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.

Purpose: This study was conducted to assess the antidepressant effects of capsaicin in chronic depressive rats and elucidate the mechanism underlying its effects. Methods: Male Wistar rats (280~320 g, 8 weeks of age) were subjected to depression induced by chronic unpredictable mild stresses. The rats were exposed to 8 kinds of stresses for 8 weeks. In the last 2 weeks, fluoxetine or capsaicin was injected subcutaneously. The dose of fluoxetine was 10 mg/kg (body weight), while the doses of capsaicin consisted of low (1 mg/kg), middle (5 mg/kg), and high (10 mg/kg). The forced swim test (FST) was conducted to evaluate the immobility time of rats. The immobility time indicates despair, one of symptoms of depression. The change of tryptophan hydroxylase (TPH) in the dorsal raphe was investigated using immunohistochemistry. In the hippocampus cornu ammonis (CA) 1 and 3, glucocorticoid receptor (GR) expression was measured. Results: The immobility time in the FST was significantly lower (p < .05) in the low-dose (M = 32.40 ± 13.41 seconds) and middle-dose (M = 28.48 ± 19.57 seconds) groups than in the non-treated depressive rats (M = 90.19 ± 45.34 seconds). The amount of TPH in the dorsal raphe was significantly higher (p < .05) in the middle-dose (M = 249.17 ± 35.02) and high-dose (M = 251.0 ± 56.85) groups than in the non-treated depressive rats (M = 159.78 ± 41.16). However, GR expression in the hippocampus CA1 and CA3 did not show significant differences between the non-treated depressive rats and the capsaicin-injected rats. Conclusion This study suggests that capsaicin produces an antidepressant-like effect on chronic unpredictable mild stress-induced depression in rats via the serotonin biosynthesis pathway.

PURPOSE: Many studies have reported that pollen-food allergy syndrome (PFAS) can cause anaphylaxis. No comprehensive investigations into anaphylaxis in PFAS have been conducted, however. In this study, we investigated the clinical manifestations and risk factors for anaphylaxis in PFAS in Korean patients with pollinosis. MATERIALS AND METHODS: Data were obtained from a nationwide cross-sectional study that previously reported on PFAS in Korean patients with pollinosis. Data from 273 patients with PFAS were collected, including demographics, list of culprit fruits and vegetables, and clinical manifestations of food allergy. We analyzed 27 anaphylaxis patients and compared them with patients with PFAS with oropharyngeal symptoms only (n=130). RESULTS: The most common cause of anaphylaxis in PFAS was peanut (33.3%), apple (22.2%), walnut (22.2%), pine nut (18.5%), peach (14.8%), and ginseng (14.8%). Anaphylaxis was significantly associated with the strength of sensitization to alder, hazel, willow, poplar, timothy, and ragweed (p<0.05, respectively). Multivariable analysis revealed that the presence of atopic dermatitis [odds ratio (OR), 3.58; 95% confidence interval (CI), 1.25–10.23; p=0.017]; sensitization to hazel (OR, 5.27; 95% CI, 1.79–15.53; p=0.003), timothy (OR, 11.8; 95% CI, 2.70–51.64; p=0.001), or ragweed (OR, 3.18; 95% CI, 1.03–9.87; p=0.045); and the number of culprit foods (OR, 1.25; 95% CI, 1.15–1.37; p<0.001) were related to the development of anaphylaxis in PFAS. CONCLUSION: The most common culprit foods causing anaphylaxis in PFAS were peanut and apple. The presence of atopic dermatitis; sensitization to hazel, timothy, or ragweed; and a greater number of culprit foods were risk factors for anaphylaxis in PFAS.
Alnus ; Ambrosia ; Anaphylaxis ; Arachis ; Cross-Sectional Studies ; Demography ; Dermatitis, Atopic ; Food Hypersensitivity ; Fruit ; Humans ; Hypersensitivity ; Juglans ; Nuts ; Panax ; Pollen ; Prunus persica ; Rhinitis, Allergic, Seasonal ; Risk Factors ; Salix ; Vegetables

This erratum is being published to correct the error on page 650 of the article. The number of participating research institution should be corrected.

PURPOSE: Pollen-food allergy syndrome (PFAS) is an immunoglobulin E (IgE)-mediated allergy in pollinosis patients caused by raw fruits and vegetables and is the most common food allergy in adults. However, there has been no nationwide study on PFAS in Korea. In this study, we investigated the prevalence and clinical characteristics of PFAS in Korea. METHODS: Twenty-two investigators participated in this study, in which patients with allergic rhinoconjunctivitis and/or bronchial asthma with pollen allergy were enrolled. The questionnaires included demographic characteristics, a list of fruits and vegetables, and clinical manifestations of food allergy. Pollen allergy was diagnosed by skin prick test and/or measurement of the serum level of specific IgE. RESULTS: A total of 648 pollinosis patients were enrolled. The prevalence of PFAS was 41.7% (n = 270). PFAS patients exhibited cutaneous (43.0%), respiratory (20.0%), cardiovascular (3.7%) or neurologic symptoms (4.8%) in addition to oropharyngeal symptoms. Anaphylaxis was noted in 8.9% of the PFAS patients. Seventy types of foods were linked to PFAS; e.g., peach (48.5%), apple (46.7%), kiwi (30.4%), peanut (17.4%), plum (16.3%), chestnut (14.8%), pineapple (13.7%), walnut (14.1%), Korean melon (12.6%), tomato (11.9%), melon (11.5%) and apricot (10.7%). Korean foods such as taro/taro stem (8.9%), ginseong (8.2%), perilla leaf (4.4%), bellflower root (4.4%), crown daisy (3.0%), deodeok (3.3%), kudzu root (3.0%) and lotus root (2.6%) were also linked to PFAS. CONCLUSIONS: This was the first nationwide study of PFAS in Korea. The prevalence of PFAS was 41.7%, and 8.9% of the PFAS patients had anaphylaxis. These results will provide clinically useful information to physicians.
Adult ; Ananas ; Anaphylaxis ; Arachis ; Asthma ; Codonopsis ; Crowns ; Cucurbitaceae ; Food Hypersensitivity ; Fruit ; Humans ; Hypersensitivity* ; Immunoglobulin E ; Immunoglobulins ; Juglans ; Korea ; Lotus ; Lycopersicon esculentum ; Neurologic Manifestations ; Perilla ; Pollen ; Prevalence ; Prunus armeniaca ; Prunus domestica ; Prunus persica ; Pueraria ; Research Personnel ; Rhinitis, Allergic, Seasonal* ; Skin ; Vegetables

BACKGROUND: Despite the established benefits of diabetes camps for the continuing education of children with type 1 diabetes mellitus, little is known about the long-term metabolic benefits of diabetes camps for middle-aged and elderly people with type 2 diabetes mellitus (T2DM), especially in terms of glycosylated hemoglobin (HbA1c) variability. METHODS: The 1-year mean and variability of HbA1c before and after the diabetes camp was compared between the participants of the diabetes camp (n=57; median age 65 years [range, 50 to 86 years]; median diabetes duration 14 years [range, 1 to 48 years]). Additional case-control analysis compared the metabolic outcomes of the participants of the diabetes camp and their propensity score-matched controls who underwent conventional diabetes education (n=93). RESULTS: The levels of HbA1c during the first year after the diabetes camp were comparable to those of the matched controls (P=0.341). In an analysis of all participants of the diabetes camp, the 1-year mean±standard deviation (SD) of HbA1c decreased (P=0.010 and P=0.041) after the diabetes camp, whereas the adjusted SD and coefficient of variance (CV) of HbA1c did not decrease. The adjusted SD and CV significantly decreased after the diabetes camp in participants whose 1-year mean HbA1c was ≥6.5% before the diabetes camp (n=40) and those with a duration of diabetes less than 15 years (n=32). CONCLUSION: The 1-year mean and SD of HbA1c decreased after the diabetes camp, with significant reduction in the adjusted SD and CV in those with higher baseline HbA1c and a shorter duration of diabetes.
Adult ; Aged* ; Case-Control Studies ; Child ; Diabetes Mellitus, Type 1 ; Diabetes Mellitus, Type 2* ; Education ; Education, Continuing* ; Hemoglobin A, Glycosylated ; Humans ; Self Care*