The potential of Generative Pre-trained Transformer 4 (GPT-4) to analyse medical notes in three different languages: a retrospective model-evaluation study.

Background: Patient notes contain substantial information but are difficult for computers to analyse due to their unstructured format. Large-language models (LLMs), such as Generative Pre-trained Transformer 4 (GPT-4), have changed our ability to process text, but we do not know how effectively they handle medical notes. We aimed to assess the ability of GPT-4 to answer predefined questions after reading medical notes in three different languages.

Blood Pressure Outcomes in NICU-Admitted Infants with Neonatal Hypertension: A Pediatric Nephrology Research Consortium Study.

Objective: To describe the blood pressure outcomes of infants admitted to the neonatal intensive care unit (NICU) with idiopathic (nonsecondary) hypertension (HTN) who were discharged on antihypertensive therapy.

Study Design: Retrospective, multicenter study of 14 centers within the Pediatric Nephrology Research Consortium. We included all infants with a diagnosis of idiopathic HTN discharged from the NICU on antihypertensive treatment.

Outcomes of granulocyte colony-stimulating factor use in pediatric kidney transplant recipients: A Pediatric Nephrology Research Consortium study.

Background: Neutropenia is common in the first year after pediatric kidney transplant and is associated with an increased risk of infection, allograft loss, and death. Granulocyte colony-stimulating factor (G-CSF) increases neutrophil production, but its use in pediatric solid organ transplant recipients remains largely undescribed.

Methods: We performed a multicenter retrospective cohort study of children with neutropenia within the first 180 days after kidney transplant.

Impact of a problem-oriented view on clinical data retrieval.

Objective: The electronic health record (EHR) data deluge makes data retrieval more difficult, escalating cognitive load and exacerbating clinician burnout. New auto-summarization techniques are needed. The study goal was to determine if problem-oriented view (POV) auto-summaries improve data retrieval workflows.

High Burden of Premature Arteriosclerosis on Renal Biopsy Results in Incident Lupus Nephritis.

Objective: Cardiovascular disease (CVD) is accelerated in patients with systemic lupus erythematosus and lupus nephritis (LN). Despite the literature suggesting that renal arteriosclerosis predicts CVD in other glomerulonephritis diseases, arteriosclerosis grading and reporting might be particularly overlooked in LN biopsies. Our objective was to examine the burden of renal arteriosclerosis in LN and to assess whether arteriosclerosis is underreported in LN biopsies.

The Use of Electronic Health Records to Identify Children with Elevated Blood Pressure and Hypertension.

Elevated blood pressures often go unrecognized in pediatric patients, potentially putting children and adolescents at risk for the sequelae of untreated hypertension. This may be partially due to the complexity involved in diagnosing elevated pediatric blood pressures, which demands a high cognitive workload from providers. Tools built into electronic health records have the potential to alleviate this workload, and studies investigating these tools confirm they show promise in improving elevated blood pressure recognition.