Evaluation of a decided sample size in machine learning applications.

BACKGROUND: An appropriate sample size is essential for obtaining a precise and reliable outcome of a study. In machine learning (ML), studies with inadequate samples suffer from overfitting of data and have a lower probability of producing true effects, while the increment in sample size increases the accuracy of prediction but may not cause a significant change after a certain sample size. Existing statistical approaches using standardized mean difference, effect size, and statistical power for determining sample size are potentially biased due to miscalculations or lack of experimental details. This study aims to design criteria for evaluating sample size in ML studies. We examined the average and grand effect sizes and the performance of five ML methods using simulated datasets and three real datasets to derive the criteria for sample size. We systematically increase the sample size, starting from 16, by randomly sampling and examine the impact of sample size on classifiers' performance and both effect sizes. Tenfold cross-validation was used to quantify the accuracy. RESULTS: The results demonstrate that the effect sizes and the classification accuracies increase while the variances in effect sizes shrink with the increment of samples when the datasets have a good discriminative power between two classes. By contrast, indeterminate datasets had poor effect sizes and classification accuracies, which did not improve by increasing sample size in both simulated and real datasets. A good dataset exhibited a significant difference in average and grand effect sizes. We derived two criteria based on the above findings to assess a decided sample size by combining the effect size and the ML accuracy. The sample size is considered suitable when it has appropriate effect sizes (≥ 0.5) and ML accuracy (≥ 80%). After an appropriate sample size, the increment in samples will not benefit as it will not significantly change the effect size and accuracy, thereby resulting in a good cost-benefit ratio. CONCLUSION: We believe that these practical criteria can be used as a reference for both the authors and editors to evaluate whether the selected sample size is adequate for a study.

Bacillus amyloliquefaciens Increases the GABA in Rice Seed for Upregulation of Type I Collagen in the Skin.

Biosynthesis of gamma-aminobutyric acid (GABA) can be achieved by naturally occurring microorganisms with the advantages of cost-effectiveness and safety. In this study, Bacillus amyloliquefaciens EH-9 strain (B. amyloliquefaciens EH-9), a soil bacterium, was used to promote the accumulation of GABA in germinated rice seed. Further, the topical application of supernatant from rice seed co-cultivated with soil B. amyloliquefaciens EH-9 can significantly increase the production of type I collagen (COL1) in the dorsal skin of mice. The knocking down of the GABA-A receptor (GABAA) significantly reduced the production of COL1 in the NIH/3T3 cells and in the dorsal skin of mice. This result suggests that topical application of GABA can promote the biosynthesis of COL1 via its interaction with the GABAA receptor in the dorsal skin of mice. In summary, our findings illustrate for the first time that soil B. amyloliquefaciens EH-9 elicits GABA production in germinated rice seed to upregulate the formation of COL1 in the dorsal skin of mice. This study is translational because the result shows a potential remedy for skin aging by stimulating COL1 synthesis using biosynthetic GABA associated with B. amyloliquefaciens EH-9.

Low-frequency oscillations in cortical level to help diagnose task-specific dystonia.

Task-specific dystonia is a neurological movement disorder that abnormal contractions of muscles result in the twisting of fixed postures or muscle spasm during specific tasks. Due to the rareness and the pathophysiology of the disease, there is no test to confirm the diagnosis of task-specific dystonia, except comprehensive observations by the experts. Evidence from neural electrophysiological data suggests that enhanced low frequency (4-12 Hz) oscillations in the subcortical structure of the globus pallidus were associated with the pathological abnormalities concerning ß and γ rhythms in motor areas and motor cortical network in patients with task-specific dystonia. However, whether patients with task-specific dystonia have any low-frequency abnormalities in motor cortical areas remains unclear. In this study, we hypothesized that low-frequency abnormalities are present in core motor areas and motor cortical networks in patients with task-specific dystonia during performing the non-symptomatic movements and those low-frequency abnormalities can help the diagnosis of this disease. We tested this hypothesis by using EEG, effective connectivity analysis, and a machine learning method. Fifteen patients with task-specific dystonia and 15 healthy controls were recruited. The machine learning method identified 8 aberrant movement-related network connections concerning low frequency, ß and γ frequencies, which enabled the separation of the data of patients from those of controls with an accuracy of 90%. Importantly, 7 of the 8 aberrant connections engaged the premotor area contralateral to the affected hand, suggesting an important role of the premotor area in the pathological abnormities. The patients exhibited significantly lower low frequency activities during the movement preparation and significantly lower ß rhythms during movements compared with healthy controls in the core motor areas. Our findings of low frequency- and ß-related abnormalities at the cortical level and aberrant motor network could help diagnose task-specific dystonia in the clinical setting, and the importance of the contralesional premotor area suggests its diagnostic potential for task-specific dystonia.

Effects of Oxytocin on Fear Memory and Neuroinflammation in a Rodent Model of Posttraumatic Stress Disorder.

Posttraumatic stress disorder (PTSD) is a trauma-induced mental disorder characterized by fear extinction abnormalities, which involve biological dysfunctions among fear circuit areas in the brain. Oxytocin (OXT) is a neuropeptide that regulates sexual reproduction and social interaction and has recently earned specific attention due to its role in adjusting neurobiological and behavioral correlates of PTSD; however, the mechanism by which this is achieved remains unclear. The present study aimed to examine whether the effects of OXT on traumatic stress-induced abnormalities of fear extinction (specifically induced by single prolonged stress (SPS), an animal model of PTSD) are associated with pro-inflammatory cytokines. Seven days after SPS, rats received intranasal OXT 40 min before a cue-dependent Pavlovian fear conditioning-extinction test in which rats' freezing degree was used to reflect the outcome of fear extinction. We also measured mRNA expression of IL-1ß, IFN-γ, and TNF-α in the medial prefrontal cortex (mPFC), hippocampus, and amygdala at the end of the study, together with plasma oxytocin, corticosterone, IL-1ß, IFN-γ, and TNF-α, to reflect the central and peripheral changes of stress-related hormones and cytokines after SPS. Our results suggested that intranasal OXT effectively amends the SPS-impaired behavior of fear extinction retrieval. Moreover, it neurochemically reverses the SPS increase in pro-inflammatory cytokines; thus, IL-1ß and IFN-γ can be further blocked by the OXT antagonist atosiban (ASB) in the hippocampus. Peripheral profiles revealed a similar response pattern to SPS of OXT and corticosterone (CORT), and the SPS-induced increase in plasma levels of IL-1ß and TNF-α could be reduced by OXT. The present study suggests potential therapeutic effects of OXT in both behavioral and neuroinflammatory profiles of PTSD.

Differential Characterization of Temozolomide-Resistant Human Glioma Cells.

Glioblastoma multiforme (GBM) is the most common type of primary and malignant tumor occurring in the adult central nervous system. Temozolomide (TMZ) has been considered to be one of the most effective chemotherapeutic agents to prolong the survival of patients with glioblastoma. Many glioma cells develop drug-resistance against TMZ that is mediated by increasing O-6-methylguanine-DNA methyltransferase (MGMT) levels. The expression of connexin 43 was increased in the resistant U251 subline compared with the parental U251 cells. The expression of epithelial-mesenchymal transition (EMT)-associated regulators, including vimentin, N-cadherin, and ß-catenin, was reduced in the resistant U251 subline. In addition, the resistant U251 subline exhibited decreased cell migratory activity and monocyte adhesion ability compared to the parental U251 cells. Furthermore, the resistant U251 subline also expressed lower levels of vascular cell adhesion molecule (VCAM)-1 after treatment with recombinant tumor necrosis factor (TNF)-α. These findings suggest differential characteristics in the drug-resistant GBM from the parental glioma cells.

Exploring the possible relationship between skin microbiome and brain cognitive functions: a pilot EEG study.

Human microbiota mainly resides on the skin and in the gut. Human gut microbiota can produce a variety of short chain fatty acids (SCFAs) that affect many physiological functions and most importantly modulate brain functions through the bidirectional gut-brain axis. Similarly, skin microorganisms also have identical metabolites of SCFAs reported to be involved in maintaining skin homeostasis. However, it remains unclear whether these SCFAs produced by skin bacteria can affect brain cognitive functions. In this study, we hypothesize that the brain's functional activities are associated with the skin bacterial population and examine the influence of local skin-bacterial growth on event-related potentials (ERPs) during an oddball task using EEG. Additionally, five machine learning (ML) methods were employed to discern the relationship between skin microbiota and cognitive functions. Twenty healthy subjects underwent three rounds of tests under different conditions-alcohol, glycerol, and water. Statistical tests confirmed a significant increase in bacterial population under water and glycerol conditions when compared to the alcohol condition. The metabolites of bacteria can turn phenol red from red-orange to yellow, confirming an increase in acidity. P3 amplitudes were significantly enhanced in response to only oddball stimulus at four channels (Fz, FCz, and Cz) and were observed after the removal of bacteria when compared with that under the water and glycerol manipulations. By using machine learning methods, we demonstrated that EEG features could be separated with a good accuracy (> 88%) after experimental manipulations. Our results suggest a relationship between skin microbiota and brain functions. We hope our findings motivate further study into the underlying mechanism. Ultimately, an understanding of the relationship between skin microbiota and brain functions can contribute to the treatment and intervention of diseases that link with this pathway.

Impaired Brain-Heart Relation in Patients With Methamphetamine Use Disorder During VR Induction of Drug Cue Reactivity.

Methamphetamine use disorder (MUD) is an illness associated with severe health consequences. Virtual reality (VR) is used to induce the drug-cue reactivity and significant EEG and ECG abnormalities were found in MUD patients. However, whether a link exists between EEG and ECG abnormalities in patients with MUD during exposure to drug cues remains unknown. This is important from the therapeutic viewpoint because different treatment strategies may be applied when EEG abnormalities and ECG irregularities are complications of MUD. We designed a VR system with drug cues and EEG and ECG were recorded during VR exposure. Sixteen patients with MUD and sixteen healthy subjects were recruited. Statistical tests and Pearson correlation were employed to analyze the EEG and ECG. The results showed that, during VR induction, the patients with MUD but not healthy controls showed significant [Formula: see text] and [Formula: see text] power increases when the stimulus materials were most intense. This finding indicated that the stimuli are indiscriminate to healthy controls but meaningful to patients with MUD. Five heart rate variability (HRV) indexes significantly differed between patients and controls, suggesting abnormalities in the reaction of patient's autonomic nervous system. Importantly, significant relations between EEG and HRV indexes changes were only identified in the controls, but not in MUD patients, signifying a disruption of brain-heart relations in patients. Our findings of stimulus-specific EEG changes and the impaired brain-heart relations in patients with MUD shed light on the understanding of drug-cue reactivity and may be used to design diagnostic and/or therapeutic strategies for MUD.

Neuronal Correlates of Task Irrelevant Distractions Enhance the Detection of Attention Deficit/Hyperactivity Disorder.

Early diagnosis and treatment can reduce the symptoms of Attention Deficit/Hyperactivity Disorder (ADHD) in children, but medical diagnosis is usually delayed. Hence, it is important to increase the efficiency of early diagnosis. Previous studies used behavioral and neuronal data during GO/NOGO task to help detect ADHD and the accuracy differed considerably from 53% to 92%, depending on the employed methods and the number of electroencephalogram (EEG) channels. It remains unclear whether data from a few EEG channels can still lead to a good accuracy of detecting ADHD. Here, we hypothesize that introducing distractions into a VR-based GO/NOGO task can augment the detection of ADHD using 6-channel EEG because children with ADHD are easily distracted. Forty-nine ADHD children and 32 typically developing children were recruited. We use a clinically applicable system with EEG to record data. Statistical analysis and machine learning methods were employed to analyze the data. The behavioral results revealed significant differences in task performance when there are distractions. The presence of distractions leads to EEG changes in both groups, indicating immaturity in inhibitory control. Importantly, the distractions additionally enhanced the between-group differences in NOGO α and γ power, reflecting insufficient inhibition in different neural networks for distraction suppression in the ADHD group. Machine learning methods further confirmed that distractions enhance the detection of ADHD with an accuracy of 85.45%. In conclusion, this system can assist in fast screenings for ADHD and the findings of neuronal correlates of distractions can help design therapeutic strategies.

Domain and functional analysis of a novel breast tumor suppressor protein, SCUBE2.

Signal peptide CUB (complement proteins C1r/C1s, Uegf, and Bmp 1)-EGF domain-containing protein 2 (SCUBE2) is a secreted, membrane-associated multidomain protein composed of five recognizable motifs: an NH(2)-terminal signal peptide sequence, nine copies of epidermal growth factor (EGF)-like repeats, a spacer region, three cysteine-rich repeats, and one CUB domain at the COOH terminus. Our previous clinical study showed that SCUBE2 may act as a novel breast tumor suppressor gene and serve as a useful prognostic marker. However, the specific domain responsible for its tumor suppressor activity and the precise mechanisms of its anti-tumor effect remain unknown. Using a combination of biochemical, molecular, and cell biology techniques, we further dissected the molecular functions and signal pathways mediated by the NH(2)-terminal EGF-like repeats or COOH-terminal CUB domain of SCUBE2. Independent overexpression of the NH(2)-terminal EGF-like repeats or COOH-terminal CUB domain resulted in suppression of MCF-7 breast cancer cell proliferation and reduced MCF-7 xenograft tumor growth in nude mice. Molecular and biochemical analyses revealed that the COOH-terminal CUB domain could directly bind to and antagonize bone morphogenetic protein activity in an autocrine manner, whereas the NH(2)-terminal EGF-like repeats could mediate cell-cell homophilic adhesions in a calcium-dependent fashion, interact with E-cadherin (a master tumor suppressor), and decrease the ß-catenin signaling pathway. Together, our data demonstrate that SCUBE2 has growth inhibitory effects through a coordinated regulation of two distinct mechanisms: antagonizing bone morphogenetic protein and suppressing the ß-catenin pathway in breast cancer cells.

A dynamic causal model for evoked and induced responses.

Neuronal responses exhibit two stimulus or task-related components: evoked and induced. The functional role of induced responses has been ascribed to 'top-down' modulation through backward connections and lateral interactions; as opposed to the bottom-up driving processes that may predominate in evoked components. The implication is that evoked and induced components may reflect different neuronal processes. The conventional way of separating evoked and induced responses assumes that they can be decomposed linearly; in that induced responses are the average of the power minus the power of the average (the evoked component). However, this decomposition may not hold if both components are generated by nonlinear processes. In this work, we propose a Dynamic Causal Model that models evoked and induced responses at the same time. This allows us to explain both components in terms of shared mechanisms (coupling) and changes in coupling that are necessary to explain any induced components. To establish the face validity of our approach, we used Bayesian Model Selection to show that the scheme can disambiguate between models of synthetic data that did and did not contain induced components. We then repeated the analysis using MEG data during a hand grip task to ask whether induced responses in motor control circuits are mediated by 'top-down' or backward connections. Our result provides empirical evidence that induced responses are more likely to reflect backward message passing in the brain, while evoked and induced components share certain characteristics and mechanisms.

Chitinase 3-like-1 expression in colonic epithelial cells as a potentially novel marker for colitis-associated neoplasia.

Chitinase 3-like-1 (CHI3L1/YKL-40) is a protein secreted from restricted cell types including colonic epithelial cells (CECs) and macrophages. CHI3L1 is an inflammation-associated molecule, and its expression is enhanced in persons with colitis and colon cancer. The biological function of CHI3L1 on CECs is unclear. In this study, we investigated the role of CHI3L1 on CECs during the development of colitis-associated neoplasia. We analyzed colonic samples obtained from healthy persons and from persons with ulcerative colitis with or without premalignant or malignant changes. DNA microarray and RT-PCR analyses significantly increased CHI3L1 expression in non-dysplastic mucosa from patients with inflammatory bowel disease (IBD) who had dysplasia/adenocarcinoma compared with that in healthy persons and in patients with IBD who did not have dysplasia. As determined by IHC, CHI3L1 was expressed in specific cell types in the crypts of colonic biopsies obtained from patients with ulcerative colitis who have remote dysplasia. Purified CHI3L1 efficiently activated the NF-κB signaling pathway and enhanced the secretion of IL-8 and TNF-α in SW480 human colon cancer cells. In addition, colon cancer cell proliferation and migration were significantly promoted in response to CHI3L1 in these cells. In summary, CHI3L1 may contribute to the proliferation, migration, and neoplastic progression of CECs under inflammatory conditions and could be a useful biomarker for neoplastic changes in patients with IBD.

Association of plasma concentration of small heat shock protein B7 with acute coronary syndrome.

BACKGROUND: Heat shock proteins (HSPs) act as chaperones and have a protective function in cardiovascular diseases. The clinical association of a novel small HSPB7 with cardiovascular disease, however, has not been reported. The aim of this study was to investigate the potential biological functions of HSPB7 and its relationship with acute coronary syndrome (ACS). METHODS AND RESULTS: A mouse myocardial infarction (MI) model and samples from clinical human subjects were used to determine plasma HSPB7 concentration after acute MI. The associations of plasma HSPB7 concentration with ACS and other risk factors of coronary artery disease were analyzed. Plasma HSPB7 concentration was found to be rapidly elevated in mice after coronary artery ligation. In addition, plasma HSPB7 concentration was significantly higher in patients with ACS than in control patients with non-cardiac chest pain (5.1 ng/ml vs. 2.9 ng/ml, P<0.001). Plasma HSPB7 was detected as early as 1-3 h after the onset of symptoms and remained detectable up to 24h. Furthermore, in patients presenting to the emergency department with acute chest pain, HSPB7 level was an independent risk factor of ACS (adjusted odds ratio, 7.44; 95% confidence interval: 1.91-28.93, P<0.01). CONCLUSIONS: HSPB7 is a potential early biomarker after MI and serves as an independent risk factor of ACS in patients with acute chest pain.

Extracellular electrons transferred from honey probiotic Bacillus circulans inhibits inflammatory acne vulgaris.

Bacillus circulans (B. circulans) is widely used as an electrogenic bacterium in microbial fuel cell (MFC) technology. This study evaluated whether B. circulans can ferment glucose to generate electricity and mitigate the effects of human skin pathogens. The electricity production of B. circulans was examined by measuring the voltage difference and verified using a ferrozine assay in vitro. To investigate the fermentation effects of B. circulans on inhibition of human skin pathogens, Cutibacterium acnes (C. acnes) was injected intradermally into mice ears to induce an inflammatory response. The results revealed that the glucose-B. circulans co-culture enhanced electricity production and significantly supressed C. acnes growth. The addition of roseoflavin to inhibit flavin production considerably reduced the electrical energy generated by B. circulans through metabolism and, in vivo test, recovered C. acnes count and macrophage inflammatory protein 2 (MIP-2) levels. This suggests that B. circulans can generate electrons that affect the growth of C. acnes through flavin-mediated electron transfer and alleviate the resultant inflammatory response. Our findings demonstrate that probiotics separated from natural substances and antimicrobial methods of generating electrical energy through carbon source fermentation can help in the treatment of bacterial infections.

Neuronal Abnormalities Induced by an Intelligent Virtual Reality System for Methamphetamine Use Disorder.

Methamphetamine use disorder (MUD) is a brain disease that leads to altered regional neuronal activity. Virtual reality (VR) is used to induce the drug cue reactivity. Previous studies reported significant frequency-specific neuronal abnormalities in patients with MUD during VR induction of drug craving. However, whether those patients exhibit neuronal abnormalities after VR induction that could serve as the treatment target remains unclear. Here, we used an integrated VR system for inducing drug related changes and investigated the neuronal abnormalities after VR exposure in patients. Fifteen patients with MUD and ten healthy subjects were recruited and exposed to drug-related VR environments. Resting-state EEG were recorded for 5 minutes twice-before and after VR and transformed to obtain the frequency-specific data. Three self-reported scales for measurement of the anxiety levels and impulsivity of participants were obtained after VR task. Statistical tests and machine learning methods were employed to reveal the differences between patients and healthy subjects. The result showed that patients with MUD and healthy subjects significantly differed in Θ, α, and γ power changes after VR. These neuronal abnormalities in patients were associated with the self-reported behavioral scales, indicating impaired impulse control. Our findings of resting-state EEG abnormalities in patients with MUD after VR exposure have the translational value and can be used to develop the treatment strategies for methamphetamine use disorder.

Nonlinear coupling in the human motor system.

The synchronous discharge of neuronal assemblies is thought to facilitate communication between areas within distributed networks in the human brain. This oscillatory activity is especially interesting, given the pathological modulation of specific frequencies in diseases affecting the motor system. Many studies investigating oscillatory activity have focused on same frequency, or linear, coupling between areas of a network. In this study, our aim was to establish a functional architecture in the human motor system responsible for induced responses as measured in normal subjects with magnetoencephalography. Specifically, we looked for evidence for additional nonlinear (between-frequency) coupling among neuronal sources and, in particular, whether nonlinearities were found predominantly in connections within areas (intrinsic), between areas (extrinsic) or both. We modeled the event-related modulation of spectral responses during a simple hand-grip using dynamic casual modeling. We compared models with and without nonlinear connections under conditions of symmetric and asymmetric interhemispheric connectivity. Bayesian model comparison suggested that the task-dependent motor network was asymmetric during right hand movements. Furthermore, it revealed very strong evidence for nonlinear coupling between sources in this distributed network, but interactions among frequencies within a source appeared linear in nature. Our results provide empirical evidence for nonlinear coupling among distributed neuronal sources in the motor system and that these play an important role in modulating spectral responses under normal conditions.

Carbohydrate-binding motif in chitinase 3-like 1 (CHI3L1/YKL-40) specifically activates Akt signaling pathway in colonic epithelial cells.

Host-microbial interactions play a key role during the development of colitis. We have previously shown that chinase 3-like 1 (CHI3L1) is an inducible molecule overexpressed in colonic epithelial cells (CECs) under inflammatory conditions. In this study, we found that chitin-binding motif (CBM) of CHI3L1 is specifically associated with the CHI3L1-mediated activation of the Akt-signaling in CEC by transfecting the CBM-mutant CHI3L1 vectors in SW480 CECs. Downstream, CHI3L1 enhanced the secretion of IL-8 and TNFα in a dose-dependent manner. We previously show that 325 through 339 amino-acids in CBM are crucial for the biological function of CHI3L1. Here we demonstrated that 325th-339th residues of CBM in CHI3L1 is a critical region for the activation of Akt, IL-8 production, and for a specific cellular localization of CHI3L1. In conclusion, CBM region of CHI3L1 is critical in activating Akt signaling in CECs, and the activation may be associated with the development of chronic colitis.

[Project to enhance bone bank tissue storage and distribution procedures].

BACKGROUND: Organ and tissue transplantation are now commonly preformed procedures. Improper organ bank handling procedures may increase infection risks. Execution accuracy in terms of tissue storage and distribution at our bone bank was 80%. We thus proposed an execution improvement project to enhance procedures in order to fulfill the intent of donors and ensure recipient safety. PURPOSE: This project was designed to raise nurse professionalism, and ensure patient safety through enhanced tissue storage and distribution procedures. RESOLUTION: Education programs developed for this project focus on teaching standard operating procedures for bone and ligament storage and distribution, bone bank facility maintenance, trouble shooting and solutions, and periodic inspection systems. RESULTS: Cognition of proper storage and distribution procedures rose from 81% to 100%; Execution accuracy also rose from 80% to 100%. CONCLUSIONS: The project successfully conveyed concepts essential to the correct execution of organ storage and distribution procedures and proper organ bank facility management. Achieving and maintaining procedural and management standards is crucial to continued organ donations and the recipient safety.

Propionic acid produced by Cutibacterium acnes fermentation ameliorates ultraviolet B-induced melanin synthesis.

Ultraviolet irradiation induces melanin accumulation, which can be reduced by the use of chemical whitening products. However, the associated safety concerns of such products have prompted the search for natural and harmless alternatives. This study aimed to identify a natural acidic formulation to reduce skin pigmentation. The metabolite propionic acid (CH3CH2COOH, PA) was the most abundant fatty acid in the filtrate from Pluronic F68 (PF68) fermentation of Cutibacterium acnes (C. acnes) and reduced the DOPA-positive melanocytes by significantly inhibiting cellular tyrosinase activity via binding to the free fatty acid receptor 2 (FFAR2). Moreover, 4 mM PA treatment did not alter melanocyte proliferation, indicating that it is an effective solution for hyperpigmentation, causing no cellular damage. The reduced DOPA-positive melanocytes and tyrosinase activity were also observed in mice ear skin tissue injected with a mixture of C. acnes and PF68, supporting that the inhibition of melanogenesis is likely to be mediated through fermentation metabolites from C. acnes fermentation using PF68 as a carbon source. Additionally, PA did not affect the growth of its parent bacteria C. acnes, hence is a potent fermentation metabolite that does not disrupt the balance of the skin microbiome.

A Machine-Learning-Based Assessment Method for Early-Stage Neurocognitive Impairment by an Immersive Virtual Supermarket.

Alzheimer's disease (AD) is a neurodegenerative disorder. Though it is not yet curable or reversible, research has shown that clinical intervention or intensive cognitive training at an early stage may effectively delay the progress of the disease. As a result, screening populations with mild cognitive impairment (MCI) or early AD via efficient, effective and low-cost cognitive assessments is important. Currently, a cognitive assessment relies mostly on cognitive tests, such as the Mini-Mental State Examination (MMSE) or the Montreal Cognitive Assessment (MoCA), which must be performed by therapists. Also, cognitive functions can be divided into a variety of dimensions, such as memory, attention, executive function, visual spatial and so on. Executive functions (EF), also known as executive control or cognitive control, refer to a set of skills necessary to perform higher-order cognitive processes, including working memory, planning, attention, cognitive flexibility, and inhibitory control. Along with the fast progress of virtual reality (VR) and artificial intelligence (AI), this study proposes an intelligent assessment method aimed at assessing executive functions. Utilizing machine learning to develop an automatic evidence-based assessment model, behavioral information is acquired through performing executive-function tasks in a VR supermarket. Clinical trials were performed individuals with MCI or early AD and six healthy participants. Statistical analysis showed that 45 out of 46 indices derived from behavioral information were found to differ significantly between individuals with neurocognitive disorder and healthy participants. This analysis indicates these indices may be potential bio-markers. Further, machine-learning methods were applied to build classifiers that differentiate between individuals with MCI or early AD and healthy participants. The accuracy of the classifier is up to 100%, demonstrating the derived features from the VR system were highly related to diagnosis of individuals with MCI or early AD.

An Intelligent Virtual-Reality System With Multi-Model Sensing for Cue-Elicited Craving in Patients With Methamphetamine Use Disorder.

Methamphetamine abuse is getting worse amongst the younger population. While there is methadone or buprenorphine harm-reduction treatment for heroin addicts, there is no drug treatment for addicts with methamphetamine use disorder (MUD). Recently, non-medication treatment, such as the cue-elicited craving method integrated with biofeedback, has been widely used. Further, virtual reality (VR) is proposed to simulate an immersive virtual environment for cue-elicited craving in therapy. In this study, we developed a VR system equipped with flavor simulation for the purpose of inducing cravings for MUD patients in therapy. The VR system was integrated with multi-model sensors, such as an electrocardiogram (ECG), galvanic skin response (GSR) and eye tracking to measure various physiological responses from MUD patients in the virtual environment. The goal of the study was to validate the effectiveness of the proposed VR system in inducing the craving of MUD patients via the physiological data. Clinical trials were performed with 20 MUD patients and 11 healthy subjects. VR stimulation was applied to each subject and the physiological data was measured at the time of pre-VR stimulation and post-VR stimulation. A variety of features were extracted from the raw data of heart rate variability (HRV), GSR and eye tracking. The results of statistical analysis found that quite a few features of HRV, GSR and eye tracking had significant differences between pre-VR stimulation and post-VR stimulation in MUD patients but not in healthy subjects. Also, the data of post-VR stimulation showed a significant difference between MUD patients and healthy subjects. Correlation analysis was made and several features between HRV and GSR were found to be correlated. Further, several machine learning methods were applied and showed that the classification accuracy between MUD and healthy subjects at post-VR stimulation attained to 89.8%. In conclusion, the proposed VR system was validated to effectively induce the drug craving in MUD patients.