Artificial intelligence (AI) for radiology has the potential to handle an ever-increasing volume of imaging examinations. However, the implementation of AI for clinical practice has not lived up to expectations. We suggest that a key problem with AI projects in radiology is that high expectations associated with new and unproven AI technology tend to scale the projects in ways that challenge their anchoring in local practice and their initial purpose of serving local needs. Empirically, we focus on the procurement of an AI solution for radiology practice at a large health trust in Norway where it was intended that AI technology would be used to process the screening of images more effectively. Theoretically, we draw on the information infrastructure literature, which is concerned with scaling innovative technologies from local settings, with a limited number of users, to broad-use contexts with many users.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.3233/SHTI220387 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Assessing the value of computed tomography (CT) of the chest in the follow-up of patients with intrahepatic cholangiocarcinoma.
J Gastrointest Oncol
December 2024
Abdominal Imaging Department, University of Texas MD Anderson Cancer Center, Houston, TX, USA.
Background: Following tumor resection, imaging recommendation for the follow-up of patients with intrahepatic cholangiocarcinoma (IHCCA) include frequent chest, abdomen and pelvis computed tomography (CT) imaging. The appropriateness of additional imaging studies is usually derived from their clinical utility. The purpose of this work is to determine the value of chest CT imaging in the follow-up of patients with IHCCA.
View Article and Find Full Text PDFAn exceptionally rare case of a diffuse midline glioma with concomitant H3.1 K27M and G34R mutations in the HIST1H3C (H3C3) gene.
Acta Neuropathol Commun
January 2025
Institute of Cancer Research, London, UK.
Histone mutations (H3 K27M, H3 G34R/V) are molecular features defining subtypes of paediatric-type diffuse high-grade gliomas (HGG) (diffuse midline glioma (DMG), H3 K27-altered, diffuse hemispheric glioma (DHG), H3 G34-mutant). The WHO classification recognises in exceptional cases, these mutations co-occur. We report one such case of a 2-year-old female presenting with neurological symptoms; MRI imaging identified a brainstem lesion which was biopsied.
View Article and Find Full Text PDFCorrelation between metabolic dysfunction-associated steatotic liver disease and subclinical coronary atherosclerosis in eastern China.
Diabetol Metab Syndr
January 2025
Department of Radiology, Shanghai Health and Medical Center, No. 67 Dajishan, Binhu District, Wuxi, 214065, China.
Background: Metabolic dysfunction-associated steatotic liver disease (MASLD) is characterized by the presence of at least one cardiovascular disease (CVD) risk factor, underscoring its potential to elevate CVD risk in affected individuals. However, evidence linking MASLD to subclinical coronary atherosclerosis remains scarce, and further investigations are necessary to elucidate the independent role of varying MASLD severities as a CVD risk factor.
Methods: This study analyzed 7,507 participants aged ≥ 40 who underwent comprehensive health evaluations at the Shanghai Health and Medical Center.
Location or size? A finite element analysis study of necrotic lesion impact on femoral head collapse.
J Orthop Surg Res
January 2025
The Third Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou, 510378, P. R. China.
Background: The location and size of necrotic lesions are important factors for collapse, The preserved angles (PAs) are divided into anterior preserved angle (APA) and lateral preserved angle (LPA), which could accurately measure the location of necrosis lesion. We used them to evaluate the effect of the location and size of necrotic lesions on collapse by finite element analysis, to offer a framework for evaluating the prognosis of osteonecrosis of the femoral head (ONFH) in clinical settings.
Methods: 3 left hip models were constructed based on CT data.
Preferences for public health insurance coverage of new anticancer drugs: a discrete choice experiment among non-small cell lung cancer patients in China.
BMC Public Health
January 2025
Medical School of Nantong University, Nantong, 226001, Jiangsu, China.
Background: Ensuring equal access to affordable, high-quality, and satisfied healthcare for cancer patients is a challenge worldwide. Our study aimed to investigate preferences for public health insurance coverage of new anticancer drugs among non-small cell lung cancer (NSCLC) patients in China.
Methods: We identified six attributes of new anticancer drugs and adopted a Bayesian-efficient design to generate choice scenarios for a discrete choice experiment (DCE).
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!