Pitfalls in interpreting calibration in comparative evaluations of risk models for precision lung cancer screening.

Lung cancer screening by low-dose computed tomography reduces lung cancer mortality, but reliable risk-based selection of participants is crucial to maximize benefits and minimize harms. Multiple risk models have been developed for this purpose, and their discrimination and calibration performance is commonly evaluated based on large-scale cohort studies. Using a recent comparative evaluation of 10 risk models as an example, we illustrate the merits, limitations and pitfalls of such evaluations.

Metastatic recurrence in women diagnosed with non-metastatic breast cancer: a systematic review and meta-analysis.

Background: To assess proportions of metastatic recurrence in women initially diagnosed with non-metastatic breast cancer by stage at diagnosis, breast cancer subtype, calendar period and age.

Methods: A systematic search of MEDLINE and Web of Science databases (January 2010-12 May 2022) was conducted. Studies reporting the proportion of distant metastatic recurrence in women with non-metastatic breast cancer were identified and outcomes and characteristics were extracted.

Evaluation of levetiracetam loading dose in adult patients with benzodiazepine-refractory status epilepticus.

Background: Status epilepticus (SE) is a neurologic emergency defined as continued seizure activity greater than five minutes or recurrent seizure activity without return to baseline. Benzodiazepine-refractory SE is continuous seizure activity despite treatment with a benzodiazepine. Treatment of benzodiazepine-refractory SE includes levetiracetam with loading doses ranging from 20 mg/kg to 60 mg/kg up to a maximum dose of 4500 mg.

Interpretable representation learning for 3D multi-piece intracellular structures using point clouds.

A key challenge in understanding subcellular organization is quantifying interpretable measurements of intracellular structures with complex multi-piece morphologies in an objective, robust and generalizable manner. Here we introduce a morphology-appropriate representation learning framework that uses 3D rotation invariant autoencoders and point clouds. This framework is used to learn representations of complex multi-piece morphologies that are independent of orientation, compact, and easy to interpret.