Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7317982 | PMC |
| http://dx.doi.org/10.1111/aos.14339 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Deep learning for kidney trauma detection: CT image algorithm performance and external validation: experimental study.
Int J Surg
January 2025
Department of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou; Chang Gung University, Taoyuan, Taiwan.
Background: Detecting kidney trauma on CT scans can be challenging and is sometimes overlooked. While deep learning (DL) has shown promise in medical imaging, its application to kidney injuries remains underexplored. This study aims to develop and validate a DL algorithm for detecting kidney trauma, using institutional trauma data and the Radiological Society of North America (RSNA) dataset for external validation.
View Article and Find Full Text PDFNarrative review of long-standing groin pain in athletes. Retrospective analysis of over 12 000 patients.
Hernia
January 2025
Centro de Patología Herniaria Argentina, Cerviño 4449, 1425, Buenos Aires, Argentina.
Purpose: This article critically examines long-standing groin pain (LSGP) in physically active adults related to sports overload by analyzing terminology, pathophysiology, and treatment.
Method: This review is based on data from over 10,000 patients managed through a multidisciplinary algorithm. (LSGP) has been variably labeled, using terms that have led to inconsistencies in understanding its origin and management.
EValuating Glucose ContrOL Using a Next-GeneraTION Automated Insulin Delivery Algorithm in Patients with Type 1 and Type 2 Diabetes: The EVOLUTION Study.
Diabetes Technol Ther
January 2025
Department of Paediatrics, University of Otago, Christchurch, New Zealand.
This study evaluated a next-generation automated insulin delivery (AID) algorithm for Omnipod in type 1 and type 2 diabetes across multiple phases: 14-day run-in with usual therapy, 48-h AID use in a hotel setting (type 1 only), and up to 6 weeks of outpatient AID use. Participants did, or did not, deliver manual boluses at alternating periods. Twelve adults with type 1 diabetes completed the hotel phase; 9 of those 12 plus 8 adults with type 2 diabetes completed the subsequent outpatient phase.
View Article and Find Full Text PDFAn Algorithmic Overview of Advanced Pain Therapies: A Narrative Review.
Curr Pain Headache Rep
January 2025
Department of Pain Medicine, Division of Anesthesiology, Critical Care & Pain Medicine, The University of Texas MD Anderson Cancer Center, Houston, TX, 77030, USA.
Purpose Of Review: Quickly referenceable, streamlined, algorithmic approaches for advanced pain management are lacking for patients, trainees, non-pain specialists, and interventional specialists. This manuscript aims to address this gap by proposing a comprehensive, evidence-based algorithm for managing neuropathic, nociceptive, and cancer-associated pain. Such an algorithm is crucial for pain medicine education, offering a structured approach for patient care refractory to conservative management.
View Article and Find Full Text PDFPrediction of surgical necessity in children with ureteropelvic junction obstruction using machine learning.
Ir J Med Sci
January 2025
Faculty of Medicine, Department of Pediatric Surgery Division of Pediatric Urology, Eskisehir Osmangazi University, Eskişehir, Turkey.
Background: Hydronephrosis developing at the ureteropelvic junction due to obstruction poses clinical challenges as it has the potential to cause renal damage.
Aims: This study aims to evaluate how well machine learning models such, as XGBClassifier and Logistic Regression can be used to predict the need for treatment in patients, with hydronephrosis resulting from ureteropelvic junction obstruction.
Methods: Hydronephrosis was diagnosed in the medical records of patients from January 2015 to December 2020.
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!