Key Points Question What is the prevalence of missing data in the medical record, and is this prevalence associated with outcome estimation for patients with cancer? Findings In this cohort study of more than 4 million patients with cancer using abstracted medical records from the National Cancer Database, a high prevalence of missing data for patients with the 3 most common cancers in the US was found. Patients with missing data had worse overall survival than those with complete data. Meaning The study’s findings suggest substantial gaps in documentation and data capture via the medical record for patients with cancer.

Experiments were designed to clarify the role of several proteins, junB, retinoblastoma protein (RB), and the transforming growth factor-beta (TGF-beta) receptors that are potential intermediates in TGF-beta activation of the alpha 2(I) collagen promoter. Treatment of NIH-3T3 cells with TGF-beta increased the activity of a transiently transfected murine alpha 2(I) collagen promoter (nucleotides -350 to +54) fused to a luciferase reporter gene 9-fold. Cotransfection of a junB stimulated the basal activity of the alpha 2(I) collagen promoter 93-fold, respectively. Expression of antisense junB RNA attenuated the effect of TGF-beta. Simian virus 40 large T antigen, an inhibitor RB function, did not prevent TGF-beta effects on the alpha 2(I) collagen promoter. A chimeric receptor containing the extracellular domain of the colony-stimulating factor-1 receptor and the intracellular domain of the type I TGF-beta receptor enhanced alpha 2(I) collagen promoter activity 4.8-fold, whereas a similar chimera containing the type II receptor intracellular domain had much weaker effects. Similar results were obtained with a plasminogen activator inhibitor-1 promoter, previously shown to be activated by TGF-beta through AP-1 elements. We conclude that TGF-beta activates the alpha 2(I) collagen and plasminogen activator inhibitor-1 promoters in NIH-3T3 cells through junB and the type I TGF-beta receptor kinase domain.

Purpose of review To discuss recent applications of artificial intelligence within the field of neuro-oncology and highlight emerging challenges in integrating artificial intelligence within clinical practice. Recent findings In the field of image analysis, artificial intelligence has shown promise in aiding clinicians with incorporating an increasing amount of data in genomics, detection, diagnosis, classification, risk stratification, prognosis, and treatment response. Artificial intelligence has also been applied in epigenetics, pathology, and natural language processing. Summary Although nascent, applications of artificial intelligence within neuro-oncology show significant promise. Artificial intelligence algorithms will likely improve our understanding of brain tumors and help drive future innovations in neuro-oncology.