Publications by authors named "I G Berk"
Article Synopsis
- The study assesses the effectiveness of an AI algorithm for detecting pulmonary nodules using ultra-low-dose CT scans in emergency departments, highlighting its role in improving diagnosis.
- A total of 870 patients were included, with the AI identifying 104 true positives but also generating 1,758 false positives, indicating a high trade-off between missed nodules and unnecessary alerts.
- The conclusion emphasizes that while AI significantly increases the detection of potentially harmful nodules (5.8 times more), it also raises the rate of false positives (42.9 times more), which can lead to additional unneeded follow-ups.
Objectives: Lymphopenia at hospital admission occurs in over one-third of patients with community-acquired pneumonia (CAP), yet its clinical relevance and pathophysiological implications remain underexplored. We evaluated outcomes and immune features of patients with lymphopenic CAP (L-CAP), a previously described immunophenotype characterized by admission lymphocyte count <0.724 × 10 cells/L.
View Article and Find Full Text PDFArticle Synopsis
- This study aimed to independently validate commercial AI products for predicting bone age using hand radiographs and detecting lung nodules on chest radiographs.
- Two AI algorithms for bone age prediction demonstrated a strong correlation with expert readers, while no significant differences in performance were found between AI and human readers.
- Four AI algorithms for lung nodule detection outperformed human readers, indicating potential advantages of using AI in this area, while others did not show a notable difference in performance.
Pneumonia pattern recognition on ultra-low-dose CT does not allow for a reliable differentiation between viral and bacterial pneumonia: A multicentre observer study.
Eur J Radiol
October 2023
Purpose: While a reliable differentiation between viral and bacterial pneumonia is not possible with chest X-ray, this study investigates whether ultra-low-dose chest-CT (ULDCT) could be used for this purpose.
Methods: In the OPTIMACT trial 281 patients had a final diagnosis of pneumonia, and 96/281 (34%) had one or more positive microbiology results: 60 patients viral pathogens, 48 patients bacterial pathogens. These 96 ULDCT's were blindly and independently evaluated by two chest radiologists, who reported CT findings, pneumonia pattern, and most likely type of pathogen.
In vivo polarisation sensitive optical coherence tomography for fibrosis assessment in interstitial lung disease: a prospective, exploratory, observational study.
BMJ Open Respir Res
August 2023
Article Synopsis
- EB-PS-OCT is a cutting-edge imaging technique that surpasses high-resolution CT in detecting pulmonary fibrosis by 50 times, effectively highlighting collagen birefringence.* -
- The study focuses on using EB-PS-OCT to visualize and quantify fibrosis in patients with interstitial lung diseases (ILD), comparing its findings to histological standards and HRCT images.* -
- Results from 19 patients showed a successful quantification of fibrosis using EB-PS-OCT, with its findings correlating well with histology, indicating its potential as a valuable tool in clinical assessments of lung diseases.*