Deep ocean warming-induced El Niño changes.

The deep ocean, a vast thermal reservoir, absorbs excess heat under greenhouse warming, which ultimately regulates the Earth's surface climate. Even if CO2 emissions are successfully reduced, the stored heat will gradually be released, resulting in a particular pattern of ocean warming. Here, we show that deep ocean warming will lead to El Niño-like ocean warming and resultant increased precipitation in the tropical eastern Pacific with southward shift of the intertropical convergence zone. Consequently, the El Niño-Southern Oscillation shifts eastward, intensifying Eastern Pacific El Niño events. In particular, the deep ocean warming could increase convective extreme El Niño events by 40 to 80% relative to the current climate. Our findings suggest that anthropogenic greenhouse warming will have a prolonged impact on El Niño variability through delayed deep ocean warming, even if CO2 stabilization is achieved.

Chemically Driven Clearance of Amyloid Aggregates by Polyfunctionalized Furo[2,3-b:4,5-b']dipyridine-Chalcone Hybrids to Ameliorate Memory in an Alzheimer Mouse Model.

The aberrant assembly of amyloid-ß (Aß) is implicated in Alzheimer's disease (AD). Recent clinical outcomes of Aß-targeted immunotherapy reinforce the notion that clearing Aß burden is a potential therapeutic approach for AD. Herein, to develop drug candidates for chemically driven clearance of Aß aggregates, we synthesized 51 novel polyfunctionalized furo[2,3-b:4,5-b']dipyridine-chalcone hybrid compounds. After conducting two types of cell-free anti-Aß functional assays, Aß aggregation prevention and Aß aggregate clearance, we selected YIAD-0336, (E)-8-((1H-pyrrol-2-yl)methylene)-10-(4-chlorophenyl)-2,4-dimethyl-7,8-dihydropyrido[3',2':4,5]furo[3,2-b]quinolin-9(6H)-one, for further in vivo investigations. As YIAD-0336 exhibited a low blood-brain barrier penetration profile, it was injected along with aggregated Aß directly into the intracerebroventricular region of ICR mice and ameliorated spatial memory in Y-maze tests. Next, YIAD-0336 was orally administered to 5XFAD transgenic mice with intravenous injections of mannitol, and YIAD-0336 significantly removed Aß plaques from the brains of 5XFAD mice. Collectively, YIAD-0336 dissociated toxic aggregates in the mouse brain and hence alleviated cognitive deterioration. Our findings indicate that chemically driven clearance of Aß aggregates is a promising therapeutic approach for AD.

Interfacial Stabilization by Prelithiated Trithiocyanuric Acid as an Organic Additive in Sulfide-Based All-Solid-State Lithium Metal Batteries.

Sulfide-based all-solid-state battery (ASSB) with a lithium metal anode (LMA) is a promising candidate to surpass conventional Li-ion batteries owing to their inherent safety against fire hazards and potential to achieve a higher energy density. However, the narrow electrochemical stability window and chemical reactivity of the sulfide solid electrolyte towards the LMA results in interfacial degradation and poor electrochemical performance. In this direction, we introduce an organic additive approach, that is the mixing of prelithiated trithiocyanuric acid, Li3TCA, with Li6PS5Cl, to establish a stable interface while preserving high ionic conductivity. Including 2.5 wt % Li3TCA alleviates the decomposition of the electrolyte on the lithium metal interface, decreasing the Li2S content in the solid-electrolyte interface (SEI) thus forming a more stable interface. In Li|Li symmetric cells, this strategy enables a rise in the critical current density from 1.0 to 1.9 mA cm-2 and stable cycling for over 750 hours at a high current density of 1.0 mA cm-2. This approach also enables Li|NbO-NCM811 full cell to operate more than 500 cycles at 0.3 C.

A Deep Learning Driven Simulation Analysis of the Emotional Profiles of Depression Based on Facial Expression Dynamics.

Objective: : Diagnosis and assessment of depression rely on scoring systems based on questionnaires, either self-reported by patients or administered by clinicians, and observation of patient facial expressions during the interviews plays a crucial role in making impressions in clinical settings. Deep learning driven approaches can assist clinicians in the course of diagnosis of depression by recognizing subtle facial expressions and emotions in depression patients. Methods: : Seventeen simulated patients who acted as depressed patients participated in this study. A trained psychiatrist structurally interviewed each participant with moderate depression in accordance with a prepared scenario and without depressive features. Interviews were video-recorded, and a facial emotion recognition algorithm was used to classify emotions of each frame. Results: : Among seven emotions (anger, disgust, fear, happiness, neutral, sadness, and surprise), sadness was expressed in a higher proportion on average in the depression-simulated group compared to the normal group. Neutral and fear were expressed in higher proportions on average in the normal group compared to the normal group. The overall distribution of emotions between the two groups was significantly different (p ＜ 0.001). Variance in emotion was significantly less in the depression-simulated group (p ＜ 0.05). Conclusion: : This study suggests a novel and practical approach to understand the emotional expression of depression patients based on deep learning techniques. Further research would allow us to obtain more perspectives on the emotional profiles of clinical patients, potentially providing helpful insights in making diagnosis of depression patients.

Rationally Designed Solution-Processible Conductive Carbon Additive Coating for Sulfide-based All-Solid-State Batteries.

Sulfide-based all-solid-state batteries (ASSBs) have emerged as promising candidates for next-generation energy storage systems owing to their superior safety and energy density. A conductive agent is necessarily added in the cathode composite of ASSBs to facilitate electron transport therein, but it causes the decomposition of the solid electrolyte and ultimately the shortening of lifetime. To resolve this dilemmatic situation, herein, we report a rationally designed solution-processible coating of zinc oxide (ZnO) onto vapor-grown carbon fiber as a conductive agent to reduce the contact between the carbon additive and the solid electrolyte and still maintain electron pathways to the active material. ASSBs with the carbon additive with an optimal coating of ZnO have markedly improved cycling performance and rate capability compared to those with the bare conductive agent, which can be attributed to hindering the decomposition of the solid electrolytes. The results highlight the usefulness of controlling the interparticle contacts in the composite cathodes in addressing the challenging interfacial degradation of sulfide-based ASSBs and improving their key electrochemical properties.

Increase in convective extreme El Niño events in a CO2 removal scenario.

Convective extreme El Niño (CEE) events, characterized by strong convective events in the eastern Pacific, are known to have a direct link to anomalous climate conditions worldwide, and it has been reported that CEE will occur more frequently under greenhouse warming. Here, using a set of CO2 ramp-up and ramp-down ensemble experiments, we show that frequency and maximum intensity of CEE events increase further in the ramp-down period from the ramp-up period. These changes in CEE are associated with the southward shift of the intertropical convergence zone and intensified nonlinear rainfall response to sea surface temperature change in the ramp-down period. The increasing frequency of CEE has substantial impacts on regional abnormal events and contributed considerably to regional mean climate changes to the CO2 forcings.

Effect of Home-based Self-administered Transcranial Direct Stimulation in Patients with Mild to Moderate Major Depressive Disorder: A Single-arm, Multicentral Trial.

Objective: Although the effects and safety of transcranial direct current stimulation (tDCS) treatment in depressive patients are largely investigated, whether the self-administration of tDCS treatment at patient's home is comparable to clinic-based treatment is still unknown. Methods: In this single-arm, multi-center clinical trial, 61 patients with mild to moderate major depressive disorder were enrolled. tDCS treatment was delivered at the patient's home once a day, 5 to 7 times a week for 6 weeks, and each session lasted for 30 minutes. The primary outcome was a total Beck-Depression Inventory-II score, and no concurrent antidepressants were used. Results: The remission rates in both Full-Analysis (FA) (n = 61) and Per-Protocol (PP) (n = 43) groups were statistically significant (FA: 57.4% [0.44-0.70], PP: 62.8% [0.47-0.77]; percent [95% confidence interval]). The degree of depression- related symptoms was also significantly improved in 2, 4, and 6 weeks after the treatment when compared with baseline. There was no significant association between treatment compliance and remission rate in both FA and PP groups. Conclusion: These results suggest that acute treatment of patient-administered tDCS might be effective in improving the subjective feeling of depressive symptoms in mild to moderate major depressive disorder patients.

Effects of Long-acting Injectable 3-Monthly Paliperidone Palmitate on the Clinical and Social Performance of Patients with Schizophrenia.

Objective: To investigate the effects of long-acting injectable 3-monthly paliperidone palmitate on the clinical and social functioning of patients with schizophrenia. Methods: This study enrolled patients with schizophrenia receiving long-acting injectable 1-monthly paliperidone palmitate for at least 4 months and who subsequently received 3-monthly paliperidone palmitate. Accordingly, 418 patients were followed up for 24 weeks. Their clinical symptoms and social functioning were measured using the Clinical Global Impression-Severity of Illness and Personal and Social Performance scales. Results: The Personal and Social Performance total score was significantly higher after 3-monthly paliperidone palmitate treatment than at baseline (baseline vs. week 24: 54.3 ± 18.0 vs. 61.0 ± 14.5 [mean ± standard deviation]; p < 0.001; Wilcoxon signed-rank test); the proportion of patients in the mildly ill group (scores 71-100) also increased significantly (baseline vs. week 24: 16.5% vs. 20.6%; p < 0.001; McNemar-Bowker test). The mean Clinical Global Impression-Severity of Illness score decreased significantly (baseline vs. week 24: 3.7 ± 1.0 vs. 3.4 ± 0.9; p < 0.001; Wilcoxon signed-rank test), as did the proportion of patients in the severely ill group (baseline vs. week 24: 4.1% vs. 2.1%; p < 0.001; McNemar-Bowker test). Conclusion: Continuous 3-monthly paliperidone palmitate treatment significantly enhances the personal and social performance of patients with schizophrenia and reduces the proportion of those with severe illness. These findings suggest that long-acting injectable antipsychotic administration at intervals longer than 1 month might improve the social functioning of and promote return to activities of daily living in patients with schizophrenia.

Development of depression detection algorithm using text scripts of routine psychiatric interview.

Background: A psychiatric interview is one of the important procedures in diagnosing psychiatric disorders. Through this interview, psychiatrists listen to the patient's medical history and major complaints, check their emotional state, and obtain clues for clinical diagnosis. Although there have been attempts to diagnose a specific mental disorder from a short doctor-patient conversation, there has been no attempt to classify the patient's emotional state based on the text scripts from a formal interview of more than 30 min and use it to diagnose depression. This study aimed to utilize the existing machine learning algorithm in diagnosing depression using the transcripts of one-on-one interviews between psychiatrists and depressed patients. Methods: Seventy-seven clinical patients [with depression (n = 60); without depression (n = 17)] with a prior psychiatric diagnosis history participated in this study. The study was conducted with 24 male and 53 female subjects with the mean age of 33.8 (± 3.0). Psychiatrists conducted a conversational interview with each patient that lasted at least 30 min. All interviews with the subjects between August 2021 and November 2022 were recorded and transcribed into text scripts, and a text emotion recognition module was used to indicate the subject's representative emotions of each sentence. A machine learning algorithm discriminates patients with depression and those without depression based on text scripts. Results: A machine learning model classified text scripts from depressive patients with non-depressive ones with an acceptable accuracy rate (AUC of 0.85). The distribution of emotions (surprise, fear, anger, love, sadness, disgust, neutral, and happiness) was significantly different between patients with depression and those without depression (p < 0.001), and the most contributing emotion in classifying the two groups was disgust (p < 0.001). Conclusion: This is a qualitative and retrospective study to develop a tool to detect depression against patients without depression based on the text scripts of psychiatric interview, suggesting a novel and practical approach to understand the emotional characteristics of depression patients and to use them to detect the diagnosis of depression based on machine learning methods. This model could assist psychiatrists in clinical settings who conduct routine conversations with patients using text transcripts of the interviews.

Room-Temperature Anode-Less All-Solid-State Batteries via the Conversion Reaction of Metal Fluorides.

All-solid-state batteries (ASSBs) that employ anode-less electrodes have drawn attention from across the battery community because they offer competitive energy densities and a markedly improved cycle life. Nevertheless, the composite matrices of anode-less electrodes impose a substantial barrier for lithium-ion diffusion and inhibit operation at room temperature. To overcome this drawback, here, the conversion reaction of metal fluorides is exploited because metallic nanodomains formed during this reaction induce an alloying reaction with lithium ions for uniform and sustainable lithium (de)plating. Lithium fluoride (LiF), another product of the conversion reaction, prevents the agglomeration of the metallic nanodomains and also protects the electrode from fatal lithium dendrite growth. A systematic analysis identifies silver (I) fluoride (AgF) as the most suitable metal fluoride because the silver nanodomains can accommodate the solid-solution mechanism with a low nucleation overpotential. AgF-based full cells attain reliable cycling at 25 °C even with an exceptionally high areal capacity of 9.7 mAh cm-2 (areal loading of LiNi0.8 Co0.1 Mn0.1 O2  = 50 mg cm-2 ). These results offer useful insights into designing materials for anode-less electrodes for sulfide-based ASSBs.

Comparative Analysis of the Psychosocial Symptoms and Experiences of Bereaved Parents and Parents of Children Who Survived the Sewol Ferry Accident After 5 Years: A Qualitative Interview Study.

BACKGROUND: This study aimed to investigate the psychosocial symptoms and experiences of bereaved parents of victims and parents of survivors of the Sewol Ferry accident five years after the accident. METHODS: In-depth interviews of 186 bereaved parents of victims or survivors of the Sewol Ferry accident were conducted. We elicited and categorized meaning units relevant to the psychological, cognitive, and physical traits of the participants from these interviews. Differences in responses between bereaved parents and survivors' parents and between genders were examined using frequency analyses and χ² tests. RESULTS: Data were organized under seven headings: observed attitude and impression of participants, difficulties due to mental health problems, difficulties due to physical pain, difficulties in relationships, negative changes following the incident, positive changes following the incident, and help needed. Within these headings, 27 themes, 60 sub-themes, and 80 meaning units were elicited. CONCLUSION: This study explored the psychiatric, physical, and relational problems reported by bereaved parents and those of survivors as well as major changes in their personal and social lives after the Sewol Ferry accident. Differences in responses according to gender were also identified. The results from this study could inform and facilitate the implementation of intervention measures, such as long-term psychological evaluation, to bereaved parents of victims or survivors of disasters.

Decreased Health-Seeking Behaviors in People With Depressive Symptoms: The Korea National Health and Nutrition Examination Survey 2014, 2016, and 2018.

OBJECTIVE: The purpose of this study was to investigate the effects of depressive symptoms on health-seeking behaviors using the large epidemiological study data of the Korea National Health and Nutrition Examination (KNHANES). METHODS: Data from the Korea National Health and Nutrition Examination Survey (KNHANES), which is a large-scale national survey, were used in this study. The Patient Health Questionnaire-9 (PHQ-9) was used to assess the depressive state of the participants. Specialized self-reported questionnaires that included questions about health-seeking behaviors were also performed. To examine the relationships between depression and health-seeking behaviors, complex sample logistic regression models with control for covariates were used. RESULTS: There was a significant association between decreased health-seeking behaviors and depressive symptoms in adults (odds ratio [OR]: 3.11, 95% confidence interval [CI]: 2.44-3.96). The association was found to be especially strong in males (OR: 2.63, 95% CI: 1.69-4.10) versus in females (OR: 2.49, 95% CI: 1.90-3.27). With regard to age group, younger adults (19-44 years of age) showed the highest OR (OR: 3.07, 95% CI: 2.12-4.45). CONCLUSION: Our findings support the idea that there is a significant association between health-seeking behaviors and depressive symptoms in the Korean population. These results suggest that individuals with decreased health-seeking behaviors could be evaluated for depressive symptoms.

Effect of Self-administered Transcranial Direct Stimulation in Patients with Major Depressive Disorder: A Randomized, Single-blinded Clinical Trial.

OBJECTIVE: In numerous studies that have addressed transcranial direct current stimulation (tDCS) devices, participants visit the hospital regularly and undergo stimulation directed by health professionals. This method has the advantage of being able to deliver accurate stimuli in a controlled environment, but it does not adopt the merits of tDCS portability and applicability. Thus, it may be necessary to investigate how self-administered tDCS treatment at home affects depression- related symptoms. METHODS: In this randomized, single-blinded clinical trial, 58 patients with major depressive disorder were assigned to active and sham tDCS stimulation groups, and treatment responses were evaluated biweekly over six weeks. Both active and sham tDCS treatment group were treated with escitalopram. All participants were instructed the protocol and usage of at-home tDCS device, and self-administered tDCS treatment at their home. RESULTS: The beck-depression inventory score decreased significantly as treatment progressed, and the degree of symptom improvement was significantly higher in the active group than in the sham tDCS group. There were no significant differences between the two groups in other indices, including the Hamilton Depression Scale. CONCLUSION: These results suggest that patient-administered tDCS treatment might be effective in improving subjective symptoms of depression.

A Deep Learning Algorithm to Predict Hazardous Drinkers and the Severity of Alcohol-Related Problems Using K-NHANES.

Purpose: The number of patients with alcohol-related problems is steadily increasing. A large-scale survey of alcohol-related problems has been conducted. However, studies that predict hazardous drinkers and identify which factors contribute to the prediction are limited. Thus, the purpose of this study was to predict hazardous drinkers and the severity of alcohol-related problems of patients using a deep learning algorithm based on a large-scale survey data. Materials and Methods: Datasets of National Health and Nutrition Examination Survey of South Korea (K-NHANES), a nationally representative survey for the entire South Korean population, were used to train deep learning and conventional machine learning algorithms. Datasets from 69,187 and 45,672 participants were used to predict hazardous drinkers and the severity of alcohol-related problems, respectively. Based on the degree of contribution of each variable to deep learning, it was possible to determine which variable contributed significantly to the prediction of hazardous drinkers. Results: Deep learning showed the higher performance than conventional machine learning algorithms. It predicted hazardous drinkers with an AUC (Area under the receiver operating characteristic curve) of 0.870 (Logistic regression: 0.858, Linear SVM: 0.849, Random forest classifier: 0.810, K-nearest neighbors: 0.740). Among 325 variables for predicting hazardous drinkers, energy intake was a factor showing the greatest contribution to the prediction, followed by carbohydrate intake. Participants were classified into Zone I, Zone II, Zone III, and Zone IV based on the degree of alcohol-related problems, showing AUCs of 0.881, 0.774, 0.853, and 0.879, respectively. Conclusion: Hazardous drinking groups could be effectively predicted and individuals could be classified according to the degree of alcohol-related problems using a deep learning algorithm. This algorithm could be used to screen people who need treatment for alcohol-related problems among the general population or hospital visitors.

Prediction of Mortality in Surgical Intensive Care Unit Patients Using Machine Learning Algorithms.

Objective: Predicting prognosis of in-hospital patients is critical. However, it is challenging to accurately predict the life and death of certain patients at certain period. To determine whether machine learning algorithms could predict in-hospital death of critically ill patients with considerable accuracy and identify factors contributing to the prediction power. Materials and Methods: Using medical data of 1,384 patients admitted to the Surgical Intensive Care Unit (SICU) of our institution, we investigated whether machine learning algorithms could predict in-hospital death using demographic, laboratory, and other disease-related variables, and compared predictions using three different algorithmic methods. The outcome measurement was the incidence of unexpected postoperative mortality which was defined as mortality without pre-existing not-for-resuscitation order that occurred within 30 days of the surgery or within the same hospital stay as the surgery. Results: Machine learning algorithms trained with 43 variables successfully classified dead and live patients with very high accuracy. Most notably, the decision tree showed the higher classification results (Area Under the Receiver Operating Curve, AUC = 0.96) than the neural network classifier (AUC = 0.80). Further analysis provided the insight that serum albumin concentration, total prenatal nutritional intake, and peak dose of dopamine drug played an important role in predicting the mortality of SICU patients. Conclusion: Our results suggest that machine learning algorithms, especially the decision tree method, can provide information on structured and explainable decision flow and accurately predict hospital mortality in SICU hospitalized patients.

Decreased cardiovascular death in schizophrenia patients treated with antipsychotics: A Korean national cohort study.

BACKGROUND: Patients with schizophrenia have a reduced life expectancy, but the association between antipsychotic usage and cause of death is uncertain. METHODS: The authors observed associations of antipsychotic usage with the mortality rate and cause of death in a population-based cohort of the Korean National Health Insurance Service database from 2003 to 2017. A total of 86,923 patients with schizophrenia were categorized by the total duration of antipsychotic prescription after schizophrenia diagnosis into treated (n = 77,139) and untreated (n = 9784) groups. The main outcome was all-cause mortality; causes of death included cardiovascular disease, pulmonary disease, diabetes, cancer, accident, suicide and homicide. RESULTS: The numbers of all-cause deaths and deaths from individual causes were significantly lower in the antipsychotic-treated group than in the untreated group (all cases, p < 10-4). When adjusted for covariates (age, sex, income, body mass index, alcohol consumption, hypertension, cancer and cerebral stroke), mortality rates due to ischemic heart disease (hazard ratio, HR, 0.38 [95% CI, 0.18-0.77]) and stroke (HR, 0.39 [95% CI, 0.19-0.80]) were significantly lower in the antipsychotic-treated group. Among 4 atypical antipsychotics (olanzapine, risperidone, aripiprazole and quetiapine), only aripiprazole was associated with a decreased mortality risk relative to olanzapine (HR, 0.55 [95% CI, 0.32-0.96]). CONCLUSIONS: Schizophrenia patients constantly prescribed antipsychotics had significantly lower rates of death from certain cardiovascular illnesses than untreated patients. Aripiprazole-treated schizophrenia was associated with a decreased risk of death compared with olanzapine-treated disease.

Factors associated with post-traumatic stress disorder among bereaved family members and surviving students two and half years after the Sewol ferry accident in South Korea.

BACKGROUND: The Sewol ferry accident was a human-made disaster that caused the death of 250 high school students on board the ferry. Post-traumatic stress disorder (PTSD) is one of the most serious mental health sequela among those exposed to disasters. Therefore this study assessed the PTSD symptoms among bereaved family members and surviving students after the disaster, along with associated risk factors. METHODS: Bereaved family members (N = 80) and surviving students (N = 48) of the disaster were assessed by self-reported questionnaires 2.5 years after the disaster. Sociodemographic and psychological variables (i.e., PTSD, depression, embitterment, rumination, and others) were obtained. Multivariable Poisson regression analyses were conducted to identify the factors associated with PTSD symptoms. RESULTS: Sixty-seven (83.8%) of the bereaved family members and three (6.3%) of the surviving students were suffering from probable PTSD. Depression and embitterment were associated with PTSD symptoms in both groups. Social support and meaning in life were related to PTSD symptoms only in the surviving students, while intrusive rumination and posttraumatic growth were related to PTSD symptoms only in the bereaved family members. CONCLUSIONS: These findings may help identify high-risk groups for PTSD and aid the development of psychological interventions to ameliorate PTSD symptoms of those affected by disasters.

Severe COVID-19 Illness: Risk Factors and Its Burden on Critical Care Resources.

In South Korea, the first confirmed case of coronavirus 2019 (COVID-19) was detected on January 20, 2020. After a month, the number of confirmed cases surged, as community transmission occurred. The local hospitals experienced severe shortages in medical resources such as mechanical ventilators and extracorporeal membrane oxygenation (ECMO) equipment. With the medical claims data of 7,590 COVID-19 confirmed patients, this study examined how the demand for major medical resources and medications changed during the outbreak and subsequent stabilization period of COVID-19 in South Korea. We also aimed to investigate how the underlying diseases and demographic factors affect disease severity. Our findings revealed that the risk of being treated with a mechanical ventilator or ECMO (critical condition) was almost twice as high in men, and a previous history of hypertension, diabetes, and psychiatric diseases increased the risk for progressing to critical condition [Odds Ratio (95% CI), 1.60 (1.14-2.24); 1.55 (1.55-2.06); 1.73 (1.25-2.39), respectively]. Although chronic pulmonary disease did not significantly increase the risk for severity of the illness, patients with a Charlson comorbidity index score of ≥5 and those treated in an outbreak area had an increased risk of developing a critical condition [3.82 (3.82-8.15); 1.59 (1.20-2.09), respectively]. Our results may help clinicians predict the demand for medical resources during the spread of COVID-19 infection and identify patients who are likely to develop severe disease.

Association Between Macronutrients Intake and Depression in the United States and South Korea.

Although the risk for depression appears to be related to daily dietary habits, how the proportion of major macronutrients affects the occurrence of depression remains largely unknown. This study aims to estimate the association between macronutrients (i.e., carbohydrate, protein, fat) and depression through national survey datasets from the United States and South Korea. Association between the prevalence of depression and each macronutrient was measured from 60,935 participants from the National Health and Nutrition Examination Survey (NHANES) and 15,700 participants from the South Korea NHANES (K-NHANES) databases. When the proportion of calories intake by protein increased by 10%, the prevalence of depression was significantly reduced both in the United States [Odds Ratio, OR (95% CI), 0.621 (0.530-0.728)] and South Korea [0.703 (0.397-0.994)]. An association between carbohydrate intake and the prevalence of depression was seen in the United States [1.194 (1.116-1.277)], but not in South Korea. Fat intake was not significantly associated with depression in either country. Subsequent analysis showed that the low protein intake groups had significantly higher risk for depression than the normal protein intake groups in both the United States [1.648 (1.179-2.304)] and South Korea [3.169 (1.598-6.286)]. In the daily diet of macronutrients, the proportion of protein intake is significantly associated with the prevalence of depression. These associations were more prominent in adults with insufficient protein intake, and the pattern of association between macronutrients and depression in Asian American and South Korean populations were similar. Our findings suggest that the proportion of macronutrients intake in everyday life may be related to the occurrence of depression.

Identifying Schizophrenia Using Structural MRI With a Deep Learning Algorithm.

OBJECTIVE: Although distinctive structural abnormalities occur in patients with schizophrenia, detecting schizophrenia with magnetic resonance imaging (MRI) remains challenging. This study aimed to detect schizophrenia in structural MRI data sets using a trained deep learning algorithm. METHOD: Five public MRI data sets (BrainGluSchi, COBRE, MCICShare, NMorphCH, and NUSDAST) from schizophrenia patients and normal subjects, for a total of 873 structural MRI data sets, were used to train a deep convolutional neural network. RESULTS: The deep learning algorithm trained with structural MR images detected schizophrenia in randomly selected images with reliable performance (area under the receiver operating characteristic curve [AUC] of 0.96). The algorithm could also identify MR images from schizophrenia patients in a previously unencountered data set with an AUC of 0.71 to 0.90. The deep learning algorithm's classification performance degraded to an AUC of 0.71 when a new data set with younger patients and a shorter duration of illness than the training data sets was presented. The brain region contributing the most to the performance of the algorithm was the right temporal area, followed by the right parietal area. Semitrained clinical specialists hardly discriminated schizophrenia patients from healthy controls (AUC: 0.61) in the set of 100 randomly selected brain images. CONCLUSIONS: The deep learning algorithm showed good performance in detecting schizophrenia and identified relevant structural features from structural brain MRI data; it had an acceptable classification performance in a separate group of patients at an earlier stage of the disease. Deep learning can be used to delineate the structural characteristics of schizophrenia and to provide supplementary diagnostic information in clinical settings.