| 1. |
- Bergquist, Magnus, 1960-, et al.
(författare)
-
OSMaaS Toolkit : Designing Open and Self Organising Mechanisms for Sustainable Mobility as a Service
- 2024
-
Rapport (populärvet., debatt m.m.)abstract
- The project Open and Self Organizing Mechanisms for Sustainable Mobility as a Service (OSMaaS) ran between 2020 and 2024, hosted by Halmstad University and funded by The Knowledge Foundation. The project was a collaboration between researchers from service design, design ethnography, business model innovation, and intelligent systems, and the companies Volvo Cars, WirelessCar, Polestar, and Devoteam. One of the project’s outputs is the OSMaaS Service Design Framework that integrates research from the different activities in the project into a toolkit for service designers. This booklet provides a guide for how to apply the framework. Each canvas can be used standalone or in any order, but our experience is that the framework is most powerful when following the design process presented here. The canvases can be downloaded from the OSMaaS webpage and are free to use.
|
|
| 2. |
- Eeg-Olofsson, Måns, 1967, et al.
(författare)
-
TTCOV19: timing of tracheotomy in SARS-CoV-2-infected patients: a multicentre, single-blinded, randomized, controlled trial
- 2022
-
Ingår i: Critical Care. - : Springer Science and Business Media LLC. - 1364-8535. ; 26:1
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Critically ill COVID-19 patients may develop acute respiratory distress syndrome and the need for respiratory support, including mechanical ventilation in the intensive care unit. Previous observational studies have suggested early tracheotomy to be advantageous. The aim of this parallel, multicentre, single-blinded, randomized controlled trial was to evaluate the optimal timing of tracheotomy. Methods: SARS-CoV-2-infected patients within the Region Vastra Gotaland of Sweden who needed intubation and mechanical respiratory support were included and randomly assigned to early tracheotomy (<= 7 days after intubation) or late tracheotomy (>= 10 days after intubation). The primary objective was to compare the total number of mechanical ventilation days between the groups. Results: One hundred fifty patients (mean age 65 years, 79% males) were included. Seventy-two patients were assigned to early tracheotomy, and 78 were assigned to late tracheotomy. One hundred two patients (68%) underwent tracheotomy of whom sixty-one underwent tracheotomy according to the protocol. The overall median number of days in mechanical ventilation was 18 (IQR 9; 28), but no significant difference was found between the two treatment regimens in the intention-to-treat analysis (between-group difference:- 1.5 days (95% CI -5.7 to 2.8); p= 0.5). A significantly reduced number of mechanical ventilation days was found in the early tracheotomy group during the per-protocol analysis (between-group difference: - 8.0 days (95% CI - 13.8 to - 2.27); p= 0.0064). The overall correlation between the timing of tracheotomy and days of mechanical ventilation was significant (Spearman's correlation: 0.39, p < 0.0001). The total death rate during intensive care was 32.7%, but no significant differences were found between the groups regarding survival, complications or adverse events. Conclusions: The potential superiority of early tracheotomy when compared to late tracheotomy in critically ill patients with COVID-19 was not confirmed by the present randomized controlled trial but is a strategy that should be considered in selected cases where the need for MV for more than 14 days cannot be ruled out.
|
|
| 3. |
|
|
| 4. |
|
|
| 5. |
- Aghanavesi, Somayeh, 1981-, et al.
(författare)
-
A multiple motion sensors index for motor state quantification in Parkinson's disease
- 2020
-
Ingår i: Computer Methods and Programs in Biomedicine. - : Elsevier BV. - 0169-2607 .- 1872-7565. ; 189
-
Tidskriftsartikel (refereegranskat)abstract
- Aim: To construct a Treatment Response Index from Multiple Sensors (TRIMS) for quantification of motor state in patients with Parkinson's disease (PD) during a single levodopa dose. Another aim was to compare TRIMS to sensor indexes derived from individual motor tasks. Method: Nineteen PD patients performed three motor tests including leg agility, pronation-supination movement of hands, and walking in a clinic while wearing inertial measurement unit sensors on their wrists and ankles. They performed the tests repeatedly before and after taking 150% of their individual oral levodopa-carbidopa equivalent morning dose.Three neurologists blinded to treatment status, viewed patients’ videos and rated their motor symptoms, dyskinesia, overall motor state based on selected items of Unified PD Rating Scale (UPDRS) part III, Dyskinesia scale, and Treatment Response Scale (TRS). To build TRIMS, out of initially 178 extracted features from upper- and lower-limbs data, 39 features were selected by stepwise regression method and were used as input to support vector machines to be mapped to mean reference TRS scores using 10-fold cross-validation method. Test-retest reliability, responsiveness to medication, and correlation to TRS as well as other UPDRS items were evaluated for TRIMS. Results: The correlation of TRIMS with TRS was 0.93. TRIMS had good test-retest reliability (ICC = 0.83). Responsiveness of the TRIMS to medication was good compared to TRS indicating its power in capturing the treatment effects. TRIMS was highly correlated to dyskinesia (R = 0.85), bradykinesia (R = 0.84) and gait (R = 0.79) UPDRS items. Correlation of sensor index from the upper-limb to TRS was 0.89. Conclusion: Using the fusion of upper- and lower-limbs sensor data to construct TRIMS provided accurate PD motor states estimation and responsive to treatment. In addition, quantification of upper-limb sensor data during walking test provided strong results. © 2019
|
|
| 6. |
- Ali, Abid, et al.
(författare)
-
Conversational Artificial Intelligence (AI) in the Healthcare Industry
- 2023
-
Ingår i: The 15th Mediterranean Conference on Information Systems (MCIS). - Madrid, Spain. ; , s. 1-17
-
Konferensbidrag (refereegranskat)abstract
- The study presents an innovative approach to incorporating AI-driven conversational agents (CAs) orsocial robots technologies into healthcare information systems (HISs) and revolutionizing healthcaredelivery systems. The study aims to improve accessibility and personalization, and minimize adverserisks, especially in the emergency departments (EDs). The study investigates patient-relatedexperiences, long waiting times, and overcrowding issues during peak hours in EDs. Design scienceresearch methodology (DSRM) principles were tailored with modelling workshop method to capturedomain contextual knowledge and include practitioners' cognitive-tacit knowledge-ability into HIS toaddress the above-mentioned issues. The developed social robot artifact incorporates an artificialintelligence markup language (AIML) technique as a model to restore domain knowledge of EDs,which serves as a foundation for developing goal-oriented interactive conversational system artifactbetween humans and machines. As a result, the study contributes that CAs, considered value-addedAI-driven applications such as CAs or social robots, serve as a coworker to facilitate healthcarepractitioners and patients, catering to patients' needs and communication to enhance care deliveryexperience and improve information flow processes using interactive services within EDs. Theresearch presents a promising solution to improve patient outcomes, reduce waiting times, andenhance communication between patients and practitioners in EDs.
|
|
| 7. |
- Ali Fareedi, Abid, 1978-, et al.
(författare)
-
Artificial Intelligence Agents and Knowledge Acquisition in Health Information System
- 2022
-
Ingår i: MCIS 2022 Proceedings.
-
Konferensbidrag (refereegranskat)abstract
- This research work highlights the need for AI-powered applications and their usages for the optimization of information flow processes in the medical sector, from the perspective of how AI-agents can impact human-machine interaction (HCI) for acquiring relevant and necessary information in emergency department (ED). This study investigates how AI-agents can be applied to manage situations of patient related unexpected experiences, such as long waiting times, overcrowding issues, and high number of patients leaving without being diagnosed. For knowledge acquisition, we incorporated modelling workshop techniques for gathering domain information from the domain experts in the context of emergency department in Karolinska Hospital, Solna, Stockholm, Sweden, and for designing the AI-agent utilizing NLP techniques. We discuss how the proposed solution can be used as an assistant to healthcare practitioners and workers to improve medical assistance in various medical procedures to increase flow and to reduce workloads and anxiety levels. The implementation part of this work is based on the natural language processing (NLP) techniques that help to develop the intelligent behavior for information acquisition and its retrieval in a natural way to support patients/relatives’ communication with the healthcare organization efficiently and in a natural way.
|
|
| 8. |
- Ali Fareedi, Abid, 1978-, et al.
(författare)
-
The Utilization of Artificial Intelligence for Developing Autonomous Social Robots within Health Information Systems
- 2023
-
Ingår i: CEUR Workshop Proceedings. - : CEUR-WS. ; , s. 34-50
-
Konferensbidrag (refereegranskat)abstract
- This study focuses on using AI systems, specifically conversational agents (CAs), to improve information flow during peak hours in healthcare emergency departments (EDs). We customized a Cross Industry Standard Process for Data Mining CRISP-DM approach to a CRISP-Knowledge graph (CRISP-KG) for overall design research. We use a knowledge graph approach to create an intelligent knowledge base (KBs) for CAs, which can enhance their reasoning, knowledge management, and context awareness abilities. We employ a collaborative methodology and ontology design patterns to develop a formal ontological model. Our goal is to build intelligent KBs for CAs that can interact with end-users and improve care quality in EDs, using Semantic Web Rule Language (SWRL) for inference. The KG approach can assist healthcare practitioners and patients in managing information flow more efficiently in EDs, ultimately improving care outcomes. © 2023 CEUR-WS. All rights reserved.
|
|
| 9. |
- Ali Fareedi, Abid, 1978-, et al.
(författare)
-
Value Added Conversational AI and Digital Health : An Ontology-Driven Approach
- 2024
-
Ingår i: Proceedings of the 57th Hawaii International Conference on System Sciences. - Honolulu : University of Hawai'i at Manoa. - 9780998133171 ; , s. 4010-4019
-
Konferensbidrag (refereegranskat)abstract
- AI-based assistants, such as conversational agents (CAs) and social robots, are becoming increasingly important in healthcare organizations. CAs provide a scalable and cost-effective platform for organizations supporting their employees by retrieving, structuring, and analyzing information to assist work processes. This study targets how knowledge graphs as ontological models manage CA that help improve the patient flow processes and reduce patients’ waiting time in the emergency departments (EDs). We tailored the design thinking (DT) method with modelling workshops employing conceptual modelling (CM) techniques to address these issues. We incorporated a hybrid formal approach of Methontology and Tove methodologies to build design artifacts, develop a goal-oriented interactive conversational system between humans and machines, and support information systems (IS). As a result, this ontology-driven approach contribution helps developers build value-added CAs to facilitate healthcare practitioners and patients. It is helpful for quality care delivery experience and improves bottlenecks in information flow within Eds.
|
|
| 10. |
- Bergquist, Ann-Kristin, et al.
(författare)
-
Creating Value Out of Waste : The Transformation of the Swedish Waste and Recycling Sector, 1970s–2010s
- 2023
-
Ingår i: Business history review. - : Cambridge University Press. - 0007-6805 .- 2044-768X. ; 97:1, s. 3-31
-
Tidskriftsartikel (refereegranskat)abstract
- This article examines the growth of the waste and recycling sector in Sweden since the 1970s and seeks to identify the conditions for market growth and underlying business dynamics. The article identifies a slow growth pattern at aggregate level in the 1970s, while a major shift toward higher growth rates took place only in the mid-1990s. Resembling the findings of existing studies of German and US industry counterparts, Swedish recycling companies grew larger in the 1970s and more knowledge-intensive from the 1980s. Our study concludes that the growth of the Swedish recycling industry has been driven not only by government policies addressing household waste but even more so by large manufacturing firms that have increasingly demanded more complex recycling services over time.
|
|
