Large language models (LLMs) have revolutionized the global landscape of technology beyond the field of natural language processing. Owing to their extensive pre-training using vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without the need for additional fine-tuning. Importantly, LLMs are on a trajectory of rapid evolution, addressing challenges such as hallucination, bias in training data, high training costs, performance drift, and privacy issues, along with the inclusion of multimodal inputs. The concept of small, on-premise open source LLMs has garnered growing interest, as fine-tuning to medical domain knowledge, addressing efficiency and privacy issues, and managing performance drift can be effectively and simultaneously achieved. This review provides conceptual knowledge, actionable guidance, and an overview of the current technological landscape and future directions in LLMs for radiologists.

Large language models (LLMs) have revolutionized the global landscape of technology beyond the field of natural language processing. Owing to their extensive pre-training using vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without the need for additional fine-tuning. Importantly, LLMs are on a trajectory of rapid evolution, addressing challenges such as hallucination, bias in training data, high training costs, performance drift, and privacy issues, along with the inclusion of multimodal inputs. The concept of small, on-premise open source LLMs has garnered growing interest, as fine-tuning to medical domain knowledge, addressing efficiency and privacy issues, and managing performance drift can be effectively and simultaneously achieved. This review provides conceptual knowledge, actionable guidance, and an overview of the current technological landscape and future directions in LLMs for radiologists.

Large language models (LLMs) have revolutionized the global landscape of technology beyond the field of natural language processing. Owing to their extensive pre-training using vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without the need for additional fine-tuning. Importantly, LLMs are on a trajectory of rapid evolution, addressing challenges such as hallucination, bias in training data, high training costs, performance drift, and privacy issues, along with the inclusion of multimodal inputs. The concept of small, on-premise open source LLMs has garnered growing interest, as fine-tuning to medical domain knowledge, addressing efficiency and privacy issues, and managing performance drift can be effectively and simultaneously achieved. This review provides conceptual knowledge, actionable guidance, and an overview of the current technological landscape and future directions in LLMs for radiologists.

Large language models (LLMs) have revolutionized the global landscape of technology beyond natural language processing. Owing to their extensive pre-training on vast datasets, contemporary LLMs can handle tasks ranging from general functionalities to domain-specific areas, such as radiology, without additional fine-tuning. General-purpose chatbots based on LLMs can optimize the efficiency of radiologists in terms of their professional work and research endeavors. Importantly, these LLMs are on a trajectory of rapid evolution, wherein challenges such as “hallucination,” high training cost, and efficiency issues are addressed, along with the inclusion of multimodal inputs. In this review, we aim to offer conceptual knowledge and actionable guidance to radiologists interested in utilizing LLMs through a succinct overview of the topic and a summary of radiology-specific aspects, from the beginning to potential future directions.

Purpose: To evaluate the effect of the emergence of coronavirus disease-19 (COVID-19) on pediatric intussusception. Materials and Methods: Patients (< 18 years) who were diagnosed with intussusception and received enema reduction from 2011 to 2020 were included. We reviewed the demographics, yearly/monthly/seasonal incidence of intussusception, method and failure rate of enema reduction, recurrence rate of intussusception, surgical record, and pathologic report. Subsequently, we investigated the differences in mean age, failure rate of enema reduction, and recurrence rate of intussusception between the cases in 2020 and those in the period from 2011 to 2019. Results: A total of 859 enema reductions were performed during the past decade, more in males and in the age < 1 year (mean age, 22.2 months). The yearly incidence was highest in 2014 and lowest in 2020, and the monthly incidence was highest on December and September. The cases in 2020 (n = 27) had a lower mean age (18.1 months vs. 22.8 months), higher failure rate of enema reduction (7.4% vs. 2.4%), and higher recurrence rate of intussusception (14.8% vs 7.3%) compared with those that occurred between 2011 and 2019 (n = 832). However, these results did not show statistical significance (p = 0.07, p = 0.15, p = 0.14, respectively). Conclusion With the emergence of COVID-19, the number of enema reductions was remarkably decreased with a lower mean age, higher failure rate, and higher recurrence rate.

Background: Previous studies on the epidemiology and complications of congenital adrenal hyperplasia (CAH) were conducted in Western countries and in children/adolescents. We aimed to explore the epidemiology of CAH, as well as the risk of comorbidities and mortality, in a Korean nationwide case-control study. Methods: CAH patients (n=2,840) were included between 2002 and 2017 from the National Health Insurance Service database and the Rare Intractable Disease program. CAH patients were compared, at a 1:10 ratio, with age-, sex-, and index year-matched controls (n=28,400). Results: The point prevalence of CAH patients in Korea was 1 in 18,745 persons in 2017. The annual incidence rate declined between 2003 and 2017 from 3.25 to 0.41 per 100,000 persons. CAH patients were at elevated risk for cardiovascular disease (odds ratio [OR], 1.6; 95% confidence interval [CI], 1.4 to 1.9), stroke (OR, 1.7; 95% CI, 1.3 to 2.0), diabetes mellitus (OR, 2.8; 95% CI, 2.6 to 3.1), dyslipidemia (OR, 2.4; 95% CI, 2.2 to 2.6), and psychiatric disorders (OR, 1.5; 95% CI, 1.3 to 1.6). Fracture risk increased in CAH patients aged over 40 years (OR, 1.4; 95% CI, 1.1 to 1.7). CAH patients were at higher risk of mortality than controls (hazard ratio, 1.6; 95% CI, 1.3 to 2.0). Conclusion Our nationwide study showed a recent decline in the incidence of CAH and an elevated risk for cardiovascular, metabolic, skeletal, and psychiatric disorders in CAH patients. Lifelong management for comorbidity risk is a crucial component of treating CAH patients.

Objectives: ：This study aims to confirm the effectiveness of a school-based very-short-term dialectical be-havior therapy-skills training (DBT-ST) program for preventing self-harm among children and adolescents, considering factors such as age, sex, self-harm history, and methods of program implementation. Methods: ：The study was conducted from September 2021 to December 2023, targeting 1,012 elementary and middle school students in the Chungcheong region. Changes in responses to the Depressed Mood Questionnaire(RDQ), the Difficulties in Emotion Regulation Scale-16 (DERS-16), ‘future self-harm possibility’ scores wereanalyzed and compared before and after the program, based on age, sex, self-harm history, and methods of program implementation. Results: ：Overall, participants showed a decrease in the ‘rumination(RDQ) scale’ (t=10.49, p<0.001), ‘reversescored distraction (RDQ)’ (t=10.67, p<0.001) and the total DERS-16 (t=5.56, p<0.001) as well as a decrease in ‘future self-harm possibility’ score (t=4.26, p<0.001). Both elementary and middle school students showed decrease in ’rumination (RDQ)’ and distraction (RDQ), but only middle school students showed a decrease in theDERS-16 and most sub-scales. Regardless of sex, self-harm history, or methods of program implementation, adecrease in ’rumination (RDQ)’, distraction (RDQ) and the total DERS-16 scale and most sub-scales decreased. Conclusions ：Our program appears to be effective as a primary prevention program for preventing self-harm among children and adolescents in a school setting.

Objectives: ：This study aims to confirm the effectiveness of a school-based very-short-term dialectical be-havior therapy-skills training (DBT-ST) program for preventing self-harm among children and adolescents, considering factors such as age, sex, self-harm history, and methods of program implementation. Methods: ：The study was conducted from September 2021 to December 2023, targeting 1,012 elementary and middle school students in the Chungcheong region. Changes in responses to the Depressed Mood Questionnaire(RDQ), the Difficulties in Emotion Regulation Scale-16 (DERS-16), ‘future self-harm possibility’ scores wereanalyzed and compared before and after the program, based on age, sex, self-harm history, and methods of program implementation. Results: ：Overall, participants showed a decrease in the ‘rumination(RDQ) scale’ (t=10.49, p<0.001), ‘reversescored distraction (RDQ)’ (t=10.67, p<0.001) and the total DERS-16 (t=5.56, p<0.001) as well as a decrease in ‘future self-harm possibility’ score (t=4.26, p<0.001). Both elementary and middle school students showed decrease in ’rumination (RDQ)’ and distraction (RDQ), but only middle school students showed a decrease in theDERS-16 and most sub-scales. Regardless of sex, self-harm history, or methods of program implementation, adecrease in ’rumination (RDQ)’, distraction (RDQ) and the total DERS-16 scale and most sub-scales decreased. Conclusions ：Our program appears to be effective as a primary prevention program for preventing self-harm among children and adolescents in a school setting.

Objectives: ：This study aims to confirm the effectiveness of a school-based very-short-term dialectical be-havior therapy-skills training (DBT-ST) program for preventing self-harm among children and adolescents, considering factors such as age, sex, self-harm history, and methods of program implementation. Methods: ：The study was conducted from September 2021 to December 2023, targeting 1,012 elementary and middle school students in the Chungcheong region. Changes in responses to the Depressed Mood Questionnaire(RDQ), the Difficulties in Emotion Regulation Scale-16 (DERS-16), ‘future self-harm possibility’ scores wereanalyzed and compared before and after the program, based on age, sex, self-harm history, and methods of program implementation. Results: ：Overall, participants showed a decrease in the ‘rumination(RDQ) scale’ (t=10.49, p<0.001), ‘reversescored distraction (RDQ)’ (t=10.67, p<0.001) and the total DERS-16 (t=5.56, p<0.001) as well as a decrease in ‘future self-harm possibility’ score (t=4.26, p<0.001). Both elementary and middle school students showed decrease in ’rumination (RDQ)’ and distraction (RDQ), but only middle school students showed a decrease in theDERS-16 and most sub-scales. Regardless of sex, self-harm history, or methods of program implementation, adecrease in ’rumination (RDQ)’, distraction (RDQ) and the total DERS-16 scale and most sub-scales decreased. Conclusions ：Our program appears to be effective as a primary prevention program for preventing self-harm among children and adolescents in a school setting.

Objectives: ：This study aims to confirm the effectiveness of a school-based very-short-term dialectical be-havior therapy-skills training (DBT-ST) program for preventing self-harm among children and adolescents, considering factors such as age, sex, self-harm history, and methods of program implementation. Methods: ：The study was conducted from September 2021 to December 2023, targeting 1,012 elementary and middle school students in the Chungcheong region. Changes in responses to the Depressed Mood Questionnaire(RDQ), the Difficulties in Emotion Regulation Scale-16 (DERS-16), ‘future self-harm possibility’ scores wereanalyzed and compared before and after the program, based on age, sex, self-harm history, and methods of program implementation. Results: ：Overall, participants showed a decrease in the ‘rumination(RDQ) scale’ (t=10.49, p<0.001), ‘reversescored distraction (RDQ)’ (t=10.67, p<0.001) and the total DERS-16 (t=5.56, p<0.001) as well as a decrease in ‘future self-harm possibility’ score (t=4.26, p<0.001). Both elementary and middle school students showed decrease in ’rumination (RDQ)’ and distraction (RDQ), but only middle school students showed a decrease in theDERS-16 and most sub-scales. Regardless of sex, self-harm history, or methods of program implementation, adecrease in ’rumination (RDQ)’, distraction (RDQ) and the total DERS-16 scale and most sub-scales decreased. Conclusions ：Our program appears to be effective as a primary prevention program for preventing self-harm among children and adolescents in a school setting.