Benjamin P. Geisler

Hospitalists frequently discuss the risks associated with tests, treatments, and/or surgical procedures with their patients. But is everyone in the clear on what a “slight risk of complications” actually means? A session on the meaning of risk to patients and how to effectively communicate risk was discussed at SHM Converge 2025, the annual meeting of the Society of Hospitalist Medicine held in Las Vegas in April.

Jimmy and his wife Molly welcomed their second child together, William “Billy” Kimmel. At three days old, Billy had successful open heart surgery at Children’s Hospital Los Angeles and is now home with his family. Jimmy opens up about his son’s birth and health complications and encourages donations

Jimmy responds to the tragic school shooting at Robb Elementary School in Uvalde, Texas, and talks about 89% of Americans wanting background checks, our cowardly leaders listening to the NRA instead of the people they actually represent, firearms becoming the #1 leading cause of death for American c

We are seeking an experienced health economist with proven modelling and analytics skills to join our HTA department. The successful candidate will lead and collaborate on high-impact research projects, develop grant applications, supervise PhD and …

The appropriate duration of anticoagulation for venous thromboembolism (VTE) in patients who have a transient provoking factor (e.g., surgery, trauma, or immobility) and concomitant enduring risk f...

How anti-immigration politics across the EU clashes with demographic reality

Background and Objectives Brain tissue oxygenation is usually inferred from arterial partial pressure of oxygen (paO2), which is in turn often inferred from pulse oximetry measurements or other non-invasive proxies. Our aim was to evaluate the feasibility of continuous paO2 prediction in an intraoperative setting among neurosurgical patients undergoing craniotomies with modern machine learning methods. Methods Data from routine clinical care of lung-healthy neurosurgical patients were extracted from databases of the respective clinical systems and normalized. We used recursive feature elimination to identify relevant features for the prediction of paO2. Six machine learning regression algorithms (gradient boosting, k-nearest neighbors, random forest, support vector, neural network, linear model with stochastic gradient descent) and a multivariable linear regression were then tuned and fitted to the selected features. A performance matrix consisting of standard deviation of absolute errors (σae), mean absolute percentage error (MAPE), adjusted R2, root mean squared error (RMSE), mean absolute error (MAE) and Spearman’s ρ was finally computed based on the test set, and used to compare and rank each algorithm. Results We analyzed N = 4,581 patients with n = 17,821 observations. Between 5 and 22 features were selected from the analysis of the training dataset comprising 3,436 patients with 13,257 observations. The best algorithm, a regularized linear model with stochastic gradient descent, could predict paO2 values with σae = 86.4 mmHg, MAPE = 16 %, adjusted R2 = 0.77, RMSE = 44 mmHg and Spearman’s ρ = 0.83. Further improvement was possible by calibrating the algorithm with the first measured paO2/FiO2 (p/F) ratio during surgery. Conclusion PaO2 can be predicted by perioperative routine data in neurosurgical patients even before blood gas analysis. The prediction improves further when including the first measured p/F ratio, realizing quasi-continuous paO2 monitoring.

Stillingstittel: PhD stipendiat i helseøkonomi (284854), Arbeidsgiver: Universitetet i Oslo, Søknadsfrist: tirsdag 30. september 2025

Nature - In a rare move for a US public official, health secretary Robert F. Kennedy Jr called for a Danish paper finding no link between aluminium in vaccines and disease to be retracted.