Latent diffusion model-based MRI superresolution enhances mild cognitive impairment prognostication and Alzheimer's disease classification.

INTRODUCTION: Timely diagnosis and prognostication of Alzheimer's disease (AD) and mild cognitive impairment (MCI) are pivotal for effective intervention. Artificial intelligence (AI) in neuroradiology may aid in such appropriate diagnosis and prognostication. This study aimed to evaluate the potential of novel diffusion model-based AI for enhancing AD and MCI diagnosis through superresolution (SR) of brain magnetic resonance (MR) images. METHODS: 1.5T brain MR scans of patients with AD or MCI and healthy controls (NC) from Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) were superresolved to 3T using a novel diffusion model-based generative AI (d3T*) and a convolutional neural network-based model (c3T*). Comparisons of image quality to actual 1.5T and 3T MRI were conducted based on signal-to-noise ratio (SNR), naturalness image quality evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE). Voxel-based volumetric analysis was then conducted to study whether 3T* images offered more accurate volumetry than 1.5T images. Binary and multiclass classifications of AD, MCI, and NC were conducted to evaluate whether 3T* images offered superior AD classification performance compared to actual 1.5T MRI. Moreover, CNN-based classifiers were used to predict conversion of MCI to AD, to evaluate the prognostication performance of 3T* images. The classification performances were evaluated using accuracy, sensitivity, specificity, F1 score, Matthews correlation coefficient (MCC), and area under the receiver-operating curves (AUROC). RESULTS: Analysis of variance (ANOVA) detected significant differences in image quality among the 1.5T, c3T*, d3T*, and 3T groups across all metrics. Both c3T* and d3T* showed superior image quality compared to 1.5T MRI in NIQE and BRISQUE with statistical significance. While the hippocampal volumes measured in 3T* and 3T images were not significantly different, the hippocampal volume measured in 1.5T images showed significant difference. 3T*-based AD classifications showed superior performance across all performance metrics compared to 1.5T-based AD classification. Classification performance between d3T* and actual 3T was not significantly different. 3T* images offered superior accuracy in predicting the conversion of MCI to AD than 1.5T images did. CONCLUSIONS: The diffusion model-based MRI SR enhances the resolution of brain MR images, significantly improving diagnostic and prognostic accuracy for AD and MCI. Superresolved 3T* images closely matched actual 3T MRIs in quality and volumetric accuracy, and notably improved the prediction performance of conversion from MCI to AD.

Network biomarkers in recovered psychosis patients who discontinued antipsychotics.

There are no studies investigating topological properties of resting-state fMRI (rs-fMRI) in patients who have recovered from psychosis and discontinued medication (hereafter, recovered patients [RP]). This study aimed to explore topological organization of the functional brain connectome in the RP using graph theory approach. We recruited 30 RP and 50 age and sex-matched healthy controls (HC). The RP were further divided into the subjects who were relapsed after discontinuation of antipsychotics (RP-R) and who maintained recovered state without relapse (RP-M). Using graph-based network analysis of rs-fMRI signals, global and local metrics and hub information were obtained. The robustness of the network was tested with random failure and targeted attack. As an ancillary analysis, Network-Based Statistic (NBS) was performed. Association of significant findings with psychopathology and cognitive functioning was also explored. The RP showed intact network properties in terms of global and local metrics. However, higher global functional connectivity strength and hyperconnectivity in the interconnected component were observed in the RP compared to HC. In the subgroup analysis, the RP-R were found to have lower global efficiency, longer characteristic path length and lower robustness whereas no such abnormalities were identified in the RP-M. Associations of the degree centrality of some hubs with cognitive functioning were identified in the RP-M. Even though network properties of the RP were intact, subgroup analysis revealed more altered topological organizations in the RP-R. The findings in the RP-R and RP-M may serve as network biomarkers for predicting relapse or maintained recovery after the discontinuation of antipsychotics.

Understanding the Fluctuations in Korea's Suicide Rates: A Change-Point Analysis and Interrupted Time Series Analysis.

BACKGROUND: Korea has witnessed significant fluctuations in its suicide rates in recent decades, which may be related to modifications in its death registration system. This study aimed to explore the structural shifts in suicide trends, as well as accidental and ill-defined deaths in Korea, and to analyze the patterns of these changes. METHODS: We analyzed age-adjusted death rates for suicides, deaths due to transport accidents, falls, drowning, fire-related incidents, poisonings, other external causes, and ill-defined deaths in Korea from 1997 to 2021. We identified change-points using the 'breakpoints' function from the 'strucchange' package and conducted interrupted time series analyses to assess trends before and after these change-points. RESULTS: Korea's suicide rates had three change-points in February 2003, September 2008, and June 2012, characterized by stair-step changes, with level jumps at the 2003 and 2008 change-points and a sharp decline at the 2012 change-point. Notably, the 2003 and 2008 spikes roughly coincided with modifications to the death ascertainment process. The trend in suicide rates showed a downward slope within the 2003-2008 and 2008-2012 periods. Furthermore, ill-defined deaths and most accidental deaths decreased rapidly through several change-points in the early and mid-2000s. CONCLUSION: The marked fluctuations in Korea's suicide rate during the 2000s may be largely attributed to improvements in suicide classification, with potential implications beyond socio-economic factors. These findings suggest that the actual prevalence of suicides in Korea in the 2000s might have been considerably higher than officially reported.

Changes in Hip and Knee Strength Are Not Associated With Improved Clinical Outcomes After Rehabilitation in Individuals With Patellofemoral Pain: A Critically Appraised Topic.

CLINICAL SCENARIO: Patellofemoral pain (PFP) is a widespread knee disorder encountered in clinical practice. Clinicians have often focused on strengthening hip and knee musculature to improve pain and disability, which are the ultimate clinical goals of PFP treatment. However, PFP literature has shown improvement in pain and disability without concurrent changes in lower-extremity strength after rehabilitation. Although some researchers have achieved a significant increase in strength after rehabilitation in PFP cohorts, there was no association with improved pain and disability. The inconsistent improvements in strength and the lack of association with clinical outcomes call for a critical appraisal of the available evidence to better understand the association between changes in hip and knee strength and improved clinical outcomes in individuals with PFP. CLINICAL QUESTION: Are changes in hip and knee strength associated with improved pain and disability after rehabilitation in individuals with PFP? SUMMARY OF KEY FINDINGS: Four studies met the inclusion criteria and were included in the appraisal. Following rehabilitation, one study achieved strength improvements in knee extension. One study achieved strength improvements in knee extension, but not in hip external rotation and hip abduction. Two studies did not achieve strength improvements in hip external rotation, hip abduction, hip extension, or knee extension. All included studies achieved improvements in pain or disability after rehabilitation. None of the studies found a significant association between changes in hip and knee strength (either improved or not) and improved pain and disability. CLINICAL BOTTOM LINE: There is consistent evidence that changes in hip and knee strength are not associated with improved clinical outcomes after rehabilitation in adults with PFP. STRENGTH OF RECOMMENDATION: Collectively, the body of evidence included is to answer the clinical question aligns with the strength of recommendation of B based on the Strength of Recommendation Taxonomy.

Stage-Specific Brain Aging in First-Episode Schizophrenia and Treatment-Resistant Schizophrenia.

BACKGROUND: Brain age is a popular brain-based biomarker that offers a powerful strategy for using neuroscience in clinical practice. We investigated the brain-predicted age difference (PAD) in patients with schizophrenia (SCZ), first-episode schizophrenia spectrum disorders (FE-SSDs), and treatment-resistant schizophrenia (TRS) using structural magnetic resonance imaging data. The association between brain-PAD and clinical parameters was also assessed. METHODS: We developed brain age prediction models for the association between 77 average structural brain measures and age in a training sample of controls (HCs) using ridge regression, support vector regression, and relevance vector regression. The trained models in the controls were applied to the test samples of the controls and 3 patient groups to obtain brain-based age estimates. The correlations were tested between the brain PAD and clinical measures in the patient groups. RESULTS: Model performance indicated that, regardless of the type of regression metric, the best model was support vector regression and the worst model was relevance vector regression for the training HCs. Accelerated brain aging was identified in patients with SCZ, FE-SSDs, and TRS compared with the HCs. A significant difference in brain PAD was observed between FE-SSDs and TRS using the ridge regression algorithm. Symptom severity, the Social and Occupational Functioning Assessment Scale, chlorpromazine equivalents, and cognitive function were correlated with the brain PAD in the patient groups. CONCLUSIONS: These findings suggest additional progressive neuronal changes in the brain after SCZ onset. Therefore, pharmacological or psychosocial interventions targeting brain health should be developed and provided during the early course of SCZ.

Multiple serum biomarkers for predicting suicidal behaviours in depressive patients receiving pharmacotherapy.

BACKGROUND: Predictive values of multiple serum biomarkers for suicidal behaviours (SBs) have rarely been tested. This study sought to evaluate and develop a panel of multiple serum biomarkers for predicting SBs in outpatients receiving a 12-month pharmacotherapy programme for depressive disorders. METHODS: At baseline, 14 serum biomarkers and socio-demographic/clinical characteristics including previous suicidal attempt and present suicidal severity were evaluated in 1094 patients with depressive disorders without a bipolar diagnosis. Of these, 884 were followed for increased suicidal severity and fatal/non-fatal suicide attempt outcomes over a 12-month treatment period. Individual and combined effects of serum biomarkers on these two prospective SBs were estimated using logistic regression analysis after adjustment for relevant covariates. RESULTS: Increased suicidal severity and fatal/non-fatal suicide attempt during the 12-month pharmacotherapy were present in 155 (17.5%) and 38 (4.3%) participants, respectively. Combined cortisol, total cholesterol, and folate serum biomarkers predicted fatal/non-fatal suicide attempt, and these with interleukin-1 beta and homocysteine additionally predicted increased suicidal severity, with clear gradients robust to adjustment (p values < 0.001). CONCLUSIONS: Application of multiple serum biomarkers could considerably improve the predictability of SBs during the outpatient treatment of depressive disorders, potentially highlighting the need for more frequent monitoring and risk appraisal.

Fully automatic volume measurement of the adrenal gland on CT using deep learning to classify adrenal hyperplasia.

OBJECTIVES: To develop a fully automated deep learning model for adrenal segmentation and to evaluate its performance in classifying adrenal hyperplasia. METHODS: This retrospective study evaluated automated adrenal segmentation in 308 abdominal CT scans from 48 patients with adrenal hyperplasia and 260 patients with normal glands from 2010 to 2021 (mean age, 42 years; 156 women). The dataset was split into training, validation, and test sets at a ratio of 6:2:2. Contrast-enhanced CT images and manually drawn adrenal gland masks were used to develop a U-Net-based segmentation model. Predicted adrenal volumes were obtained by fivefold splitting of the dataset without overlapping the test set. Adrenal volumes and anthropometric parameters (height, weight, and sex) were utilized to develop an algorithm to classify adrenal hyperplasia, using multilayer perceptron, support vector classification, a random forest classifier, and a decision tree classifier. To measure the performance of the developed model, the dice coefficient and intraclass correlation coefficient (ICC) were used for segmentation, and area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were used for classification. RESULTS: The model for segmenting adrenal glands achieved a Dice coefficient of 0.7009 for 308 cases and an ICC of 0.91 (95% CI, 0.90-0.93) for adrenal volume. The models for classifying hyperplasia had the following results: AUC, 0.98-0.99; accuracy, 0.948-0.961; sensitivity, 0.750-0.813; and specificity, 0.973-1.000. CONCLUSION: The proposed segmentation algorithm can accurately segment the adrenal glands on CT scans and may help clinicians identify possible cases of adrenal hyperplasia. KEY POINTS: • A deep learning segmentation method can accurately segment the adrenal gland, which is a small organ, on CT scans. • The machine learning algorithm to classify adrenal hyperplasia using adrenal volume and anthropometric parameters (height, weight, and sex) showed good performance. • The proposed segmentation algorithm may help clinicians identify possible cases of adrenal hyperplasia.

Deciphering Functional Connectivity Differences Between Motor Imagery and Execution of Target-Oriented Grasping.

This study aimed to delineate overlapping and distinctive functional connectivity in visual motor imagery, kinesthetic motor imagery, and motor execution of target-oriented grasping action of the right hand. Functional magnetic resonance imaging data were obtained from 18 right-handed healthy individuals during each condition. Seed-based connectivity and multi-voxel pattern analyses were employed after selecting seed regions with the left primary motor cortex and supplementary motor area. There was equivalent seed-based connectivity during the three conditions in the bilateral frontoparietal and temporal areas. When the seed region was the left primary motor cortex, increased connectivity was observed in the left cuneus and superior frontal area during visual and kinesthetic motor imageries, respectively, compared with that during motor execution. Multi-voxel pattern analyses revealed that each condition was differentiated by spatially distributed connectivity patterns of the left primary motor cortex within the right cerebellum VI, cerebellum crus II, and left lingual area. When the seed region was the left supplementary motor area, the connectivity patterns within the right putamen, thalamus, cerebellar areas IV-V, and left superior parietal lobule were significantly classified above chance level across the three conditions. The present findings improve our understanding of the spatial representation of functional connectivity and its specific patterns among motor imagery and motor execution. The strength and fine-grained connectivity patterns of the brain areas can discriminate between motor imagery and motor execution.

Measurement of level of consciousness by AVPU scale assessment system based on automated video and speech recognition technology.

OBJECTIVE: To develop an alert/verbal/painful/unresponsive (AVPU) scale assessment system based on automated video and speech recognition technology (AVPU-AVSR) that can automatically assess a patient's level of consciousness and evaluate its performance through clinical simulation. METHODS: We developed an AVPU-AVSR system with a whole-body camera, face camera, and microphone. The AVPU-AVSR system automatically extracted essential audiovisual features to assess the AVPU score from the recorded video files. Arm movement, pain stimulus, and eyes-open state were extracted using a rule-based approach using landmarks estimated from pre-trained pose and face estimation models. Verbal stimuli were extracted using a pre-trained speech-recognition model. Simulations of a physician examining the consciousness of 12 simulated patients for 16 simulation scenarios (4 for each of "Alert", "Verbal", "Painful", and "Unresponsive") were conducted under the AVPU-AVSR system. The accuracy, sensitivity, and specificity of the AVPU-AVSR system were assessed. RESULTS: A total of 192 cases with 12 simulated patients were assessed using the AVPU-AVSR system with a multi-class accuracy of 0.95 (95% confidence interval [CI] (0.92-0.98). The sensitivity and specificity (95% CIs) for detecting impaired consciousness were 1.00 (0.97-1.00) and 0.88 (0.75-0.95), respectively. The sensitivity and specificity of each extracted feature ranged from 0.88 to 1.00 and 0.98 to 1.00. CONCLUSIONS: The AVPU-AVSR system showed good accuracy in assessing consciousness levels in a clinical simulation and has the potential to be implemented in clinical practice to automatically assess mental status.

Fingerprint ridges allow primates to regulate grip.

Fingerprints are unique to primates and koalas but what advantages do these features of our hands and feet provide us compared with the smooth pads of carnivorans, e.g., feline or ursine species? It has been argued that the epidermal ridges on finger pads decrease friction when in contact with smooth surfaces, promote interlocking with rough surfaces, channel excess water, prevent blistering, and enhance tactile sensitivity. Here, we found that they were at the origin of a moisture-regulating mechanism, which ensures an optimal hydration of the keratin layer of the skin for maximizing the friction and reducing the probability of catastrophic slip due to the hydrodynamic formation of a fluid layer. When in contact with impermeable surfaces, the occlusion of the sweat from the pores in the ridges promotes plasticization of the skin, dramatically increasing friction. Occlusion and external moisture could cause an excess of water that would defeat the natural hydration balance. However, we have demonstrated using femtosecond laser-based polarization-tunable terahertz wave spectroscopic imaging and infrared optical coherence tomography that the moisture regulation may be explained by a combination of a microfluidic capillary evaporation mechanism and a sweat pore blocking mechanism. This results in maintaining an optimal amount of moisture in the furrows that maximizes the friction irrespective of whether a finger pad is initially wet or dry. Thus, abundant low-flow sweat glands and epidermal furrows have provided primates with the evolutionary advantage in dry and wet conditions of manipulative and locomotive abilities not available to other animals.

Psychological and Personality Characteristics Associated With COVID-19 Vaccination Behavior in Korean General Population.

BACKGROUND: This study characterized coronavirus disease 2019 (COVID-19) vaccination behavior in the Korean general population using cluster analysis and explored related psychological factors. METHODS: We categorized 1,500 individuals based on their attitudes toward COVID-19 vaccination using hierarchical clustering and identified their level of vaccine acceptance. We examined the associations between vaccine acceptance and behavioral and psychological characteristics. RESULTS: Clustering revealed three groups according to vaccine acceptance: 'totally accepting' (n = 354, 23.6%), 'somewhat accepting' (n = 523, 34.9%), and 'reluctant' (n = 623, 41.5%). Approximately 60% of all participants who belonged to the 'totally accepting' and 'somewhat accepting' groups were willing to receive a COVID-19 vaccine despite concerns about its side effects. High vaccine acceptance was associated with older age, regular influenza vaccination, and trust in formal sources of information. Participants with high vaccine acceptance had higher levels of gratitude, extraversion, agreeableness, and conscientiousness, and lower levels of depression, anxiety, and neuroticism. CONCLUSIONS: People weighed the benefits of COVID-19 vaccination against the risk of side effects when deciding to receive the COVID-19 vaccine. Our findings also indicate that this vaccination behavior may be affected by coping mechanisms and psychological factors.

Exercise-induced fatigue affects knee proprioceptive acuity and quadriceps neuromuscular function more in patients with ACL reconstruction or meniscus surgery than in healthy individuals.

PURPOSE: To observe how knee proprioceptive acuity and quadriceps neuromuscular function change during and after repeated isokinetic knee-extension exercise in patients with anterior cruciate ligament reconstruction (ACLR) or meniscus surgery. METHODS: Patients with ACLR or meniscus surgery and matched controls (n = 19 in each group) performed knee-flexion replication at 15° and 75°, and quadriceps peak torque (PT), central activation ratio (CAR) and rate of torque development (RTD) at baseline and immediately after every five sets of isokinetic knee-extension exercise (times 1-5). RESULTS: Compared to the baseline, the ACLR and control groups displayed errors in knee-flexion replication at 75° only at time 5 (115.9-155.6%; p ≤ 0.04, d ≥ 0.97), whereas the meniscus surgery group exhibited errors at all time points (142.5-265.6%; p ≤ 0.0003, d ≥ 1.4). Significant percentage reductions in quadriceps CAR were observed between times 4 and 5 in the ACLR group (-5.8%; p = 0.0002, d = 0.96), but not in the meniscus surgery (-1.4%; n.s.) and control (0.1%; n.s.) groups. Significant percentage reductions in quadriceps RTD were observed between times 4 and 5 in the ACLR (-24.2%; p = 0.007, d = 0.99) and meniscus surgery (-23.0%; p = 0.01, d = 0.85) groups, but not in the control group (-0.2%; n.s.). CONCLUSION: Patients with ACLR or meniscus surgery displayed a greater loss in knee proprioceptive acuity and quadriceps neuromuscular function during and after exercise than healthy individuals. Evidence-based interventions to enhance exercise-induced fatigue resistance should be implemented following ACLR or meniscus surgery, aiming to prevent proprioceptive and neuromuscular changes within the knee joint and quadriceps. LEVEL OF EVIDENCE: III.

Diagnosis of schizophrenia with functional connectome data: a graph-based convolutional neural network approach.

Previous deep learning methods have not captured graph or network representations of brain structural or functional connectome data. To address this, we developed the BrainNet-Global Covariance Pooling-Attention Convolutional Neural Network (BrainNet-GA CNN) by incorporating BrainNetCNN and global covariance pooling into the self-attention mechanism. Resting-state functional magnetic resonance imaging data were obtained from 171 patients with schizophrenia spectrum disorders (SSDs) and 161 healthy controls (HCs). We conducted an ablation analysis of the proposed BrainNet-GA CNN and quantitative performance comparisons with competing methods using the nested tenfold cross validation strategy. The performance of our model was compared with competing methods. Discriminative connections were visualized using the gradient-based explanation method and compared with the results obtained using functional connectivity analysis. The BrainNet-GA CNN showed an accuracy of 83.13%, outperforming other competing methods. Among the top 10 discriminative connections, some were associated with the default mode network and auditory network. Interestingly, these regions were also significant in the functional connectivity analysis. Our findings suggest that the proposed BrainNet-GA CNN can classify patients with SSDs and HCs with higher accuracy than other models. Visualization of salient regions provides important clinical information. These results highlight the potential use of the BrainNet-GA CNN in the diagnosis of schizophrenia.

Longitudinal symptom network structure in first-episode psychosis: a possible marker for remission.

BACKGROUND: Network approach has been applied to a wide variety of psychiatric disorders. The aim of the present study was to identify network structures of remitters and non-remitters in patients with first-episode psychosis (FEP) at baseline and the 6-month follow-up. METHODS: Participants (n = 252) from the Korean Early Psychosis Study (KEPS) were enrolled. They were classified as remitters or non-remitters using Andreasen's criteria. We estimated network structure with 10 symptoms (three symptoms from the Positive and Negative Syndrome Scale, one depressive symptom, and six symptoms related to schema and rumination) as nodes using a Gaussian graphical model. Global and local network metrics were compared within and between the networks over time. RESULTS: Global network metrics did not differ between the remitters and non-remitters at baseline or 6 months. However, the network structure and nodal strengths associated with positive-self and positive-others scores changed significantly in the remitters over time. Unique central symptoms for remitters and non-remitters were cognitive brooding and negative-self, respectively. The correlation stability coefficients for nodal strength were within the acceptable range. CONCLUSION: Our findings indicate that network structure and some nodal strengths were more flexible in remitters. Negative-self could be an important target for therapeutic intervention.

Prospective associations of multimodal serum biomarkers with 12-week and 12-month remission in patients with depressive disorders receiving stepwise psychopharmacotherapy.

Prognostic biomarkers for depression treatment outcomes have yet to be elucidated. This study sought to evaluate whether a multi-modal serum biomarker panel was prospectively associated with 12-week and 12-month remission in outpatients with depressive disorders receiving stepwise psychopharmacotherapy. At baseline, 14 serum biomarkers and socio-demographic/clinical characteristics were evaluated in 1094 patients. They received initial antidepressant monotherapy followed, as required by a protocol of successive alternative pharmacological strategies administered in 3-week steps during the acute (3-12 week) phase (N = 1086), and in 3-month steps during the continuation (6-12 month) phase (N = 884). Remission was defined as a Hamilton Depression Rating Scale score of ≤ 7. Remission was achieved in 490 (45.1%) over the 12-week, and in 625 (70.7%) over the 12-month, treatment periods. Combination scores of four serum biomarkers (high-sensitivity C-reactive protein, interleukin-1 beta, interleukin-6, and leptin) were prospectively associated with 12-week remission; and four (high-sensitivity C-reactive protein, tumor necrosis factor-alpha, interleukin-1 beta, and brain-derived neurotrophic factor) were prospectively associated with 12-month remission in a clear gradient manner (P-values < 0.001) and after adjustment for relevant covariates. These associations were evident after the Step 1 treatment monotherapy but weakened with increasing treatment steps, falling below statistical significance after 4 + treatment steps. Application of combined multiple serum biomarkers, particularly on inflammatory markers, could improve predictability of remission at acute and continuation treatment phases for depressive disorders. Patients with unfavourable biomarkers might require alternative treatment regimes for better outcomes.

Interaction effect between childhood abuse and interleukin-1ß levels on suicidality in depressed patients.

INTRODUCTION: The roles of childhood abuse and interleukin (IL)-1ß levels, a representative pro-inflammatory cytokine, in suicidal behavior are unclear. This study investigated the main and interactive effects of childhood abuse and IL-1ß levels on suicidal behavior in patients with a depressive disorder before and after pharmacological treatment. METHODS: At baseline, exposure to self-reported childhood abuse, including emotional, physical, and sexual abuse, before the age of 16 years, and IL-1ß levels, were measured in 1,094 outpatients with a depressive disorder, 884 of whom were followed for 1 year. Suicidal behavior was evaluated, including previous suicide attempts (at baseline), suicidal ideation (at baseline and follow-up), and fatal/non-fatal suicide attempts (at follow-up). The main and interaction effects of self-reported childhood abuse and IL-1ß level on the four types of suicidal behavior were analyzed using logistic regression after adjusting for covariates. RESULTS: Individual associations of self-reported childhood abuse were significant only with previous suicidal attempt but not with other suicidal behaviors. There was no significant association of plasma IL-1ß level with any suicidal behavior. There were significant interactive associations of self-reported childhood abuse and a high IL-1ß level on previous suicide attempts, baseline suicidal ideation, and fatal/non-fatal suicidal attempts during follow-up. CONCLUSION: Suicidal behavior in patients with a depressive disorder could be influenced by considering the interactive effect of childhood abuse and IL-1ß levels. Our study suggests that childhood trauma and biochemical factors play roles in the pathology of suicide in depressed patients.

Machine Learning Analysis to Identify Data Entry Errors in Prehospital Patient Care Reports: A Case Study of a National Out-of-Hospital Cardiac Arrest Registry.

Background: The objective of this study was to develop and validate machine learning models for data entry error detection in a national out-of-hospital cardiac arrest (OHCA) prehospital patient care report database.Methods: Adult OHCAs of presumed cardiac etiology were included. Data entry errors were defined as discrepancies between the coded data and the free-text note documenting the intervention or event; for example, information that was recorded as "absent" in the coded data but "present" in the free-text note. Machine learning models using the extreme gradient boosting, logistic regression, extreme gradient boosting outlier detection, and K-nearest neighbor outlier detection algorithms for error detection within nine core variables were developed and then validated for each variable.Results: Among 12,100 OHCAs, the proportion of cases with at least one error type was 16.2%. The area under the receiver operating characteristic curve (AUC) of the best-performing model (model with the highest AUC for each outcome variable) was 0.71-0.95. Machine learning models detected errors most efficiently for outcome place and initial rhythm errors; 82.6% of place errors and 93.8% of initial rhythm errors could be detected while checking 11 and 35% of data, respectively, compared to the strategy of checking all data.Conclusion: Machine learning models can detect data entry errors in care reports of emergency medical services (EMS) clinicians with acceptable performance and likely can improve the efficiency of the process of data quality control. EMS organizations that provide more prehospital interventions for OHCA patients could have higher error rates and may benefit from the adoption of error-detection models.

Correlation between craniofacial changes and respiratory improvement after nasomaxillary skeletal expansion in pediatric obstructive sleep apnea patients.

PURPOSE: The aim of this study was to investigate the correlation between the changes in respiratory function and dimensions of the nasomaxillary complex (NMC) and upper airway (UA) compartments after nasomaxillary skeletal expansion (NMSE) treatment for pediatric patients with obstructive sleep apnea (OSA). METHODS: Nonobese OSA patients (mean age, 13.6 ± 2.9 years; mean body mass index, 18.1 ± 3.0 kg/m2); mean apnea-hypopnea index (AHI, 7.0 ± 5.4 events/h) presenting with transverse nasomaxillary constriction were evaluated before and after NMSE using cone-beam computed tomography (CBCT), home sleep test, and modified pediatric sleep questionnaire (m-PSQ). Paired t tests were performed to examine the treatment-related changes in all the parameters, and a multiple regression analysis adjusted for age and sagittal and vertical skeletal patterns was conducted to determine the dimensional parameters to affect the functional improvement. RESULTS: Among 26 patients, NMSE treatment significantly increased NMC dimensions at all tested levels and all UA compartments in CBCT, except glossopharyngeal airway. Concurrently, AHI, oxygen desaturation index, the lowest oxygen saturation (LSaO2), flow limitation (FL), snoring, and m-PSQ were significantly improved. AHI reduction was correlated with UA enlargement with no correlation with NMC expansion, whereas FL reduction was affected by NMC expansion. The minimal cross-sectional area was the most predictive of functional improvement, presenting correlations with AHI, LSaO2, and m-PSQ. CONCLUSION: NMSE can be a good treatment for pediatric OSA patients when applied to enhance the nasal and pharyngeal airway patencies beyond the NMC, ultimately to improve pharyngeal collapsibility as well as nasal airflow.

Prediction of bacteremia at the emergency department during triage and disposition stages using machine learning models.

INTRODUCTION: Bacteremia is a common but critical condition with high mortality that requires timely and optimal treatment in the emergency department (ED). The prediction of bacteremia at the ED during triage and disposition stages could support the clinical decisions of ED physicians regarding the appropriate treatment course and safe ED disposition. This study developed and validated machine learning models to predict bacteremia in the emergency department during triage and disposition stages. METHODS: This study enrolled adult patients who visited a single tertiary hospital from 2016 to 2018 and had at least two sets of blood cultures during their ED stay. Demographic information, chief complaint, triage level, vital signs, and laboratory data were used as model predictors. We developed and validated prediction models using 10 variables at the time of ED triage and 42 variables at the time of disposition. The extreme gradient boosting (XGB) model was compared with the random forest and multivariable logistic regression models. We compared model performance by assessing the area under the receiver operating characteristic curve (AUC), test characteristics, and decision curve analysis. RESULTS: A total of 24,768 patients were included: 16,197 cases were assigned to development, and 8571 cases were assigned to validation. The proportion of bacteremia was 10.9% and 10.4% in the development and validation datasets, respectively. The Triage XGB model (AUC, 0.718; 95% confidence interval (CI), 0.701-0.735) showed acceptable discrimination performance with a sensitivity over 97%. The Disposition XGB model (AUC, 0.853; 95% CI, 0.840-0.866) showed excellent performance and provided the greatest net benefit throughout the range of thresholds probabilities. CONCLUSIONS: The Triage XGB model could be used to identify patients with a low risk of bacteremia immediately after initial ED triage. The Disposition XGB model showed excellent discriminative performance.

A development of a graph-based ensemble machine learning model for skin sensitization hazard and potency assessment.

Many defined approaches (DAs) for skin sensitization assessment based on the adverse outcome pathway (AOP) have been developed to replace animal testing because the European Union has banned animal testing for cosmetic ingredients. Several DAs have demonstrated that machine learning models are beneficial. In this study, we have developed an ensemble prediction model utilizing the graph convolutional network (GCN) and machine learning approach to assess skin sensitization. The model integrates in silico parameters and data from alternatives to animal testing of well-defined AOP to improve DA predictivity. Multiple ensemble models were created using the probability produced by the GCN with six physicochemical properties, direct peptide reactivity assay, KeratinoSens™, and human cell line activation test (h-CLAT), using a multilayer perceptron approach. Models were evaluated by predicting the testing set's human hazard class and three potency classes (strong, weak, and non-sensitizer). When the GCN feature was used, 11 models out of 16 candidates showed the same or improved accuracy in the testing set. The ensemble model with the feature set of GCN, KeratinoSens™, and h-CLAT produced the best results with an accuracy of 88% for assessing human hazards. The best three-class potency model was created with the feature set of GCN and all three assays, resulting in 64% accuracy. These results from the ensemble approach indicate that the addition of the GCN feature could provide an improved predictivity of skin sensitization hazard and potency assessment.