ChatGPT and Large Language Models in Radiology: Perspectives From the Field.

Generative artificial intelligence (AI) and large language models (LLMs) are increasingly being recognized as tools with the potential to transform many industries, including health care. Implementation and use of these tools among radiologists is likely variable, driven by radiology practice and institutional factors. Radiologists from various practices were asked about their perspectives on generative AI and LLMs in radiology.

Drug-Induced Liver Injury in Pregnancy: The U.S. Drug-Induced Liver Injury Network Experience.

There are limited data on the causative agents and characteristics of drug-induced liver injury in pregnant individuals. Data from patients with drug-induced liver injury enrolled in the ongoing multicenter Drug-Induced Liver Injury Network between 2004 and 2022 and occurring during pregnancy or 6 months postpartum were reviewed and compared with cases of drug-induced liver injury in nonpregnant women of childbearing age. Among 325 individuals of childbearing age in the Drug-Induced Liver Injury Network, 16 cases of drug-induced liver injury (5%) occurred during pregnancy or postpartum.

Histology-driven hypofractionated radiation therapy schemes for early-stage lung adenocarcinoma and squamous cell carcinoma.

Background And Purpose: Histology was found to be an important prognostic factor for local tumor control probability (TCP) after stereotactic body radiotherapy (SBRT) of early-stage non-small-cell lung cancer (NSCLC). A histology-driven SBRT approach has not been explored in routine clinical practice and histology-dependent fractionation schemes remain unknown. Here, we analyzed pooled histologic TCP data as a function of biologically effective dose (BED) to determine histology-driven fractionation schemes for SBRT and hypofractionated radiotherapy of two predominant early-stage NSCLC histologic subtypes adenocarcinoma (ADC) and squamous cell carcinoma (SCC).

Optimal hypofractionated radiation therapy schemes for early-stage hepatocellular carcinoma.

Purpose: Stereotactic body radiation therapy (SBRT) has been emerging as an efficacious and safe treatment modality for early-stage hepatocellular carcinoma (HCC), but optimal fractionation regimens are unknown. This study aims to analyze published clinical tumor control probability (TCP) data as a function of biologically effective dose (BED) and to determine radiobiological parameters and optimal fractionation schemes for SBRT and hypofractionated radiation therapy of early-stage HCC.

Material And Methods: Clinical 1- to 5-year TCP data of 4313 patients from 41 published papers were collected for hypofractionated radiation therapy at 2.

Drug-induced liver injury (DILI) ascribed to non-steroidal anti-inflammatory drugs (NSAIDs) in the USA-Update with genetic correlations.

Objective: To describe patients with NSAID-DILI, including genetic factors associated with idiosyncratic DILI.

Methods: In DILIN, subjects with presumed DILI are enrolled and followed for at least 6 months. Causality is adjudicated by a Delphic approach.

Optimal Radiation Therapy Fractionation Regimens for Early-Stage Non-Small Cell Lung Cancer.

Purpose: A series of radiobiological models were developed to study tumor control probability (TCP) for stereotactic body radiation therapy (SBRT) of early-stage non-small cell lung cancer (NSCLC) per the Hypofractionated Treatment Effects in the Clinic (HyTEC) working group. This study was conducted to further validate 3 representative models with the recent clinical TCP data ranging from conventional radiation therapy to SBRT of early-stage NSCLC and to determine systematic optimal fractionation regimens in 1 to 30 fractions for radiation therapy of early-stage NSCLC that were found to be model-independent.

Methods And Materials: Recent clinical 1-, 2-, 3-, and 5-year actuarial or Kaplan-Meier TCP data of 9808 patients from 56 published papers were collected for radiation therapy of 2 to 4 Gy per fraction and SBRT of early-stage NSCLC.

Using Kotter's Change Management Framework to Redesign Departmental GME Recruitment.

Background: In light of the COVID-19 pandemic, dramatic change in the graduate medical education (GME) trainee recruitment process was required. Kotter's 8-Step Change Model is a change management framework that has been successfully applied to a variety of GME initiatives but not for recruitment redesign.

Objective: To implement major change in program recruitment during the COVID-19 pandemic while maintaining Match outcomes and a high-quality candidate experience.