AI Article Synopsis
- The study evaluated the non-germinal center (GC) profile as a potential marker for patient response and survival in diffuse large B-cell lymphoma (DLBCL) treated with rituximab-based therapies.
- The analysis included 712 newly diagnosed DLBCL patients from 7 centers, categorizing them into GC and non-GC profiles using the Hans algorithm.
- Although non-GC patients showed trends of worse overall survival and progression-free survival, these differences weren't statistically significant, but they did have a lower complete response rate compared to GC patients, particularly among Asian individuals.
Article Abstract
Our objective was to evaluate the non-germinal center (GC) profile as a marker for response and survival in DLBCL and to compare the characteristics of patients with GC and non-GC DLBCL treated with rituximab-containing regimens. In this patient-level meta-analysis, retrospective data from 712 newly diagnosed DLBCL patients treated with chemoimmunotherapy from 7 centers were analyzed. GC and non-GC profiles were defined according to the Hans algorithm. Although the non-GC profile showed a trend towards worse overall survival (HR 1.24, 95% CI 0.92-1.66; p=0.15) and progression-free survival (HR 1.29, 95% CI 0.96-1.73; p=0.09), it did not retain its value in the multivariate survival analysis. Additionally, the non-GC profile was independently associated with worse complete response rates (OR 0.55, 95% CI 0.37-0.83; p<0.01) in the multivariate logistic regression analysis. Interestingly, Asian patients had higher proportion of GC DLBCL (p=0.01).
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.leukres.2011.12.012 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
ChatGPT (GPT-4) versus doctors on complex cases of the Swedish family medicine specialist examination: an observational comparative study.
BMJ Open
December 2024
General Practice / Family Medicine, School of Public Health and Community Medicine, Sahlgrenska Academy, University of Gothenburg Institute of Medicine, Gothenburg, Sweden.
Background: Recent breakthroughs in artificial intelligence research include the development of generative pretrained transformers (GPT). ChatGPT has been shown to perform well when answering several sets of medical multiple-choice questions. However, it has not been tested for writing free-text assessments of complex cases in primary care.
View Article and Find Full Text PDFIn silico based re-engineering of a computationally designed biosensor with altered signalling mode and improved dynamic range.
Arch Biochem Biophys
December 2024
Alberta RNA Research and Training Institute (ARRTI), University of Lethbridge, Lethbridge, AB, Canada; Department of Chemistry and Biochemistry, University of Lethbridge, Lethbridge, AB, Canada. Electronic address:
A current challenge in the rational design of biomolecular sensors is the ability to custom design binding affinities and detection mode in silico. To this end, we re-engineered a previously reported computationally-designed fluorescent maltooligosaccharide (MOS)-detecting biosensor to both alter its ligand-binding affinity and to analyse the underlying sensing mechanism. The dynamic range of the biosensor was expanded through the computer aided introduction of a series of amino acid substitutions in the starting protein scaffold (MalX from Streptococcus pneumoniae), which generated a biosensor set with binding affinities spanning over five orders of magnitude.
View Article and Find Full Text PDFMRI classification of progressive supranuclear palsy, Parkinson disease and controls using deep learning and machine learning algorithms for the identification of regions and tracts of interest as potential biomarkers.
Comput Biol Med
December 2024
Department of Neurology, University of Ulm, Ulm, Germany. Electronic address:
Background: Quantitative magnetic resonance imaging (MRI) analysis has shown promise in differentiating neurodegenerative Parkinsonian syndromes and has significantly advanced our understanding of diseases like progressive supranuclear palsy (PSP) in recent years.
Objective: The aim of this study was to develop, implement and compare MRI analysis algorithms based on artificial intelligence (AI) that can differentiate PSP not only from healthy controls but also from Parkinson disease (PD), by analyzing changes in brain structure and microstructure. Specifically, this study focused on identifying regions of interest (ROIs) and tracts of interest (TOIs) that are crucial for the algorithms to provide clinically relevant performance indices for the distinction between disease variants.
Augmenting small biomedical datasets using generative AI methods based on self-organizing neural networks.
Brief Bioinform
November 2024
Institute of Clinical Pharmacology, Goethe - University, Theodor - Stern - Kai 7, 60590 Frankfurt am Main, Germany.
Article Synopsis
- Small sample sizes in biomedical research lead to poor reproducibility and difficulties in applying findings clinically, caused by factors like limited resources and ethical concerns.
- A new generative algorithm leveraging self-organizing maps (SOMs) has been developed to effectively increase sample sizes by identifying structures in small datasets and generating new data points without altering the original data's integrity.
- Experiments show that the generated data maintains the same structure as the original, aiding research in rare diseases like leukemia and arthritis, and the method is available through the R library "Umatrix."
Detecting and Mitigating the Clever Hans Effect in Medical Imaging: A Scoping Review.
J Imaging Inform Med
November 2024
Laboratory for Computational Physiology, Massachusetts Institute of Technology, Cambridge, MA, USA.
The Clever Hans effect occurs when machine learning models rely on spurious correlations instead of clinically relevant features and poses significant challenges to the development of reliable artificial intelligence (AI) systems in medical imaging. This scoping review provides an overview of methods for identifying and addressing the Clever Hans effect in medical imaging AI algorithms. A total of 173 papers published between 2010 and 2024 were reviewed, and 37 articles were selected for detailed analysis, with classification into two categories: detection and mitigation approaches.
View Article and Find Full Text PDFWant 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!