Anna Bakidou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Anna Bakidou has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Bengt Arne Sjöqvist
Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden
4 shared publications - Stefan Candefjord
Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden
4 shared publications - Mattias Seth
Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden
3 shared publications - Anders Jonsson
PreHospen - Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, Borås, Sweden
2 shared publications - Eva-Corina Caragounis
Department of Surgery, Institute of Clinical Sciences, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden
2 shared publications - Magnus Andersson Hagiwara
PreHospen - Centre for Prehospital Research, Faculty of Caring Science, Work Life and Social Welfare, University of Borås, Borås, Sweden
2 shared publications
Latest Publications
- Open Access
- 24 July 2026
- Published by Springer Nature in Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine
- Vol. 34 (1) , 129
Evaluating performance and potential clinical benefit of the Swedish On Scene Injury Severity Prediction (OSISP) model for prehospital field triage on Norwegian trauma data
Background: Rule-based field triage protocols used by Emergency Medicine Service (EMS) personnel for assessment and prioritization of trauma patients achieve suboptimal field triage performance. An On Scene Injury Severity Prediction (OSISP) model was previously developed on Swedish trauma data with indications to improve field triage performance. This study aims to apply OSISP on external Norwegian data to assess its performance and clinical impact on unseen data. Methods: Adult trauma incidents involving EMS resources at the scene of incident were included. An eXtreme Gradient Boosting OSISP model was developed on Swedish trauma registry (SweTrau) data for 2013–2020 and trained to predict severely injured patients defined as new injury severity score (NISS) > 15. OSISP was evaluated on Norwegian trauma registry (NTR) data for 2017–2022. The model performance on NTR data was evaluated using overall performance measures for discrimination and calibration (receiver operating characteristic curve, precision-recall curve, area under these curves, Brier score, calibration curve, calibration slope, calibration in the large). OSISP’s clinical impact was assessed by evaluating its under- and overtriage rates and comparing to current clinical outcome and mortality. Results: The raw data from SweTrau and NTR had 75,602 and 76,529 registrations, with 47,357 and 29,709 remaining after applying eligibility criteria. In the included data, there were 16.9% and 25.2% patients with NISS > 15 in SweTrau and NTR, respectively. The OSISP predictors represented age, sex, details of the patient’s condition, incident and injury details, vital signs, and administrative details. OSISP applied on NTR data yielded an overall performance of AUC ROC =0.83, AUC PR =0.64, Brier score = 0.14, calibration slope = 0.79, and calibration in the large=–0.09. On its own, OSISP reduced undertriage to 5.0% but increased overtriage to 61.0%, while the complementary use (NTR’s triage outcomes combined with OSISP’s predictions) reduced undertriage to 2.7%, overtriage to 19.7% (compare to current clinical practice with an undertriage = 56.0% and overtriage = 30.6%), and mortality from 4.1% to 3.4–3.5%. Conclusions: OSISP’s overall performance was successfully validated and a potential capability to improve triage and decrease mortality was observed, also for elderly and patients from the northern region, groups often missed with current triage tools. Registration: Not applicable. Trial registration: Not applicable.
- 24 July 2026
- Published by Springer Nature in Scandinavian Journal of Trauma, Resuscitation and Emergency Medicine
- Vol. 34 (1) , 129
Open AccessEvaluating performance and potential clinical benefit of the Swedish On Scene Injury Severity Prediction (OSISP) model for prehospital field triage on Norwegian trauma data
Background: Rule-based field triage protocols used by Emergency Medicine Service (EMS) personnel for assessment and prioritization of trauma patients achieve suboptimal field triage performance. An On Scene Injury Severity Prediction (OSISP) model was previously developed on Swedish trauma data with indications to improve field triage performance. This study aims to apply OSISP on external Norwegian data to assess its performance and clinical impact on unseen data. Methods: Adult trauma incidents involving EMS resources at the scene of incident were included. An eXtreme Gradient Boosting OSISP model was developed on Swedish trauma registry (SweTrau) data for 2013–2020 and trained to predict severely injured patients defined as new injury severity score (NISS) > 15. OSISP was evaluated on Norwegian trauma registry (NTR) data for 2017–2022. The model performance on NTR data was evaluated using overall performance measures for discrimination and calibration (receiver operating characteristic curve, precision-recall curve, area under these curves, Brier score, calibration curve, calibration slope, calibration in the large). OSISP’s clinical impact was assessed by evaluating its under- and overtriage rates and comparing to current clinical outcome and mortality. Results: The raw data from SweTrau and NTR had 75,602 and 76,529 registrations, with 47,357 and 29,709 remaining after applying eligibility criteria. In the included data, there were 16.9% and 25.2% patients with NISS > 15 in SweTrau and NTR, respectively. The OSISP predictors represented age, sex, details of the patient’s condition, incident and injury details, vital signs, and administrative details. OSISP applied on NTR data yielded an overall performance of AUC ROC =0.83, AUC PR =0.64, Brier score = 0.14, calibration slope = 0.79, and calibration in the large=–0.09. On its own, OSISP reduced undertriage to 5.0% but increased overtriage to 61.0%, while the complementary use (NTR’s triage outcomes combined with OSISP’s predictions) reduced undertriage to 2.7%, overtriage to 19.7% (compare to current clinical practice with an undertriage = 56.0% and overtriage = 30.6%), and mortality from 4.1% to 3.4–3.5%. Conclusions: OSISP’s overall performance was successfully validated and a potential capability to improve triage and decrease mortality was observed, also for elderly and patients from the northern region, groups often missed with current triage tools. Registration: Not applicable. Trial registration: Not applicable.
- 1 January 2026
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 35 (2)
FHIR Data Mapping Quality Assessment: A Scoping Review and Expert-Informed Requirements for Future Pre-Mapping Frameworks
Background: Healthcare systems increasingly rely on effective data sharing to support safe and efficient care. The fast healthcare interoperability resources (FHIR) standard provides a widely adopted framework for interoperability. However, many existing healthcare information systems predate FHIR and require translation or mapping of their data models and data elements to the FHIR standard to enable interoperability. Despite growing FHIR adoption, robust approaches for assessing mapping quality remain limited. Objective: This scoping review aimed to identify and synthesize existing tools and approaches for evaluating FHIR data mapping quality, examine methodological challenges and gaps, and formulate and refine requirements for more consistent and transparent assessment. Methods: A scoping review was conducted across IEEE Xplore, ACM Digital Library, PubMed, and the JMIR journal family. Studies were screened using predefined eligibility criteria and analyzed through thematic synthesis focusing on mapping tools, validation approaches, challenges, and quality assessment dimensions. FHIR mapping quality was conceptualized using 7 quality dimensions adapted from data quality literature. Candidate framework requirements were formulated and refined through expert consultation ( n = 4). Results: A total of 742 studies were screened and 39 included. The literature revealed fragmented practices with limited consensus on FHIR mapping quality assessment. Most studies relied on manual evaluation of the transformed data, while few considered source-to-target relationships before transformation. Six requirements for future pre-mapping quality assessment frameworks were formulated and refined. Conclusions: Current FHIR mapping quality assessment approaches remain fragmented and largely rely on manual evaluation. The findings highlight the need for more transparent and formalized pre-mapping assessment approaches to support future FHIR implementations.
- 1 January 2026
- Published by American Association for the Advancement of Science (AAAS) in Computational and Structural Biotechnology Journal
- Vol. 35 (2)
FHIR Data Mapping Quality Assessment: A Scoping Review and Expert-Informed Requirements for Future Pre-Mapping Frameworks
Background: Healthcare systems increasingly rely on effective data sharing to support safe and efficient care. The fast healthcare interoperability resources (FHIR) standard provides a widely adopted framework for interoperability. However, many existing healthcare information systems predate FHIR and require translation or mapping of their data models and data elements to the FHIR standard to enable interoperability. Despite growing FHIR adoption, robust approaches for assessing mapping quality remain limited. Objective: This scoping review aimed to identify and synthesize existing tools and approaches for evaluating FHIR data mapping quality, examine methodological challenges and gaps, and formulate and refine requirements for more consistent and transparent assessment. Methods: A scoping review was conducted across IEEE Xplore, ACM Digital Library, PubMed, and the JMIR journal family. Studies were screened using predefined eligibility criteria and analyzed through thematic synthesis focusing on mapping tools, validation approaches, challenges, and quality assessment dimensions. FHIR mapping quality was conceptualized using 7 quality dimensions adapted from data quality literature. Candidate framework requirements were formulated and refined through expert consultation ( n = 4). Results: A total of 742 studies were screened and 39 included. The literature revealed fragmented practices with limited consensus on FHIR mapping quality assessment. Most studies relied on manual evaluation of the transformed data, while few considered source-to-target relationships before transformation. Six requirements for future pre-mapping quality assessment frameworks were formulated and refined. Conclusions: Current FHIR mapping quality assessment approaches remain fragmented and largely rely on manual evaluation. The findings highlight the need for more transparent and formalized pre-mapping assessment approaches to support future FHIR implementations.
- Open Access
- 1 May 2025
- Published by SAGE Publications in Digital Health
- Vol. 11
Human–AI collaboration for prehospital trauma triage: Designing the On Scene Injury Severity Prediction (OSISP) model as a clinical decision support system
Objective: This study aims to advance the On Scene Injury Severity Prediction (OSISP), an Artificial Intelligence (AI)-based model, as a Clinical Decision Support System (CDSS) that supports Emergency Medical Service (EMS) personnel during on-scene assessment of adult trauma patients. The objectives are to explore the integration of OSISP with the prehospital trauma workflow and to refine the User Interface (UI) that communicates the predictions. Methods: Workflow integration was studied in a workshop by analysis of a customer journey map created by personnel with experience of working in the EMS setting ( n = 8). Literature reviews were conducted to identify key factors enabling efficient human–AI collaboration and implementation options. Identified UI components derived from workshop and literature review findings were then evaluated and selected to refine the OSISP UI. Results: The workshop derived that OSISP is a service to be used on portable IT platforms as a second opinion, support for prioritization, and support during patient assessment. The literature reviews identified key content, characteristics, and goals of communicating predictions to users. The refined UI consisted of eight information components (prediction, entered predictors, missing predictors, and model details), and four functions (notification, exploration mode, and filtering of top three entered and missing predictors), to communicate the OSISP prediction. Conclusions: The refined OSISP UI has potential to integrate well into the clinical workflow during patient assessment, as well as enhance human–AI collaboration through customizable information when communicating predictions. However, usability testing of the OSISP UI is needed to ensure clinical utility.
- 1 May 2025
- Published by SAGE Publications in Digital Health
- Vol. 11
Open AccessHuman–AI collaboration for prehospital trauma triage: Designing the On Scene Injury Severity Prediction (OSISP) model as a clinical decision support system
Objective: This study aims to advance the On Scene Injury Severity Prediction (OSISP), an Artificial Intelligence (AI)-based model, as a Clinical Decision Support System (CDSS) that supports Emergency Medical Service (EMS) personnel during on-scene assessment of adult trauma patients. The objectives are to explore the integration of OSISP with the prehospital trauma workflow and to refine the User Interface (UI) that communicates the predictions. Methods: Workflow integration was studied in a workshop by analysis of a customer journey map created by personnel with experience of working in the EMS setting ( n = 8). Literature reviews were conducted to identify key factors enabling efficient human–AI collaboration and implementation options. Identified UI components derived from workshop and literature review findings were then evaluated and selected to refine the OSISP UI. Results: The workshop derived that OSISP is a service to be used on portable IT platforms as a second opinion, support for prioritization, and support during patient assessment. The literature reviews identified key content, characteristics, and goals of communicating predictions to users. The refined UI consisted of eight information components (prediction, entered predictors, missing predictors, and model details), and four functions (notification, exploration mode, and filtering of top three entered and missing predictors), to communicate the OSISP prediction. Conclusions: The refined OSISP UI has potential to integrate well into the clinical workflow during patient assessment, as well as enhance human–AI collaboration through customizable information when communicating predictions. However, usability testing of the OSISP UI is needed to ensure clinical utility.
- Open Access
- 9 October 2023
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 23 (1) , 1-19
On Scene Injury Severity Prediction (OSISP) model for trauma developed using the Swedish Trauma Registry
Background: Providing optimal care for trauma, the leading cause of death for young adults, remains a challenge e.g., due to field triage limitations in assessing a patient’s condition and deciding on transport destination. Data-driven On Scene Injury Severity Prediction (OSISP) models for motor vehicle crashes have shown potential for providing real-time decision support. The objective of this study is therefore to evaluate if an Artificial Intelligence (AI) based clinical decision support system can identify severely injured trauma patients in the prehospital setting. Methods: The Swedish Trauma Registry was used to train and validate five models – Logistic Regression, Random Forest, XGBoost, Support Vector Machine and Artificial Neural Network – in a stratified 10-fold cross validation setting and hold-out analysis. The models performed binary classification of the New Injury Severity Score and were evaluated using accuracy metrics, area under the receiver operating characteristic curve (AUC) and Precision-Recall curve (AUCPR), and under- and overtriage rates. Results: There were 75,602 registrations between 2013–2020 and 47,357 (62.6%) remained after eligibility criteria were applied. Models were based on 21 predictors, including injury location. From the clinical outcome, about 40% of patients were undertriaged and 46% were overtriaged. Models demonstrated potential for improved triaging and yielded AUC between 0.80–0.89 and AUCPR between 0.43–0.62. Conclusions: AI based OSISP models have potential to provide support during assessment of injury severity. The findings may be used for developing tools to complement field triage protocols, with potential to improve prehospital trauma care and thereby reduce morbidity and mortality for a large patient population.
- 9 October 2023
- Published by Springer Nature in BMC Medical Informatics and Decision Making
- Vol. 23 (1) , 1-19
Open AccessOn Scene Injury Severity Prediction (OSISP) model for trauma developed using the Swedish Trauma Registry
Background: Providing optimal care for trauma, the leading cause of death for young adults, remains a challenge e.g., due to field triage limitations in assessing a patient’s condition and deciding on transport destination. Data-driven On Scene Injury Severity Prediction (OSISP) models for motor vehicle crashes have shown potential for providing real-time decision support. The objective of this study is therefore to evaluate if an Artificial Intelligence (AI) based clinical decision support system can identify severely injured trauma patients in the prehospital setting. Methods: The Swedish Trauma Registry was used to train and validate five models – Logistic Regression, Random Forest, XGBoost, Support Vector Machine and Artificial Neural Network – in a stratified 10-fold cross validation setting and hold-out analysis. The models performed binary classification of the New Injury Severity Score and were evaluated using accuracy metrics, area under the receiver operating characteristic curve (AUC) and Precision-Recall curve (AUCPR), and under- and overtriage rates. Results: There were 75,602 registrations between 2013–2020 and 47,357 (62.6%) remained after eligibility criteria were applied. Models were based on 21 predictors, including injury location. From the clinical outcome, about 40% of patients were undertriaged and 46% were overtriaged. Models demonstrated potential for improved triaging and yielded AUC between 0.80–0.89 and AUCPR between 0.43–0.62. Conclusions: AI based OSISP models have potential to provide support during assessment of injury severity. The findings may be used for developing tools to complement field triage protocols, with potential to improve prehospital trauma care and thereby reduce morbidity and mortality for a large patient population.
- Open Access
Early identification and characterisation of stroke to support prehospital decision-making using artificial intelligence: a scoping review protocol
Introduction Stroke is a time-critical condition and one of the leading causes of mortality and disability worldwide. To decrease mortality and improve patient outcome by improving access to optimal treatment, there is an emerging need to improve the accuracy of the methods used to identify and characterise stroke in prehospital settings and emergency departments (EDs). This might be accomplished by developing computerised decision support systems (CDSSs) that are based on artificial intelligence (AI) and potential new data sources such as vital signs, biomarkers and image and video analysis. This scoping review aims to summarise literature on existing methods for early characterisation of stroke by using AI. Methods and analysis The review will be performed with respect to the Arksey and O’Malley’s model. Peer-reviewed articles about AI-based CDSSs for the characterisation of stroke or new potential data sources for stroke CDSSs, published between January 1995 and April 2023 and written in English, will be included. Studies reporting methods that depend on mobile CT scanning or with no focus on prehospital or ED care will be excluded. Screening will be done in two steps: title and abstract screening followed by full-text screening. Two reviewers will perform the screening process independently, and a third reviewer will be involved in case of disagreement. Final decision will be made based on majority vote. Results will be reported using a descriptive summary and thematic analysis. Ethics and dissemination The methodology used in the protocol is based on information publicly available and does not need ethical approval. The results from the review will be submitted for publication in a peer-reviewed journal. The findings will be shared at relevant national and international conferences and meetings in the field of digital health and neurology.
Open AccessEarly identification and characterisation of stroke to support prehospital decision-making using artificial intelligence: a scoping review protocol
Introduction Stroke is a time-critical condition and one of the leading causes of mortality and disability worldwide. To decrease mortality and improve patient outcome by improving access to optimal treatment, there is an emerging need to improve the accuracy of the methods used to identify and characterise stroke in prehospital settings and emergency departments (EDs). This might be accomplished by developing computerised decision support systems (CDSSs) that are based on artificial intelligence (AI) and potential new data sources such as vital signs, biomarkers and image and video analysis. This scoping review aims to summarise literature on existing methods for early characterisation of stroke by using AI. Methods and analysis The review will be performed with respect to the Arksey and O’Malley’s model. Peer-reviewed articles about AI-based CDSSs for the characterisation of stroke or new potential data sources for stroke CDSSs, published between January 1995 and April 2023 and written in English, will be included. Studies reporting methods that depend on mobile CT scanning or with no focus on prehospital or ED care will be excluded. Screening will be done in two steps: title and abstract screening followed by full-text screening. Two reviewers will perform the screening process independently, and a third reviewer will be involved in case of disagreement. Final decision will be made based on majority vote. Results will be reported using a descriptive summary and thematic analysis. Ethics and dissemination The methodology used in the protocol is based on information publicly available and does not need ethical approval. The results from the review will be submitted for publication in a peer-reviewed journal. The findings will be shared at relevant national and international conferences and meetings in the field of digital health and neurology.