ResearchPad - Artificial Intelligence Default RSS Feed en-us © 2020 Newgen KnowledgeWorks <![CDATA[LoAdaBoost: Loss-based AdaBoost federated machine learning with reduced computational complexity on IID and non-IID intensive care data]]>

Intensive care data are valuable for improvement of health care, policy making and many other purposes. Vast amount of such data are stored in different locations, on many different devices and in different data silos. Sharing data among different sources is a big challenge due to regulatory, operational and security reasons. One potential solution is federated machine learning, which is a method that sends machine learning algorithms simultaneously to all data sources, trains models in each source and aggregates the learned models. This strategy allows utilization of valuable data without moving them. One challenge in applying federated machine learning is the possibly different distributions of data from diverse sources. To tackle this problem, we proposed an adaptive boosting method named LoAdaBoost that increases the efficiency of federated machine learning. Using intensive care unit data from hospitals, we investigated the performance of learning in IID and non-IID data distribution scenarios, and showed that the proposed LoAdaBoost method achieved higher predictive accuracy with lower computational complexity than the baseline method.

<![CDATA[A compound attributes-based predictive model for drug induced liver injury in humans]]>

Drug induced liver injury (DILI) is one of the key safety concerns in drug development. To assess the likelihood of drug candidates with potential adverse reactions of liver, we propose a compound attributes-based approach to predicting hepatobiliary disorders that are routinely reported to US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS). Specifically, we developed a support vector machine (SVM) model with recursive feature extraction, based on physicochemical and structural properties of compounds as model input. Cross validation demonstrates that the predictive model has a robust performance with averaged 70% of both sensitivity and specificity over 500 trials. An independent validation was performed on public benchmark drugs and the results suggest potential utility of our model for identifying safety alerts. This in silico approach, upon further validation, would ultimately be implemented, together with other in vitro safety assays, for screening compounds early in drug development.

<![CDATA[Predicting 30-day hospital readmissions using artificial neural networks with medical code embedding]]>

Reducing unplanned readmissions is a major focus of current hospital quality efforts. In order to avoid unfair penalization, administrators and policymakers use prediction models to adjust for the performance of hospitals from healthcare claims data. Regression-based models are a commonly utilized method for such risk-standardization across hospitals; however, these models often suffer in accuracy. In this study we, compare four prediction models for unplanned patient readmission for patients hospitalized with acute myocardial infarction (AMI), congestive health failure (HF), and pneumonia (PNA) within the Nationwide Readmissions Database in 2014. We evaluated hierarchical logistic regression and compared its performance with gradient boosting and two models that utilize artificial neural networks. We show that unsupervised Global Vector for Word Representations embedding representations of administrative claims data combined with artificial neural network classification models improves prediction of 30-day readmission. Our best models increased the AUC for prediction of 30-day readmissions from 0.68 to 0.72 for AMI, 0.60 to 0.64 for HF, and 0.63 to 0.68 for PNA compared to hierarchical logistic regression. Furthermore, risk-standardized hospital readmission rates calculated from our artificial neural network model that employed embeddings led to reclassification of approximately 10% of hospitals across categories of hospital performance. This finding suggests that prediction models that incorporate new methods classify hospitals differently than traditional regression-based approaches and that their role in assessing hospital performance warrants further investigation.

<![CDATA[Fluid–structure interaction simulations outperform computational fluid dynamics in the description of thoracic aorta haemodynamics and in the differentiation of progressive dilation in Marfan syndrome patients]]>

Abnormal fluid dynamics at the ascending aorta may be at the origin of aortic aneurysms. This study was aimed at comparing the performance of computational fluid dynamics (CFD) and fluid–structure interaction (FSI) simulations against four-dimensional (4D) flow magnetic resonance imaging (MRI) data; and to assess the capacity of advanced fluid dynamics markers to stratify aneurysm progression risk. Eight Marfan syndrome (MFS) patients, four with stable and four with dilating aneurysms of the proximal aorta, and four healthy controls were studied. FSI and CFD simulations were performed with MRI-derived geometry, inlet velocity field and Young's modulus. Flow displacement, jet angle and maximum velocity evaluated from FSI and CFD simulations were compared to 4D flow MRI data. A dimensionless parameter, the shear stress ratio (SSR), was evaluated from FSI and CFD simulations and assessed as potential correlate of aneurysm progression. FSI simulations successfully matched MRI data regarding descending to ascending aorta flow rates (R2 = 0.92) and pulse wave velocity (R2 = 0.99). Compared to CFD, FSI simulations showed significantly lower percentage errors in ascending and descending aorta in flow displacement (−46% ascending, −41% descending), jet angle (−28% ascending, −50% descending) and maximum velocity (−37% ascending, −34% descending) with respect to 4D flow MRI. FSI- but not CFD-derived SSR differentiated between stable and dilating MFS patients. Fluid dynamic simulations of the thoracic aorta require fluid–solid interaction to properly reproduce complex haemodynamics. FSI- but not CFD-derived SSR could help stratifying MFS patients.

<![CDATA[Robust subspace methods for outlier detection in genomic data circumvents the curse of dimensionality]]>

The application of machine learning to inference problems in biology is dominated by supervised learning problems of regression and classification, and unsupervised learning problems of clustering and variants of low-dimensional projections for visualization. A class of problems that have not gained much attention is detecting outliers in datasets, arising from reasons such as gross experimental, reporting or labelling errors. These could also be small parts of a dataset that are functionally distinct from the majority of a population. Outlier data are often identified by considering the probability density of normal data and comparing data likelihoods against some threshold. This classical approach suffers from the curse of dimensionality, which is a serious problem with omics data which are often found in very high dimensions. We develop an outlier detection method based on structured low-rank approximation methods. The objective function includes a regularizer based on neighbourhood information captured in the graph Laplacian. Results on publicly available genomic data show that our method robustly detects outliers whereas a density-based method fails even at moderate dimensions. Moreover, we show that our method has better clustering and visualization performance on the recovered low-dimensional projection when compared with popular dimensionality reduction techniques.

<![CDATA[Early warning of some notifiable infectious diseases in China by the artificial neural network]]>

In order to accurately grasp the timing for the prevention and control of diseases, we established an artificial neural network model to issue early warning signals. The real-time recurrent learning (RTRL) and extended Kalman filter (EKF) methods were performed to analyse four types of respiratory infectious diseases and four types of digestive tract infectious diseases in China to comprehensively determine the epidemic intensities and whether to issue early warning signals. The numbers of new confirmed cases per month between January 2004 and December 2017 were used as the training set; the data from 2018 were used as the test set. The results of RTRL showed that the number of new confirmed cases of respiratory infectious diseases in September 2018 increased abnormally. The results of the EKF showed that the number of new confirmed cases of respiratory infectious diseases increased abnormally in January and February of 2018. The results of these two algorithms showed that the number of new confirmed cases of digestive tract infectious diseases in the test set did not have any abnormal increases. The neural network and machine learning can further enrich and develop the early warning theory.

<![CDATA[Reconciling periodic rhythms of large-scale biological networks by optimal control]]>

Periodic rhythms are ubiquitous phenomena that illuminate the underlying mechanism of cyclic activities in biological systems, which can be represented by cyclic attractors of the related biological network. Disorders of periodic rhythms are detrimental to the natural behaviours of living organisms. Previous studies have shown that the state transition from one to another attractor can be accomplished by regulating external signals. However, most of these studies until now have mainly focused on point attractors while ignoring cyclic ones. The aim of this study is to investigate an approach for reconciling abnormal periodic rhythms, such as diminished circadian amplitude and phase delay, to the regular rhythms of complex biological networks. For this purpose, we formulate and solve a mixed-integer nonlinear dynamic optimization problem simultaneously to identify regulation variables and to determine optimal control strategies for state transition and adjustment of periodic rhythms. Numerical experiments are implemented in three examples including a chaotic system, a mammalian circadian rhythm system and a gastric cancer gene regulatory network. The results show that regulating a small number of biochemical molecules in the network is sufficient to successfully drive the system to the target cyclic attractor by implementing an optimal control strategy.

<![CDATA[Intermediacy of publications]]>

Citation networks of scientific publications offer fundamental insights into the structure and development of scientific knowledge. We propose a new measure, called intermediacy, for tracing the historical development of scientific knowledge. Given two publications, an older and a more recent one, intermediacy identifies publications that seem to play a major role in the historical development from the older to the more recent publication. The identified publications are important in connecting the older and the more recent publication in the citation network. After providing a formal definition of intermediacy, we study its mathematical properties. We then present two empirical case studies, one tracing historical developments at the interface between the community detection literature and the scientometric literature and one examining the development of the literature on peer review. We show both conceptually and empirically how intermediacy differs from main path analysis, which is the most popular approach for tracing historical developments in citation networks. Main path analysis tends to favour longer paths over shorter ones, whereas intermediacy has the opposite tendency. Compared to the main path analysis, we conclude that intermediacy offers a more principled approach for tracing the historical development of scientific knowledge.

<![CDATA[Dealing with uncertainty in agent-based models for short-term predictions]]>

Agent-based models (ABMs) are gaining traction as one of the most powerful modelling tools within the social sciences. They are particularly suited to simulating complex systems. Despite many methodological advances within ABM, one of the major drawbacks is their inability to incorporate real-time data to make accurate short-term predictions. This paper presents an approach that allows ABMs to be dynamically optimized. Through a combination of parameter calibration and data assimilation (DA), the accuracy of model-based predictions using ABM in real time is increased. We use the exemplar of a bus route system to explore these methods. The bus route ABMs developed in this research are examples of ABMs that can be dynamically optimized by a combination of parameter calibration and DA. The proposed model and framework is a novel and transferable approach that can be used in any passenger information system, or in an intelligent transport systems to provide forecasts of bus locations and arrival times.

<![CDATA[FaceLift: a transparent deep learning framework to beautify urban scenes]]>

In the area of computer vision, deep learning techniques have recently been used to predict whether urban scenes are likely to be considered beautiful: it turns out that these techniques are able to make accurate predictions. Yet they fall short when it comes to generating actionable insights for urban design. To support urban interventions, one needs to go beyond predicting beauty, and tackle the challenge of recreating beauty. Unfortunately, deep learning techniques have not been designed with that challenge in mind. Given their ‘black-box nature’, these models cannot be directly used to explain why a particular urban scene is deemed to be beautiful. To partly fix that, we propose a deep learning framework (which we name FaceLift1) that is able to both beautify existing urban scenes (Google Street Views) and explain which urban elements make those transformed scenes beautiful. To quantitatively evaluate our framework, we cannot resort to any existing metric (as the research problem at hand has never been tackled before) and need to formulate new ones. These new metrics should ideally capture the presence (or absence) of elements that make urban spaces great. Upon a review of the urban planning literature, we identify five main metrics: walkability, green spaces, openness, landmarks and visual complexity. We find that, across all the five metrics, the beautified scenes meet the expectations set by the literature on what great spaces tend to be made of. This result is further confirmed by a 20-participant expert survey in which FaceLift has been found to be effective in promoting citizen participation. All this suggests that, in the future, as our framework’s components are further researched and become better and more sophisticated, it is not hard to imagine technologies that will be able to accurately and efficiently support architects and planners in the design of the spaces we intuitively love.

<![CDATA[Neuroimaging modality fusion in Alzheimer’s classification using convolutional neural networks]]>

Automated methods for Alzheimer’s disease (AD) classification have the potential for great clinical benefits and may provide insight for combating the disease. Machine learning, and more specifically deep neural networks, have been shown to have great efficacy in this domain. These algorithms often use neurological imaging data such as MRI and FDG PET, but a comprehensive and balanced comparison of the MRI and amyloid PET modalities has not been performed. In order to accurately determine the relative strength of each imaging variant, this work performs a comparison study in the context of Alzheimer’s dementia classification using the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset with identical neural network architectures. Furthermore, this work analyzes the benefits of using both modalities in a fusion setting and discusses how these data types may be leveraged in future AD studies using deep learning.

<![CDATA[The Tumor Target Segmentation of Nasopharyngeal Cancer in CT Images Based on Deep Learning Methods]]>

Radiotherapy is the main treatment strategy for nasopharyngeal carcinoma. A major factor affecting radiotherapy outcome is the accuracy of target delineation. Target delineation is time-consuming, and the results can vary depending on the experience of the oncologist. Using deep learning methods to automate target delineation may increase its efficiency. We used a modified deep learning model called U-Net to automatically segment and delineate tumor targets in patients with nasopharyngeal carcinoma. Patients were randomly divided into a training set (302 patients), validation set (100 patients), and test set (100 patients). The U-Net model was trained using labeled computed tomography images from the training set. The U-Net was able to delineate nasopharyngeal carcinoma tumors with an overall dice similarity coefficient of 65.86% for lymph nodes and 74.00% for primary tumor, with respective Hausdorff distances of 32.10 and 12.85 mm. Delineation accuracy decreased with increasing cancer stage. Automatic delineation took approximately 2.6 hours, compared to 3 hours, using an entirely manual procedure. Deep learning models can therefore improve accuracy, consistency, and efficiency of target delineation in T stage, but additional physician input may be required for lymph nodes.

<![CDATA[Adaptive multi-degree of freedom Brain Computer Interface using online feedback: Towards novel methods and metrics of mutual adaptation between humans and machines for BCI]]>

This paper proposes a novel adaptive online-feedback methodology for Brain Computer Interfaces (BCI). The method uses ElectroEncephaloGraphic (EEG) signals and combines motor with speech imagery to allow for tasks that involve multiple degrees of freedom (DoF). The main approach utilizes the covariance matrix descriptor as feature, and the Relevance Vector Machines (RVM) classifier. The novel contributions include, (1) a new method to select representative data to update the RVM model, and (2) an online classifier which is an adaptively-weighted mixture of RVM models to account for the users’ exploration and exploitation processes during the learning phase. Instead of evaluating the subjects’ performance solely based on the conventional metric of accuracy, we analyze their skill’s improvement based on 3 other criteria, namely the confusion matrix’s quality, the separability of the data, and their instability. After collecting calibration data for 8 minutes in the first run, 8 participants were able to control the system while receiving visual feedback in the subsequent runs. We observed significant improvement in all subjects, including two of them who fell into the BCI illiteracy category. Our proposed BCI system complements the existing approaches in several aspects. First, the co-adaptation paradigm not only adapts the classifiers, but also allows the users to actively discover their own way to use the BCI through their exploration and exploitation processes. Furthermore, the auto-calibrating system can be used immediately with a minimal calibration time. Finally, this is the first work to combine motor and speech imagery in an online feedback experiment to provide multiple DoF for BCI control applications.

<![CDATA[Structure and variability of delay activity in premotor cortex]]>

Voluntary movements are widely considered to be planned before they are executed. Recent studies have hypothesized that neural activity in motor cortex during preparation acts as an ‘initial condition’ which seeds the proceeding neural dynamics. Here, we studied these initial conditions in detail by investigating 1) the organization of neural states for different reaches and 2) the variance of these neural states from trial to trial. We examined population-level responses in macaque premotor cortex (PMd) during the preparatory stage of an instructed-delay center-out reaching task with dense target configurations. We found that after target onset the neural activity on single trials converges to neural states that have a clear low-dimensional structure which is organized by both the reach endpoint and maximum speed of the following reach. Further, we found that variability of the neural states during preparation resembles the spatial variability of reaches made in the absence of visual feedback: there is less variability in direction than distance in neural state space. We also used offline decoding to understand the implications of this neural population structure for brain-machine interfaces (BMIs). We found that decoding of angle between reaches is dependent on reach distance, while decoding of arc-length is independent. Thus, it might be more appropriate to quantify decoding performance for discrete BMIs by using arc-length between reach end-points rather than the angle between them. Lastly, we show that in contrast to the common notion that direction can better be decoded than distance, their decoding capabilities are comparable. These results provide new insights into the dynamical neural processes that underline motor control and can inform the design of BMIs.

<![CDATA[Normalization enhances brain network features that predict individual intelligence in children with epilepsy]]>

Background and purpose

Architecture of the cerebral network has been shown to associate with IQ in children with epilepsy. However, subject-level prediction on this basis, a crucial step toward harnessing network analyses for the benefit of children with epilepsy, has yet to be achieved. We compared two network normalization strategies in terms of their ability to optimize subject-level inferences on the relationship between brain network architecture and brain function.

Materials and methods

Patients with epilepsy and resting state fMRI were retrospectively identified. Brain network nodes were defined by anatomic parcellation, first in patient space (nodes defined for each patient) and again in template space (same nodes for all patients). Whole-brain weighted graphs were constructed according to pair-wise correlation of BOLD-signal time courses between nodes. The following metrics were then calculated: clustering coefficient, transitivity, modularity, path length, and global efficiency. Metrics computed on graphs in patient space were normalized to the same metric computed on a random network of identical size. A machine learning algorithm was used to predict patient IQ given access to only the network metrics.


Twenty-seven patients (8–18 years) comprised the final study group. All brain networks demonstrated expected small world properties. Accounting for intrinsic population heterogeneity had a significant effect on prediction accuracy. Specifically, transformation of all patients into a common standard space as well as normalization of metrics to those computed on a random network both substantially outperformed the use of non-normalized metrics.


Normalization contributed significantly to accurate subject-level prediction of cognitive function in children with epilepsy. These findings support the potential for quantitative network approaches to contribute clinically meaningful information in children with neurological disorders.

<![CDATA[Exploit fully automatic low-level segmented PET data for training high-level deep learning algorithms for the corresponding CT data]]>

We present an approach for fully automatic urinary bladder segmentation in CT images with artificial neural networks in this study. Automatic medical image analysis has become an invaluable tool in the different treatment stages of diseases. Especially medical image segmentation plays a vital role, since segmentation is often the initial step in an image analysis pipeline. Since deep neural networks have made a large impact on the field of image processing in the past years, we use two different deep learning architectures to segment the urinary bladder. Both of these architectures are based on pre-trained classification networks that are adapted to perform semantic segmentation. Since deep neural networks require a large amount of training data, specifically images and corresponding ground truth labels, we furthermore propose a method to generate such a suitable training data set from Positron Emission Tomography/Computed Tomography image data. This is done by applying thresholding to the Positron Emission Tomography data for obtaining a ground truth and by utilizing data augmentation to enlarge the dataset. In this study, we discuss the influence of data augmentation on the segmentation results, and compare and evaluate the proposed architectures in terms of qualitative and quantitative segmentation performance. The results presented in this study allow concluding that deep neural networks can be considered a promising approach to segment the urinary bladder in CT images.

<![CDATA[Efficient neural decoding of self-location with a deep recurrent network]]>

Place cells in the mammalian hippocampus signal self-location with sparse spatially stable firing fields. Based on observation of place cell activity it is possible to accurately decode an animal’s location. The precision of this decoding sets a lower bound for the amount of information that the hippocampal population conveys about the location of the animal. In this work we use a novel recurrent neural network (RNN) decoder to infer the location of freely moving rats from single unit hippocampal recordings. RNNs are biologically plausible models of neural circuits that learn to incorporate relevant temporal context without the need to make complicated assumptions about the use of prior information to predict the current state. When decoding animal position from spike counts in 1D and 2D-environments, we show that the RNN consistently outperforms a standard Bayesian approach with either flat priors or with memory. In addition, we also conducted a set of sensitivity analysis on the RNN decoder to determine which neurons and sections of firing fields were the most influential. We found that the application of RNNs to neural data allowed flexible integration of temporal context, yielding improved accuracy relative to the more commonly used Bayesian approaches and opens new avenues for exploration of the neural code.

<![CDATA[Optimizing predictive performance of criminal recidivism models using registration data with binary and survival outcomes]]>

In a recidivism prediction context, there is no consensus on which modeling strategy should be followed for obtaining an optimal prediction model. In previous papers, a range of statistical and machine learning techniques were benchmarked on recidivism data with a binary outcome. However, two important tree ensemble methods, namely gradient boosting and random forests were not extensively evaluated. In this paper, we further explore the modeling potential of these techniques in the binary outcome criminal prediction context. Additionally, we explore the predictive potential of classical statistical and machine learning methods for censored time-to-event data. A range of statistical manually specified statistical and (semi-)automatic machine learning models is fitted on Dutch recidivism data, both for the binary outcome case and censored outcome case. To enhance generalizability of results, the same models are applied to two historical American data sets, the North Carolina prison data. For all datasets, (semi-) automatic modeling in the binary case seems to provide no improvement over an appropriately manually specified traditional statistical model. There is however evidence of slightly improved performance of gradient boosting in survival data. Results on the reconviction data from two sources suggest that both statistical and machine learning should be tried out for obtaining an optimal model. Even if a flexible black-box model does not improve upon the predictions of a manually specified model, it can serve as a test whether important interactions are missing or other misspecification of the model are present and can thus provide more security in the modeling process.

<![CDATA[Exploring the use of machine learning for risk adjustment: A comparison of standard and penalized linear regression models in predicting health care costs in older adults]]>


Payers and providers still primarily use ordinary least squares (OLS) to estimate expected economic and clinical outcomes for risk adjustment purposes. Penalized linear regression represents a practical and incremental step forward that provides transparency and interpretability within the familiar regression framework. This study conducted an in-depth comparison of prediction performance of standard and penalized linear regression in predicting future health care costs in older adults.

Methods and findings

This retrospective cohort study included 81,106 Medicare Advantage patients with 5 years of continuous medical and pharmacy insurance from 2009 to 2013. Total health care costs in 2013 were predicted with comorbidity indicators from 2009 to 2012. Using 2012 predictors only, OLS performed poorly (e.g., R2 = 16.3%) compared to penalized linear regression models (R2 ranging from 16.8 to 16.9%); using 2009–2012 predictors, the gap in prediction performance increased (R2:15.0% versus 18.0–18.2%). OLS with a reduced set of predictors selected by lasso showed improved performance (R2 = 16.6% with 2012 predictors, 17.4% with 2009–2012 predictors) relative to OLS without variable selection but still lagged behind the prediction performance of penalized regression. Lasso regression consistently generated prediction ratios closer to 1 across different levels of predicted risk compared to other models.


This study demonstrated the advantages of using transparent and easy-to-interpret penalized linear regression for predicting future health care costs in older adults relative to standard linear regression. Penalized regression showed better performance than OLS in predicting health care costs. Applying penalized regression to longitudinal data increased prediction accuracy. Lasso regression in particular showed superior prediction ratios across low and high levels of predicted risk. Health care insurers, providers and policy makers may benefit from adopting penalized regression such as lasso regression for cost prediction to improve risk adjustment and population health management and thus better address the underlying needs and risk of the populations they serve.

<![CDATA[Analysis on urban densification dynamics and future modes in southeastern Wisconsin, USA]]>

Urban change (urbanization) has dominated land change science for several decades. However, few studies have focused on what many scholars call the urban densification process (i.e., urban intensity expansion) despite its importance to both planning and subsequent impacts to the environment and local economies. This paper documents past urban densification patterns and uses this information to predict future densification trends in southeastern Wisconsin (SEWI) by using a rich dataset from the United States and by adapting the well-known Land Transformation Model (LTM) for this purpose. Urban densification is a significant and progressive process that often accompanies urbanization more generally. The increasing proportion of lower density areas, rather than higher density areas, was the main characteristic of the urban densification in SEWI from 2001 to 2011. We believe that improving urban land use efficiency to maintain rational densification are effective means toward a sustainable urban landscape. Multiple goodness-of-fit metrics demonstrated that the reconfigured LTM performed relatively well to simulate urban densification patterns in 2006 and 2011, enabling us to forecast densification to 2016 and 2021. The predicted future urban densification patterns are likely to be characterized by higher densities continue to increase at the expense of lower densities. We argue that detailed categories of urban density and specific relevant predictor variables are indispensable for densification prediction. Our study provides researchers working in land change science with important insights into urban densification process modeling. The outcome of this model can help planners to identify the current trajectory of urban development, enabling them to take informed action to promote planning objectives, which could benefit sustainable urbanization definitely.