Crack Detection on a Retaining Wall with an Innovative, Ensemble Learning Method in a Dynamic Imaging System.

In this study, an innovative, ensemble learning method in a dynamic imaging system of an unmanned vehicle is presented. The feasibility of the system was tested in the crack detection of a retaining wall in a climbing area or a mountain road. The unmanned vehicle can provide a lightweight and remote cruise routine with a Geographic Information System sensor, a Gyro sensor, and a charge-coupled device camera. The crack was the target to be tested, and the retaining wall was patrolled through the drone flight path setting, and then the horizontal image was instantly returned by using the wireless transmission of the system. That is based on the cascade classifier, and the feature comparison classifier was designed further, and then the machine vision correlation algorithm was used to analyze the target type information. First, the system collects the target image and background to establish the samples database, and then uses the Local Binary Patterns feature extraction algorithm to extract the feature values for classification. When the first stage classification is completed, the classification results are target features, and edge feature comparisons. The innovative ensemble learning classifier was used to analyze the image and determine the location of the crack for risk assessment.

Photoacoustic method for measuring the elasticity of polydimethylsiloxane at various mixing ratios.

Measuring elasticity without physical contact is challenging, as current methods often require deconstruction of the test sample. This study addresses this challenge by proposing and testing a photoacoustic effect-based method for measuring the elasticity of polydimethylsiloxane (PDMS) at various mixing ratios, which may be applied on the wide range of applications such as biomedical and optical fields. A dual-light laser source of the photoacoustic (PA) system is designed, employing cross-correlation signal processing techniques. The platform systems and a mathematical model for performing PDMS elasticity measurements are constructed. During elasticity detection, photoacoustic signal features, influenced by hardness and shapes, are analyzed using cross-correlation calculations and phase difference detection. Results from phantom tests demonstrate the potential of predicting Young's modulus using the cross-correlation method, aligning with the American Society for Testing and Materials (ASTM) standard samples. However, accuracy may be affected by mixed materials and short tubes. Normalization or calibration of signals is suggested for aligning with Young's coefficient.

Changes in heart rate variability during TOVA testing in patients with major depressive disorder.

AIM: The aim of this study was to identify major depressive disorder (MDD) based on heart rate variability (HRV) during tests of variables of attention (TOVA). METHOD: Forty-five MDD patients without cardiovascular disease and 45 controls matched by age and gender participated in this study. RESULTS: Compared to the controls, the MDD group had lower resting HRV parameters, more omissions and variability and longer response times on TOVA, and failure of attention employment to decrease HRV. CONCLUSIONS: The resting HRV parameters may provide easily measured, clinically useful ways to identify patients with MDD and to monitor their progress in treatment.

Photoacoustic and absorption spectroscopy imaging analysis of human blood.

Photoacoustic and absorption spectroscopy imaging are safe and non-invasive molecular quantification techniques, which do not utilize ionizing radiation and allow for repeated probing of samples without them being contaminated or damaged. Here we assessed the potential of these techniques for measuring biochemical parameters. We investigated the statistical association between 31 time and frequency domain features derived from photoacoustic and absorption spectroscopy signals and 19 biochemical blood parameters. We found that photoacoustic and absorption spectroscopy imaging features are significantly correlated with 14 and 17 individual biochemical parameters, respectively. Moreover, some of the biochemical blood parameters can be accurately predicted based on photoacoustic and absorption spectroscopy imaging features by polynomial regression. In particular, the levels of uric acid and albumin can be accurately explained by a combination of photoacoustic and absorption spectroscopy imaging features (adjusted R-squared > 0.75), while creatinine levels can be accurately explained by the features of the photoacoustic system (adjusted R-squared > 0.80). We identified a number of imaging features that inform on the biochemical blood parameters and can be potentially useful in clinical diagnosis. We also demonstrated that linear and non-linear combinations of photoacoustic and absorption spectroscopy imaging features can accurately predict some of the biochemical blood parameters. These results demonstrate that photoacoustic and absorption spectroscopy imaging systems show promise for future applications in clinical practice.

The effectiveness and safety of adjunctive aripiprazole in Taiwanese patients with antidepressant-refractory major depressive disorder: a prospective, open-label trial.

There is currently no published clinical trial on the safety and effectiveness of aripiprazole in Taiwanese patients with treatment-refractory major depressive disorder. We were interested in determining the applicability of current recommended doses of aripiprazole as an adjunct to antidepressant therapy in this population. We conducted a prospective, open-label nonrandomized, 4-week flexibly dosed (2.5-5 mg/d) trial with aripiprazole augmentation in 9 Taiwanese patients who had a history of nonresponse to at least 2 adequate courses of antidepressant therapy with different types of antidepressants. The primary end point for clinical effectiveness was mean change in the 17-item Hamilton Rating Scale for Depression at the end of the 4-week trial. Secondary end points for clinical effectiveness included mean change in Beck Depression Inventory and Beck Anxiety Inventory scores. The Systematic Assessment of Treatment Emergent Events-General Inquiry was used to assess adverse effects. All patients completed the trial and responded to treatment; the remission rate was 77.8%. The mean daily dose of adjunctive aripiprazole was 4.2 mg. Common treatment-emergent adverse events included insomnia and sedation (33.3%) and akathisia (22.2%). We found high effectiveness despite a lower mean daily dose of adjunctive aripiprazole (4.2 mg) when compared with previously reported findings; however, we also observed a higher frequency of treatment-emergent adverse effects. Additional studies are required to ascertain whether there are ethnic differences in the pharmacokinetics and/or pharmacodynamics of aripiprazole in treatment-refractory depression.

Use of cardio-ankle vascular index in chronic dialysis patients.

BACKGROUND: Arterial stiffness is an independent predictor of all-cause and cardiovascular mortality, particularly in patients with chronic kidney disease and end-stage renal disease (ESRD). The objective of this study was to determine the risk factors for de novo arterial stiffness in long-term dialysis patients. MATERIALS AND METHODS: A total of 59 dialysis patients without initial arterial stiffness were studied for 1 year. Cardio-ankle vascular index (CAVI) was measured and a CAVI value ≥ 9 at the end of 1 year was defined as de novo arterial stiffness. The initial baseline characteristics and laboratory parameters and final laboratory parameters after 1 year were analysed. RESULTS: Dialysis patients with de novo arterial stiffness were significantly older than dialysis patients without de novo arterial stiffness. Initial serum phosphorus and calcium × phosphorus product of dialysis patients with de novo arterial stiffness were significantly greater than those of dialysis patients without de novo arterial stiffness. The haematocrit of dialysis patients with de novo arterial stiffness was significantly lower than that of dialysis patients without de novo arterial stiffness. Multivariate logistic regression analysis showed that age and initial serum phosphorus were independent risk factors for de novo arterial stiffness in dialysis patients. CONCLUSION: After 1-year follow-up, de novo arterial stiffness in dialysis patients as determined by CAVI was significantly associated with age and initial serum phosphorus.

Plasmonic Gold Nanomaterials as Photoacoustic Signal Resonant Enhancers for Cysteine Detection.

The development of photoacoustic systems is important for the real-time detection of cysteine (Cys), a biothiol in biological systems that serves as a significant biomarker for human health. Advanced photoacoustic (PA) signals with colloidal plasmonic Au nanomaterials rely on the efficient conversion of light to energy waves under moderately pulsed laser irradiation. In this study, we synthesized Cys-capped Au nanorods (Au@Cys NRs) and Cys-capped Au nanoparticles (Au@Cys NPs) through a conjugate of three Cys concentrations (10, 100, and 1000 µM). These plasmonic Au nanomaterials can be used as a PA resonance reagent due to their maximum localized surface plasmon resonance (LSPR) absorption bands at 650 nm and 520 nm in Au NRs and Au NPs, respectively. Subsequently, the PA signals were noticeably increased proportionally to the concentrations in the Au@Cys NRs and Au@Cys NPs under 658 nm and 520 nm laser irradiation, respectively, according to our portable photoacoustic system. Furthermore, PA signal amplitudes in Cys detection are boosted by ~233.01% with Au@Cys NRs and ~102.84% with Au@Cys NPs enhancement, compared to free Cys, according to ultrasound transducers at frequencies of 3 MHz.

An artificial immune system with bootstrap sampling for the diagnosis of recurrent endometrial cancers.

Endometrial cancer is one of the most common gynecological malignancies in developed countries. The prevention of the recurrence of endometrial cancer has always been a clinical challenge. Endometrial cancer is asymptomatic in the early stage, and there remains a lack of time-series correlation patterns of clinical pathway transfer, recurrence, and treatment. In this study, the artificial immune system (AIS) combined with bootstrap sampling was compared with other machine learning techniques, which included both supervised and unsupervised learning categories. The back propagation neural network, support vector machine (SVM) with a radial basis function kernel, fuzzy c-means, and ant k-means were compared with the proposed method to verify the sensitivity and specificity of the datasets, and the important factors of recurrent endometrial cancer were predicted. In the unsupervised learning algorithms, the AIS algorithm had the highest accuracy (83.35%), sensitivity (77.35%), and specificity (92.31%); in supervised learning algorithms, the SVM algorithm had the highest accuracy (97.51%), sensitivity (95.02%), and specificity (99.29%). The results of our study showed that histology and chemotherapy are important factors affecting the prediction of recurrence. Finally, behavior code and radiotherapy for recurrent endometrial cancer are important factors for future adjuvant treatment.

The Changes of qEEG Approximate Entropy during Test of Variables of Attention as a Predictor of Major Depressive Disorder.

Evaluating brain function through biosignals remains challenging. Quantitative electroencephalography (qEEG) outcomes have emerged as a potential intermediate biomarker for diagnostic clarification in psychological disorders. The Test of Variables of Attention (TOVA) was combined with qEEG to evaluate biomarkers such as absolute power, relative power, cordance, and approximate entropy from covariance matrix images to predict major depressive disorder (MDD). EEG data from 18 healthy control and 18 MDD patients were monitored during the resting state and TOVA. TOVA was found to provide aspects for the evaluation of MDD beyond resting electroencephalography. The results showed that the prefrontal qEEG theta cordance of the control and MDD groups were significantly different. For comparison, the changes in qEEG approximate entropy (ApEn) patterns observed during TOVA provided features to distinguish between participants with or without MDD. Moreover, ApEn scores during TOVA were a strong predictor of MDD, and the ApEn scores correlated with the Beck Depression Inventory (BDI) scores. Between-group differences in ApEn were more significant for the testing state than for the resting state. Our results provide further understanding for MDD treatment selection and response prediction during TOVA.

Genetic signatures of heroin addiction.

Heroin addiction is a complex psychiatric disorder with a chronic course and a high relapse rate, which results from the interaction between genetic and environmental factors. Heroin addiction has a substantial heritability in its etiology; hence, identification of individuals with a high genetic propensity to heroin addiction may help prevent the occurrence and relapse of heroin addiction and its complications. The study aimed to identify a small set of genetic signatures that may reliably predict the individuals with a high genetic propensity to heroin addiction. We first measured the transcript level of 13 genes (RASA1, PRKCB, PDK1, JUN, CEBPG, CD74, CEBPB, AUTS2, ENO2, IMPDH2, HAT1, MBD1, and RGS3) in lymphoblastoid cell lines in a sample of 124 male heroin addicts and 124 male control subjects using real-time quantitative PCR. Seven genes (PRKCB, PDK1, JUN, CEBPG, CEBPB, ENO2, and HAT1) showed significant differential expression between the 2 groups. Further analysis using 3 statistical methods including logistic regression analysis, support vector machine learning analysis, and a computer software BIASLESS revealed that a set of 4 genes (JUN, CEBPB, PRKCB, ENO2, or CEBPG) could predict the diagnosis of heroin addiction with the accuracy rate around 85% in our dataset. Our findings support the idea that it is possible to identify genetic signatures of heroin addiction using a small set of expressed genes. However, the study can only be considered as a proof-of-concept study. As the establishment of lymphoblastoid cell line is a laborious and lengthy process, it would be more practical in clinical settings to identify genetic signatures for heroin addiction directly from peripheral blood cells in the future study.

Using surface electromyography (SEMG) to classify low back pain based on lifting capacity evaluation with principal component analysis neural network method.

Low back pain (LBP) is a leading cause of disability. The population with low back pain is continuously growing in the recent years. This study tries to distinguish LBP patients with healthy subjects by using the objective surface electromyography (SEMG) as a quantitative score for clinical evaluations. There are 26 healthy and 26 low back pain subjects who involved in this research. They lifted different weights by static and dynamic lifting process. Multiple features are extracted from the raw SEMG data, including energy and frequency indexes. Moreover, false discovery rate (FDR) omitted the false positive features. Then, a principal component analysis neural network (PCANN) was used for classifications. The results showed the features with different loadings (including 30%, and 50% loading) on lifting which can be used for distinguishing healthy and back pain subjects. By using PCANN method, more than 80% accuracies are achieved when different lifting weights were applied. Moreover, it is correlated between some EMG features and clinical scales, on exertion, fatigue, and pain. This technology can be potentially used for the future researches as a computer-aid diagnosis tool of LBP evaluation.

Characterization of the psychological, physiological and EEG profile of acute betel quid intoxication in naïve subjects.

Betel quid use and abuse is wide spread in Asia but the physiological basis of intoxication and addiction are unknown. In subjects naïve to the habit of betel quid intoxication, the psychological and physiological profile of intoxication has never been reported. We compared the effect of chewing gum or chewing betel quid, and subsequent betel quid intoxication, on psychological assessment, prospective time interval estimation, numerical and character digit span, computerized 2 choice tests and mental tasks such as reading and mathematics with concurrent monitoring of ECG, EEG and face temperature in healthy, non-sleep deprived, male subjects naïve to the habit of chewing betel quid. Betel quid intoxication, dose dependently induced tachycardia (max 30 bpm) and elevated face temperature (0.7°C) (P<0.001) above the effects observed in response to chewing gum (max 12 bpm and 0.3°C) in 12 subjects. Gross behavioral indices of working memory such as numerical or character digit span in 8 subjects, or simple visual-motor performance such as reaction speed or accuracy in a two choice scenario in 8 subjects were not affected by betel quid intoxication. Betel quid intoxication strongly influenced the psychological aspects of perception such as slowing of the prospective perception of passage of a 1 minute time interval in 8 subjects (P<0.05) and perceived increased arousal (P<0.01) and perceived decreased ability to think (P<0.05) in 31 subjects. The EEG spectral profile recorded from mental states associated with open and closed eyes, and mental tasks such as reading and eyes closed mental arithmetic were significantly modified (P<0.05) relative to chewing gum by betel quid intoxication in 10 subjects. The prevalence of betel quid consumption across a range of social and work settings warrants greater investigation of this widespread but largely under researched drug.

Detection and prediction of sudden cardiac death (SCD) for personal healthcare.

Sudden Cardiac Death (SCD) is one of continuing challenges to the modern clinician. It is responsible for an estimated 400,000 deaths per year in the United States and millions of deaths worldwide. This research developed a personal cardiac homecare system by sensing Lead-I ECG signals for detecting and predicting SCD events, which also builds in ECG identity verification. A MIT/BIH SCD Holter Database plus our ECG database were investigated. The system includes a self-made ECG amplifier, a NI DAQ card, a laptop computer, LabView and MatLab programs. The wavelet analysis was applied to detect SCD and the overall performance is 87.5% correct detection rate. In addition, artificial neural networks (ANN) were used to predict SCD events. The correct prediction rates by applying least mean square (LMS), decision based neural network (DBNN), and back propagation (BP) neural network were 67.44%, 58.14% and 55.81% respectively.