.php/shi/article/view/459 Clinical trials need to adapt to the rapid development of today’s digital health technologies. The fast phase these technologies are changing today, make the clinical study administration demanding. To meet this challenge, new and more efficient platforms for performing clinical trials in this domain need to be designed. Since the process of following up such trials is very time-consuming, it calls for revisiting several of the methods for performing both randomized, and other clinical trials. We present system for electronic management of clinical studies that addresses many of the time-consuming challenges, which additionally address many of the quality assurance aspects. We also present results from testing the system in two studies with 50 and 8 participants. Miroslav Muzny Meghan Bradway Håvard Blixgård Eirik Årsand Copyright (c) 2022 Miroslav Muzny, Meghan Bradway, Håvard Blixgård, Eirik Årsand https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 187 194 10.3384/ecp187031 https://ecp.ep.liu.se/index.php/shi/article/view/460 Many in health and technology research opt to focus on those who are already “engaged”, not those who are considered “hard-to-reach” or “unreached”. This exacerbates the digital divide and inequity in healthcare. We report findings of a scoping review of literature in PubMed/Medline from 2000-2022. 90 of 795 articles were identified based upon 1) the health researchers’ recruitment of unreached groups with a chronic condition for active participation in a study and 2) clear definitions of who they considered to be unreached. Findings support the need for interdisciplinary and community-level involvement to reach and include unreached groups in health studies. Meghan Bradway Henriette Nybakke Stine Ingebrigsten Kari Dyb Copyright (c) 2022 Meghan Bradway, Henriette Nybakke, Stine Ingebrigsten, Kari Dyb https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 195 202 10.3384/ecp187032 https://ecp.ep.liu.se/index.php/shi/article/view/461 The concept of conditional method agreement is introduced and respective solutions are proposed to define homogeneous subgroups in terms of mean and variance of the differences in measurements. Siranush Karapetyan Alexander Hapfelmeier Copyright (c) 2022 Siranush Karapetyan, Alexander Hapfelmeier https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 204 205 10.3384/ecp187033 https://ecp.ep.liu.se/index.php/shi/article/view/462 The present systematic review aims to provide an overview and categorization of dose guidance methods that support basal insulin titration for people with type 2 diabetes. At the time of writing, quality assessment of the included articles is ongoing. Camilla Heisel Nyholm Thomsen Stine Hangaard Thomas Kronborg Peter Vestergaard Ole Hejlesen Morten Hasselstrøm Jensen Copyright (c) 2022 Camilla Heisel Nyholm Thomsen, Stine Hangaard, Thomas Kronborg, Peter Vestergaard, Ole Hejlesen, Morten Hasselstrøm Jensen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 206 207 10.3384/ecp187034 https://ecp.ep.liu.se/index.php/shi/article/view/463 The treatment goal in type 2 diabetes (T2D) is to keep the blood glucose within a target range. In the early stages of diabetes, the treatment may consist entirely of oral antidiabetics (OAD), which may be preferable over injectables for some people. However, previously published systematic reviews found a low OAD adherence and that the adherence differs between different OAD types. These systematic reviews were performed before 2015, and several new OADs have been marketed since then. Thus, a systematic review will be undertaken to review the newest studies on adherence to oral second line antidiabetics in people with T2D. Nynne Sophie Holdt-Caspersen Stine Hangaard Casper Peter Vestergaard Claus Dethlefsen Morten Hasselstrøm Jensen Copyright (c) 2022 Nynne Sophie Holdt-Caspersen, Stine Hangaard Casper, Peter Vestergaard, Claus Dethlefsen, Morten Hasselstrøm Jensen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 208 209 10.3384/ecp187035 https://ecp.ep.liu.se/index.php/shi/article/view/464 Successful e-Health system engineering mainly depends on accurate and complete modelling of the HealthCare (HC) processes. These HC service processes are governed by a variety of regulations and rules enforced by many distinct authorities. Availability of these governance directives mostly on paper based-medium makes a bunch of information logistics and related issues in HC processes of e-Health systems. Further, even captured such directives are getting often buried in lower technical realizations making its impossible not only real-time adoption but also manipulation on long run by respective non-technical higher authorities. In order to rectify and to facilitate these stakeholders’ requirements for assistance with their access to these governing layers of e-Health solutions, in this work, we have proposed a three-dimensional ontological framework. This framework is expected to provide a complete and sound platform first to identify and then to develop eHealth solutions in compliance with those governing directives. In addition, it will ensure making convenient access with the non-technical higher healthcare authorities to monitoring and to governing HC processes. Proposed framework consists of three dimensions; 1) HC process activity dimension, 2) HC responsibility dimension and 3) HC directive enforcement dimension. The proposed approach facilitates the separation of concerns in HC governing perspectives in e-health solution development. Gilmini Dantanarayana Prasad Jayaweera Copyright (c) 2022 Gilmini Dantanarayana, Prasad Jayaweera https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 210 211 10.3384/ecp187036 https://ecp.ep.liu.se/index.php/shi/article/view/465 The objective is to describe how the uptake of online video consultations was affected by the Covid-19 pandemic, using data from a Swedish primary care setting. There seem to be a relationship between the use of video consultations and spread of Covid-19, especially in 2020 when the use varied more with the contagion waves. In 2021 the use was more consistent over time. In summary, the Covid-19 pandemic had a direct impact on the adoption of video consultations in our primary care setting, yet after the initial high use, it appears to have stabilized on a lower level. Lovisa Jäderlund Hagstedt Maria Hägglund Göran Petersson Nadia Davoody Helena Hvitfeldt Copyright (c) 2022 Lovisa Jäderlund Hagstedt, Maria Hägglund, Göran Petersson, Nadia Davoody, Helena Hvitfeldt https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 212 213 10.3384/ecp187037 https://ecp.ep.liu.se/index.php/shi/article/view/466 Study investigating the validity of a contactless monitor during sleep. Overall, the contactless monitor seems to be a valid method for monitoring vital parameters, even though parameters such as position and number of people in bed might have implications for monitoring. Tanja Fredensborg Holm Julie Egmose Katrine Holmstrup Sørensen Ole Hejlesen Morten Hasselstrøm Jensen Stine Hangaard Copyright (c) 2022 Tanja Fredensborg Holm, Julie Egmose, Katrine Holmstrup Sørensen, Ole Hejlesen, Morten Hasselstrøm Jensen, Stine Hangaard https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 214 215 10.3384/ecp187038 https://ecp.ep.liu.se/index.php/shi/article/view/467 The PEPPPSY(Pilot Testing and Evaluation of Participatory Patient Record in Psychiatric Care) project is a new initiative from the Digital Health group of the Centre for Health Services Research in Brandenburg. PEPPPSY stands for “Pilot Testing and Evaluation of a Participatory Patient Record in Psychiatric Care”. The project is based on the United States-based initiative, OpenNotes[1], an international movement promoting and studying transparent communication in healthcare. The project is created with open communication in mind, as it aims towards giving patients insight into their treatments by accessing their psychiatric records. This will hopefully increase trust, engagement, and understanding of both themselves and the therapeutic process. Molly Gibson Magne Halvorsen Mikkel Angelo Anchissi Joner Mari Lehne Elise Rabassa Stautland Gustaf Svensson Hanna Thevik Georgia Fehler Stefan Hochwarter Copyright (c) 2022 Molly Gibson, Magne Halvorsen, Mikkel Angelo Anchissi Joner, Mari Lehne, Elise Rabassa Stautland, Gustaf Svensson, Hanna Thevik, Georgia Fehler, Stefan Hochwarter https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 216 217 10.3384/ecp187039 https://ecp.ep.liu.se/index.php/shi/article/view/468 A systematic review will be conducted to update the evidence base and provide an overview of insulin adherence quantification in adults with insulin-treated type 2 diabetes, i.e., the methods used to assess insulin adherence and the cut-off points that constitute adequate insulin adherence. Jannie Toft Damsgaard Nørlev Morten Hasselstrøm Jensen Ole Hejlesen Tinna Björk Aradóttir Nicholas William Ciccone Stine Hangaard Copyright (c) 2022 Jannie Toft Damsgaard Nørlev, Morten Hasselstrøm Jensen, Ole Hejlesen, Tinna Björk Aradóttir, Nicholas William Ciccone, Stine Hangaard https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 218 219 10.3384/ecp187040 https://ecp.ep.liu.se/index.php/shi/article/view/469 A usability study exploring the usability of a contactless monitoring system used during sleep. Overall, the participants found the contactless monitor easy and satisfying, but further improvements to the user manual and design might optimize the usability of the monitor. Katrine Holmstrup Sørensen Tanja Fredensborg Holm Julie Egmose Ole Hejlesen Morten Hasselstrøm Jensen Stine Hangaard Copyright (c) 2022 Katrine Holmstrup Sørensen, Tanja Fredensborg Holm, Julie Egmose, Ole Hejlesen, Morten Hasselstrøm Jensen, Stine Hangaard https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 220 221 10.3384/ecp187041 https://ecp.ep.liu.se/index.php/shi/article/view/470 This extended abstract describes the plan and status of a PhD project using a design science research approach to explore how to design digital psychosocial follow-up for survivors of childhood critical illness. Marte Hoff Hagen Copyright (c) 2022 Marte Hoff Hagen https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 222 223 10.3384/ecp187042 https://ecp.ep.liu.se/index.php/shi/article/view/471 In this work, we propose an encoder-decoder-based automatic report generation system capable of generating radiology reports for chest x-rays. We tested five backbone Convolutional Neural Networks, namely VGG16, InceptionV3, Resnet50, MobileNet and NasNet mobile, to extract visual features and used Long Short-Term Long Memory (LSTM) to extract the text features from the reports. Both features are concatenated and given to a deep network for report generation. We performed experiments on publicly available Indiana University’s NLMCXR dataset. We evaluated our system against different backbones and evaluated accuracy and BLEU score. The result showed that our method achieved reliable and convincing results. Muhammad Kamran Mohib Ullah Ali Shariq Imran Muhammad Sajjad Copyright (c) 2022 Muhammad Kamran, Mohib Ullah, Ali Shariq Imran, Muhammad Sajjad https://creativecommons.org/licenses/by/4.0/ 2022-08-22 2022-08-22 224 225 10.3384/ecp187043