Objective: To build a supervised machine learning (ML) model that selects the best first-line treatment strategy for unruptured bAVMs.
Methods: A Randomized Trial of Unruptured Brain Arteriovenous Malformations (ARUBA) trial data was obtained from the National Institute of Neurological Disorders and Stroke (NINDS). A team of five clinicians examined the demographic, clinical, and radiological details of each patient at baseline and reached a consensus on the best first-line treatment for bAVMs. Their treatment choice was used to train an automated supervised ML (autoML) model to select treatments for bAVMs for the training dataset. The accuracy and AUC of the algorithm in selecting the treatment strategy were measured for the test dataset, and feature importance scores of the included variables were calculated.
Results: Among the 100,000 combinations of supervised ML algorithms and their hyperparameters attempted by autoML, gradient boosting classifier had the best predictive performance with an overall accuracy of 0.74 and an area under the curve (AUC) of 0.88. The treatment-specific accuracies were 0.96, 0.85, 0.84, and 0.82; and AUCs were 0.75, 0.95, 0.80, and 0.88 for medical management, surgery, endovascular embolization, and gamma-knife radiosurgery, respectively. Spetzler-Martin score, followed by eloquent AVM location and AVM size, were the three most important features in determining treatments.
Conclusion: ML could reliably select the best first-line treatment strategy for bAVMs as per multidisciplinary expert consensus. This study can be replicated for larger population-based AVM registries, with the inclusion of outcome data, thus helping address the bias involved in the management of unruptured bAVMs.
Download full-text PDF |
Source |
---|---|
http://dx.doi.org/10.1016/j.clineuro.2024.108681 | DOI Listing |
Surv Ophthalmol
December 2024
Department of Ophthalmology, Taipei City Hospital, Renai Branch, Taipei, Taiwan; Department of Special Education, University of Taipei, Taipei, Taiwan; Department of Ophthalmology, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan. Electronic address:
Anti-vascular endothelial growth factor (VEGF) agents administered as either monotherapy or combination with verteporfin photodynamic therapy (PDT) are the 2 dominant treatment for polypoidal choroidal vasculopathy (PCV); However, controversies remain due to small sample sizes and inconsistency in prognosis from randomized controlled trials (RCTs). In accordance with the PRISMA statement, we investigated the efficacy of PDT plus anti-VEGF combination with anti-VEGF monotherapy. This study was accepted by the International Prospective Register of Systematic Reviews (CRD42023471362).
View Article and Find Full Text PDFJ Fr Ophtalmol
December 2024
Service d'ophtalmologie, hôpital Pierre-Paul-Riquet, CHU de Toulouse, place du Dr-Baylac, 31059 Toulouse, France.
Objective: To evaluate in a real-world setting an intravitreal clindamycin treatment protocol for ocular toxoplasmosis.
Methods: This was a single-center, retrospective review with a 6-month follow-up. Our protocol proposed an IVT of clindamycin as first-line treatment, and management was chosen according to the patient's status (past medical history of ocular toxoplasmosis or not).
Lung Cancer
December 2024
Medical Oncology, IRCCS Azienda Ospedaliero-Universitaria di Bologna, Bologna, Italy.
Background: As for squamous (Sq)-NSCLC, Checkmate-017 trial showed a significant overall survival (OS) improvement in favor of Nivolumab (Nivo) over Docetaxel in 2nd-line. We hypothesized that anticipating Nivo use, as early switch maintenance after 1st-line chemotherapy (CHT), might have improved survival as compared to delayed 2nd-line treatment.
Methods: EDEN was an open-label, 2-arm, phase III study which randomized (1:1) stage IIIB/IV Sq-NSCLC pts non-progressive after 1st-line platinum-based CHT, to receive early Nivo as switch maintenance (Arm A) or standard best supportive care followed by 2nd-line Nivo at disease progression (Arm B).
Lennox-Gastaut syndrome (LGS) is a severe developmental and epileptic encephalopathy (DEE) characterized by multiple types of drug-resistant seizures (which must include tonic seizures) with classical onset before 8 years (although some cases with later onset have also been described), abnormal electroencephalographic features, and cognitive and behavioral impairments. Management and treatment of LGS are challenging, due to associated comorbidities and the treatment resistance of seizures. A panel of five epileptologists reconvened to provide updated guidance and treatment algorithms for LGS, incorporating recent advancements in antiseizure medications (ASMs) and understanding of DEEs.
View Article and Find Full Text PDFExpert Rev Cardiovasc Ther
December 2024
School of Biomedical Engineering and Imaging Sciences, King's College London, UK.
Introduction: Cardiac Resynchronization Therapy (CRT) is an effective treatment for heart failure (HF) in approximately two-thirds of recipients, with a third remaining CRT 'non-responders.' There is an increasing body of evidence exploring the reasons behind non-response, as well as ways to preempt or counteract it.
Areas Covered: This review will examine the most recent evidence regarding optimizing outcomes from CRT, as well as explore whether traditional CRT indeed remains the best first-line therapy for electrical resynchronization in HF.
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!