lnu.sePublications
Change search
Link to record
Permanent link

Direct link
Publications (10 of 94) Show all publications
Woldamanuel, Y., Rossen, J., Anderbro, T., Von Rosen, P., Bergman, P., Hagströmer, M. & Johansson, U.-B. (2026). Self-Reported Depression, Anxiety, Stress, Health-Related Quality of Life, and Diabetes Distress During a 2-Year Pedometer-Based Physical Activity Intervention in Prediabetes and Type 2 Diabetes: Secondary Outcomes of a Randomized Controlled Trial. Journal of Primary Care & Community Health, 17
Open this publication in new window or tab >>Self-Reported Depression, Anxiety, Stress, Health-Related Quality of Life, and Diabetes Distress During a 2-Year Pedometer-Based Physical Activity Intervention in Prediabetes and Type 2 Diabetes: Secondary Outcomes of a Randomized Controlled Trial
Show others...
2026 (English)In: Journal of Primary Care & Community Health, ISSN 2150-1319, E-ISSN 2150-1327, Vol. 17Article in journal (Refereed) Published
Abstract [en]

BACKGROUND: Regular physical activity is essential for preventing and managing type 2 diabetes. This study evaluates self-reported outcomes including depression, anxiety, stress, diabetes distress, and health-related quality of life during a 2-year pedometer-based intervention, with or without physical activity counseling, in people with prediabetes or type 2 diabetes.

METHODS: This study was a 3-armed parallel randomized controlled trial conducted in primary healthcare, involving people with prediabetes or type 2 diabetes. The 3 arms were: a multi-component intervention (self-monitoring of steps with counseling support), a single-component intervention (self-monitoring of steps without counseling support), and a control group (standard care). Secondary outcomes were measured using questionnaires for self-reported depression and anxiety (the Hospital Anxiety and Depression Scale [HADS]), stress (Perceived Stress Scale [PSS]), health-related quality of life (EuroQol, [EQ-5D 3L, and EQ-VAS] ), and diabetes distress (The Problem Areas in Diabetes questionnaire, [Swe-PAID-20]), at baseline and at months 3, 6, 12, 18, and 24. Intervention effects were evaluated by a robust linear mixed model.

RESULTS: In total, 188 patients (n = 64, 59, 65 in the respective group) were included. The mean (SD) age was 64.1 (7.7) years, 21% had prediabetes, 40% were female, and HbA1c was 49.9 (11.4) mmol/mol. The retention rate was approximately 91% of participants in the first year and 81% at the end of the second year. There were no significant within-group changes in self-reported outcomes from baseline up to 24 months. Moreover, there were no significant differences in outcomes between the interventions and control group at any time in any outcome.

CONCLUSION: This 2-year, pedometer-based physical activity intervention, despite its effectiveness for other outcomes in previous studies, is likely insufficient on its own to improve psychological well-being or reduce diabetes distress in a primary care population with prediabetes or type 2 diabetes with generally well-managed mental health at baseline. The study offers methodological insights that can guide future research. It highlights the complexity of assessing mental health outcomes within practical, low-intensity physical activity interventions.

Place, publisher, year, edition, pages
Sage Publications, 2026
Keywords
physical activity, prediabetes, questionnaires, randomized controlled trial, type 2 diabetes
National Category
Endocrinology and Diabetes
Research subject
Health and Caring Sciences, Health Informatics
Identifiers
urn:nbn:se:lnu:diva-145741 (URN)10.1177/21501319261434134 (DOI)001728672000001 ()41910155 (PubMedID)
Available from: 2026-04-01 Created: 2026-04-01 Last updated: 2026-04-07Bibliographically approved
Nordqvist, O., Björneld, O., Bergman, P., Wettermark, B., Lincke, A., Andersson, M. L. & Hammar, T. (2025). Drug-Induced QT Prolongation: Associations Between Risk Classifications in a Swedish Clinical Decision Support System and Clinical Outcomes. Clinical Pharmacology and Therapeutics, 119(2), 503-513
Open this publication in new window or tab >>Drug-Induced QT Prolongation: Associations Between Risk Classifications in a Swedish Clinical Decision Support System and Clinical Outcomes
Show others...
2025 (English)In: Clinical Pharmacology and Therapeutics, ISSN 0009-9236, E-ISSN 1532-6535, Vol. 119, no 2, p. 503-513Article in journal (Refereed) Published
Abstract [en]

Potential adverse drug events can be signaled in Clinical Decision Support Systems (CDSSs). This study validated a Swedish CDSS (Janusmed Risk Profile) by investigating associations between calculated risk classifications of drugs with QT-prolonging potential and registered related clinical outcomes. Subjects living in Kalmar County, Sweden, between 2011 and 2020 exposed to risk drugs (risk level I: somewhat increased risk, II: moderate increased risk, III: significant increased risk) were extracted from regional electronic health records and matched to controls (risk level 0: no known increased risk) by age, sex, and index date. Ventricular arrhythmia (VA), Torsade de Pointes, cardiac arrest and death were outcomes followed for one year. Logistic regression analysis was performed adjusted for age, sex, number of drugs, days in hospital and previous diagnosis. Among the 188,453 subjects, a higher proportion of those classified by the CDSS as having a risk of QT prolongation experienced VA compared to controls (risk level I = 0.26%, II = 0.34%, III = 0.71% vs risk level 0 = 0.17%). When adjusting for other risk factors, the association decreased, but risk level III remained significant with OR 2.1 (95% CI 1.6-2.9) compared to controls. Similar results were seen for the other outcomes. Although there was an association between CDSS risk classifications and clinical outcomes, only a few subjects are affected, and other factors, such as previous diagnosis, play an important role. The need for multifactorial CDSS algorithms is thus crucial to better guide prescribers in finding high-risk patients.

Place, publisher, year, edition, pages
John Wiley & Sons, 2025
National Category
Cardiology and Cardiovascular Disease
Identifiers
urn:nbn:se:lnu:diva-143003 (URN)10.1002/cpt.70121 (DOI)001609911300001 ()41208201 (PubMedID)2-s2.0-105021300285 (Scopus ID)
Available from: 2025-12-16 Created: 2025-12-16 Last updated: 2026-04-16Bibliographically approved
Olovsson, J., Ekstedt, M., Fagerström, C., Bergman, P. & Backåberg, S. (2025). Exploring Health Care Professionals’ Perspectives on Using Video Feedback and Movement Analysis to Facilitate Physical Functioning for Older Adults Living at Home: Co-Design Approach. JMIR Formative Research, 9, Article ID e73527.
Open this publication in new window or tab >>Exploring Health Care Professionals’ Perspectives on Using Video Feedback and Movement Analysis to Facilitate Physical Functioning for Older Adults Living at Home: Co-Design Approach
Show others...
2025 (English)In: JMIR Formative Research, E-ISSN 2561-326X, Vol. 9, article id e73527Article in journal (Refereed) Published
Abstract [en]

Background: Maintaining and motivating physical functioning among older adults has substantial health-related benefits, such as reducing the risk of falls and increasing the opportunities for independent living. Supporting preventive actions among older adults also has socioeconomic relevance. Previous studies have shown that digital tools involving video feedback can facilitate reflection and learning by encouraging active engagement.

Objective: This study aimed to explore health care professionals’ experiences of using a video-based tool as part of the rehabilitation to facilitate physical functioning among older adults (aged ≥65 years) living at home.

Methods: An experience-based co-design approach was used, involving 20 health care professionals. Nine iterative workshops were conducted, followed by 9 group interviews held between 2022 and 2023. The data were analyzed using reflexive thematic analysis.

Results: The results from this study captured the experiences of health care professionals using a video-based tool to facilitate physical functioning in older adults living at home. The participants described focusing on supporting patient commitment, creating a shared language to enhance collaboration in the rehabilitation process, and navigating barriers to adopting the video-based tool in practice.

Conclusions: From the perspective of health care professionals, video feedback has the potential to improve movement performance in daily activities and may play a crucial role in providing motivation and promoting sustainable physical functioning among older adults. Clinical recommendations include training health care professionals to introduce video feedback in a patient-centered manner and using it to foster shared communication that promotes professional development and patient engagement. Further research is needed to assess the impact of video feedback on older adults’ health outcomes and to identify strategies for implementation in complex rehabilitation needs.

Place, publisher, year, edition, pages
JMIR Publications, 2025
Keywords
eHealth, motivation, older adults, physical functioning, rehabilitation, video feedback
National Category
Public Health, Global Health and Social Medicine
Research subject
Health and Caring Sciences
Identifiers
urn:nbn:se:lnu:diva-142465 (URN)10.2196/73527 (DOI)001639350600034 ()41197125 (PubMedID)2-s2.0-105020824647 (Scopus ID)
Available from: 2025-11-13 Created: 2025-11-13 Last updated: 2026-04-10Bibliographically approved
Niklasson, J., Fagerström, C., Backåberg, S., Bergman, P. & Lindberg, T. (2025). Exploring predictors of the five-time sit-to-stand test based on cross-sectional findings from the Swedish National Study on Aging and Care (SNAC). BMC Geriatrics, 25(1), Article ID 79.
Open this publication in new window or tab >>Exploring predictors of the five-time sit-to-stand test based on cross-sectional findings from the Swedish National Study on Aging and Care (SNAC)
Show others...
2025 (English)In: BMC Geriatrics, E-ISSN 1471-2318, Vol. 25, no 1, article id 79Article in journal (Refereed) Published
Abstract [en]

Background As we age, staying physically active and reducing sedentary behavior becomes crucial. To understand how to achieve this, factors related to daily physical function such as five-time sit-to-stand (STS) time should be explored. This study aimed to investigate the associations between STS time, self-rated physical activity, physical function, health-related quality of life, physical and mental health in community-dwelling older adults aged >= 60 years. Method Cross-sectional design with self-reported and objectively measured data from adults aged >= 60 years (n = 819), acquired from the Swedish National Study on Aging and Care. Data was analyzed through multiple linear regression. Results The model (R-2 = 0.268) showed that STS time was predicted by grip strength (beta' = -0.204, p < 0.05), age (beta' = 0.202, p < 0.05), health-related quality of life (beta' = -0.192, p < 0.05), having fallen within the preceding twelve months (beta' = -0.127, p < 0.05), physical activities of perceived light to moderate intensity (beta' = -0.121, p < 0.05), one-leg stand (beta' = -0.099, p < 0.05), and education level (beta' = -0.092, p < 0.05). For STS time, health-related quality of life (beta = -0.354, confidence interval [CI] (-0.509)-(-0.199)), having fallen within the preceding twelve months (beta = -0.222, CI (-0.365)-(-0.078)), and physical activities of perceived light to moderate intensity (beta = -0.166, CI (-0.278)-(-0.053)) were the most prominent predictors. Conclusion The model highlights the importance of grip strength and health-related quality of life in predicting STS time in older adults. Clinicians can use these insights to develop interventions that maintain physical function by regularly assessing and monitoring these factors. Future research should explore the relationship between fall history, faster STS time, and the impact of grip strength and health-related quality of life on sedentary behavior among older adults.

Place, publisher, year, edition, pages
BioMed Central (BMC), 2025
Keywords
Aging, Balance, Physical activity, Physical function, Quality of life, Sedentary behavior, Sit-to-stand
National Category
Geriatrics Public Health, Global Health and Social Medicine
Research subject
Health and Caring Sciences
Identifiers
urn:nbn:se:lnu:diva-136983 (URN)10.1186/s12877-025-05737-8 (DOI)001414294100001 ()39905293 (PubMedID)2-s2.0-85218068978 (Scopus ID)
Available from: 2025-02-26 Created: 2025-02-26 Last updated: 2026-04-10Bibliographically approved
Danielsson, T., Carlsson, J., Fridolfsson, J., Ahnesjö, J. & Bergman, P. (2025). Is accelerations during the marathon part of a full distance Ironman associated with skeletal and heart muscle damage?. In: Presented at The European College of Sport Science (ECSS) Annual Congress, Rimini, Italy, 1-4 July, 2025: . Paper presented at The European College of Sport Science (ECSS) Annual Congress, Rimini, Italy, 1-4 July, 2025. , Article ID 391.
Open this publication in new window or tab >>Is accelerations during the marathon part of a full distance Ironman associated with skeletal and heart muscle damage?
Show others...
2025 (English)In: Presented at The European College of Sport Science (ECSS) Annual Congress, Rimini, Italy, 1-4 July, 2025, 2025, article id 391Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Background: It is well known that ultra-endurance races such as a full distance ironman triathlon causes damage to skeletal and cardiac muscles. However, the underlying factors causing these disturbances are less investigated. In this study we investigated if there is an association between ground reaction forces, measured with accelerometry, during the marathon part of an Ironman triathlon and markers of skeletal and cardiac muscle damage. Our hypothesis is that higher ground reaction forces is positively associated with skeletal and heart muscle damage with no difference between the genders in this association.

Methods: In all 20 (8 women) subjects completed a full distance ironman triathlon (3.8 km swimming, 180 km cycling and 42 km running) and provided a full set of data and was included in the analysis. As markers for skeletal muscle damage, creatin kinas (CK) and myoglobin was analysed. As markers for cardiac muscle damage cardiac troponin t (cTnT), the N-terminal of the prohormone brain natriuretic peptide (NT-proBNP) was analysed. Ground reaction forces was estimated using an accelerometer (ActiGraph GT3x). Based on the official transition times we sliced out the raw accelerations for the marathon part of the race and calculated the mean vector magnitude (VM) expressed in milliG per second (mG/s). Due to outliers among the dependent variables, Spearman rank correlations (rho) stratified by sex was calculated.

Results: As seen in figure 1, no significant association between the biomarkers and mechanical stress was observed (all p>0.05).

Conclusion: We did not find any support to our initial hypothesis that there should be a positive association between ground reaction forces and markers of skeletal and heart muscle damage. The small sample size in the groups and the fact that we did not adjust for any potential confounder in this study warrants causing in the interpretation of the results. 

National Category
Sport and Fitness Sciences
Research subject
Social Sciences, Sport Science; Social Sciences, Sport Science
Identifiers
urn:nbn:se:lnu:diva-141179 (URN)
Conference
The European College of Sport Science (ECSS) Annual Congress, Rimini, Italy, 1-4 July, 2025
Available from: 2025-08-20 Created: 2025-08-20 Last updated: 2025-08-22Bibliographically approved
Woldamanuel, Y., Bergman, P., von Rosen, P., Johansson, U.-B., Hagströmer, M. & Rossen, J. (2024). Association between Weather and Self-Monitored Steps in Individuals with Prediabetes and Type 2 Diabetes in Sweden over Two Years. International Journal of Environmental Research and Public Health, 21(4), 379-379
Open this publication in new window or tab >>Association between Weather and Self-Monitored Steps in Individuals with Prediabetes and Type 2 Diabetes in Sweden over Two Years
Show others...
2024 (English)In: International Journal of Environmental Research and Public Health, ISSN 1661-7827, E-ISSN 1660-4601, Vol. 21, no 4, p. 379-379Article in journal (Refereed) Published
Abstract [en]

Background: Many studies have identified key factors affecting the rates of engagement in physical activity in older adults with chronic disease. Environmental conditions, such as weather variations, can present challenges for individuals with chronic diseases, such as type 2 diabetes when engaging in physical activity. However, few studies have investigated the influence of weather on daily steps in people with chronic diseases, especially those with prediabetes and type 2 diabetes. Objective: This study investigated the association between weather variations and daily self-monitored step counts over two years among individuals with prediabetes and type 2 diabetes in Sweden. Methods: The study is a secondary analysis using data from the Sophia Step Study, aimed at promoting physical activity among people with prediabetes and type 2 diabetes, which recruited participants from two urban primary care centers in Stockholm and one rural primary care center in southern Sweden over eight rounds. This study measured physical activity using step counters (Yamax Digiwalker SW200) and collected self-reported daily steps. Environmental factors such as daily average temperature, precipitation, and hours of sunshine were obtained from the Swedish Meteorological and Hydrological Institute. A robust linear mixed-effects model was applied as the analysis method. Results: There was no association found between weather variations and the number of steps taken on a daily basis. The analysis indicated that only 10% of the variation in daily steps could be explained by the average temperature, precipitation, and sunshine hours after controlling for age, gender, and BMI. Conversely, individual factors explained approximately 38% of the variation in the observations. Conclusion: This study revealed that there was no association between weather conditions and the number of daily steps reported by individuals with prediabetes and type 2 diabetes taking part in a physical activity intervention over two years. Despite the weather conditions, women and younger people reported more steps than their male and older counterparts.

Place, publisher, year, edition, pages
MDPI, 2024
National Category
Public Health, Global Health and Social Medicine
Research subject
Natural Science, Medicine
Identifiers
urn:nbn:se:lnu:diva-132646 (URN)10.3390/ijerph21040379 (DOI)38673292 (PubMedID)2-s2.0-85191251942 (Scopus ID)
Available from: 2024-09-20 Created: 2024-09-20 Last updated: 2025-05-30Bibliographically approved
Niklasson, J., Fagerström, C., Backåberg, S., Lindberg, T. & Bergman, P. (2024). Daily activity patterns in older adults receiving initial support: the association between daily steps and sitting in bouts of at least 60 min. BMC Geriatrics, 24(1), Article ID 88.
Open this publication in new window or tab >>Daily activity patterns in older adults receiving initial support: the association between daily steps and sitting in bouts of at least 60 min
Show others...
2024 (English)In: BMC Geriatrics, E-ISSN 1471-2318, Vol. 24, no 1, article id 88Article in journal (Refereed) Published
Abstract [en]

Background

Aging has a significant impact on health, underlining the importance of maintaining physical function and reducing time spent sitting among older adults. To understand how to reduce prolonged sitting or increase physical activity, factors related to the daily living and observed daily activity patterns should be explored. This study aimed to investigate the association between daily steps, self-rated health, physical activity, sedentary behavior, motivation to exercise and fear of falling among older adults receiving initial support.

Method

Cross-sectional design with total population questionnaire data from adults aged ≥ 60 years (n = 917), living at home with initial support from municipal care in southern Sweden. The older adults were offered to participate in a follow-up study measuring daily activity patterns with accelerometers (n = 72). Linear regression was used to analyze associations between daily steps and possible predictors.

Results

The linear model (

0.478) showed that sitting in unbroken bouts of > 60 min (β = -0.313, p < 0.05), walking independently outdoors (β = 0.301, p < 0.05), intending to increase physical activity (β = -0.294, p < 0.05), sex (β = 0.279, p < 0.05), relative autonomy index (β = 0.258, p < 0.05), fear of falling (β = -0.238, p < 0.05), and self-rated health (β = 0.213, p < 0.05) predicted daily steps.

Conclusion

The model of predictors brings new understanding regarding daily steps among community-dwelling older adults. The association between sitting in bouts of > 60 min and daily steps is interesting as 35% of participants had a number of sitting bouts that on average, showed 30% less steps taken. Minimizing long sitting bouts and maintaining physical functioning to promote independence when walking outdoors can be tools for clinical practitioners devising interventions to break prolonged sitting among community-dwelling older adults. Future research should prioritize studying older adults’ outdoor walking independence, including its relation to walking with or without assistive devices and its impact on physical activity and sedentary behavior.

Place, publisher, year, edition, pages
BioMed Central (BMC), 2024
Keywords
Accelerometer Aging Physical activity Sedentary behavior Sitting Walking independence
National Category
Public Health, Global Health and Social Medicine
Research subject
Health and Caring Sciences, Caring Science
Identifiers
urn:nbn:se:lnu:diva-127281 (URN)10.1186/s12877-024-04681-3 (DOI)001148301500001 ()38263077 (PubMedID)2-s2.0-85182847415 (Scopus ID)
Funder
Linnaeus University
Available from: 2024-01-30 Created: 2024-01-30 Last updated: 2025-06-02Bibliographically approved
Niklasson, J., Backåberg, S., Lindberg, T., Bergman, P. & Fagerström, C. (2024). Embodied navigation: the influence of lived experience on physical activity and sedentary behavior among older adults. International Journal of Qualitative Studies on Health and Well-being, 19(1), Article ID 2313657.
Open this publication in new window or tab >>Embodied navigation: the influence of lived experience on physical activity and sedentary behavior among older adults
Show others...
2024 (English)In: International Journal of Qualitative Studies on Health and Well-being, ISSN 1748-2623, E-ISSN 1748-2631, Vol. 19, no 1, article id 2313657Article in journal (Refereed) Published
Abstract [en]

PurposeThe impact of a sedentary lifestyle on health and well-being is well recognized. However, there is limited understanding of how a lifetime of physical activity and sedentary behaviour influences an active lifestyle in older adults. The aim of this study was to describe how lived experience of physical activity and sedentary behaviour impacts daily activities among older adults, from a life course perspective.MethodsQualitative content analysis was used; individual telephone interviews were conducted with fourteen older adults aged 71 to 92 years. The participants received initial support from community care and lived in ordinary housing in southern Sweden.ResultsThe interviews yielded one theme, “Navigating with an embodied activity compass,” and two sub-themes: “Being guided by the past” and “Unveiling pathways through body awareness.”ConclusionsOur study highlights how older adults’ lived experiences of physical activity, with their connections to body awareness and acceptance, impact daily physical activity. These findings offer new knowledge for clinical practitioners balancing recommendations of sedentary behaviour and physical activity, to promote healthy daily physical activity among older adults. Future research and policies should consider the lived experiences of older adults when addressing public health matters related to sedentary behaviour and physical activity.

Place, publisher, year, edition, pages
Taylor & Francis Group, 2024
National Category
Nursing
Research subject
Health and Caring Sciences, Nursing; Medicine, Gerontology
Identifiers
urn:nbn:se:lnu:diva-127765 (URN)10.1080/17482631.2024.2313657 (DOI)001161297400001 ()2-s2.0-85185205340 (Scopus ID)
Funder
Linnaeus University
Available from: 2024-02-14 Created: 2024-02-14 Last updated: 2025-03-26Bibliographically approved
Danielsson, T., Bergman, P. & Carlsson, J. (2024). Intra-individual variability of markers of skeletal and heart muscle damage after two full distance Ironman: the Iron(WO)man study. Discover Medicine, 1, Article ID 53.
Open this publication in new window or tab >>Intra-individual variability of markers of skeletal and heart muscle damage after two full distance Ironman: the Iron(WO)man study
2024 (English)In: Discover Medicine, ISSN 2521-2273, Vol. 1, article id 53Article in journal (Refereed) Published
Abstract [en]

Purpose

To examine the tracking, i.e., the stability, of response in biomarkers signaling cardiac- and skeletal muscle damage after two full distance Ironman races separated by one year.

Methods

Thirteen individuals (7 females) who participated in two Ironman races in Sweden year 2015 and 2016 and had been included in the Iron(WO)man study were investigated. Blood samples were drawn immediately after the race and were analyzed for cardiac troponin T, N-terminal of the prohormone brain natriuretic peptide, myoglobin, creatine kinase and serum creatinine. Stability of the biomarker response between the year-to-year was estimated by calculating tracking coefficients using Spearman correlation.

Results

There were no intra-individual differences in the post-race values in any of the studied biomarkers (all p > 0.05). All tracking coefficients showed a substantial stability (rho = 0.60–0.77).

Conclusion

It appears that there are individuals who are at particular risk of getting high levels of biomarkers signaling cardiac and skeletal muscle damage. However, this secondary analysis was neither designed nor powered to give definite answers and could not rule out the possibility that higher markers in fact represent occult heart disease.

Place, publisher, year, edition, pages
Springer Nature, 2024
Keywords
Triathlon, Health, Ultra-endurance
National Category
Cardiology and Cardiovascular Disease
Research subject
Natural Science, Medicine
Identifiers
urn:nbn:se:lnu:diva-132731 (URN)10.1007/s44337-024-00067-x (DOI)
Available from: 2024-09-24 Created: 2024-09-24 Last updated: 2025-05-15Bibliographically approved
Lincke, A., Roth, J., Macedo, A. F., Bergman, P., Löwe, W. & Lagali, N. S. (2023). AI-Based Decision-Support System for Diagnosing Acanthamoeba Keratitis Using In Vivo Confocal Microscopy Images. Translational Vision Science & Technology, 12(11), Article ID 29.
Open this publication in new window or tab >>AI-Based Decision-Support System for Diagnosing Acanthamoeba Keratitis Using In Vivo Confocal Microscopy Images
Show others...
2023 (English)In: Translational Vision Science & Technology, E-ISSN 2164-2591, Vol. 12, no 11, article id 29Article in journal (Refereed) Published
Abstract [en]

Purpose: In vivo confocal microscopy (IVCM) of the cornea is a valuable tool for clinical assessment of the cornea but does not provide stand-alone diagnostic support. The aim of this work was to develop an artificial intelligence (AI)-based decision-support system (DSS) for automated diagnosis of Acanthamoeba keratitis (AK) using IVCM images.

Methods: The automated workflow for the AI-based DSS was defined and implemented using deep learning models, image processing techniques, rule-based decisions, and valuable input from domain experts. The models were evaluated with 5-fold-cross validation on a dataset of 85 patients (47,734 IVCM images from healthy, AK, and other disease cases) collected at a single eye clinic in Sweden. The developed DSS was validated on an additional 26 patients (21,236 images).

Results: Overall, the DSS uses as input raw unprocessed IVCM image data, successfully separates artefacts from true images (93% accuracy), then classifies the remaining images by their corneal layer (90% accuracy). The DSS subsequently predicts if the cornea is healthy or diseased (95% model accuracy). In disease cases, the DSS detects images with AK signs with 84% accuracy, and further localizes the regions of diagnostic value with 76.5% accuracy.

Conclusions: The proposed AI-based DSS can automatically and accurately preprocess IVCM images (separating artefacts and sorting images into corneal layers) which decreases screening time. The accuracy of AK detection using raw IVCM images must be further explored and improved.

Translational Relevance: The proposed automated DSS for experienced specialists assists in diagnosing AK using IVCM images.

Place, publisher, year, edition, pages
Association for research in vision and ophthalmology (ARVO), 2023
Keywords
image analysis, acanthamoeba keratitis, deep learning, in vivo confocal microscopy images
National Category
Computer Systems Medical Imaging
Research subject
Computer and Information Sciences Computer Science, Computer Science
Identifiers
urn:nbn:se:lnu:diva-125803 (URN)10.1167/tvst.12.11.29 (DOI)001125044500009 ()2-s2.0-85178009830 (Scopus ID)
Available from: 2023-11-28 Created: 2023-11-28 Last updated: 2025-02-18Bibliographically approved
Organisations
Identifiers
ORCID iD: ORCID iD iconorcid.org/0000-0003-4934-8684

Search in DiVA

Show all publications