Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

Background: The diagnosis of major depressive disorder (MDD) relies primarily on clinical interviews, which can be subjective and time consuming. Thus, there is a need for more objective diagnostic tools. The aim of this study was to develop an artificial intelligence (AI) application that predicts the antidepressant drug response of individual patients with MDD based on longitudinal data. Methods: Longitudinal data from patient records, including sex, age, outpatient or inpatient status, medication type and dosage, and the Hamilton Depression Rating Scale (HAMD) scores, were used to train the Transformer model and the 1-dimensional convolutional neural network model. Individual patient records were allocated to training (80%), validation (10%), and testing (10%) datasets. Results: The AI model demonstrated 88% sensitivity and 92% specificity for predicting the treatment response. Significant factors independently associated with the antidepressant response included age, sex, history of depression, and baseline HAMD scores. Conclusion This AI-driven software application provides a clinically valuable tool for predicting treatment response.While promising, further research is needed to incorporate voice data into the AI model using the voice recording feature to further improve diagnostic accuracy.

BACKGROUND: Transient elastography (FibroScan®) is a non-invasive and rapid method for assessing liver fibrosis. While the feasibility and usefulness of FibroScan® have been proven in adults, few studies have focused on pediatric populations. We aimed to determine the feasibility and usefulness of FibroScan® in Korean children. METHODS: FibroScan® examinations were performed in 106 children (age, 5–15 years) who visited the Konyang University Hospital between June and September 2018. Liver steatosis was measured in terms of the controlled attenuation parameter (CAP), while hepatic fibrosis was evaluated in terms of the liver stiffness measurement (LSM). Children were stratified into obese and non-obese controls, according to body mass index (≥ or < 95th percentile, respectively). RESULTS: The obese group was characterized by significantly higher levels of aspartate aminotransferase (AST, 57.00 ± 48.47 vs. 26.40 ± 11.80 IU/L; P < 0.001) and alanine aminotransferase (ALT, 91.27 ± 97.67 vs. 16.28 ± 9.78 IU/L; P < 0.001), frequency of hypertension and abdominal obesity (abdominal circumference > 95% percentile) (P < 0.001), CAP (244.4–340.98 dB/m), and LSM (3.85–7.77 kPa) (P < 0.001). On FibroScan®, 30 of 59 obese children had fibrosis (LSM > 5.5 kPa), whereas the remaining 29 did not (LSM < 5.5 kPa). Obese children with fibrosis had higher levels of AST (73.57 ± 56.00 vs. 39.86 ± 31.93 IU/L; P = 0.009), ALT (132.47 ± 113.88 vs. 48.66 ± 51.29 IU/L; P = 0.001), and gamma-glutamyl transferase (106.67 ± 69.31 vs. 28.80 ± 24.26 IU/L; P = 0.042) compared to obese children without fibrosis. LSM had high and significant correlation (P < 0.05) with AST, ALT, homeostasis model assessment for insulin resistance, and AST-to-platelet ratio index. CONCLUSION: FibroScan® is clinically feasible and facilitates non-invasive, rapid, reproducible, and reliable detection of hepatic steatosis and liver fibrosis in the Korean pediatric population.
Adult ; Alanine Transaminase ; Aspartate Aminotransferases ; Body Mass Index ; Child ; Diagnosis ; Elasticity Imaging Techniques ; Fatty Liver ; Fibrosis ; Homeostasis ; Humans ; Hypertension ; Insulin Resistance ; Liver Cirrhosis ; Liver ; Methods ; Non-alcoholic Fatty Liver Disease ; Obesity, Abdominal ; Transferases

BACKGROUND: Diabetes can be efficiently prevented by life style modification and medical therapy. So, identification for high risk subjects for incident type 2 diabetes is important. The aim of this study is to identify the best β-cell function index to identify high risk subjects in non-diabetic Koreans. METHODS: This is a retrospective longitudinal study. Total 140 non-diabetic subjects who underwent standard 2-hour 75 g oral glucose tolerance test from January 2007 to February 2007 at Kangbuk Samsung Hospital and followed up for more than 1 year were analyzed (mean follow-up, 54.9±16.4 months). The subjects were consist of subjects with normal glucose tolerance (n=44) and subjects with prediabetes (n=97) who were 20 years of age or older. Samples for insulin and C-peptide levels were obtained at 0 and 30 minutes at baseline. RESULTS: Thirty subjects out of 140 subjects (21.4%) developed type 2 diabetes. When insulin-based index and C-peptide-based index are compared between progressor and non-progressor to diabetes, all C-peptide-based indices were statistically different between two groups, but only insulinogenic index and disposition index among insulin-based index were statistically different. C-peptide-based index had higher value of area under receiver operating characteristic curve (AROC) value than that of insulin-based index. "C-peptidogenic" index had highest AROC value among indices (AROC, 0.850; 95% confidence interval, 0.761 to 0.915). C-peptidogenic index had significantly higher AROC than insulinogenic index (0.850 vs. 0.731 respectively; P=0.014). CONCLUSION: C-peptide-based index was more closely related to incident type 2 diabetes in non-diabetic subjects than insulin-based index.
C-Peptide ; Follow-Up Studies ; Glucose ; Glucose Tolerance Test ; Insulin ; Life Style ; Longitudinal Studies ; Prediabetic State ; Retrospective Studies ; ROC Curve

PURPOSE: Transurethral resection of the prostate (TURP) is the gold standard treatment for symptomatic benign prostate hyperplasia, but significant complications are associated with this procedure. The aim of this study was to compare the standard TURP with the high power (80W) potassium-titanyl-phosphate laser (KTP/532; Greenlights PVTM laser system; Laserscope, San Jose, USA) to elucidate the efficacy and safety of laser treatment. MATERIALS AND METHODS: We performed comparative trials of 40 patients suffering with symptomatic bladder outlet obstruction due to benign prostatic hyperplasia from February 2005 to June 2005. Twenty patients were treated with TURP (Group I) and 20 patients were treated with KTP (Group II). All patients were assessed preoperatively and at an interval of 3 months postoperatively based on the International Prostate Symptom Score (IPSS), the quality of life (QoL) index, changes in maximum urinary flow rate (Qmax), and the postvoid residual urine (ml). The safety parameters we evaluated included the operative time (minutes), the postoperative catheterization time (day) and the blood loss (ml). The Kolmogorov- Smirnov & Shapiro-Wilk test, Student's t-test, Student's t-test (paired), and Fisher's Exact test were performed for statistical analysis. RESULTS: The mean age of each group was 68.9+/-9.9 years (group 1) and 63.9+/-9.7 years (group II), and the prostate weight was 49.5+/-15.4cc and 45.0+/-17.3cc, respectively. The mean operation time was shorter for group II (27.7+/-13.6min) than for group I (48.1+/-22.6min) (p<0.05). The mean catheterization time was 5.6+/-1.82 and 1.36+/-1.64 days, respectively, (p<0.001). The blood loss was lower in group II (11.7+/-11.4ml) than in group I (181.9+/-168.17ml, respectively) (p<0.001). CONCLUSIONS: In this preliminary short-term study, KTP Laser enucleation of the prostate was shown to be an effective alternative for treating benign prostate hyperplasia as compared with standard TURP.
Catheterization ; Catheters ; Humans ; Hyperplasia ; Laser Therapy* ; Lasers, Solid-State ; Operative Time ; Prostate* ; Prostatic Hyperplasia ; Quality of Life ; Transurethral Resection of Prostate ; Urinary Bladder Neck Obstruction

PURPOSE: The aim of this study was to evaluate the efficacy of a combination drug therapy (tamsulosin plus finasteride) for benign prostatic hyperplasia, with a small prostate volume of less than 40 grams. MATERIALS AND METHODS: One hundred and twenty-three patients, with symptomatic benign prostatic hyperplasia of less than 40 grams, were analysed. Group 1 (n=67) had been treated with a combination of finasteride (5mg/day) and tamsulosin (0.2mg/ day), and Group 2 (n=56) with tamsulosin only (0.2mg/day) over a 12 month period. The patients were periodically assessed by IPSS (international prostate symptom score), uroflowmetry and residual urine, during the treatment period. RESULTS: The mean changes in the total symptom score, obstructive and irritative symptom score for group 1 and group 2 at 1 year were -7.21+/-7.44 (39.86%), -4.79+/-5.07 (45.02%) and -2.42+/-3.25 (48.11%), and -7.39+/-9.98 (43.06%), -4.82+/-6.91 (45.21%) and -2.39+/-4.00 (37.82%) points, respectively. The mean changes in the peak urinary-flow rates and postvoid residual urine for group 1 and group 2 at 1 year were 2.07+/-5.42 (16.65%)ml/s and -31.58+/-60.99 (56.47%)ml, and 2.38+/-6.57 (16.53%)ml/s and -34.78+/-86.77 (50.24%)ml, respectively. The effects of the combination of finasteride and tamsulosin were no greater than the tamsulosin monotherapy (p>0.01). CONCLUSIONS: A combination of finasteride and tamsulosin is no more effective than tamsulosin alone, in patients with benign prostatic hyperplasia, with a prostate volume of less than 40 grams.
Drug Therapy, Combination ; Finasteride* ; Humans ; Prostate* ; Prostatic Hyperplasia*

OBJECTIVE: Treating patients with bipolar disorder has many problems such as recurrent various episodes, breakthroughs, treatment resistance, switching and worsening of its course. In addition to these obstacles, recent developments of psychiatric medications make it difficult to choose the appropriate pharmacological options. This study was performed to survey the expert opinion of medication treatment for bipolar disorder. METHODS: The survey questionnaire used in 'The Expert Consensus Guideline Series-Medication Treatment of Bipolar Disorder 2000' was translated in Korean and amended by executive committee according to Korean situations. Forty eight of 50 (96%) members of review committee completed the survey. RESULTS: In acute manic episode lithium or divalproex is a first-line drug as a monotherapy, and combination treatment is considered in partial or non-responder. Carbamazepine is also a first-line drug in dysphoric and mixed episodes. For moderate and more severe depression, an antidepressant is added with a mood stabilizer. For psychotic bipolar disorder, mania or depression, both atypical antipsychotics and high potency typical antipsychotics are preferred, but the latter is less likely to be recommended. A mood stabilizer should be used in rapid cycling bipolar illness. For manic episode in rapid cycler a mood stabilizer and an atypical antipsychotic drug are recommended in combination as an initial treatment. CONCLUSION: Most experts present strong consensus for many options concerning to initial strategies and first-line medications, although there are some non-consensus and gaps between research data and clinical usage in some steps. Nevertheless these data might be a cornerstone for producing the Korean medication algorithm for bipolar disorder.
Advisory Committees ; Antipsychotic Agents ; Bipolar Disorder ; Carbamazepine ; Consensus ; Depression ; Expert Testimony ; Humans ; Lithium ; Questionnaires ; Valproic Acid