A5073101069- Radiology practices and education
- Artificial Intelligence in Healthcare and Education
- Osteoarthritis Treatment and Mechanisms
- Total Knee Arthroplasty Outcomes
- Radiation Dose and Imaging
- Radiomics and Machine Learning in Medical Imaging
- Ultrasound in Clinical Applications
- Appendicitis Diagnosis and Management
- Musculoskeletal synovial abnormalities and treatments
- Clinical Reasoning and Diagnostic Skills
- Orthopedic Infections and Treatments
- Abdominal Surgery and Complications
- Trauma and Emergency Care Studies
- Acute Ischemic Stroke Management
- Knee injuries and reconstruction techniques
- Lung Cancer Diagnosis and Treatment
- Rheumatoid Arthritis Research and Therapies
- COVID-19 diagnosis using AI
- Hemodynamic Monitoring and Therapy
- Venous Thromboembolism Diagnosis and Management
- Orthopedic Surgery and Rehabilitation
- Cerebrovascular and Carotid Artery Diseases
- Emergency and Acute Care Studies
- Advanced X-ray and CT Imaging
- Brain Tumor Detection and Classification
University of Copenhagen
2019-2024
Frederiksberg Hospital
2020-2024
Gentofte Hospital
2019-2024
Copenhagen University Hospital
2023-2024
Aarhus University Hospital
2024
Capital Region of Denmark
2023
Bispebjerg Hospital
2022-2023
Siemens Healthcare (United States)
2020
Background Commercially available artificial intelligence (AI) tools can assist radiologists in interpreting chest radiographs, but their real-life diagnostic accuracy remains unclear. Purpose To evaluate the of four commercially AI for detection airspace disease, pneumothorax, and pleural effusion on radiographs. Materials Methods This retrospective study included consecutive adult patients who underwent radiography at one Danish hospitals January 2020. Two thoracic (or three, cases...
Background Due to conflicting findings in the literature, there are concerns about a lack of objectivity grading knee osteoarthritis (KOA) on radiographs. Purpose To examine how artificial intelligence (AI) assistance affects performance and interobserver agreement radiologists orthopedists various experience levels when evaluating KOA radiographs according established Kellgren-Lawrence (KL) system. Materials Methods In this retrospective observer study, consecutive standing from patients...
Background Radiology practices have a high volume of unremarkable chest radiographs and artificial intelligence (AI) could possibly improve workflow by providing an automatic report. Purpose To estimate the proportion radiographs, where AI can correctly exclude pathology (ie, specificity) without increasing diagnostic errors. Materials Methods In this retrospective study, consecutive in unique adult patients (≥18 years age) were obtained January 1-12, 2020, at four Danish hospitals....
To externally validate an artificial intelligence (AI) tool for radiographic knee osteoarthritis severity classification on a clinical dataset.This retrospective, consecutive patient sample, external validation study used weight-bearing, non-fixed-flexion posterior-anterior radiographs from production PACS. The index test was ordinal Kellgren-Lawrence grading by AI tool, two musculoskeletal radiology consultants, reporting technologists, and resident radiologists. Grading repeated all...
The first patient was misclassified in the diagnostic conclusion according to a local clinical expert opinion new implementation of knee osteoarthritis artificial intelligence (AI) algorithm at Bispebjerg-Frederiksberg University Hospital, Copenhagen, Denmark. In preparation for evaluation AI algorithm, team collaborated with internal and external partners plan workflows, externally validated. After misclassification, left wondering: what is an acceptable error rate low-risk algorithm? A...
Background Patients with wrist trauma and negative findings on radiographs often undergo additional MRI examinations to assess for radiographically occult fractures. Dual-energy CT may be more readily available than in some settings. Purpose To evaluate the diagnostic test accuracy of dual-energy helping detect bone marrow edema fracture participants clinical suspicion a but radiographs. Materials Methods Adults were prospectively enrolled between January 2018 November 2018. Wrists examined...
The primary aim was to investigate the diagnostic performance of an Artificial Intelligence (AI) algorithm for pneumoperitoneum detection in patients with acute abdominal pain who underwent CT scan.This retrospective test accuracy study used a consecutive patient cohort from Acute High-risk Abdominal population at Herlev and Gentofte Hospital, Denmark between January 1, 2019 September 25, 2019. As reference standard, all studies were rated (subgroups: none, small, medium, large amounts) by...
To create a scalable and feasible retrospective consecutive knee osteoarthritis (OA) radiographic database with limited human labor using commercial custom-built artificial intelligence (AI) tools.
This study investigated how an AI tool impacted radiologists reading time for non-contrast chest CT exams.An was implemented into the PACS workflow of exams between April and May 2020. The recorded one CONSULTANT RADIOLOGIST RADIOLOGY RESIDENT by external observer. After each case answered questions regarding additional findings perceived overview. Reading times were 25 cases without 20 with assistance reader. Differences in assessed using Welch's t-test non-inferiority limits defined as 100...
Humans have been shown to biases when reading medical images, raising questions about whether humans are uniform in their disease gradings. Artificial intelligence (AI) tools trained on human-labeled data may inherent human non-uniformity. In this study, we used a radiographic knee osteoarthritis external validation dataset of 50 patients and six-year retrospective consecutive clinical cohort 8,273 patients. An FDA-approved CE-marked AI tool was tested for potential non-uniformity...
Introduction We investigated if large language models (LLMs) can be used for abstract screening in systematic- and scoping reviews. Methods Two broad reviews were designed: a systematic review structured according to the PRISMA guideline with inclusion based on PICO criteria; review, where we defined characteristics features of interest look for. For both 500 abstracts sampled. readers independently screened disagreements handled arbitrations or consensus, which served as reference standard....
Abstract Background Rapidly diagnosing fractures in appendicular skeletons is vital the ED, where junior physicians often interpret initial radiographs. However, missed remain a concern, prompting AI-assisted detection exploration. Yet, existing studies lack clinical context. We propose multi-center retrospective study evaluating AI aid RBfracture™ v.1, aiming to assess AI’s impact on diagnostic thinking by analyzing consecutive cases with data, providing insights into fracture and...
Abstract Background Radiographic evaluation of knee osteoarthritis (KOA) commonly supports clinical findings. Ground truth is difficult to establish and concerns exist on the inter-and intrarater agreement RBknee™ a CE-marked FDA-cleared AI tool for automatic assessment reporting radiographic KOA standard projection radiographs. Objectives To investigate how use an affects accuracy among human readers across three European hospitals in grading severity associated individual features. In...
Background: Several commercially available artificial intelligence (AI) tools can analyze chest radiographs (CXRs), but their real-life diagnostic accuracy, utility, and limitations remain unclear. This study evaluates current generation AI for the detection of airspace disease, pneumothorax, pleural effusion.Methods: We created a multicenter retrospective cohort consecutive patients having CXR in Capital Region Denmark. Four were tested against reference standard, based on consensus among...