Functional dyspepsia in depression: A population-based cohort study.

BACKGROUND: Patients with functional dyspepsia (FD) are more likely to have persistent depression, yet whether depression and antidepressant treatments are associated with subsequent risk of FD remain unclear. METHODS: Using population-based insurance administrative data of Taiwan, an 11-year historic cohort study was assembled, comparing cases aged 18 and above with the diagnosis of depressive disorder, to a propensity score-matched sample of adults without depression. Incident FD as a primary diagnosis was ascertained. Hazard ratios of FD were calculated using Cox regression models by age, gender, other comorbidities, nonsteroidal anti-inflammatory medications, antidepressants and antidiabetic agents. RESULTS: A total of 20,197 people with depressive disorder and 20,197 propensity score-matched comparisons without depression were followed up. The incidence of FD was 1.7-fold greater in the depressive cohort than in comparisons (12.9 versus 7.57 per 1000 person-years), with an adjusted hazard ratio (aHR) of 2.16 (95% confidence interval (CI) 1.93~2.41). Increased risks were significant regardless of comorbidities or medication uses, the highest in the untreated depression group compared to the group without depression, with an aHR of 2.51(95% CI 2.15~2.93). CONCLUSIONS: This population-based study showed that patients with depressive disorder are at elevated risk of FD. Antidepressant treatment could reduce the risk of FD.

Progress on Range of Motion After Total Knee Replacement by Sensor-Based System.

For total knee replacement (TKR) patients, rehabilitation after the surgery is key toregaining mobility. This study proposes a sensor-based system for effectively monitoringrehabilitation progress after TKR. The system comprises a hardware module consisting of thetriaxial accelerometer and gyroscope, a microcontroller, and a Bluetooth module, and a softwareapp for monitoring the motion of the knee joint. Three indices, namely the number of swings, themaximum knee flexion angle, and the duration of practice each time, were used as metrics tomeasure the knee rehabilitation progress. The proposed sensor device has advantages such asusability without spatiotemporal constraints and accuracy in monitoring the rehabilitation progress.The performance of the proposed system was compared with the measured range of motion of theCybex isokinetic dynamometer (or Cybex) professional rehabilitation equipment, and the resultsrevealed that the average absolute errors of the measured angles were between 1.65° and 3.27° forthe TKR subjects, depending on the swing speed. Experimental results verified that the proposedsystem is effective and comparable with the professional equipment.

The Psychometric Properties in the Chinese Version of the Reasons for Living Inventory and the Relationship with Suicidal Behaviors Among Psychiatric Patients in Taiwan.

This study examines the reliability, factor structure, convergent, and construct validities of the Mandarin Chinese version of the Reasons For Living Inventory (RFL) among Taiwanese psychiatric patients. Demographical characteristics of patients who hold these adaptive cognitions and differences on the level of endorsement between suicidal and non-suicidal individuals were also investigated. All adult patients that had visited the psychiatric ambulatory clinic or had been admitted to the psychiatric ward in a general hospital in Taiwan over a 3-month period were consecutively invited to complete an inventory that included background information, the Mandarin Chinese versions of the RFL, the Suicidal Behaviors Questionnaire-Revised (SBQ-R), and the Beck Hopeless Scale (BHS). Of the 254 respondents aged 19 to 65 years, 47.2% had suicidal ideations or attempts within the past year. The original six-factor structure of the American version was confirmed to be acceptable. The Cronbach α was 0.964.Total scores on RFL were inversely and significantly correlated with that from BHS. Multivariate analysis with demographic data and items from SBQ-R revealed that higher scores on the RFL have been associated with married, have children or religious beliefs, fewer past and current suicidal ideations and attempts, fewer histories of suicidal threats, and a less self-reported likelihood of future suicide in our sample. The Mandarin version of the RFL inventory showed acceptable psychometric properties and could distinguish suicidal patients from non-suicidal ones.

Differential Diagnostic Value of Machine Learning-Based Models for Embolic Stroke.

Cancer-associated thrombosis (CAT) and atrial fibrillation (AF)-related stroke are two subtypes of acute embolic stroke with distinct lesion patterns on diffusion weighted imaging (DWI). This pilot study aimed to evaluate the feasibility and performance of DWI-based machine learning models for differentiating between CAT and AF-related stroke. Patients with CAT and AF-related stroke were enrolled. In this pilot study with a small sample size, DWI images were augmented by flipping and/or contrast shifting to build convolutional neural network (CNN) predicative models. DWI images from 29 patients, including 9 patients with CAT and 20 with AF-related stroke, were analyzed. Training and testing accuracies of the DWI-based CNN model were 87.1% and 78.6%, respectively. Training and testing accuracies were 95.2% and 85.7%, respectively, for the second CNN model that combined DWI images with demographic/clinical characteristics. There were no significant differences in sensitivity, specificity, accuracy, and AUC between two CNN models (all P = n.s.).The DWI-based CNN model using data augmentation may be useful for differentiating CAT from AF-related stroke.

Computer-Aided Detection of Retinopathy of Prematurity Severity in Preterm Infants via Measurement of Temporal Vessel Width and Angle.

Retinopathy of prematurity (ROP) is a retinal disorder that occurs in preterm infants with low birth weight and is the leading cause of preventable blindness in children. Early identification of high-risk patients and early diagnosis and timely treatment of ROP can substantially improve patients' visual outcomes. However, manual screening consumes both time and resources. Telescreening using retinal fundus images has the potential to reduce the burden engendered by the necessity of on-site screening. Recently, substantial progress has been made in using computer-aided diagnosis with retinal fundus images, and this approach has attracted considerable attention for the diagnosis of eye diseases. Abnormalities of and alterations in retinal blood vessels may relate to the occurrence and progression of ROP. In this study, we examined the hypothesis that ROP severity may be associated with the angle and width of arteries and veins. We computationally determined the artery-artery and vein-vein angles in the temporal quadrants-the temporal artery angle (TAA) and temporal vein angle (TVA)-under normal conditions and in different ROP stages. We also estimated retinal vessel width-temporal artery width (TAW) and temporal vein width (TVW)-by applying the Radon transform method to fundus images. Our results revealed significant decreases in TAA and TVA and increases in TAW and TVW with increasing ROP severity (all P < 0.0001).In addition, we observed positive TAA-TVA and TAW-TVW correlations (both P < 0.0001). The TAA was negatively correlated with the TAW (r = -0.162, P = 0.0314). These retinal vessel features may be useful in assisting ophthalmologists in the early detection of ROP and its progression.

Automated detection of early-stage ROP using a deep convolutional neural network.

BACKGROUND/AIM: To automatically detect and classify the early stages of retinopathy of prematurity (ROP) using a deep convolutional neural network (CNN). METHODS: This retrospective cross-sectional study was conducted in a referral medical centre in Taiwan. Only premature infants with no ROP, stage 1 ROP or stage 2 ROP were enrolled. Overall, 11 372 retinal fundus images were compiled and split into 10 235 images (90%) for training, 1137 (10%) for validation and 244 for testing. A deep CNN was implemented to classify images according to the ROP stage. Data were collected from December 17, 2013 to May 24, 2019 and analysed from December 2018 to January 2020. The metrics of sensitivity, specificity and area under the receiver operating characteristic curve were adopted to evaluate the performance of the algorithm relative to the reference standard diagnosis. RESULTS: The model was trained using fivefold cross-validation, yielding an average accuracy of 99.93%±0.03 during training and 92.23%±1.39 during testing. The sensitivity and specificity scores of the model were 96.14%±0.87 and 95.95%±0.48, 91.82%±2.03 and 94.50%±0.71, and 89.81%±1.82 and 98.99%±0.40 when predicting no ROP versus ROP, stage 1 ROP versus no ROP and stage 2 ROP, and stage 2 ROP versus no ROP and stage 1 ROP, respectively. CONCLUSIONS: The proposed system can accurately differentiate among ROP early stages and has the potential to help ophthalmologists classify ROP at an early stage.

An ensemble learning based hybrid model and framework for air pollution forecasting.

As advance of economy and industry, the impact of air pollution has gradually gained attention. In order to predict air quality, there were many studies that exploited various machine learning techniques to build predictive model for pollutant concentration or air quality prediction. However, enhancing the prediction performance always is the common problem of existing studies. Traditional templates based on machine learning and deep learning methods, such as GBTR (gradient boosted tree regression), SVR (support vector machine-based regression), and LSTM (long short-term memory), are most promising approaches to address these problems. Some previous researches showed that ensemble learning technology can improve predictive performance of other domains. In order to improve the accuracy of forecasting, in this paper, we propose a hybrid model and framework to improve the forecasting accuracy of air pollution. We not only exploit stacking-based ensemble learning scheme with Pearson correlation coefficient to calculate the correlation between different machine learning models to integrate various forecasting models together, but also construct a framework based on Spark+Hadoop machine learning and TensorFlow deep learning framework to physically integrate these models to demonstrate the next 1 to 8 h' air pollution forecasting. We also conduct experiments and compare the result with GBTR, SVR, LSTM, and LSTM2 (version 2) models to demonstrate the proposed hybrid model's predictive performance. The experimental results show that the hybrid model is superior to the existing models used for predicting air pollution.

Clinical information and guidance shared via a patient infotainment system can reduce hospital stay and maintain 2 medical quality for total knee arthroplasty: A single-blinded quasi-randomised controlled trial.

BACKGROUND: The demand for total knee arthroplasty is increasing worldwide. Optimising results and meeting patients' expectations are more challenging than before, because the length of hospitalisation has markedly reduced and the standard care processes have been accelerated. We incorporated an interactive patient infotainment system into the standard clinical pathway for total knee arthroplasty in the hope of improving patients' length of stay. OBJECTIVES: To analyse whether incorporation of an interactive infotainment system reduced the length of stay and improved the quality of medical care (in terms of number of medical orders and emergency room returns). DESIGN: A prospective, quasi-randomised controlled trial. PARTICIPANTS AND SETTING: Data of 86 patients hospitalised for a unilateral total knee arthroplasty at a medical centre in Taiwan were analysed. METHODS: From January 2017 to July 2017, 86 patients who underwent unilateral total knee arthroplasty and were cared for under a standard clinical pathway were included. The study group (41 patients) had access to electronic programs and video demonstrations related to health literacy, physical therapy, home care and precautions following total knee arthroplasty via a patient infotainment system, while the control group (45 patients) did not. Hospital course, quality indices, in-hospital medical costs, returns to the emergency room and readmission at 30 or 90 days were analysed and compared between the two groups of patients. RESULTS: The study group had a shorter length of stay (4.4 vs. 4.8 days, mean differences [MD] = -0.37, 95% CI -0.71 to -0.03, p = 0.026) and fewer medical orders (109 vs 111 orders, MD = -1.86, 95% confidence intervals (CI) -3.58 to -0.15, p = 0.047) as compared with the control group. The incidences of emergency room return and readmission to the hospital at 30 or 90 days were comparable between the two groups. No difference in the total medical cost was found between the two groups, with only the cost of laboratory tests in the study group being significantly lower than that in the control group ($144 vs. $163, MD = -21.7, 95% CI -41.0 to -2.25, p = 0.007). CONCLUSIONS: The incorporation of a patient infotainment system into the standard clinical pathway for total knee arthroplasty can efficiently reduce the length of hospital stay and maintain the quality of medical care. Further studies on improvement of patient medical literacy with the help of the infotainment system would be of interest in order to improve clinical practice and patient satisfaction. REGISTRATION NUMBER: NCT03788798 TWEETABLE ABSTRACT: A patient infotainment system can reduce hospital stay and maintain medical quality for total knee arthroplasty.

Validity of a Novel Touch Screen Tablet-Based Assessment for Mild Cognitive Impairment and Probable AD in Older Adults.

This study aimed to develop a psychometrically valid touch screen tablet-based cognitive test battery to identify early cognitive impairment due to dementia in older adults. The battery includes eight tests with 13 subscores, evaluating visual attention, auditory attention, information processing speed, visual memory, motor control, and visuospatial perception. Among the participants, 43 had been diagnosed with mild cognitive impairment (MCI) and 36 with probable Alzheimer's disease (AD); 41 had no cognitive impairment. The average time to administer the tablet-based tests was 10 minutes. Significant correlations with the Mini-Mental State Examination were found in 9 out of 13 subscores. Patients with probable AD scored significantly lower than controls in 8 out of 13 subscores, whereas those with MCI scored significantly lower in 4 out of 13 subscores. Confirmatory factor analysis using Promax rotation showed that four factors caused lower subscores in the MCI group compared with the controls: information processing speed, memory, visuospatial perception, and motor control. All four factors significantly discriminated the controls from the MCI and probable AD groups, and in the expected direction. The touch screen tablet-based cognitive test battery is psychometrically valid for evaluating cognition in older adults.

The Prevalence and Severity of Myopia among Suburban Schoolchildren in Taiwan.

INTRODUCTION: We aimed to determine the prevalence and severity of myopia in suburban schoolchildren. The refractive error, best corrected visual acuity (BCVA) and other ocular indices of 6069 schoolchildren (aged 6 to 15 years) from elementary and junior high schools in Chiayi County, Taiwan were examined in 2013-2015. MATERIALS AND METHODS: Spherical equivalent (SE) was stratified into 4 categories: emmetropia, mild myopia, moderate myopia, and high myopia for underlying analysis. Chi-squared (χ2) tests were used to determine significant associations between myopia and BCVA and age levels. To compare statistical significance among different age levels, P values of Bonferroni tests were calculated. Receiver operating characteristic (ROC) curves and correlation coefficient were calculated to assess the correlation between myopia and each ocular index. RESULTS: The youngest subject diagnosed with myopia was a 7-year-old. Myopia had significant associations with both BCVA and age levels (95% confidence intervals [CI] = 2.553, 2.713 and -0.284, -0.248, respectively), under P <0.05. Among the calculated ROC values, BCVA had the highest area of 0.676 with myopia. This further confirmed that BCVA was highly correlated with myopia in schoolchildren. Other ocular indices like intraocular pressure (IOP), pupil distance, ocular alignments, or ocular height had ROC curves below 0.5 to myopia. CONCLUSION: This study concluded that the onset of myopia started earlier and progressively worsened with years of investigation among the suburban schoolchildren. Myopia had significant associations with BCVA and age levels. To effectively reduce the prevalence and severity of myopia, it is time to take actions on eye care education for suburban schoolchildren.

The effectiveness of Culturally Sensitive Collaborative Treatment of depressed Chinese in family medicine clinics: A randomized controlled trial.

OBJECTIVE: To investigate whether the Culturally Sensitive Collaborative Treatment (CSCT) would improve outcomes for patients with major depression who were managed in family medicine clinics in Taiwan. METHOD: A single-blinded randomized trial was conducted in 26 family medicine clinics. Patients with major depressive disorder were consecutively randomized to either CSCT or treatment as usual (TAU). The primary outcome was the severity of depression. Secondary outcomes included treatment response, treatment remission, quality of life, and medication adherence. Outcomes were compared using hierarchical linear models (mixed-effects models) from baseline to 26-week follow-up assessments. RESULTS: Of the 280 patients, 141 were randomized to TAU and 139 to CSCT. Hierarchical linear modeling revealed that the CSCT group displayed significantly greater improvement in depressive symptoms over the study period when compared to the TAU group (B=-2.60, P<0.001). The odds of achieving the response, remission, and medication adherence were significantly greater for the CSCT group compared to the TAU group (odds ratio=4.65, 4.12, and 2.06, respectively; all Ps<0.05). However, both groups did not differ significantly in quality of life. CONCLUSION: CSCT is effective in improving treatment outcomes for major depression in family medicine clinics in Taiwan.

An intelligent subtitle detection model for locating television commercials.

A strategy for locating television (TV) commercials in TV programs is proposed. Based on the observation that most TV commercials do not have subtitles, the first stage exploits six subtitle constraints and an adaptive neurofuzzy inference system model to determine whether a frame contains a subtitle or not. The second stage involves locating the mark-in/mark-out points using a genetic algorithm. An interactive user interface allows users to efficiently identify and fine-tune the exact boundaries separating the commercials from the program content. Furthermore, erroneous boundaries are manually corrected. Experimental results show that the precision rate and recall rates exceed 90%.

Relationship Between Predictors of Incident Deliberate Self-Harm and Suicide Attempts Among Adolescents.

PURPOSE: Data on the incidence of deliberate self-harm (DSH) and suicide attempts (SAs) are lacking in non-Western adolescents, and no studies have investigated differences in incident DSH and SA worldwide. This study aimed to investigate the incidence rates and relationships between predictors in DSH and SA. METHODS: The Taiwanese Adolescent Self-Harm Project was a longitudinal study of DSH among adolescents. We recruited 5,879 students from 14 senior high schools in northern Taiwan. Online questionnaires on sociodemographic data, suicidality, depressive symptoms, self-esteem, social support, family discord, impulsivity, and alcohol and tobacco use were assessed at baseline (T1) and at 1 year of follow-up (T2). Logistic regression analyses were performed to evaluate the predictors of incident DSH and SA. RESULTS: The mean age was 16.02 years, and 56.73% of the cohort was female. At T1, the lifetime prevalence rates of DSH and SA were 25.04% and 3.50%, respectively. At T2, 4,331 (73.67%) students had completed follow-up assessments. The 1-year incidence rates of DSH and SA were 4.04% and 1.53%, respectively. The predictors of incident DSH included perceived family discord and more depressive symptoms at T1. The predictors of incident SA were lifetime suicide ideation, more depressive symptoms, and tobacco use at T1. CONCLUSIONS: The incidence rates of DSH and SA were similar to those reported in Western countries. The predictors of incident DSH and SA were similar but not identical. Our results highlight the risk factors which should be considered in terms of early identification and intervention among adolescents to prevent suicidality.

Correlation of impulsivity with self-harm and suicidal attempt: a community study of adolescents in Taiwan.

OBJECTIVES: The aim of this study was to investigate differences and similarities in risk factors for deliberate self-harm (DSH) and suicidal attempt (SA), and the role of impulsivity among a group of community adolescents. SETTING: This is a cross-sectional study conducted at high schools in Northern Taiwan. DATA AND PARTICIPANTS: We recruited grade 1 students from 14 high schools. A total of 5879 participants (mean age 16.02 years, female adolescents: 57.7%) completed the online assessment. OUTCOME MEASURES: Participants completed online questionnaires about sociodemographic data, suicidality, history of DSH and SA, depressed mood, self-esteem, social support, family discord, impulsivity (Barratt Impulsiveness Scale Version 11 (BIS-11)) and the use of alcohol, tobacco and illicit drugs. A subsample was interviewed about lifetime SA, and the results were compared with those from the online questionnaires. RESULTS: In our sample, 25% of the students had lifetime DSH and 3.5% had lifetime SA. Two hundred and seventy-two students received face-to-face interviews. The concordance between the online questionnaires and interviews in terms of ascertaining cases of SA was moderate (concordance rate 82.76%; kappa value 0.59). Similar risk factors for DSH/SA among the whole sample included female gender, lower academic performance, depression, substance use (tobacco and alcohol) and low self-esteem. The BIS-11 score was correlated with DSH. Factor 3 score of the BIS-11 (novelty seeking) was correlated with DSH in both boys and girls, whereas factor 2 score (lack of self-control) was correlated with SA in boys. Social support was a protective factor against SA among the female adolescents. Gender modulated the association of impulsivity and DSH/SA. Associations between impulsivity and DSH and SA were particularly strong among boys. CONCLUSIONS: Risk factors for DSH and SA were similar, but not identical. Early identification of those at risk and appropriate interventions may be helpful.

Temperament traits in suicidal and non-suicidal mood disorder patients in Taiwan.

Suicide is a major social and clinical problem in Asia. Although studies have suggested that personality traits are possible risk factors for suicide, no study has been conducted among Chinese to compare the temperament traits of suicidal and non-suicidal mood disorder patients with those of healthy controls. This study compared temperament traits of two patient groups, those with a mood disorder who have attempted suicide (n=204), and those with a mood disorder who have not attempted suicide (n=160), and compared the traits of these patients to those of healthy controls (n=178), assessed by Cloninger's Tridimensional Personality Questionnaire and the Brown-Goodwin Aggression Inventory. Patients with suicidal attempts had significantly higher novelty seeking and aggression scores than healthy controls and patients without suicidal attempts. Two groups of patients with mood disorder had significantly higher harm avoidance scores than the healthy controls. However, patients with suicidal attempts did not have higher harm avoidance scores than patients without suicidal attempts. This study confirms findings that harm avoidance and mood disorder are related, and extends them by suggesting that those with a mood disorder and suicide attempts have higher novelty seeking and lifetime aggression scores than those without suicidal attempt, either patients or healthy controls.