Effects of Class Imbalance and Data Scarcity on the Performance of Binary Classification Machine Learning Models Developed Based on ToxCast/Tox21 Assay Data.

The development of toxicity classification models using the ToxCast database has been extensively studied. Machine learning approaches are effective in identifying the bioactivity of untested chemicals. However, ToxCast assays differ in the amount of data and degree of class imbalance (CI). Therefore, the resampling algorithm employed should vary depending on the data distribution to achieve optimal classification performance. In this study, the effects of CI and data scarcity (DS) on the performance of binary classification models were investigated using ToxCast bioassay data. An assay matrix based on CI and DS was prepared for 335 assays with biologically intended target information, and 28 CI assays and 3 DS assays were selected. Thirty models established by combining five molecular fingerprints (i.e., Morgan, MACCS, RDKit, Pattern, and Layered) and six algorithms [i.e., gradient boosting tree, random forest (RF), multi-layered perceptron, k-nearest neighbor, logistic regression, and naive Bayes] were trained using the selected assay data set. Of the 30 trained models, MACCS-RF showed the best performance and thus was selected for analyses of the effects of CI and DS. Results showed that recall and F1 were significantly lower when training with the CI assays than with the DS assays. In addition, hyperparameter tuning of the RF algorithm significantly improved F1 on CI assays. This study provided a basis for developing a toxicity classification model with improved performance by evaluating the effects of data set characteristics. This study also emphasized the importance of using appropriate evaluation metrics and tuning hyperparameters in model development.

Low-Asymmetry Interface for Multiuser VR Experiences with Both HMD and Non-HMD Users.

We propose a low-asymmetry interface to improve the presence of non-head-mounted-display (non-HMD) users in shared virtual reality (VR) experiences with HMD users. The low-asymmetry interface ensures that the HMD and non-HMD users' perception of the VR environment is almost similar. That is, the point-of-view asymmetry and behavior asymmetry between HMD and non-HMD users are reduced. Our system comprises a portable mobile device as a visual display to provide a changing PoV for the non-HMD user and a walking simulator as an in-place walking detection sensor to enable the same level of realistic and unrestricted physical-walking-based locomotion for all users. Because this allows non-HMD users to experience the same level of visualization and free movement as HMD users, both of them can engage as the main actors in movement scenarios. Our user study revealed that the low-asymmetry interface enables non-HMD users to feel a presence similar to that of the HMD users when performing equivalent locomotion tasks in a virtual environment. Furthermore, our system can enable one HMD user and multiple non-HMD users to participate together in a virtual world; moreover, our experiments show that the non-HMD user satisfaction increases with the number of non-HMD participants owing to increased presence and enjoyment.

Full-band TDM-OPDMA for OBI-reduced simultaneous multiple access in a single-wavelength optical access network.

Simultaneous multiple access (MA) within a single wavelength can increase the data rate and split ratio in a passive optical network while optical beat interference (OBI) becomes serious in the uplink. Previous techniques to reduce OBI were limited by their complexity and lack of extendibility; as well, bandwidth allocation among MA signals is needed for single photo diode (PD) detection. We proposed and experimentally demonstrated full-band optical pulse division multiplexing-based MA (OPDMA) in an optical access network, which can effectively reduce OBI with extendibility and fully utilize frequency resources of optical modulator without bandwidth allocation in a single-wavelength MA.

Laboratory measurement of apixaban using anti-factor Xa assays in acute ischemic stroke patients with non-valvular atrial fibrillation.

Apixaban is effective and safe for preventing stroke, and its usage has increased exponentially in recent years. However, data concerning the therapeutic range of apixaban is limited. This study determined the trough and peak levels of apixaban-specific anti-factor Xa activity (AFXaA) in acute ischemic stroke patients with non-valvular atrial fibrillation (NVAF) in Korea. The study included 85 patients who received apixaban. Blood samples were taken to measure the trough and peak levels of AFXaA using a chromogenic anti-factor assay, as well as prothrombin time (PT) and activated partial thromboplastin time (aPTT). We also reviewed complications such as major bleeding of patients treated with apixaban. In patients given a 5.0-mg apixaban dose, the median trough and peak levels of AFXaA were 104.5 and 202.0 ng/mL. In patients given a 2.5-mg apixaban dose, the median trough and peak AFXaA levels were 76.0 and 151.0 ng/mL. The PT showed a positive correlation with increased AFXaA activity at both levels (Trough R = 0.486, Peak R = 0.592), but the aPTT had no relationship with AFXaA activity at both levels (Trough R = 0.181, Peak R = 0.129). Two cases with intracranial bleeding belonged to the highest AFXaA quartile (Trough, p = 0.176; Peak, p = 0.053). In conclusion, we determined the trough and peak levels of AFXaA in patients with NVAF while being treated with the apixaban in Korea. Our results could be used as a starting point when setting the reference ranges for laboratories using anti-Xa assay. Large-scale studies are needed to establish the reference range for AFXaA in patients with NVAF.

Efficient Representation of Detailed Foam Waves by Incorporating Projective Space.

We propose an efficient framework to realistically simulate foam effects in which 3D water particles from a base water solver are first projected onto 2D screen space in order to reduce computational complexity of finding foam particles. Because foam effects are often created primarily in fast and complicated water flows, we analyze acceleration and curvature values to identify the areas exhibiting such flow patterns. Identified foam particles are emitted in 3D simulation space, and each foam particle is advected by its classified type based on its velocity, thereby capturing the essential characteristics of foam wave motions (e.g., floating waves or scattering bubbles). In addition, we provide an intuitive and flexible mechanism (e.g., user sketch or image) to customize parameters and control the appearance of foam effects while minimizing the occurrence of popping artifacts. Experiments convincingly demonstrate that the proposed approach is efficient and easy to use while delivering high-quality results.

Optical pulse division multiplexing-based OBI reduction for single wavelength uplink multiple access in IM/DD OFDMA-PON.

Orthogonal frequency division multiple access-based passive optical network (OFDMA-PON) is considered as a strong candidate for next-generation optical access network. In intensity modulation/direct detection system, OFDMA-PON downlink transmission is relatively stable, but critical issues exist in uplink multiple access. Because of different optical paths, optical beat interference (OBI) and timing offset effect are generated, which seriously disturb signal detection. We propose optical pulse division multiplexing-based OBI reduction. By considering both the spectrum broadening effect and the time domain near orthogonality, OBI could be reduced. We demonstrate that the spectral efficiency can be improved from 0.37 to 3.8 bit/s/Hz in 1-GHz signal bandwidth.

Endovascular Treatment of Intracranial Aneurysms in Patients With Autosomal Dominant Polycystic Kidney Disease.

BACKGROUND: Little is known about the outcome of endovascular treatment for intracranial aneurysms in patients with autosomal dominant polycystic kidney disease (ADPKD). OBJECTIVE: To present clinical outcomes in terms of safety, effectiveness, and renal functions to assess contrast-induced nephropathy in endovascular coil embolization for intracranial aneurysms in ADPKD patients. METHODS: Nineteen ADPKD patients (female:male, 15:4; mean age, 49.8 years; range, 20-67 years) had 26 aneurysms (mean size, 5.86 mm; range, 2.5-11.6 mm) and underwent 22 endovascular treatment sessions from 2001 to 2013. Four patients presented with ruptured aneurysms. Periprocedural complications, clinical outcomes with modified Rankin Scale scores, laboratory findings, and chronic kidney disease (CKD) stage before and after treatment were documented. Acute renal impairment was defined as serum creatinine (Cr) elevation by ≥ 0.5 mg/dL or 25% relative to baseline. RESULTS: Symptomatic periprocedural complications developed after 1 endovascular procedure (1 of 22, 4.5%), and good clinical outcomes (modified Rankin Scale scores, 0-1) were achieved in 90% of patients (17 of 19). Overall, acute renal impairment occurred in 9.1% of treatment sessions (2 of 22). Acute renal impairment developed in 25% of high-risk patients (baseline Cr > 2.0 mg/dL) and 33.3% of baseline CKD stage 5 sessions but in none of the low-risk patients (baseline Cr ≤ 2.0 mg/dL) and in no CKD stage 1 to 4 sessions. CONCLUSION: With appropriate management, coil embolization may be safe and effective for intracranial aneurysms in ADPKD. There is a concern about contrast-induced nephropathy in patients with CKD stage 5 or high serum Cr level (>2.0 mg/dL).

Metabolic responses to Orientia tsutsugamushi infection in a mouse model.

Tsutsugamushi disease is an infectious disease transmitted to humans through the bite of the Orientia tsutsugamushi-infected chigger mite; however, host-pathogen interactions and the precise mechanisms of damage in O. tsutsugamushi infections have not been fully elucidated. Here, we analyzed the global metabolic effects of O. tsutsugamushi infection on the host using 1H-NMR and UPLC-Q-TOF mass spectroscopy coupled with multivariate statistical analysis. In addition, the effect of O. tsutsugamushi infection on metabolite concentrations over time was analyzed by two-way ANOVAs. Orthogonal partial least squares-discriminant analysis (OPLS-DA) showed distinct metabolic patterns between control and O. tsutsugamushi-infected mice in liver, spleen, and serum samples. O. tsutsugamushi infection caused decreased energy production and deficiencies in both remethylation sources and glutathione. In addition, O. tsutsugamushi infection accelerated uncommon energy production pathways (i.e., excess fatty acid and protein oxidation) in host body. Infection resulted in an enlarged spleen with distinct phospholipid and amino acid characteristics. This study suggests that metabolite profiling of multiple organ tissues and serum could provide insight into global metabolic changes and mechanisms of pathology in O. tsutsugamushi-infected hosts.

Shape changes of the basal ganglia and thalamus in Alzheimer's disease: a three-year longitudinal study.

BACKGROUND: A large number of Alzheimer's disease (AD) studies have focused on medial temporal and cortical atrophy, while changes in the basal ganglia or thalamus have received less attention. OBJECTIVE: The aim of this study was to investigate the existence of progressive topographical shape changes in the basal ganglia (caudate nucleus, putamen, and globus pallidus) and thalamus concurrent with AD disease progression over three years. This study also examined whether declines in volumes of the basal ganglia or thalamus might be responsible for cognitive decline in patients with AD. METHODS: Thirty-six patients with early stage AD and 14 normal control subjects were prospectively recruited for this study. All subjects were assessed with neuropsychological tests and MRI at baseline and Years 1 and 3. A longitudinal shape analysis of the basal ganglia and thalamus was performed by employing a boundary surface-based shape analysis method. RESULTS: AD patients exhibited specific regional atrophy in the right caudate nucleus and the bilateral putamen at baseline, and as the disease progressed, regional atrophic changes in the left caudate nucleus were found to conform to a distinct topography after controlling the total brain volume. Volumetric decline of the caudate nucleus and putamen correlated with cognitive decline in frontal function after controlling for age, gender, education, follow-up years, and total brain volume changes. CONCLUSION: Our findings suggest that shape changes of the basal ganglia occurred regardless of whole brain atrophy as AD progressed and were also responsible for cognitive decline that was observed from the frontal function tests.

Hippocampal and cortical atrophy in amyloid-negative mild cognitive impairments: comparison with amyloid-positive mild cognitive impairment.

Although patients with amnestic mild cognitive impairment (aMCI) are at higher risk of developing Alzheimer's disease (AD), their pathologies could be heterogeneous. We aimed to evaluate structural changes in amyloid-negative and amyloid-positive aMCI patients. Forty-eight aMCI patients who underwent Pittsburgh compound B (PiB) positron emission tomography were recruited. They were classified as PiB (-) aMCI (N = 16) and PiB (+) (N = 32). Hippocampal shape and regional cortical thickness were compared with 41 subjects with normal cognition (NC). Relative to NC, PiB(-) aMCI exhibited hippocampal deformity in the right cornu ammonis 1, whereas PiB(+) aMCI exhibited hippocampal deformity in bilateral subiculum and cornu ammonis 1 subregions. Relative to NC, PiB(-) aMCI showed cortical thinning in the left medial prefrontal and right anterior temporal regions, whereas PiB(+) aMCI exhibited cortical thinning in bilateral medial temporal regions, temporoparietal junctions and precuneus, and prefrontal cortices. Our findings suggest that structural changes in PiB(-) aMCI might be due to several possible pathologic changes, whereas structural changes in PiB(+) aMCI reflect AD-like structural changes.

Individual subject classification of mixed dementia from pure subcortical vascular dementia based on subcortical shape analysis.

Subcortical vascular dementia (SVaD), one of common causes of dementia, has concomitant Alzheimer's disease (AD) pathology in over 30%, termed "mixed dementia". Identifying mixed dementia from SVaD is important because potential amyloid-targeted therapies may be effective for treatment in mixed dementia. The purpose of this study was to discriminate mixed dementia from pure SVaD using magnetic resonance imaging (MRI). We measured brain amyloid deposition using the 11C-Pittsburgh compound B positron emission tomography (PiB-PET) in 68 patients with SVaD. A PiB retention ratio greater than 1.5 was considered PiB(+). Hippocampal and amygdalar shape were used in the incremental learning method to discriminate mixed dementia from pure SVaD because these structures are known to be prominently involved by AD pathologies. Among 68 patients, 23 (33.8%) patients were positive for PiB binding. With use of hippocampal shape analysis alone, PiB(+) SVaD could be discriminated from PiB(-) SVaD with 77.9% accuracy (95.7% sensitivity and 68.9% specificity). With use of amygdalar shape, the discrimination accuracy was 75.0% (87.0% sensitivity and 68.9% specificity). When hippocampal and amygdalar shape were analyzed together, accuracy increased to 82.4% (95.7% sensitivity and 75.6% specificity). An incremental learning method using hippocampal and amygdalar shape distinguishes mixed dementia from pure SVaD. Furthermore, our results suggest that amyloid pathology and vascular pathology have different effects on the shape of the hippocampus and amygdala.

Changes in subcortical structures in early- versus late-onset Alzheimer's disease.

Patients with early-onset Alzheimer's disease (EOAD) are reported to be different from those with late-onset Alzheimer's disease (LOAD) in terms of neuropsychological and neuroimaging findings. In this study, we aimed to compare the longitudinal volume changes of 6 subcortical structures (the amygdala, hippocampus, thalamus, putamen, globus pallidus, and caudate nucleus) between patients with EOAD and LOAD for 3 years. We prospectively recruited 36 patients with probable Alzheimer's disease (14 EOAD, 22 LOAD) and 14 normal control subjects. We analyzed the volume of subcortical structures using an automatic surface-based method. At baseline, there were no differences in the volumes of subcortical structures between patients with EOAD and LOAD. However, over 3 years of longitudinal follow-up, patients with EOAD showed more rapid volumetric decline in the caudate, putamen, and thalamus than patients with LOAD, which is consistent with neuropsychological results. Our findings suggested that the cognitive reserve theory might be applicable to explain different decline rates of the volumes of the basal ganglia and thalamus according to onset age.

Suicide rate differences by sex, age, and urbanicity, and related regional factors in Korea.

OBJECTIVES: Identify the characteristics related to the suicide rates in rural and urban areas of Korea and discover the factors that influence the suicide rate of the rural and urban areas. METHODS: Using the data on causes of death from 2006 to 2008, the suicide rates were calculated and compared after age-standardization based on gender, age group and urbanicity. And, in order to understand the factors that influence suicide rate, total 10 local characteristics in four domains--public service, social integration, residential environment, and economic status--were selected for multiple regression analysis. RESULTS: The suicide rates were higher in men than women, in rural areas than urban, and in older people than the younger. Generally, although there were variations according to age group and urbanicity, suicide rates were significantly related to residential environment and regional economic status but not related to regional welfare spending and social integration. In addition, the population over the age of 65 years, only regional economic status has significantly influence on their suicide rates. CONCLUSIONS: The influence of characteristics of regions on suicide rate is various by age-group, gender, and urbanicity. Therefore, in order to lower suicide rate and reduce the gap between regions, various approaches must be adopted by taking into account the socioeconomic characteristics of the regions.

Adaptive synthesis of distance fields.

We address the computational resource requirements of 3D example-based synthesis with an adaptive synthesis technique that uses a tree-based synthesis map. A signed-distance field (SDF) is determined for the 3D exemplars, and then new models can be synthesized as SDFs by neighborhood matching. Unlike voxel synthesis approach, our input is posed in the real domain to preserve maximum detail. In comparison to straightforward extensions to the existing volume texture synthesis approach, we made several improvements in terms of memory requirements, computation times, and synthesis quality. The inherent parallelism in this method makes it suitable for a multicore CPU. Results show that computation times and memory requirements are very much reduced, and large synthesized scenes exhibit fine details which mimic the exemplars.

Analytic solutions of integral moving least squares for polygon soups.

This paper presents analytic solutions to the integral moving least squares (MLS) equations originally proposed by Shen et al. by choosing another specific weighting function that renders the numerator in the MLS equation unitless. In addition, we analyze the original method to show that their approximation surfaces (i.e., enveloping surfaces with nonzero values in the weighting function) often form zero isosurfaces near concavities behind the triangle-soup models. This paper also presents error terms for the integral MLS formulations against signed distance fields. Based on our analytic solutions, we show that our method provides both interpolation and approximation surfaces faster and more efficiently. Because our method computes solutions for integral MLS equations directly, it does not rely on numerical steps that might have numerical-accuracy issues. In particular, unlike the original method that deals with incorrect approximation surfaces by iteratively adjusting parameters, this paper proposes faster and more efficient approximations to surfaces without needing iterative routines. We also present computational efficiency comparisons, in which our method is 15-fold faster in computing integrations, even with conservative assumptions. Finally, we show that the surface normal vectors on the implicit surfaces formed by our analytic solutions are identical to the angle-weighted pseudonormal vectors.

A probable cavernoma in the medulla oblongata presenting only as upbeat nystagmus.

A cavernoma is a vascular malformation in the central nervous system. Brainstem cavernoma are relatively common and induce variable neurological symptoms. A 19-year-old woman visited our hospital with complaints of continuous dizziness. On a neurological examination, continuous conjugated upbeat nystagmus was observed in the primary position of gaze. A brain CT scan and MRI showed focal hemorrhagic signals in the central caudal medulla caused by a cavernoma. The spontaneous upbeat nystagmus disappeared gradually. To our knowledge, this is the first report of a probable cavernoma in the medulla oblongata presenting with upbeat nystagmus only.

Evolving physically simulated flying creatures for efficient cruising.

The body-brain coevolution of aerial life forms has not been developed as far as aquatic or terrestrial locomotion in the field of artificial life. We are studying physically simulated 3D flying creatures by evolving both wing shapes and their controllers. A creature's wing is modeled as a number of articulated cylinders, connected by triangular films (patagia). The wing structure and its motor controllers for cruising flight are generated by an evolutionary algorithm within a simulated aerodynamic environment. The most energy-efficient cruising speed and the lift and drag coefficients of each flier are calculated from its morphological characteristics and used in the fitness evaluation. To observe a wide range of creature size, the evolution is run separately for creatures categorized into three species by body weight. The resulting creatures vary in size from pigeons to pterosaurs, with various wing configurations. We discuss the characteristics of shape and motion of the evolved creatures, including flight stability and Strouhal number.