Publications by authors named "L H Lehman"

Epidural steroid injections (ESIs) are often used to treat low back pain (LBP) due to lumbosacral radiculopathy as well as LBP without a clear component of radiculopathy, in some cases. While it is increasingly recognized that psychosocial factors are associated with pain outcomes, few studies have assessed the contribution of these factors to common pain interventions like ESIs. This study aimed to summarize the scope and nature of how psychosocial factors are accounted for in research on ESIs for the treatment of LBP with or without lumbosacral radiculopathy and to identify gaps and recommendations for future research.

View Article and Find Full Text PDF

Although prediction models for heart transplantation outcomes have been developed previously, a comprehensive benchmarking of survival machine learning methods for mortality prognosis in the most contemporary era of heart transplants following the 2018 donor heart allocation policy change is warranted. This study assessed seven statistical and machine learning algorithms-Lasso, Ridge, Elastic Net, Cox Gradient Boost, Extreme Gradient Boost Linear, Extreme Gradient Boost Tree, and Random Survival Forests in a post-policy cohort of 7,160 adult heart-only transplant recipients in the Scientific Registry of Transplant Recipients (SRTR) database who received their first transplant on or after October 18, 2018. A cross-validation framework was designed in mlr.

View Article and Find Full Text PDF

Background: Otitic hydrocephalus is increased intracranial pressure without ventricular dilation secondary to mastoiditis and cerebral venous sinus thrombosis (CVST). It is associated with significant visual morbidity, though more detailed data on visual outcomes is lacking. We sought to better characterize the management of increased intracranial pressure and visual outcomes in this population.

View Article and Find Full Text PDF
Article Synopsis
  • The study evaluates the role of cardiorespiratory variables in a Reinforcement Learning (RL) model designed to optimize drug treatment strategies for septic patients in the ICU.
  • The RL model developed showcases a significant performance boost when using cardiorespiratory data, outperforming other models that utilized different sets of features.
  • The findings advocate for real-time recommendation systems in sepsis treatment, leveraging the continuous availability of cardiorespiratory monitoring data.
View Article and Find Full Text PDF