Decision Support for Healthcare Processes and Services

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 9 of 9
  • Item
    Investigating User Satisfaction: An Adaptation of IS Success Model for Short-term Use
    ( 2023-01-03) Zhang, Lidan ; Tulu, Bengisu ; Djamasbi, Soussan ; Sankar, Gaayathri ; Muehlschlegel, Susanne
    Research investigating the acceptance of information systems mostly focuses on systems designed for long-term use, rather than one-time or short-term use. However, short-term use systems are part of the health information technology portfolio. We propose a theoretical model inspired by the D&M IS Success Model to investigate user satisfaction, as a measure of acceptance, with a web-based decision aid designed for short-term decision-making. We hypothesize that media richness affects perceived usefulness, perceived ease of use, learnability, information quality, perceived social presence, and trust, which eventually affect user satisfaction. We propose a mixed method to test hypotheses using eye-tracking, surveys, and interviews. As a pilot qualitative study (N=8), the survey outcomes indicated that constructs performed well (mean 7-point Likert scores >= 5.15 and mean system usability scale = 75). The eye-tracking and interview results showed that participants prefer multimedia, and pictures and visual designs drew their attention to the decision aid website.
  • Item
    Feedback on Shopping Receipt Data Through a Mobile App: A Pilot Study
    ( 2023-01-03) Lurz, Martin ; Esterbauer, Alexander ; Böhm, Markus ; Krcmar, Helmut
    Mobile applications have become popular tools for supporting healthy nutrition behavior. Current tools are primarily based on the detailed tracking of a user’s direct consumption, thus intervening only during or even after a user has eaten something. With increasing home office hours (especially during the COVID-19 pandemic), people are eating more often at home, which has also led to a decrease in fruit and vegetable consumption. Therefore, we aim to support people in the food-shopping process. We suggest a mobile application that helps people reflect on their purchases and tries to nudge users toward healthier product choices. We conducted a pilot study with 31 participants who used the application for two consecutive weeks. During this time, we observed a decrease in the caloric values per 100 g of purchases. Furthermore, we collected positive feedback on the app regarding acceptance, usability, and user experience.
  • Item
    DiGA, an Innovation Made in Germany -- Status Quo and a Perspective of Potential Users
    ( 2023-01-03) Jacquemin, Philippe ; Reuter-Oppermann, Melanie
    The German health care system has to face raising costs, an increase in demand as well as a shortage of staff, making an efficient use of resources as well as the design of innovative services and digital solutions necessary. Even though the digitalization of the health care system is far behind, Germany was the first country to integrate DiGA, a special form of digital health apps, into the health care market. While this is a very promising development, it is still unclear whether patients actually know about these apps and if processes are efficient enough to promise a significant benefit to them. Therefore, we discuss the different stakeholders and performed an online survey with 262 participants from Germany to study the patients's view on DiGA. The results show that their intention to use is high, but many are not aware of the actual DiGA offered.
  • Item
    Introduction to the Minitrack on Decision Support for Healthcare Processes and Services
    ( 2023-01-03) Reuter-Oppermann, Melanie ; Walker, Cameron ; Furian, Nikolaus
  • Item
    Using Task Technology Fit Theory to Guide the Codesign of Mobile Clinical Decision Support Systems
    ( 2023-01-03) Ulapane, Nalika ; Forkan, Abdur Rahim Mohammad ; Jayaraman, Prem Prakash ; Schofield, Penelope ; Burbury, Kate ; Wickramasinghe, Nilmini
    A clinical decision support system (CDSS) is designed to assist health professionals in perioperative patient management. Robust CDSSs are vital to deliver enhanced healthcare services. Incorporating the latest advancements in digital technologies, mobile device based CDSSs are being introduced to healthcare settings at a considerable pace. However, given the nascency of this tech-health synergy, well-defined systematic approaches to be followed to design and develop mobile CDSSs to ensure developed technological solutions are of best fit-for-purpose, are lacking. To address this void, this study proposes an approach combining Task Technology Fit theory and Design Science Research Methodology, to guide the design and development of mobile CDSSs. The proposed approach is applied to a case study to design a mobile CDSS to assist perioperative optimization of surgery patients. The learnings from the case study are reported.
  • Item
    Binary Models for Arboviruses Classification Using Machine Learning: A Benchmarking Evaluation
    ( 2023-01-03) Da Silva Neto, Sebastião Rogerio ; Tabosa, Thomás ; Medeiros Neto, Leonides ; Teixeira, Igor Vitor ; Sadok, Sara ; De Souza Sampaio, Vanderson ; Endo, Patricia Takako
    Arboviral diseases are common worldwide. Infection with arboviruses can lead to serious health problems, even death in severe cases. Such health problems can be prevented by the early and correct detection of these arboviruses, but this is challenging due to the overlap of their symptoms. In this work, we benchmark different Machine Learning (ML) models to classify two types of arboviruses. We propose two distinct binary models: (i) a model to classify if the patient has arbovirus or another disease; and (ii) a model to classify if the patient has Dengue or Chikungunya. We configure and evaluate several ML models using hyperparameter optimization and feature selection techniques. The Random Forest and XGboost tree-based models present the best results with over 80% recall in the Chikungunya and Inconclusive classes.
  • Item
    Understanding the Role of Expert Intuition in Medical Image Annotation: A Cognitive Task Analysis Approach
    ( 2023-01-03) Leiser, Florian ; Warsinsky, Simon ; Daum, Marie ; Schmidt-Kraepelin, Manuel ; Thiebes, Scott ; Wagner, Martin ; Sunyaev, Ali
    To improve contemporary machine learning (ML) models, research is increasingly looking at tapping in and incorporating the knowledge of domain experts. However, expert knowledge often relies on intuition, which is difficult to formalize for incorporation into ML models. Against this backdrop, we investigate the role of intuition in the context of expert medical image annotation. We apply a cognitive task analysis approach, where we observe and interview six expert medical image annotators to gain insights into pertinent decision cues and the role of intuition during annotation. Our results show that intuition plays an important role in various steps of the medical image annotation process, particularly in the appraisals of very easy or very difficult images, and in case purely cognitive appraisals remain inconclusive. Overall, we contribute to a better understanding of expert intuition in medical image annotation and provide possible interfaces to incorporate said intuition into ML models.
  • Item
    Reconsidering Bipolar Scales Data As Compositional Data Improves Psychometric Healthcare Data Analytics
    ( 2023-01-03) Lehmann, Rene ; Vogt, Bodo
    Correct psychometric profiling and the choice of adequate therapeutic measures are the basis of any psychotherapeutic treatment. The preparation of a correct psychological profile benefits the patient and saves time and costs. Regarding psychometric questionnaires it is common practice to consider data of bipolar scales as interval scaled. This paper reveals the true compositional data structure (namely the Simplex) with respect to the psychometric limit of quantification of bipolar traits and constructs. The Simplex heavily affects the set of statistical procedures applicable. Disregarding the Simplex causes serious bias and results in erroneous standards and standard deviations, biased correlations, reduced convergent validity and a loss of statistical power. In this paper, the isometric log-ratio (ilr) transformation is suggested. It transforms Simplex data towards the interval scale and provides unbiased results, e.g., standards. By means of a simulation study, this paper shows that up to an 18\% increase in the statistical power of the well-known correlation test based on Student's t-distribution can be achieved. As the statistical power increases the sample size of psychometric studies can be reduced resulting in lower data collection costs. Besides economic and psychotherapeutic aspects, the results of the simulation study generalize from correlation analysis towards a larger set of standard statistical procedures. For example, testing the hypothesis of equality of the two means of independent samples using a t-test based on Student's t distribution is equivalent to testing the hypothesis of a null-correlation between the binary grouping variable and the dependent variable. Furthermore, the coefficient of correlation contributes to the slope of a regression line. Thus, the ilr approach also affects linear regression techniques.
  • Item
    Realizing the Value Potential of AI in Service Needs Assessment: Cases in Child Welfare and Mental Health Services
    ( 2023-01-03) Pesonen, Kaisa ; Korpela, Jukka ; Vilko, Jyri ; Elfvengren, Kalle
    In social and health care the use of technology that utilizes data has great potential from the point of view of value creation. This case study examines the factors that impact the value potential realization of AI prediction models as part of the customer/patient service need assessment process. The research focuses on a pilot project of a Finnish case organization, in which prediction models were tested in child welfare and mental health services. Both positive and negative value-realizing factors were found in the research. The information produced by artificial intelligence has great value potential. Regulation and transparency of data need to be addressed, but at the same time, more flexible use of social and health register data needs to be considered to ensure that resources are allocated in a value-added way.