Validity of Diagnostic Support Model for Attention Deficit Hyperactivity Disorder: A Machine Learning Approach.

An accurate and early diagnosis of attention deficit hyperactivity disorder can improve health outcomes and prevent unnecessary medical expenses. This study developed a diagnostic support model using a machine learning approach to effectively screen individuals for attention deficit hyperactivity disorder. Three models were developed: a logistic regression model, a classification and regression tree (CART), and a neural network. The models were assessed by using a receiver operating characteristic analysis. In total, 74 participants were enrolled into the disorder group, while 21 participants were enrolled in the control group. The sensitivity and specificity of each model, indicating the rate of true positive and true negative results, respectively, were assessed. The CART model demonstrated a superior performance compared to the other two models, with region values of receiver operating characteristic analyses in the following order: CART (0.848) > logistic regression model (0.826) > neural network (0.67). The sensitivity and specificity of the CART model were 78.8% and 50%, respectively. This model can be applied to other neuroscience research fields, including the diagnoses of autism spectrum disorder, Tourette syndrome, and dementia. This will enhance the effect and practical value of our research.

Shortened neural conduction time in young adults with tinnitus as revealed by chirp-evoked auditory brainstem response.

Tinnitus is generally considered to be caused by neuroplastic changes in the central nervous system, triggered by a loss of input from the damaged peripheral system; however, conflicting results on auditory brainstem responses (ABRs) to clicks have been reported previously in humans with tinnitus. This study aimed to compare the effect of tinnitus on ABRs to chirps with those to clicks in normal-hearing young adults with tinnitus. The results showed that the tinnitus group had no significantly poorer hearing thresholds (0.25-16 kHz), click-evoked otoacoustic emissions (1-16 kHz), and speech perception in noise (SPIN) than the control group. Although chirps evoked significantly larger wave I and V amplitudes than clicks, people with tinnitus had no significantly smaller wave I amplitudes for either stimulus. Nevertheless, adults with tinnitus exhibited significantly smaller interpeak interval (IPI) between waves I and V for chirps (IPI-chirp) but not for clicks. In addition, the IPI-chirp correlated significantly with the SPIN for individuals with tinnitus when the signal-to-noise ratio was low. The present results suggest that the chirp-evoked ABR may be a valuable clinical tool for objectively assessing the SPIN in individuals with tinnitus. Further studies should be conducted to investigate possible etiologies of tinnitus.

Development of Internet suicide message identification and the Monitoring-Tracking-Rescuing model in Taiwan.

BACKGROUND: Suicide messages can be transmitted infinitely online; the Internet is influential in suicide prevention. Identifying suicide risks online via artificial technological advances may help predict suicide. METHODS: We built a classifier that detects open messages containing suicidal ideation or behavior-related words in social media via text mining methods and developed the Monitoring-Tracking-Rescuing model, which links data monitoring and tracking to high-risk suicide rescues. Natural language processing (NLP) techniques such as Long Short-Term Memory and Bidirectional Encoder Representations from Transformers were applied to online posts of common social media sites in Taiwan. This model uses a two-step high-risk identification procedure: an automatic prediction process using NLP to classify suicide-risk levels, followed by professional validation by a senior psychiatrist and a nursing faculty specialized in suicidology. RESULTS: From a dataset containing 404 high-risk and 2226 no- or low-risk articles, the sensitivity and specificity of our model reached 80 %. LIMITATIONS: The model is limited to data platforms that can be "crawled" and excludes suicide-risk content from graphics, video and audio files. Additionally, machine learning does not provide the best recognition rate from complex online messages. Keywords for high-risk suicide in long articles are difficult to interpret using this model. Finally, the model lacks keywords for suicide-protective factors. CONCLUSIONS: Artificial intelligence techniques may help detect and monitor high-risk suicide posts and inform mental health professionals of these posts. Periodic tracking plus manual validation to determine risk levels are recommended to enhance the reliability and effectiveness of Internet suicide-prevention tasks.

Quality of life changes and their predictors in young adult narcolepsy patients after treatment: A real-world cohort study.

Background: We conducted a five-year prospective follow-up study to track the real-world quality of life of patients with narcolepsy after medication and analyzed predictors. Methods: The study ultimately included 157 participants who completed 5-year follow-up, 111 had type 1 narcolepsy (NT1) and 46 had type 2 narcolepsy (NT2). Polysomnography, multiple sleep latency test, actigraphy and HLA-typing were conducted. The Short Form 36 Health Survey Questionnaire (SF-36), the Stanford Center for Narcolepsy Sleep Inventory, the Epworth Sleepiness Scale (ESS), the visual analog for hypersomnolence (VAS), and Conners' Continuous Performance Test were used. Descriptive statistics, repeated measures, and hierarchical linear models were applied for analysis. Results: Most demographic and clinical data did not significantly differ between groups, but the NT1 group had significantly more overweight, more severe narcoleptic symptoms, more positive HLA typing, shorter mean sleep latency, and more sleep onset rapid eye movement periods. No significant change to the physical domains of SF-36 was found in the total group, but we observed significant changes in emotional role functioning and social function. The NT1 group showed significant improvements in physical role functioning, emotional role functioning, and social function. The NT2 group demonstrated significant improvements in emotional role functioning. At the baseline, the NT2 group had significantly better scores, but there was no significant group difference after treatment, except for physical and social function. ESS and VAS were significantly improved during follow-up. At the baseline, the NT1 group had significantly higher ESS and VAS scores, and continuously significantly higher ESS scores during follow-up. Narcolepsy types, HLA typing, age of onset, symptom severity, attention and vigilance were significantly correlated with SF-36. Conclusion: Symptom control greatly associates with the quality of life in narcoleptic patients, and medication can play the most important role. Management targeting narcoleptic symptoms, attention impairment, and drug adherence should be provided.

The Impact of Global Budgeting on the Efficiency of Healthcare under a Single-Payer System in Taiwan.

Since 1995, a national health insurance (NHI) program has been in operation in Taiwan, which provides uniform comprehensive coverage. Forced by severe financial deficit, global budgeting reimbursement was adopted in the healthcare sector to control healthcare expenditures in 2002. A two-stage data envelopment analysis (DEA) approach was used to measure the efficiency of hospital resource allocation among stakeholders in Taiwan's NHI system, and to further explore the changes in resource allocation after the introduction of a global budgeting payment scheme. The dataset was collected from the annual statistical reports of Taiwan's Ministry of Health and Welfare (MOHW) and was used to estimate the efficiency of resource allocation in hospital-based healthcare services under global budgeting. In terms of efficiency during the period from 2003 to 2009, one-third of decision-making units (DMUs) improved their productivity in stage I, and seven out of the total of eighteen DMUs saw falls in financial efficiency in stage II. After global budgeting was implemented, there were significant positive impacts on the efficiency of hospital resource allocation in Taiwan. The two-stage DEA model for analyzing the effects of the global budgeting reimbursement system on productivity and financial efficiency represents a key decision-making tool for hospital administrators and policymakers.

Different circadian rest-active rhythms in Kleine-Levin syndrome: a prospective and case-control study.

STUDY OBJECTIVES: Kleine-Levin syndrome (KLS) is a rare recurrent hypersomnia. Our study aimed at monitoring the movements of patients with KLS using actigraphy and evaluating their circadian rhythm. METHODS: Twenty young patients with KLS and 14 age-matched controls were recruited. Each individual wore an actigraphy for more than 6 months to monitor at least two attacks. Controls kept wearing the device for at least 7 days. The activity counts were averaged in hourly basis and the day-to-night amplitude was quantified by the differences of the averaged activity counts during daytime and nighttime. The hourly activities of different days were aligned and averaged to construct the circadian profile. Parametric and nonparametric estimation of circadian rhythm was calculated. We applied detrended fluctuation analysis to evaluate the temporal correlations beneath the activity fluctuations at multiple time scales. RESULTS: Circadian rhythm in asymptomatic period showed no significant difference compared to the controls. During hypersomnia attack, the amplitude of the circadian rest-active rhythms drastically decreased and decreased interdaily stability (IS) was found, as well as significant decreased M10 and short-time fractal correlation (α1). Drastically decreased mean and standard deviation of activity were noted, compared to the pre-attack phase and recovery phase. α1 and M10 increased during the late attack phase, and overcompensated IS was noted in the recovery phase. CONCLUSIONS: This study confirmed that circadian rest-active rhythms was affected when KLS hypersomnia attack. Several parameters including M10, IS, and α1 may be physiological markers of KLS, which can help to predict the end of hypersomnia episodes.

Association between real-world home blood pressure measurement patterns and blood pressure variability among older individuals with hypertension: A community-based blood pressure variability study.

Home blood pressure (BP) monitoring is a useful tool for hypertension management. BP variability (BPV) has been associated with an increased risk of cardiovascular events. However, little is known about the correlation between BPV and different measurement patterns of long-term home BP monitoring. This longitudinal cohort study aimed to assess the associations between dynamic BP measurement patterns and BPV. A total of 1128 participants (mean age, 77.4 ± 9.3 years; male, 51%) with 23 269 behavior measuring units were included. We used sliding window sampling to classify the home BP data with a regular 6-month interval into units in a sliding manner until the data are not continuous. Three measurement patterns (stable frequent [SF], stable infrequent [SI], and unstable [US]) were assessed based on the home BP data obtained within the first 3 months of the study, and the data in the subsequent 3 months were used to assess the BPV of that unit. We used linear mixed-effects model to assess the association between BP measurement patterns and BPV with adjustment for possible confounding factors including average BP. Average real variability and coefficient variability were used as measures of the BPV. No significant differences were observed in average BP between the SF, SI, and US patterns. However, BPV in the SF group was significantly lower than that in the US and SI groups (all p-values < .05). The BPV in SI and US groups was not significantly different. A stable and frequent BP measuring pattern was independently associated with a lower BPV.

[Applying Big Data in Smart Healthcare].

People have traditionally associated being 'not ill' with being 'healthy'. This concept has changed due to the improvement of Taiwan's population structure, advances in medical care, and better education. The word 'health' is defined by the World Health Organization as a state of complete physical, mental, and social well-being, and not merely the absence of disease or infirmity. In the future, people in Taiwan must address the challenges of population aging and create a society oriented to the long-term care needs of its citizens. People have different healthcare requirements during the respective stages of healthy, sub-healthy, and disability. Advancing technology has allowed the creation of many healthcare applications such as "health big data" that incorporate Internet of things (IoT) capabilities. Applying artificial intelligence opens many new possibilities and solutions. This article was written to introduce the application of big data techniques in smart healthcare that are appropriate to the three stages of healthy, sub-healthy, and disability.

Using Mobile Electroencephalography and Actigraphy to Diagnose Attention-Deficit/Hyperactivity Disorder: Case-Control Comparison Study.

BACKGROUND: Children with attention-deficit/hyperactivity disorder (ADHD), a neurobehavioral disorder, display behaviors of inattention, hyperactivity, or impulsivity, which can affect their ability to learn and establish proper family and social relationships. Various tools are currently used by child and adolescent psychiatric clinics to diagnose, evaluate, and collect information and data. The tools allow professional physicians to assess if patients need further treatment, following a thorough and careful clinical diagnosis process. OBJECTIVE: We aim to determine potential indicators extracted from a mobile electroencephalography (EEG) device (Mindset; NeuroSky) and an actigraph (MotionWatch 8; CamNtech) and to validate them for diagnosis of ADHD. The 3 indicators are (1) attention, measured by the EEG; (2) meditation, measured by the EEG; and (3) activity, measured by the actigraph. METHODS: A total of 63 participants were recruited. The case group comprised 40 boys and 9 girls, while the control group comprised 5 boys and 9 girls. The groups were age matched. The test was divided into 3 stages-pretest, in-test, and posttest-with a testing duration of 20 minutes each. We used correlation analysis, repeated measures analysis of variance, and regression analysis to investigate which indicators can be used for ADHD diagnosis. RESULTS: With the EEG indicators, the analysis results show a significant correlation of attention with both hit reaction time (RT) interstimulus interval (ISI) change (r=-0.368; P=.003) and hit standard error (SE) ISI change (r=-0.336; P=.007). This indicates that the higher the attention of the participants, the smaller both the hit RT change and the hit SE ISI change. With the actigraph indicator, confidence index (r=0.352; P=.005), omissions (r=0.322; P=.01), hit RT SE (r=0.393; P=.001), and variability (r=0.351; P=.005) were significant. This indicates that the higher the activity amounts, the higher the impulsive behavior of the participants and the more target omissions in the continuous performance test (CPT). The results show that the participants with ADHD present a significant difference in activity amounts (P<0.001). The actigraph outperforms the EEG in screening ADHD. CONCLUSIONS: When the participants with ADHD are stimulated under restricted conditions, they will present different amounts of activity than in unrestricted conditions due to participants' inability to exercise control over their concentration. This finding could be a new electronic physiological biomarker of ADHD. An actigraph can be used to detect the amount of activity exhibited and to help physicians diagnose the disorder in order to develop more objective, rapid auxiliary diagnostic tools.

Inflammatory Factors: Nonobese Pediatric Obstructive Sleep Apnea and Adenotonsillectomy.

BACKGROUND: Inflammation is often considered relating to pediatric obstructive sleep apnea (OSA). We conducted a study investigating cytokines, including Il-17 and Il-23, in children with OSA before and after adenotonsillectomy (T&A), compared with controls. METHODS: Children with OSA between age 4 and 12 receiving T&A were prospectively followed. Evaluation before and reevaluation six months after the treatment were done, including polysomnography (PSG), blood tests, and questionnaires. Blood samples were obtained to determine the values of high-sensitivity-C-reactive-protein (HS-CRP); tumor-necrosis-factor-alpha (TNF-α); and interleukin (IL)-1, 6, 10, 12, 17, and 23. We compared the results with an age-matched control group. RESULTS: We included 55 OSA children and 32 controls. Children with OSA presented significant improvement after T&A in complaints, signs, apnea hypopnea index (AHI) (p < 0.001), mean oxygen desaturation index (p < 0.001), and mean oxygen saturation (p = 0.010). Upon entering this study, children with OSA had significantly higher cytokine levels than the controls and significant changes in HS-CRP (p = 0.013), TNF-α (p = 0.057), IL-1ß (p = 0.022), IL-10 (p = 0.035), and IL-17 (p = 0.010) after T&A. Children with improved but persistently abnormal AHI did not have all cytokine levels normalized, particularly IL-23 and HS-CRP. CONCLUSION: Sleep-disordered breathing can persist after T&A and can continue to have a negative inflammatory effect. HS-CRP and IL-23 may serve as blood markers for the persistence of sleep-disordered breathing after T&A.

Mobile community learning programme's effectiveness in case management for psychiatric nurses: A preliminary randomised controlled trial.

BACKGROUND: The global health care system has applied case management (CM) as a care delivery service provided by nurses. Nurses require continuing education in CM to enhance their professional knowledge and competence. Mobile communities have been used to promote continuing education for medical professionals. However, limited studies have examined the effectiveness of such learning programmes in CM for psychiatric nurses. OBJECTIVE: To evaluate the effectiveness of a mobile community learning (MCL) programme in CM for psychiatric nurses. DESIGN: This study used an experimental two-group pre- and post-test design. SETTINGS AND PARTICIPANTS: Psychiatric nurses employed in a psychiatric teaching hospital situated in northern Taiwan were recruited. METHODS: Nurses were randomly allocated to the experimental or comparison group. The former participated in the learning intervention in CM. The CM knowledge index and a competence scale were used to determine outcomes. Pre-tests and 2-month post-tests were conducted. The MCL programme comprised five simulated learning modules, self-assessment questions, learning cases, learning resources and experience sharing. A two-way repeated-measures analysis of variance was performed to evaluate the effect of the intervention on target outcomes. RESULTS: The questionnaires were completed by 48 participants. The two groups possessed high homogeneity with regard to characteristics and pre-test outcomes. Differences between the two groups regarding CM knowledge (F = 22.99, p < .01) and competence (F = 6.33, p = .015) were significant. The programme had a positive benefit on the learning experience in the experimental group; the mean satisfaction score for the programme reached 4.27 (range, 1-5). CONCLUSIONS: MCL programmes for psychiatric nurses can effectively enhance CM knowledge and competence. However, these methods cannot completely replace the continuing education approach for achieving CM competence.

Reliability and validity of DS-ADHD: A decision support system on attention deficit hyperactivity disorders.

BACKGROUND AND OBJECTIVES: The purpose of this study is to examine the reliability of the clinical use of the self-built decision support system, diagnosis-supported attention deficit hyperactivity disorder (DS-ADHD), in an effort to develop the DS-ADHD system, by probing into the development of indicating patterns of past screening support systems for ADHD. METHODS: The study collected data based on 107 subjects, who were divided into two groups, non-ADHD and ADHD, based on the doctor's determination, using the DSM-IV diagnostic standards. The two groups then underwent Test of Variables of Attention (TOVA) and DS-ADHD testing. The survey and testing results underwent one-way ANOVA and split-half method statistical analysis, in order to further understand whether there were any differences between the DS-ADHD and the identification tools used in today's clinical trials. RESULTS: The results of the study are as follows: 1) The ROC area between the TOVA and the clinical identification rate is 0.787 (95% confidence interval: 0.701-0.872); 2) The ROC area between the DS-ADHD and the clinical identification rate is 0.867 (95% confidence interval: 0.801-0.933). CONCLUSIONS: The study results show that DS-ADHD has the characteristics of screening for ADHD, based on its reliability and validity. It does not display any statistical differences when compared with TOVA systems that are currently on the market. However, the system is more effective and the accuracy rate is better than TOVA. It is a good tool to screen ADHD not only in Chinese children, but also in western country.

The development and preliminary effectiveness of a nursing case management e-learning program.

The purpose of this article was to describe the development and preliminary effectiveness of a digital case management education program. The e-learning program was built through the collaboration of a nurse educator and an informatics professor. The program was then developed according to the following steps: (1) building a visual interface, (2) scripting each unit, (3) preparing the course material and assessment tests, (4) using teaching software to record audio and video courses, (5) editing the audio recordings, (6) using instructional media or hyperlinks to finalize the interactions, (7) creating the assessment and obtaining feedback, and (8) testing the overall operation. The digital program consisted of five learning modules, self-assessment questions, learning cases, sharing experiences, and learning resources. Forty nurses participated in this study and fully completed the questionnaires both before and after the program. The knowledge and confidence levels in the experimental group were significantly higher over time than those of the comparison group. The results supported the use of educational technology to provide a more flexible and effective presentation method for continuing education programs.