1.Using machine learning techniques for early prediction of tracheal intubation in patients with septic shock: a multi-center study in South Korea
Ji Han HEO ; Taegyun KIM ; Tae Gun SHIN ; Gil Joon SUH ; Woon Yong KWON ; Hayoung KIM ; Heesu PARK ; Heejun KIM ; Sol HAN ;
Acute and Critical Care 2025;40(2):221-234
Background:
Patients with septic shock frequently require tracheal intubation in the emergency department (ED). However, the criteria for tracheal intubation are subjective, based on physician experience, or require serial evaluations over relatively long intervals to make accurate predictions, which might not be feasible in the ED. We used supervised learning approaches and features routinely available during the initial stages of evaluation and resuscitation to stratify the risks of tracheal intubation within a 24-hour time window.
Methods:
We retrospectively analyzed the data of patients diagnosed with septic shock based on the SEPSIS-3 criteria across 21 university hospital EDs in the Republic of Korea. A principal component analysis revealed a complex, non-linear decision boundary with respect to the application of tracheal intubation within a 24-hour time window. Stratified five-fold cross validation and a grid search were used with extreme gradient boost. Shapley values were calculated to explain feature importance and preferences.
Results:
In total, data for 4,762 patients were analyzed; within that population, 1,486 (31%) were intubated within a 24-hour window, and 3,276 (69%) were not. The area under the receiver operating characteristic curve and F1 scores for intubation within a 24-hour window were 0.829 (95% CI, 0.801–0.878) and 0.654 (95% CI, 0.627–0.681), respectively. The Shapley values identified lactate level after initial fluids, suspected lung infection, initial pH, Sequential Organ Failure Assessment score at enrollment, and respiratory rate at enrollment as important features for prediction.
Conclusions
An extreme gradient boosting machine can moderately discriminate whether intubation is warranted within 24 hours of the recognition of septic shock in the ED.
2.Simulating the Effect of Junction Setup Error in Dual-Isocentric Volumetric Modulated Arc Therapy for Pelvic Radiotherapy with a Large Target
Hojeong LEE ; Dong Woon KIM ; Ji Hyeon JOO ; Yongkan KI ; Wontaek KIM ; Dahl PARK ; Jiho NAM ; Dong Hyeon KIM ; Hosang JEON
Progress in Medical Physics 2024;35(2):52-57
Purpose:
The use of two adjacent radiation beams to treat a lesion that is larger than the maximum field of a machine may lead to higher or lower dose distribution at the junction than expected. Therefore, evaluation of the junction dose is crucial for radiotherapy. Volumetric modulated arc therapy (VMAT) can effectively protect surrounding normal tissues by implementing a complex dose distribution; therefore, two adjacent VMAT fields can effectively treat large lesions. However, VMAT can lead to significant errors in the junction dose between fields if setup errors occur due to its highly complex dose distributions.
Methods:
In this study, setup errors of ±1, ±3, and ±5 mm were assumed during radiotherapy for treating large lesions in the lower abdomen, and their effects on the treatment dose distribution and target coverage were analyzed using gamma pass rate (GP) and homogeneity index (HI). All studies were performed using a computational simulation method based on our radiation treatment planning software.
Results:
Consequently, when the setup error was more than ±3 mm, most GP values using a 3%/3-mm criterion decreased by <90%. GP was independent of the direction of the field gap (FG), whereas HI values were relatively more affected by negative values for FG.
Conclusions
Therefore, the size and direction of setup errors should be carefully managed when performing dual-isocentric VMATs for large targets.
3.Korean Multicenter Registry of ELUVIA Stent for Femoropopliteal Artery Disease: K-ELUVIA Registry
Joongmin KIM ; Young-Guk KO ; Seung-Jun LEE ; Chul-Min AHN ; Seung-Woon RHA ; Cheol Ung CHOI ; Pil-Ki MIN ; Jong Kwan PARK ; Ji-Yong JANG ; Young Jin YOUN ; Tae-Soo KANG ; Chang-Hwan YOON ; Donghoon CHOI
Korean Circulation Journal 2024;54(9):565-576
Background and Objectives:
The K-ELUVIA study aimed to investigate the clinical effectiveness and safety of Eluvia™, a polymer-coated, paclitaxel-eluting stent, for femoropopliteal artery disease using data from a prospective Korean multicenter registry.
Methods:
A total of 105 patients with femoropopliteal artery disease who received endovascular treatment (EVT) with Eluvia™ stents at 7 Korean sites were enrolled in a prospective cohort and followed for 2 years. The primary endpoint was the 2-year clinical patency. The secondary endpoint was 2-year freedom from clinically driven target lesion revascularization (TLR).
Results:
Mean patient age was 68.2±10.4 years, and most patients (82.7%) were male. Mean lesion length was 168.3±117.6 mm. Chronic total occlusion was found in 57.7% of patients.Trans-Atlantic Inter-Society Consensus for the Management of Peripheral Arterial Disease (TASC II) type C or D lesions were present in 46.1% of patients. Procedural success was achieved in 99.0% of patients. The clinical patency rate was 84.4% at 1 year after EVT and 76.3% at 2 years post-EVT. The freedom from TLR rate was 89.1% at 1 year after EVT and 79.1% at 2 years post-EVT. Chronic total occlusion (hazard ratio [HR], 3.53; 95% confidence interval [CI], 1.08–11.67; p=0.039) and smaller mean stent diameter (HR, 0.40; 95% CI, 0.16– 0.98; p=0.044) were identified as independent predictors of loss of clinical patency at 2 years.
Conclusions
The K-ELUVIA study demonstrated favorable 2-year clinical effectiveness and safety outcomes of Eluvia stent for femoropopliteal artery lesions in real-world practice.
4.Simulating the Effect of Junction Setup Error in Dual-Isocentric Volumetric Modulated Arc Therapy for Pelvic Radiotherapy with a Large Target
Hojeong LEE ; Dong Woon KIM ; Ji Hyeon JOO ; Yongkan KI ; Wontaek KIM ; Dahl PARK ; Jiho NAM ; Dong Hyeon KIM ; Hosang JEON
Progress in Medical Physics 2024;35(2):52-57
Purpose:
The use of two adjacent radiation beams to treat a lesion that is larger than the maximum field of a machine may lead to higher or lower dose distribution at the junction than expected. Therefore, evaluation of the junction dose is crucial for radiotherapy. Volumetric modulated arc therapy (VMAT) can effectively protect surrounding normal tissues by implementing a complex dose distribution; therefore, two adjacent VMAT fields can effectively treat large lesions. However, VMAT can lead to significant errors in the junction dose between fields if setup errors occur due to its highly complex dose distributions.
Methods:
In this study, setup errors of ±1, ±3, and ±5 mm were assumed during radiotherapy for treating large lesions in the lower abdomen, and their effects on the treatment dose distribution and target coverage were analyzed using gamma pass rate (GP) and homogeneity index (HI). All studies were performed using a computational simulation method based on our radiation treatment planning software.
Results:
Consequently, when the setup error was more than ±3 mm, most GP values using a 3%/3-mm criterion decreased by <90%. GP was independent of the direction of the field gap (FG), whereas HI values were relatively more affected by negative values for FG.
Conclusions
Therefore, the size and direction of setup errors should be carefully managed when performing dual-isocentric VMATs for large targets.
5.Simulating the Effect of Junction Setup Error in Dual-Isocentric Volumetric Modulated Arc Therapy for Pelvic Radiotherapy with a Large Target
Hojeong LEE ; Dong Woon KIM ; Ji Hyeon JOO ; Yongkan KI ; Wontaek KIM ; Dahl PARK ; Jiho NAM ; Dong Hyeon KIM ; Hosang JEON
Progress in Medical Physics 2024;35(2):52-57
Purpose:
The use of two adjacent radiation beams to treat a lesion that is larger than the maximum field of a machine may lead to higher or lower dose distribution at the junction than expected. Therefore, evaluation of the junction dose is crucial for radiotherapy. Volumetric modulated arc therapy (VMAT) can effectively protect surrounding normal tissues by implementing a complex dose distribution; therefore, two adjacent VMAT fields can effectively treat large lesions. However, VMAT can lead to significant errors in the junction dose between fields if setup errors occur due to its highly complex dose distributions.
Methods:
In this study, setup errors of ±1, ±3, and ±5 mm were assumed during radiotherapy for treating large lesions in the lower abdomen, and their effects on the treatment dose distribution and target coverage were analyzed using gamma pass rate (GP) and homogeneity index (HI). All studies were performed using a computational simulation method based on our radiation treatment planning software.
Results:
Consequently, when the setup error was more than ±3 mm, most GP values using a 3%/3-mm criterion decreased by <90%. GP was independent of the direction of the field gap (FG), whereas HI values were relatively more affected by negative values for FG.
Conclusions
Therefore, the size and direction of setup errors should be carefully managed when performing dual-isocentric VMATs for large targets.
6.Korean Multicenter Registry of ELUVIA Stent for Femoropopliteal Artery Disease: K-ELUVIA Registry
Joongmin KIM ; Young-Guk KO ; Seung-Jun LEE ; Chul-Min AHN ; Seung-Woon RHA ; Cheol Ung CHOI ; Pil-Ki MIN ; Jong Kwan PARK ; Ji-Yong JANG ; Young Jin YOUN ; Tae-Soo KANG ; Chang-Hwan YOON ; Donghoon CHOI
Korean Circulation Journal 2024;54(9):565-576
Background and Objectives:
The K-ELUVIA study aimed to investigate the clinical effectiveness and safety of Eluvia™, a polymer-coated, paclitaxel-eluting stent, for femoropopliteal artery disease using data from a prospective Korean multicenter registry.
Methods:
A total of 105 patients with femoropopliteal artery disease who received endovascular treatment (EVT) with Eluvia™ stents at 7 Korean sites were enrolled in a prospective cohort and followed for 2 years. The primary endpoint was the 2-year clinical patency. The secondary endpoint was 2-year freedom from clinically driven target lesion revascularization (TLR).
Results:
Mean patient age was 68.2±10.4 years, and most patients (82.7%) were male. Mean lesion length was 168.3±117.6 mm. Chronic total occlusion was found in 57.7% of patients.Trans-Atlantic Inter-Society Consensus for the Management of Peripheral Arterial Disease (TASC II) type C or D lesions were present in 46.1% of patients. Procedural success was achieved in 99.0% of patients. The clinical patency rate was 84.4% at 1 year after EVT and 76.3% at 2 years post-EVT. The freedom from TLR rate was 89.1% at 1 year after EVT and 79.1% at 2 years post-EVT. Chronic total occlusion (hazard ratio [HR], 3.53; 95% confidence interval [CI], 1.08–11.67; p=0.039) and smaller mean stent diameter (HR, 0.40; 95% CI, 0.16– 0.98; p=0.044) were identified as independent predictors of loss of clinical patency at 2 years.
Conclusions
The K-ELUVIA study demonstrated favorable 2-year clinical effectiveness and safety outcomes of Eluvia stent for femoropopliteal artery lesions in real-world practice.
7.Korean Multicenter Registry of ELUVIA Stent for Femoropopliteal Artery Disease: K-ELUVIA Registry
Joongmin KIM ; Young-Guk KO ; Seung-Jun LEE ; Chul-Min AHN ; Seung-Woon RHA ; Cheol Ung CHOI ; Pil-Ki MIN ; Jong Kwan PARK ; Ji-Yong JANG ; Young Jin YOUN ; Tae-Soo KANG ; Chang-Hwan YOON ; Donghoon CHOI
Korean Circulation Journal 2024;54(9):565-576
Background and Objectives:
The K-ELUVIA study aimed to investigate the clinical effectiveness and safety of Eluvia™, a polymer-coated, paclitaxel-eluting stent, for femoropopliteal artery disease using data from a prospective Korean multicenter registry.
Methods:
A total of 105 patients with femoropopliteal artery disease who received endovascular treatment (EVT) with Eluvia™ stents at 7 Korean sites were enrolled in a prospective cohort and followed for 2 years. The primary endpoint was the 2-year clinical patency. The secondary endpoint was 2-year freedom from clinically driven target lesion revascularization (TLR).
Results:
Mean patient age was 68.2±10.4 years, and most patients (82.7%) were male. Mean lesion length was 168.3±117.6 mm. Chronic total occlusion was found in 57.7% of patients.Trans-Atlantic Inter-Society Consensus for the Management of Peripheral Arterial Disease (TASC II) type C or D lesions were present in 46.1% of patients. Procedural success was achieved in 99.0% of patients. The clinical patency rate was 84.4% at 1 year after EVT and 76.3% at 2 years post-EVT. The freedom from TLR rate was 89.1% at 1 year after EVT and 79.1% at 2 years post-EVT. Chronic total occlusion (hazard ratio [HR], 3.53; 95% confidence interval [CI], 1.08–11.67; p=0.039) and smaller mean stent diameter (HR, 0.40; 95% CI, 0.16– 0.98; p=0.044) were identified as independent predictors of loss of clinical patency at 2 years.
Conclusions
The K-ELUVIA study demonstrated favorable 2-year clinical effectiveness and safety outcomes of Eluvia stent for femoropopliteal artery lesions in real-world practice.
8.Simulating the Effect of Junction Setup Error in Dual-Isocentric Volumetric Modulated Arc Therapy for Pelvic Radiotherapy with a Large Target
Hojeong LEE ; Dong Woon KIM ; Ji Hyeon JOO ; Yongkan KI ; Wontaek KIM ; Dahl PARK ; Jiho NAM ; Dong Hyeon KIM ; Hosang JEON
Progress in Medical Physics 2024;35(2):52-57
Purpose:
The use of two adjacent radiation beams to treat a lesion that is larger than the maximum field of a machine may lead to higher or lower dose distribution at the junction than expected. Therefore, evaluation of the junction dose is crucial for radiotherapy. Volumetric modulated arc therapy (VMAT) can effectively protect surrounding normal tissues by implementing a complex dose distribution; therefore, two adjacent VMAT fields can effectively treat large lesions. However, VMAT can lead to significant errors in the junction dose between fields if setup errors occur due to its highly complex dose distributions.
Methods:
In this study, setup errors of ±1, ±3, and ±5 mm were assumed during radiotherapy for treating large lesions in the lower abdomen, and their effects on the treatment dose distribution and target coverage were analyzed using gamma pass rate (GP) and homogeneity index (HI). All studies were performed using a computational simulation method based on our radiation treatment planning software.
Results:
Consequently, when the setup error was more than ±3 mm, most GP values using a 3%/3-mm criterion decreased by <90%. GP was independent of the direction of the field gap (FG), whereas HI values were relatively more affected by negative values for FG.
Conclusions
Therefore, the size and direction of setup errors should be carefully managed when performing dual-isocentric VMATs for large targets.
9.Korean Multicenter Registry of ELUVIA Stent for Femoropopliteal Artery Disease: K-ELUVIA Registry
Joongmin KIM ; Young-Guk KO ; Seung-Jun LEE ; Chul-Min AHN ; Seung-Woon RHA ; Cheol Ung CHOI ; Pil-Ki MIN ; Jong Kwan PARK ; Ji-Yong JANG ; Young Jin YOUN ; Tae-Soo KANG ; Chang-Hwan YOON ; Donghoon CHOI
Korean Circulation Journal 2024;54(9):565-576
Background and Objectives:
The K-ELUVIA study aimed to investigate the clinical effectiveness and safety of Eluvia™, a polymer-coated, paclitaxel-eluting stent, for femoropopliteal artery disease using data from a prospective Korean multicenter registry.
Methods:
A total of 105 patients with femoropopliteal artery disease who received endovascular treatment (EVT) with Eluvia™ stents at 7 Korean sites were enrolled in a prospective cohort and followed for 2 years. The primary endpoint was the 2-year clinical patency. The secondary endpoint was 2-year freedom from clinically driven target lesion revascularization (TLR).
Results:
Mean patient age was 68.2±10.4 years, and most patients (82.7%) were male. Mean lesion length was 168.3±117.6 mm. Chronic total occlusion was found in 57.7% of patients.Trans-Atlantic Inter-Society Consensus for the Management of Peripheral Arterial Disease (TASC II) type C or D lesions were present in 46.1% of patients. Procedural success was achieved in 99.0% of patients. The clinical patency rate was 84.4% at 1 year after EVT and 76.3% at 2 years post-EVT. The freedom from TLR rate was 89.1% at 1 year after EVT and 79.1% at 2 years post-EVT. Chronic total occlusion (hazard ratio [HR], 3.53; 95% confidence interval [CI], 1.08–11.67; p=0.039) and smaller mean stent diameter (HR, 0.40; 95% CI, 0.16– 0.98; p=0.044) were identified as independent predictors of loss of clinical patency at 2 years.
Conclusions
The K-ELUVIA study demonstrated favorable 2-year clinical effectiveness and safety outcomes of Eluvia stent for femoropopliteal artery lesions in real-world practice.
10.Simulating the Effect of Junction Setup Error in Dual-Isocentric Volumetric Modulated Arc Therapy for Pelvic Radiotherapy with a Large Target
Hojeong LEE ; Dong Woon KIM ; Ji Hyeon JOO ; Yongkan KI ; Wontaek KIM ; Dahl PARK ; Jiho NAM ; Dong Hyeon KIM ; Hosang JEON
Progress in Medical Physics 2024;35(2):52-57
Purpose:
The use of two adjacent radiation beams to treat a lesion that is larger than the maximum field of a machine may lead to higher or lower dose distribution at the junction than expected. Therefore, evaluation of the junction dose is crucial for radiotherapy. Volumetric modulated arc therapy (VMAT) can effectively protect surrounding normal tissues by implementing a complex dose distribution; therefore, two adjacent VMAT fields can effectively treat large lesions. However, VMAT can lead to significant errors in the junction dose between fields if setup errors occur due to its highly complex dose distributions.
Methods:
In this study, setup errors of ±1, ±3, and ±5 mm were assumed during radiotherapy for treating large lesions in the lower abdomen, and their effects on the treatment dose distribution and target coverage were analyzed using gamma pass rate (GP) and homogeneity index (HI). All studies were performed using a computational simulation method based on our radiation treatment planning software.
Results:
Consequently, when the setup error was more than ±3 mm, most GP values using a 3%/3-mm criterion decreased by <90%. GP was independent of the direction of the field gap (FG), whereas HI values were relatively more affected by negative values for FG.
Conclusions
Therefore, the size and direction of setup errors should be carefully managed when performing dual-isocentric VMATs for large targets.

Result Analysis
Print
Save
E-mail