1.A Multimodal Ensemble Deep Learning Model for Functional Outcome Prognosis of Stroke Patients
Hye-Soo JUNG ; Eun-Jae LEE ; Dae-Il CHANG ; Han Jin CHO ; Jun LEE ; Jae-Kwan CHA ; Man-Seok PARK ; Kyung Ho YU ; Jin-Man JUNG ; Seong Hwan AHN ; Dong-Eog KIM ; Ju Hun LEE ; Keun-Sik HONG ; Sung-Il SOHN ; Kyung-Pil PARK ; Sun U. KWON ; Jong S. KIM ; Jun Young CHANG ; Bum Joon KIM ; Dong-Wha KANG ;
Journal of Stroke 2024;26(2):312-320
Background:
and Purpose The accurate prediction of functional outcomes in patients with acute ischemic stroke (AIS) is crucial for informed clinical decision-making and optimal resource utilization. As such, this study aimed to construct an ensemble deep learning model that integrates multimodal imaging and clinical data to predict the 90-day functional outcomes after AIS.
Methods:
We used data from the Korean Stroke Neuroimaging Initiative database, a prospective multicenter stroke registry to construct an ensemble model integrated individual 3D convolutional neural networks for diffusion-weighted imaging and fluid-attenuated inversion recovery (FLAIR), along with a deep neural network for clinical data, to predict 90-day functional independence after AIS using a modified Rankin Scale (mRS) of 3–6. To evaluate the performance of the ensemble model, we compared the area under the curve (AUC) of the proposed method with that of individual models trained on each modality to identify patients with AIS with an mRS score of 3–6.
Results:
Of the 2,606 patients with AIS, 993 (38.1%) achieved an mRS score of 3–6 at 90 days post-stroke. Our model achieved AUC values of 0.830 (standard cross-validation [CV]) and 0.779 (time-based CV), which significantly outperformed the other models relying on single modalities: b-value of 1,000 s/mm2 (P<0.001), apparent diffusion coefficient map (P<0.001), FLAIR (P<0.001), and clinical data (P=0.004).
Conclusion
The integration of multimodal imaging and clinical data resulted in superior prediction of the 90-day functional outcomes in AIS patients compared to the use of a single data modality.
2.Direct Immunofluorescence for Dermatologic Disorders:A Single-Center Retrospective Analysis for 11 Years
Dong-Wha YOO ; Jang-Hoon YI ; Kyung-Deok PARK ; Hyeok-Jin KWON ; Ki-Ho KIM ; Jung-Ho YOON
Korean Journal of Dermatology 2024;62(1):18-28
Background:
Direct immunofluorescence (DIF) is a histochemical technique used to detect tissue-bound autoantibodies and diagnose various immune-mediated skin diseases.
Objective:
This study aimed to evaluate the sensitivity of DIF for each disorder, and the consistency between clinical, histopathological, and DIF results.
Methods:
A retrospective study was conducted in 194 patients who underwent skin biopsy and DIF testing at our hospital between January 2011 and December 2021. An antibody panel against immunoglobulin G (IgG), IgA, IgM, C3, C1q, and fibrinogen was used. The concordance rate and κ-coefficient between the clinical, histopathological, and DIF results were evaluated.
Results:
DIF was observed to be positive in 87 cases; 51 cases of immune-mediated bullous diseases, seven cases of connective tissue diseases (CTDs), 25 cases of vasculitis, and four cases of other diseases. The overall sensitivity of DIF for immune-mediated bullous diseases was 71.8%, which was higher than that of histopathology (64.8%). In CTDs and vasculitis, the overall sensitivities of DIF were 30.4% and 65.8%, respectively, which were lower than those of histopathology (73.9% and 84.2%, respectively). In addition, good concordance among the clinical, histological, and DIF results was observed.
Conclusion
DIF is a useful diagnostic method, especially for immune-mediated bullous diseases, lupus erythematosus, and Henoch-Schonlein purpura. However, in other CTDs and vasculitis cases, the sensitivity of DIF is relatively low. Therefore, the diagnostic value of DIF along with clinical and histopathological findings will be maximized only when the DIF test is performed for appropriate diseases.
3.Spontaneous Improvement of Eosinophilic Dermatosis of Hematologic Malignancy Concurrent with Follicular Lymphoma after Rituximab and Bendamustine Therapy
Kyung-Deok PARK ; Dong-Wha YOO ; Hyeok-Jin KWON ; Jang-Hoon YI ; Ho-Jin KIM ; Ki-Ho KIM ; Jung-Ho YOON
Korean Journal of Dermatology 2024;62(3):172-176
Eosinophilic dermatosis of hematological malignancy (EDHM) is a rare condition associated with various hematologic malignancies, characterized by pruritic skin eruptions. We present a case of a 66-year-old woman with follicular lymphoma who developed urticarial and vesicular lesions indicative of EDHM following chemotherapy.The diagnosis was confirmed through histological analysis, revealing eosinophilic infiltration. Treatment included additional chemotherapy sessions and topical corticosteroids, resulting in complete resolution of skin lesions and lymphoma. EDHM requires careful differentiation based on clinical and histological findings. The pathogenesis remains unclear, but addressing underlying hematologic malignancies appears crucial in management. Early recognition of EDHM is essential for appropriate intervention due to its limited therapeutic options.
4.A Case of Blastic Plasmacytoid Dendritic Cell Neoplasm with Mutations in DNMT3A, TET2, SRSF2, and ATRX Genes
Dong-Wha YOO ; Kyung-Deok PARK ; Hyeok-Jin KWON ; Ki-Ho KIM ; Jung-Ho YOON
Korean Journal of Dermatology 2023;61(1):57-61
Blastic plasmacytoid dendritic cell neoplasm (BPDCN) is a rare and aggressive lymphoma with an overall incidence of 0.04 cases per 100,000 people. BPDCN is a hematopoietic clonal neoplasm that originates from plasmacytoid dendritic cell precursors. A 63-year-old man presented with multiple erythematous nodules over his whole body, including his face, trunk, and both upper and lower extremities that appeared 1 month ago. Skin biopsy showed diffuse dermal infiltration by monomorphic atypical lymphocytes with large, irregular nuclei and scant cytoplasms. Immunohistochemical staining was positive for CD4, CD56, and CD123. The karyotype test showed abnormalities in male chromosomes 47, XY, +8 [2]/46, and XY [25], and mutations in DNMT3A, TET2, SRSF2, and ATRX genes were identified in a next-generation sequencing (NGS)-based acute myeloid leukemia gene panel test. The patient was diagnosed with BPDCN and treated with a KALLA 1406 regimen; however, he died on the 17th day of treatment.
5.Explanatory Power and Prognostic Implications of Factors Associated with Troponin Elevation in Acute Ischemic Stroke
Sung-Ho AHN ; Ji-Sung LEE ; Mi-Sook YUN ; Jung-Hee HAN ; Soo-Young KIM ; Young-Hak KIM ; Sang-Hyun LEE ; Min-Gyu PARK ; Kyung-Pil PARK ; Dong-Wha KANG ; Jong S. KIM ; Sun U. KWON
Journal of Stroke 2023;25(1):141-150
Background:
and Purpose We investigated the impact of comorbidity burden on troponin elevation, with separate consideration of neurological conditions, in patients with acute ischemic stroke (AIS).
Methods:
This prospective, observational cohort study consecutively enrolled patients with AIS for 2 years. Serum cardiac troponin I was repeatedly measured, and disease-related biomarkers were collected for diagnosis of preassigned comorbidities, including atrial fibrillation (AF), ischemic heart disease (IHD), myocardial hypertrophy (MH), heart failure (HF), renal insufficiency (RI), and active cancer. The severity of neurological deficits and insular cortical ischemic lesions were assessed as neurological conditions. Adjusted associations between these factors and troponin elevation were determined using a multivariate ordinal logistic regression model and area under the receiver operating characteristic curve (AUC). Cox proportional hazards model was used to determine the prognostic significance of comorbidity beyond neurological conditions.
Results:
Among 1,092 patients (66.5±12.4 years, 63.3% male), 145 (13.3%) and 335 (30.7%) had elevated (≥0.040 ng/mL) and minimally-elevated (0.040–0.010 ng/mL) troponin, respectively. In the adjusted analysis, AF, MH, HF, RI, active cancer, and neurological deficits were associated with troponin elevation. The multivariate model with six comorbidities and two neurological conditions exhibited an AUC of 0.729 (95% confidence interval [CI], 0.698–0.759). In Cox regression, AF, IHD, and HF were associated with adverse cardio-cerebrovascular events, whereas HF and active cancer were associated with mortality.
Conclusion
Troponin elevation in patients with AIS can be explained by the burden of comorbidities in combination with neurological status, which explains the prognostic significance of troponin assay.
8.2021 Clinical Practice Guidelines for Diabetes Mellitus in Korea
Kyu Yeon HUR ; Min Kyong MOON ; Jong Suk PARK ; Soo-Kyung KIM ; Seung-Hwan LEE ; Jae-Seung YUN ; Jong Ha BAEK ; Junghyun NOH ; Byung-Wan LEE ; Tae Jung OH ; Suk CHON ; Ye Seul YANG ; Jang Won SON ; Jong Han CHOI ; Kee Ho SONG ; Nam Hoon KIM ; Sang Yong KIM ; Jin Wha KIM ; Sang Youl RHEE ; You-Bin LEE ; Sang-Man JIN ; Jae Hyeon KIM ; Chong Hwa KIM ; Dae Jung KIM ; SungWan CHUN ; Eun-Jung RHEE ; Hyun Min KIM ; Hyun Jung KIM ; Donghyun JEE ; Jae Hyun KIM ; Won Seok CHOI ; Eun-Young LEE ; Kun-Ho YOON ; Seung-Hyun KO ;
Diabetes & Metabolism Journal 2021;45(4):461-481
The Committee of Clinical Practice Guidelines of the Korean Diabetes Association (KDA) updated the previous clinical practice guidelines for Korean adults with diabetes and prediabetes and published the seventh edition in May 2021. We performed a comprehensive systematic review of recent clinical trials and evidence that could be applicable in real-world practice and suitable for the Korean population. The guideline is provided for all healthcare providers including physicians, diabetes experts, and certified diabetes educators across the country who manage patients with diabetes or the individuals at the risk of developing diabetes mellitus. The recommendations for screening diabetes and glucose-lowering agents have been revised and updated. New sections for continuous glucose monitoring, insulin pump use, and non-alcoholic fatty liver disease in patients with diabetes mellitus have been added. The KDA recommends active vaccination for coronavirus disease 2019 in patients with diabetes during the pandemic. An abridgement that contains practical information for patient education and systematic management in the clinic was published separately.
9.2021 Clinical Practice Guidelines for Diabetes Mellitus in Korea
Kyu Yeon HUR ; Min Kyong MOON ; Jong Suk PARK ; Soo-Kyung KIM ; Seung-Hwan LEE ; Jae-Seung YUN ; Jong Ha BAEK ; Junghyun NOH ; Byung-Wan LEE ; Tae Jung OH ; Suk CHON ; Ye Seul YANG ; Jang Won SON ; Jong Han CHOI ; Kee Ho SONG ; Nam Hoon KIM ; Sang Yong KIM ; Jin Wha KIM ; Sang Youl RHEE ; You-Bin LEE ; Sang-Man JIN ; Jae Hyeon KIM ; Chong Hwa KIM ; Dae Jung KIM ; SungWan CHUN ; Eun-Jung RHEE ; Hyun Min KIM ; Hyun Jung KIM ; Donghyun JEE ; Jae Hyun KIM ; Won Seok CHOI ; Eun-Young LEE ; Kun-Ho YOON ; Seung-Hyun KO ;
Diabetes & Metabolism Journal 2021;45(4):461-481
The Committee of Clinical Practice Guidelines of the Korean Diabetes Association (KDA) updated the previous clinical practice guidelines for Korean adults with diabetes and prediabetes and published the seventh edition in May 2021. We performed a comprehensive systematic review of recent clinical trials and evidence that could be applicable in real-world practice and suitable for the Korean population. The guideline is provided for all healthcare providers including physicians, diabetes experts, and certified diabetes educators across the country who manage patients with diabetes or the individuals at the risk of developing diabetes mellitus. The recommendations for screening diabetes and glucose-lowering agents have been revised and updated. New sections for continuous glucose monitoring, insulin pump use, and non-alcoholic fatty liver disease in patients with diabetes mellitus have been added. The KDA recommends active vaccination for coronavirus disease 2019 in patients with diabetes during the pandemic. An abridgement that contains practical information for patient education and systematic management in the clinic was published separately.
10.Reliability and Clinical Utility of Machine Learning to Predict Stroke Prognosis: Comparison with Logistic Regression
Su-Kyeong JANG ; Jun Young CHANG ; Ji Sung LEE ; Eun-Jae LEE ; Yong-Hwan KIM ; Jung Hoon HAN ; Dae-Il CHANG ; Han Jin CHO ; Jae-Kwan CHA ; Kyung Ho YU ; Jin-Man JUNG ; Seong Hwan AHN ; Dong-Eog KIM ; Sung-Il SOHN ; Ju Hun LEE ; Kyung-Pil PARK ; Sun U. KWON ; Jong S. KIM ; Dong-Wha KANG ;
Journal of Stroke 2020;22(3):403-406

Result Analysis
Print
Save
E-mail