Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Comparative analysis of kidney function prediction: traditional statistical methods vs. deep learning techniques.
Clin Exp Nephrol
January 2025
Kawasaki Medical School, Department of Nephrology and Hypertension, Kurashiki, Japan.
Background: Chronic kidney disease (CKD) represents a significant public health challenge, with rates consistently on the rise. Enhancing kidney function prediction could contribute to the early detection, prevention, and management of CKD in clinical practice. We aimed to investigate whether deep learning techniques, especially those suitable for processing missing values, can improve the accuracy of predicting future renal function compared to traditional statistical method, using the Japan Chronic Kidney Disease Database (J-CKD-DB), a nationwide multicenter CKD registry.
View Article and Find Full Text PDFAttention-guided erasing for enhanced transfer learning in breast abnormality classification.
Int J Comput Assist Radiol Surg
January 2025
Pattern Recognition Lab, Friedrich-Alexander-University Erlangen-Nuremberg, Martensstr. 3, 91058, Erlangen, Bayern, Germany.
Purpose: Breast cancer remains one of the most prevalent cancers globally, necessitating effective early screening and diagnosis. This study investigates the effectiveness and generalizability of our recently proposed data augmentation technique, attention-guided erasing (AGE), across various transfer learning classification tasks for breast abnormality classification in mammography.
Methods: AGE utilizes attention head visualizations from DINO self-supervised pretraining to weakly localize regions of interest (ROI) in images.
Time course of hospitalizations in patients with heart failure and chronic obstructive pulmonary disease around sleep-disordered-breathing diagnosis.
Sleep Breath
January 2025
Department of Internal Medicine II (Cardiology, Pneumology, and Intensive Care), University Medical Centre Regensburg, Regensburg, Germany.
Purpose: In heart failure (HF) and chronic obstructive pulmonary disease (COPD) populations, sleep-disordered breathing (SDB) is associated with impaired health outcomes. We evaluated whether in patients with HF, concomitant HF and COPD or COPD, the number of hospitalizations would be reduced in the year after testing for SDB with and without treatment initiation compared to the year before.
Methods: We performed a multicentre retrospective study of 390 consecutive sleep-clinic patients who had a primary diagnosis of chronic HF, HF and COPD or COPD and a secondary diagnosis of SDB.
Ocrelizumab dose selection for treatment of pediatric relapsing-remitting multiple sclerosis: results of the OPERETTA I study.
J Neurol
January 2025
Division of Child Neurology, Children's Hospital of Philadelphia, Departments of Neurology and Pediatrics, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
Background: The presented study identified the appropriate ocrelizumab dosing regimen for patients with pediatric-onset multiple sclerosis (POMS).
Methods: Patients with POMS aged 10-17 years were enrolled into cohort 1 (body weight [BW] < 40 kg, ocrelizumab 300 mg) and cohort 2 (BW ≥ 40 kg, ocrelizumab 600 mg) during a 24-week dose-exploration period (DEP), followed by an optional ocrelizumab (given every 24 weeks) extension period.
Primary Endpoints: pharmacokinetics, pharmacodynamics (CD19 B-cell count); secondary endpoint: safety; exploratory endpoints: MRI activity, protocol-defined relapses, Expanded Disability Status Scale (EDSS) score change.
BDNF levels in serum and CSF are associated with clinicoradiological characteristics of aggressive disease in MS patients.
J Neurol
January 2025
Department of Neurology, University Hospital Frankfurt, Frankfurt Am Main, Germany.
Background: BDNF has increasingly gained attention as a key molecule controlling remyelination with a prominent role in neuroplasticity and neuroprotection. Still, it remains unclear how BDNF relates to clinicoradiological characteristics particularly at the early stage of the disease where precise prognosis for the further MS course is crucial.
Methods: BDNF, NfL and GFAP concentrations in serum and CSF were assessed in 106 treatment naïve patients with MS (pwMS) as well as 73 patients with other inflammatory/non-inflammatory neurological or somatoform disorders using a single molecule array HD-1 analyser.
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!