Search

Background and objective: To take full advantage of decision support, machine learning, and patient-level prediction models, it is important that models are not only created, but also deployed in a clinical setting. The KETOS platform demonstrated in this work implements a tool for researchers allowing them to perform statistical analyses and deploy resulting models in a secure environment. Methods: The proposed system uses Docker virtualization to provide researchers with reproducible data analysis and development environments, accessible via Jupyter Notebook, to perform statistical analysis and develop, train and deploy models based on standardized input data. The platform is built in a modular fashion and interfaces with web services using the Health Level 7 (HL7) Fast Healthcare Interoperability Resources (FHIR) standard to access patient data. In our prototypical implementation we use an OMOP common data model (OMOP-CDM) database. The architecture supports the entire research lifecycle from creating a data analysis environment, retrieving data, and training to final deployment in a hospital setting. Results: We evaluated the platform by establishing and deploying an analysis and end user application for hemoglobin reference intervals within the University Hospital Erlangen. To demonstrate the potential of the system to deploy arbitrary models, we loaded a colorectal cancer dataset into an OMOP database and built machine learning models to predict patient outcomes and made them available via a web service. We demonstrated both the integration with FHIR as well as an example end user application. Finally, we integrated the platform with the open source DataSHIELD architecture to allow for distributed privacy preserving data analysis and training across networks of hospitals. Conclusion: The KETOS platform takes a novel approach to data analysis, training and deploying decision support models in a hospital or healthcare setting. It does so in a secure and privacy-preserving manner, combining the flexibility of Docker virtualization with the advantages of standardized vocabularies, a widely applied database schema (OMOP-CDM), and a standardized way to exchange medical data (FHIR). [ABSTRACT FROM AUTHOR]

Background: The Sequential Organ Failure Assessment (SOFA) score is commonly used in ICUs around the world, designed to assess the severity of the patient's clinical state based on function/dysfunction of six major organ systems. The goal of this work is to build a computational model to predict mortality based on a series of SOFA scores. In addition, we examined the possibility of improving the prediction by incorporating a new component designed to measure the performance of the gastrointestinal system, added to the other six components. Methods: In this retrospective study, we used patients’ three latest SOFA scores recorded during an individual ICU stay as input to different machine learning models and ensemble learning models. We added three validated parameters representing gastrointestinal failure. Among others, we used classification models such as Support Vector Machines (SVMs), Neural Networks, Logistic Regression and a penalty function used to increase model robustness in regard to certain extreme cases, which may be found in ICU population. We used the Area under Curve (AUC) performance metric to examine performance. Results: We found an ensemble model of linear and logistic regression achieves a higher AUC compared related works in past years. After incorporating the gastrointestinal failure score along with the penalty function, our best performing ensemble model resulted in an additional improvement in terms of AUC metrics. We implemented and compared 36 different models that were built using both the information from the SOFA score as well as that of the gastrointestinal system. All compared models have approximately similar and relatively large AUC (between 0.8645 and 0.9146) with the best results are achieved by incorporating the gastrointestinal parameters into the prediction models. Conclusions: Our findings indicate that gastrointestinal parameters carry significant information as a mortality predictor in addition to the conventional SOFA score. This information improves the predictive power of machine learning models by extending the SOFA to include information related to gastrointestinal organ system. The described method improves mortality prediction by considering the dynamics of the extended SOFA score. Although tested on a limited data set, the results' stability across different models suggests robustness in real-time use. [ABSTRACT FROM AUTHOR]

Comprehensive information on the timing and location of gene expression is fundamental to our understanding of embryonic development and tissue formation. While high-throughput in situ hybridization projects provide invaluable information about developmental gene expression patterns for model organisms like Drosophila, the output of these experiments is primarily qualitative, and a high proportion of protein coding genes and most non-coding genes lack any annotation. Accurate data-centric predictions of spatio-temporal gene expression will therefore complement current in situ hybridization efforts. Here, we applied a machine learning approach by training models on all public gene expression and chromatin data, even from whole-organism experiments, to provide genome-wide, quantitative spatio-temporal predictions for all genes. We developed structured in silico nano-dissection, a computational approach that predicts gene expression in >200 tissue-developmental stages. The algorithm integrates expression signals from a compendium of 6,378 genome-wide expression and chromatin profiling experiments in a cell lineage-aware fashion. We systematically evaluated our performance via cross-validation and experimentally confirmed 22 new predictions for four different embryonic tissues. The model also predicts complex, multi-tissue expression and developmental regulation with high accuracy. We further show the potential of applying these genome-wide predictions to extract tissue specificity signals from non-tissue-dissected experiments, and to prioritize tissues and stages for disease modeling. This resource, together with the exploratory tools are freely available at our webserver , which provides a valuable tool for a range of applications, from predicting spatio-temporal expression patterns to recognizing tissue signatures from differential gene expression profiles. [ABSTRACT FROM AUTHOR]

The blood flow through the major vessels holds great diagnostic potential for the identification of cardiovascular complications and is therefore routinely assessed with current diagnostic modalities. Heart valves are subject to high hydrodynamic loads which render them prone to premature degradation. Failing native aortic valves are routinely replaced with bioprosthetic heart valves. This type of prosthesis is limited by a durability that is often less than the patient’s life expectancy. Frequent assessment of valvular function can therefore help to ensure good long-term outcomes and to plan reinterventions. In this article, we describe how unsupervised novelty detection algorithms can be used to automate the interpretation of blood flow data to improve outcomes through early detection of adverse cardiovascular events without requiring repeated check-ups in a clinical environment. The proposed method was tested in an in-vitro flow loop which allowed simulating a failing aortic valve in a laboratory setting. Aortic regurgitation of increasing severity was deliberately introduced with tube-shaped inserts, preventing complete valve closure during diastole. Blood flow recordings from a flow meter at the location of the ascending aorta were analyzed with the algorithms introduced in this article and a diagnostic index was defined that reflects the severity of valvular degradation. The results indicate that the proposed methodology offers a high sensitivity towards pathological changes of valvular function and that it is capable of automatically identifying valvular degradation. Such methods may be a step towards computer-assisted diagnostics and telemedicine that provide the clinician with novel tools to improve patient care. [ABSTRACT FROM AUTHOR]

Objective: The Centers for Disease Control and Prevention (CDC) coordinates a labor-intensive process to measure the prevalence of autism spectrum disorder (ASD) among children in the United States. Random forests methods have shown promise in speeding up this process, but they lag behind human classification accuracy by about 5%. We explore whether more recently available document classification algorithms can close this gap. Materials and methods: Using data gathered from a single surveillance site, we applied 8 supervised learning algorithms to predict whether children meet the case definition for ASD based solely on the words in their evaluations. We compared the algorithms’ performance across 10 random train-test splits of the data, using classification accuracy, F1 score, and number of positive calls to evaluate their potential use for surveillance. Results: Across the 10 train-test cycles, the random forest and support vector machine with Naive Bayes features (NB-SVM) each achieved slightly more than 87% mean accuracy. The NB-SVM produced significantly more false negatives than false positives (P = 0.027), but the random forest did not, making its prevalence estimates very close to the true prevalence in the data. The best-performing neural network performed similarly to the random forest on both measures. Discussion: The random forest performed as well as more recently available models like the NB-SVM and the neural network, and it also produced good prevalence estimates. NB-SVM may not be a good candidate for use in a fully-automated surveillance workflow due to increased false negatives. More sophisticated algorithms, like hierarchical convolutional neural networks, may not be feasible to train due to characteristics of the data. Current algorithms might perform better if the data are abstracted and processed differently and if they take into account information about the children in addition to their evaluations. Conclusion: Deep learning models performed similarly to traditional machine learning methods at predicting the clinician-assigned case status for CDC’s autism surveillance system. While deep learning methods had limited benefit in this task, they may have applications in other surveillance systems. [ABSTRACT FROM AUTHOR]

High Content Analysis (HCA) has become a cornerstone of cellular analysis within the drug discovery industry. To expand the capabilities of HCA, we have applied the same analysis methods, validated in numerous mammalian cell models, to microbiology methodology. Image acquisition and analysis of various microbial samples, ranging from pure cultures to culture mixtures containing up to three different bacterial species, were quantified and identified using various machine learning processes. These HCA techniques allow for faster cell enumeration than standard agar-plating methods, identification of “viable but not plate culturable” microbe phenotype, classification of antibiotic treatment effects, and identification of individual microbial strains in mixed cultures. These methods greatly expand the utility of HCA methods and automate tedious and low-throughput standard microbiological methods. [ABSTRACT FROM AUTHOR]

Neural correlates of mind wandering: The ability to detect mind wandering as it occurs is an important step towards improving our understanding of this phenomenon and studying its effects on learning and performance. Current detection methods typically rely on observable behaviour in laboratory settings, which do not capture the underlying neural processes and may not translate well into real-world settings. We address both of these issues by recording electroencephalography (EEG) simultaneously from 15 participants during live lectures on research in orthopedic surgery. We performed traditional group-level analysis and found neural correlates of mind wandering during live lectures that are similar to those found in some laboratory studies, including a decrease in occipitoparietal alpha power and frontal, temporal, and occipital beta power. However, individual-level analysis of these same data revealed that patterns of brain activity associated with mind wandering were more broadly distributed and highly individualized than revealed in the group-level analysis. Mind wandering detection: To apply these findings to mind wandering detection, we used a data-driven method known as common spatial patterns to discover scalp topologies for each individual that reflects their differences in brain activity when mind wandering versus attending to lectures. This approach avoids reliance on known neural correlates primarily established through group-level statistics. Using this method for individual-level machine learning of mind wandering from EEG, we were able to achieve an average detection accuracy of 80–83%. Conclusions: Modelling mind wandering at the individual level may reveal important details about its neural correlates that are not reflected when using traditional observational and statistical methods. Using machine learning techniques for this purpose can provide new insight into the varieties of neural activity involved in mind wandering, while also enabling real-time detection of mind wandering in naturalistic settings. [ABSTRACT FROM AUTHOR]

In-silico identification of potential target genes for disease is an essential aspect of drug target discovery. Recent studies suggest that successful targets can be found through by leveraging genetic, genomic and protein interaction information. Here, we systematically tested the ability of 12 varied algorithms, based on network propagation, to identify genes that have been targeted by any drug, on gene-disease data from 22 common non-cancerous diseases in OpenTargets. We considered two biological networks, six performance metrics and compared two types of input gene-disease association scores. The impact of the design factors in performance was quantified through additive explanatory models. Standard cross-validation led to over-optimistic performance estimates due to the presence of protein complexes. In order to obtain realistic estimates, we introduced two novel protein complex-aware cross-validation schemes. When seeding biological networks with known drug targets, machine learning and diffusion-based methods found around 2-4 true targets within the top 20 suggestions. Seeding the networks with genes associated to disease by genetics decreased performance below 1 true hit on average. The use of a larger network, although noisier, improved overall performance. We conclude that diffusion-based prioritisers and machine learning applied to diffusion-based features are suited for drug discovery in practice and improve over simpler neighbour-voting methods. We also demonstrate the large impact of choosing an adequate validation strategy and the definition of seed disease genes. [ABSTRACT FROM AUTHOR]

In transcriptomics, micro RNAs (miRNAs) has gained much interest especially as potential disease indicators. However, apart from holding a great promise related to their clinical application, a lot of inconsistent results have been published. Our aim was to compare the miRNA expression levels in ovarian cancer and healthy subjects using the Bayesian multilevel model and to assess their potential usefulness in diagnosis. We have analyzed a case-control observational data on expression profiling of 49 preselected miRNA-based ovarian cancer indicators in 119 controls and 59 patients. A Bayesian multilevel model was used to characterize the effect of disease on miRNA levels controlling for differences in age and body weight. The difference between the miRNA level and health status of the patient on the scale of the data variability were discussed in the context of their potential usefulness in diagnosis. Additionally, the cross-validated area under the ROC curve (AUC) was used to assess the expected out-of-sample discrimination index of a different sets of miRNAs. The proposed model allowed us to describe the set of miRNA levels in patients and controls. Three highly correlated miRNAs: miR-101-3p, miR-142-5p, miR-148a-3p rank the highest with almost identical effect sizes that ranges from 0.45 to 1.0. For those miRNAs the credible interval for AUC ranged from 0.63 to 0.67 indicating their limited discrimination potential. A little benefit in adding information from other miRNAs was observed. There were several miRNAs in the dataset (miR-604, hsa-miR-221-5p) for which inferences were uncertain. For those miRNAs more experimental effort is needed to fully assess their effect in the context of new hits discovery and usefulness as disease indicators. The proposed multilevel Bayesian model can be used to characterize the panel of miRNA profile and to assess the difference in expression levels between healthy and cancer individuals. [ABSTRACT FROM AUTHOR]

Purpose: To benchmark the human and machine performance of spectral-domain (SD) and swept-source (SS) optical coherence tomography (OCT) image segmentation, i.e., pixel-wise classification, for the compartments vitreous, retina, choroid, sclera. Methods: A convolutional neural network (CNN) was trained on OCT B-scan images annotated by a senior ground truth expert retina specialist to segment the posterior eye compartments. Independent benchmark data sets (30 SDOCT and 30 SSOCT) were manually segmented by three classes of graders with varying levels of ophthalmic proficiencies. Nine graders contributed to benchmark an additional 60 images in three consecutive runs. Inter-human and intra-human class agreement was measured and compared to the CNN results. Results: The CNN training data consisted of a total of 6210 manually segmented images derived from 2070 B-scans (1046 SDOCT and 1024 SSOCT; 630 C-Scans). The CNN segmentation revealed a high agreement with all grader groups. For all compartments and groups, the mean Intersection over Union (IOU) score of CNN compartmentalization versus group graders’ compartmentalization was higher than the mean score for intra-grader group comparison. Conclusion: The proposed deep learning segmentation algorithm (CNN) for automated eye compartment segmentation in OCT B-scans (SDOCT and SSOCT) is on par with manual segmentations by human graders. [ABSTRACT FROM AUTHOR]

Background: Current diagnostics are inadequate to meet the challenges presented by co-infection with Mycobacterium tuberculosis (Mtb) and HIV, the leading cause of death for HIV-infected individuals. Improved characterization of Mtb/HIV coinfection as a distinct disease state may lead to better identification and treatment of affected individuals. Methods: Four previously-published TB and HIV co-infection related datasets were used to train and validate multinomial machine learning classifiers that simultaneously predict TB and HIV status. Classifier predictive performance was measured using leave-one-out cross validation on the training set and blind predictive performance on multiple test sets using area under the ROC curve (AUC) as the performance metric. Linear modelling of signature gene expression was applied to systematically classify genes as TB-only, HIV-only or combined TB/HIV. Results: The optimal signature discovered was a 10-gene random forest multinomial signature that robustly discriminated active tuberculosis (TB) from other non-TB disease states with improved performance compared with previously published signatures (AUC: 0.87), and specifically discriminated active TB/HIV co-infection from all other conditions (AUC: 0.88). Signature genes exhibited a variety of transcriptional patterns including both TB-only and HIV-only response genes and genes with expression patterns driven by interactions between HIV and TB infection states, including the CD8+ T-cell receptor LAG3 and the apoptosis-related gene CERKL. Conclusions: By explicitly including distinct disease states within the machine learning analysis framework, we developed a compact and highly diagnostic signature that simultaneously discriminates multiple disease states associated with Mtb/HIV co-infection. Examination of the expression patterns of signature genes suggests mechanisms underlying the unique inflammatory conditions associated with active TB in the presence of HIV. In particular, we observed that dysregulation of CD8+ effector T-cell and NK-cell associated genes may be an important feature of Mtb/HIV co-infection. [ABSTRACT FROM AUTHOR]

Omic data analysis is steadily growing as a driver of basic and applied molecular biology research. Core to the interpretation of complex and heterogeneous biological phenotypes are computational approaches in the fields of statistics and machine learning. In parallel, constraint-based metabolic modeling has established itself as the main tool to investigate large-scale relationships between genotype, phenotype, and environment. The development and application of these methodological frameworks have occurred independently for the most part, whereas the potential of their integration for biological, biomedical, and biotechnological research is less known. Here, we describe how machine learning and constraint-based modeling can be combined, reviewing recent works at the intersection of both domains and discussing the mathematical and practical aspects involved. We overlap systematic classifications from both frameworks, making them accessible to nonexperts. Finally, we delineate potential future scenarios, propose new joint theoretical frameworks, and suggest concrete points of investigation for this joint subfield. A multiview approach merging experimental and knowledge-driven omic data through machine learning methods can incorporate key mechanistic information in an otherwise biologically-agnostic learning process. [ABSTRACT FROM AUTHOR]

A key goal of precision medicine is predicting the best drug therapy for a specific patient from genomic information. In oncology, cancers that appear similar pathologically can vary greatly in how they respond to the same drug. Fortunately, data from high-throughput screening programs often reveal important relationships between genomic variability of cancer cells and their response to drugs. Nevertheless, many current computational methods to predict compound activity against cancer cells require large quantities of genomic, epigenomic, and additional cellular data to develop and to apply. Here we integrate recent screening data and machine learning to train classification models that predict the activity/inactivity of compounds against cancer cells based on the mutational status of only 145 oncogenes and a set of compound structural descriptors. Using IC50 values of 1 μM as activity cutoffs, our predictive models have sensitivities of 87%, specificities of 87%, and yield an area under the receiver operating characteristic curve equal to 0.94. We also develop regression models to predict log(IC50) values of compounds for cancer cells; the models achieve a Pearson correlation coefficient of 0.86 for cross-validation and up to 0.65–0.73 against blind test sets. Predictive performance remains strong when as few as 50 oncogenes are included. Finally, even when 40% of experimental IC50 values are missing from screening data, they can be imputed with sufficient reliability that classification accuracy is not diminished. The presented models are fast to generate and may serve as easily implemented screening tools for personalized oncology medicine, drug repurposing, and drug discovery. [ABSTRACT FROM AUTHOR]

Alzheimer's disease and related dementias (ADRD) are highly prevalent conditions, and prior efforts to develop predictive models have relied on demographic and clinical risk factors using traditional logistical regression methods. We hypothesized that machine-learning algorithms using administrative claims data may represent a novel approach to predicting ADRD. Using a national de-identified dataset of more than 125 million patients including over 10,000 clinical, pharmaceutical, and demographic variables, we developed a cohort to train a machine learning model to predict ADRD 4–5 years in advance. The Lasso algorithm selected a 50-variable model with an area under the curve (AUC) of 0.693. Top diagnosis codes in the model were memory loss (780.93), Parkinson’s disease (332.0), mild cognitive impairment (331.83) and bipolar disorder (296.80), and top pharmacy codes were psychoactive drugs. Machine learning algorithms can rapidly develop predictive models for ADRD with massive datasets, without requiring hypothesis-driven feature engineering. [ABSTRACT FROM AUTHOR]

Optical coherence tomography (OCT) based measurements of retinal layer thickness, such as the retinal nerve fibre layer (RNFL) and the ganglion cell with inner plexiform layer (GCIPL) are commonly employed for the diagnosis and monitoring of glaucoma. Previously, machine learning techniques have relied on segmentation-based imaging features such as the peripapillary RNFL thickness and the cup-to-disc ratio. Here, we propose a deep learning technique that classifies eyes as healthy or glaucomatous directly from raw, unsegmented OCT volumes of the optic nerve head (ONH) using a 3D Convolutional Neural Network (CNN). We compared the accuracy of this technique with various feature-based machine learning algorithms and demonstrated the superiority of the proposed deep learning based method. Logistic regression was found to be the best performing classical machine learning technique with an AUC of 0.89. In direct comparison, the deep learning approach achieved a substantially higher AUC of 0.94 with the additional advantage of providing insight into which regions of an OCT volume are important for glaucoma detection. Computing Class Activation Maps (CAM), we found that the CNN identified neuroretinal rim and optic disc cupping as well as the lamina cribrosa (LC) and its surrounding areas as the regions significantly associated with the glaucoma classification. These regions anatomically correspond to the well established and commonly used clinical markers for glaucoma diagnosis such as increased cup volume, cup diameter, and neuroretinal rim thinning at the superior and inferior segments. [ABSTRACT FROM AUTHOR]

Many complex physical systems exhibit a rich variety of discrete behavioural modes. Often, the system complexity limits the applicability of standard modelling tools. Hence, understanding the underlying physics of different behaviours and distinguishing between them is challenging. Although traditional machine learning techniques could predict and classify behaviour well, typically they do not provide any meaningful insight into the underlying physics of the system. In this paper we present a novel method for extracting physically meaningful clusters of discrete behaviour from limited experimental observations. This method obtains a set of physically plausible functions that both facilitate behavioural clustering and aid in system understanding. We demonstrate the approach on the V-shaped falling paper system, a new falling paper type system that exhibits four distinct behavioural modes depending on a few morphological parameters. Using just 49 experimental observations, the method discovered a set of candidate functions that distinguish behaviours with an error of 2.04%, while also aiding insight into the physical phenomena driving each behaviour. [ABSTRACT FROM AUTHOR]

A brain-computer interface (BCI), based on motor imagery EEG, uses information extracted from the electroencephalography signals generated by a person who intends to perform any action. One of the most important issues of current research is how to detect automatically whether the user intends to send some message to a certain device. This study presents a proposal, based on a hierarchical structured system, for recognising intentional and non-intentional mental tasks on a BCI system by applying machine learning techniques to the EEG signals. First-level clustering is performed to distinguish between intentional control (IC) and non-intentional control (NC) state patterns. Then, the patterns recognised as IC are passed on to a second stage where supervised learning techniques are used to classify them. In BCI applications, it is critical to correctly classify NC states with a low false positive rate (FPR) to avoid undesirable effects. According to the literature, we selected a maximum FPR of 10%. Under these conditions, our proposal achieved an average test accuracy of 66.6%, with an 8.2% FPR, for the BCI competition IIIa dataset. The main contribution of this paper is the hierarchical approach, based on machine learning paradigms, which performs intentional and non-intentional discrimination and, depending on the case, classifies the intended command selected by the user. [ABSTRACT FROM AUTHOR]

We have attempted to reproduce the results in Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, published in JAMA 2016; 316(22), using publicly available data sets. We re-implemented the main method in the original study since the source code is not available. The original study used non-public fundus images from EyePACS and three hospitals in India for training. We used a different EyePACS data set from Kaggle. The original study used the benchmark data set Messidor-2 to evaluate the algorithm's performance. We used another distribution of the Messidor-2 data set, since the original data set is no longer available. In the original study, ophthalmologists re-graded all images for diabetic retinopathy, macular edema, and image gradability. We have one diabetic retinopathy grade per image for our data sets, and we assessed image gradability ourselves. We were not able to reproduce the original study's results with publicly available data. Our algorithm's area under the receiver operating characteristic curve (AUC) of 0.951 (95% CI, 0.947-0.956) on the Kaggle EyePACS test set and 0.853 (95% CI, 0.835-0.871) on Messidor-2 did not come close to the reported AUC of 0.99 on both test sets in the original study. This may be caused by the use of a single grade per image, or different data. This study shows the challenges of reproducing deep learning method results, and the need for more replication and reproduction studies to validate deep learning methods, especially for medical image analysis. Our source code and instructions are available at: . [ABSTRACT FROM AUTHOR]

With the prosperity of machine learning and cloud computing, meaningful information can be mined from mass electronic medical data which help physicians make proper disease diagnosis for patients. However, using medical data and disease information of patients frequently raise privacy concerns. In this paper, based on single-layer perceptron, we propose a scheme of privacy-preserving clinical decision with cloud support (PPCD), which securely conducts disease model training and prediction for the patient. Each party learns nothing about the other’s private information. In PPCD, a lightweight secure multiplication is presented and introduced to improve the model training. Security analysis and experimental results on real data confirm the high accuracy of disease prediction achieved by the proposed PPCD without the risk of privacy disclosure. [ABSTRACT FROM AUTHOR]

Clinical resistance against Bedaquiline, the first new anti-tuberculosis compound with a novel mechanism of action in over 40 years, has already been detected in Mycobacterium tuberculosis. As a new drug, however, there is currently insufficient clinical data to facilitate reliable and timely identification of genomic determinants of resistance. Here we investigate the structural basis for M. tuberculosis associated bedaquiline resistance in the drug target, AtpE. Together with the 9 previously identified resistance-associated variants in AtpE, 54 non-resistance-associated mutations were identified through comparisons of bedaquiline susceptibility across 23 different mycobacterial species. Computational analysis of the structural and functional consequences of these variants revealed that resistance associated variants were mainly localized at the drug binding site, disrupting key interactions with bedaquiline leading to reduced binding affinity. This was used to train a supervised predictive algorithm, which accurately identified likely resistance mutations (93.3% accuracy). Application of this model to circulating variants present in the Asia-Pacific region suggests that current circulating variants are likely to be susceptible to bedaquiline. We have made this model freely available through a user-friendly web interface called SUSPECT-BDQ, StrUctural Susceptibility PrEdiCTion for bedaquiline (). This tool could be useful for the rapid characterization of novel clinical variants, to help guide the effective use of bedaquiline, and to minimize the spread of clinical resistance. [ABSTRACT FROM AUTHOR]

As the challenge of mental health problems such as anxiety and depression increasing today, more convenient, objective, real-time assessing techniques of mental state are in need. The Microsoft Kinect camera is a possible option for contactlessly capturing human gait, which could reflect the walkers’ mental state. So we tried to propose a novel method for monitoring individual’s anxiety and depression based on the Kinect-recorded gait pattern. In this study, after finishing the 7-item Generalized Anxiety Disorder Scale (GAD-7) and the 9-item Patient Health Questionnaire (PHQ-9), 179 participants were required to walked on the footpath naturally while shot by the Kinect cameras. Fast Fourier Transforms (FFT) were conducted to extract features from the Kinect-captured gait data after preprocessing, and different machine learning algorithms were used to train the regression models recognizing anxiety and depression levels, and the classification models detecting the cases with specific depressive symptoms. The predictive accuracies of the regression models achieved medium to large level: The correlation coefficient between predicted and questionnaire scores reached 0.51 on anxiety (by epsilon-Support Vector Regression, e-SVR) and 0.51 on depression (by Gaussian Processes, GP). The predictive accuracies could be even higher, 0.74 on anxiety (by GP) and 0.64 on depression (by GP), while training and testing the models on the female sample. The classification models also showed effectiveness on detecting the cases with some symptoms. These results demonstrate the possibility to recognize individual’s questionnaire measured anxiety/depression levels and some depressive symptoms based on Kinect-recorded gait data through machine learning method. This approach shows the potential to develop non-intrusive, low-cost methods for monitoring individuals’ mental health in real time. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) is a common base signal used to monitor brain activities and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the performance of the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and κ = 0.79. Our developed model can be applied to other sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at . [ABSTRACT FROM AUTHOR]

Objective: To compare axonal loss in ganglion cells detected with swept-source optical coherence tomography (SS-OCT) in eyes of patients with multiple sclerosis (MS) versus healthy controls using different machine learning techniques. To analyze the capability of machine learning techniques to improve the detection of retinal nerve fiber layer (RNFL) and the complex Ganglion Cell Layer–Inner plexiform layer (GCL+) damage in patients with multiple sclerosis and to use the SS-OCT as a biomarker to early predict this disease. Methods: Patients with relapsing-remitting MS (n = 80) and age-matched healthy controls (n = 180) were enrolled. Different protocols from the DRI SS-OCT Triton system were used to obtain the RNFL and GCL+ thicknesses in both eyes. Macular and peripapilar areas were analyzed to detect the zones with higher thickness decrease. The performance of different machine learning techniques (decision trees, multilayer perceptron and support vector machine) for identifying RNFL and GCL+ thickness loss in patients with MS were evaluated. Receiver-operating characteristic (ROC) curves were used to display the ability of the different tests to discriminate between MS and healthy eyes in our population. Results: Machine learning techniques provided an excellent tool to predict MS disease using SS-OCT data. In particular, the decision trees obtained the best prediction (97.24%) using RNFL data in macular area and the area under the ROC curve was 0.995, while the wide protocol which covers an extended area between macula and papilla gave an accuracy of 95.3% with a ROC of 0.998. Moreover, it was obtained that the most significant area of the RNFL to predict MS is the macula just surrounding the fovea. On the other hand, in our study, GCL+ did not contribute to predict MS and the different machine learning techniques performed worse in this layer than in RNFL. Conclusions: Measurements of RNFL thickness obtained with SS-OCT have an excellent ability to differentiate between healthy controls and patients with MS. Thus, the use of machine learning techniques based on these measures can be a reliable tool to help in MS diagnosis. [ABSTRACT FROM AUTHOR]

Antenna selection in Multiple-Input Multiple-Output (MIMO) systems has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity. Recently, deep learning based methods have achieved promising performance in many application fields. This paper proposed a deep learning (DL) based antenna selection technique. First, we generated the label of training antenna systems by maximizing the channel capacity. Then, we adopted the deep convolutional neural network (CNN) on the channel matrices to explicitly exploit the massive latent cues of attenuation coefficients. Finally, we used the adopted CNN to assign the class label and then select the optimal antenna subset. Experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based antenna selection. [ABSTRACT FROM AUTHOR]

Background: The postmortem microbiome can provide valuable information to a death investigation and to the human health of the once living. Microbiome sequencing produces, in general, large multi-dimensional datasets that can be difficult to analyze and interpret. Machine learning methods can be useful in overcoming this analytical challenge. However, different methods employ distinct strategies to handle complex datasets. It is unclear whether one method is more appropriate than others for modeling postmortem microbiomes and their ability to predict attributes of interest in death investigations, which require understanding of how the microbial communities change after death and may represent those of the once living host. Methods and findings: Postmortem microbiomes were collected by swabbing five anatomical areas during routine death investigation, sequenced and analyzed from 188 death cases. Three machine learning methods (boosted algorithms, random forests, and neural networks) were compared with respect to their abilities to predict case attributes: postmortem interval (PMI), location of death, and manner of death. Accuracy depended on the method used, the numbers of anatomical areas analyzed, and the predicted attribute of death. Conclusions: All algorithms performed well but with distinct features to their performance. Xgboost often produced the most accurate predictions but may also be more prone to overfitting. Random forest was the most stable across predictions that included more anatomic areas. Analysis of postmortem microbiota from more than three anatomic areas appears to yield limited returns on accuracy, with the eyes and rectum providing the most useful information correlating with circumstances of death in most cases for this dataset. [ABSTRACT FROM AUTHOR]

High dimensional biomedical data contain tens of thousands of features, accurate and effective identification of the core features in these data can be used to assist diagnose related diseases. However, there are often a large number of irrelevant or redundant features in biomedical data, which seriously affect subsequent classification accuracy and machine learning efficiency. To solve this problem, a novel filter feature selection algorithm based on redundant removal (FSBRR) is proposed to classify high dimensional biomedical data in this paper. First of all, two redundant criteria are determined by vertical relevance (the relationship between feature and class attribute) and horizontal relevance (the relationship between feature and feature). Secondly, to quantify redundant criteria, an approximate redundancy feature framework based on mutual information (MI) is defined to remove redundant and irrelevant features. To evaluate the effectiveness of our proposed algorithm, controlled trials based on typical feature selection algorithm are conducted using three different classifiers, and the experimental results indicate that the FSBRR algorithm can effectively reduce the feature dimension and improve the classification accuracy. In addition, an experiment of small sample dataset is designed and conducted in the section of discussion and analysis to clarify the specific implementation process of FSBRR algorithm more clearly. [ABSTRACT FROM AUTHOR]

Restoration of communication in people with complete motor paralysis—a condition called complete locked-in state (CLIS)—is one of the greatest challenges of brain-computer interface (BCI) research. New findings have recently been presented that bring us one step closer to this goal. However, the validity of the evidence has been questioned: independent reanalysis of the same data yielded significantly different results. Reasons for the failure to replicate the findings must be of a methodological nature. What is the best practice to ensure that results are stringent and conclusive and analyses replicable? Confirmation bias and the counterintuitive nature of probability may lead to an overly optimistic interpretation of new evidence. Lack of detail complicates replicability. [ABSTRACT FROM AUTHOR]

Purpose: To determine if deep learning networks could be trained to forecast future 24–2 Humphrey Visual Fields (HVFs). Methods: All data points from consecutive 24–2 HVFs from 1998 to 2018 were extracted from a university database. Ten-fold cross validation with a held out test set was used to develop the three main phases of model development: model architecture selection, dataset combination selection, and time-interval model training with transfer learning, to train a deep learning artificial neural network capable of generating a point-wise visual field prediction. The point-wise mean absolute error (PMAE) and difference in Mean Deviation (MD) between predicted and actual future HVF were calculated. Results: More than 1.7 million perimetry points were extracted to the hundredth decibel from 32,443 24–2 HVFs. The best performing model with 20 million trainable parameters, CascadeNet-5, was selected. The overall point-wise PMAE for the test set was 2.47 dB (95% CI: 2.45 dB to 2.48 dB), and deep learning showed a statistically significant improvement over linear models. The 100 fully trained models successfully predicted future HVFs in glaucomatous eyes up to 5.5 years in the future with a correlation of 0.92 between the MD of predicted and actual future HVF and an average difference of 0.41 dB. Conclusions: Using unfiltered real-world datasets, deep learning networks show the ability to not only learn spatio-temporal HVF changes but also to generate predictions for future HVFs up to 5.5 years, given only a single HVF. [ABSTRACT FROM AUTHOR]

Workers processing nephrite, antigorite, or talc may be exposed to paragenetic asbestos minerals. An effective screening method for pneumoconiosis in workers exposed to asbestos-contaminated minerals is still lacking. The objective of this study was to assess the diagnostic accuracy of serum and urinary biomarkers for pneumoconiosis in workers exposed to asbestos-contaminated minerals. We conducted a case-control study in a cohort of stone craft workers in Hualien, where asbestos, nephrite, antigorite, and talc are produced. A total of 140 subjects were screened between March 2013 and July 2014. All subjects received a questionnaire survey and a health examination that included a physical examination; chest X-ray; and tests for standard pulmonary function, fractional exhaled nitric oxide, serum soluble mesothelin-related peptide (SMRP), fibulin-3, carcinoembryonic antigen (CEA), and urinary 8-Oxo-2'-deoxyguanosine (8-OHdG)/creatinine. After excluding subjects with uraemia and chronic obstructive pulmonary disease (COPD), we included 48 subjects with pneumoconiosis and 90 control subjects without pneumoconiosis for analysis. In terms of occupational history, 43/48 (90%) case subjects and 68% (61/90) of the control subjects had processed asbestos-contaminated minerals, including nephrite, antigorite, and talc. The case group had decreased pulmonary function in forced vital capacity (FVC), forced expiratory volume in one second, and forced expiratory flow between 25% and 75% of the FVC. The levels of SMRP, fibulin-3, urinary 8-OHdG/creatinine, and CEA were higher in the case group than in the control group. Subjects exposed to nephrite had significantly higher SMRP levels (0.84 ± 0.52 nM) than subjects exposed to other types of minerals (0.60 ± 0.30 nM). A dose-response relationship was observed between the SMRP level and the severity of pneumoconiosis. Machine learning algorithms, including variables of sex, age, SMRP, fibulin-3, CEA, and 8-OHdG/creatinine, can predict pneumoconiosis with high accuracy. The areas under the receiver operating characteristic curves ranged from 0.7 to 1.0. We suggest that SMRP and fibulin-3 could be used as biomarkers of pneumoconiosis in workers exposed to asbestos-contaminated minerals. [ABSTRACT FROM AUTHOR]

MiRNAs and proteins play important roles in different stages of breast tumor development and serve as biomarkers for the early diagnosis of breast cancer. A new algorithm that combines machine learning algorithms and multilayer complex network analysis is hereby proposed to explore the potential diagnostic values of miRNAs and proteins. XGBoost and random forest algorithms were employed to screen the most important miRNAs and proteins. Maximal information coefficient was applied to assess intralayer and interlayer connection. A multilayer complex network was constructed to identify miRNAs and proteins that could serve as biomarkers for breast cancer. Proteins and miRNAs that are nodes in the network were subsequently categorized into two network layers considering their distinct functions. The betweenness centrality was used as the first measurement of the importance of the nodes within each single layer. The degree of the nodes was chosen as the second measurement to map their signalling pathways. By combining these two measurements into one score and comparing the difference of the same candidate between normal tissue and cancer tissue, this novel multilayer network analysis could be applied to successfully identify molecules associated with breast cancer. [ABSTRACT FROM AUTHOR]

Objectives: We propose a bottom-up, machine-learning approach, for the objective vestibular and balance diagnostic data of concussion patients, to provide insight into the differences in patients’ phenotypes, independent of existing diagnoses (unsupervised learning). Methods: Diagnostic data from a battery of validated balance and vestibular assessments were extracted from the database of the Swiss Concussion Center. The desired number of clusters within the patient database was estimated using Calinski-Harabasz criteria. Complex (self-organizing map, SOM) and standard (k-means) clustering tools were used, and the formed clusters were compared. Results: A total of 96 patients (81.3% male, age (median [IQR]): 25.0[10.8]) who were expected to suffer from sports-related concussion or post-concussive syndrome (52[140] days between diagnostic testing and the concussive episode) were included. The cluster evaluation indicated dividing the data into two groups. Only the SOM gave a stable clustering outcome, dividing the patients in group-1 (n = 38) and group-2 (n = 58). A large significant difference was found for the caloric summary score for the maximal speed of the slow phase, where group-1 scored 30.7% lower than group-2 (27.6[18.2] vs. 51.0[31.0]). Group-1 also scored significantly lower on the sensory organisation test composite score (69.0[22.3] vs. 79.0[10.5]) and higher on the visual acuity (-0.03[0.33] vs. -0.14[0.12]) and dynamic visual acuity (0.38[0.84] vs. 0.20[0.20]) tests. The importance of caloric, SOT and DVA, was supported by the PCA outcomes. Group-1 tended to report headaches, blurred vision and balance problems more frequently than group-2 (>10% difference). Conclusion: The SOM divided the data into one group with prominent vestibular disorders and another with no clear vestibular or balance problems, suggesting that artificial intelligence might help improve the diagnostic process. [ABSTRACT FROM AUTHOR]

The broadly neutralizing antibody (bnAb) VRC01 is being evaluated for its efficacy to prevent HIV-1 infection in the Antibody Mediated Prevention (AMP) trials. A secondary objective of AMP utilizes sieve analysis to investigate how VRC01 prevention efficacy (PE) varies with HIV-1 envelope (Env) amino acid (AA) sequence features. An exhaustive analysis that tests how PE depends on every AA feature with sufficient variation would have low statistical power. To design an adequately powered primary sieve analysis for AMP, we modeled VRC01 neutralization as a function of Env AA sequence features of 611 HIV-1 gp160 pseudoviruses from the CATNAP database, with objectives: (1) to develop models that best predict the neutralization readouts; and (2) to rank AA features by their predictive importance with classification and regression methods. The dataset was split in half, and machine learning algorithms were applied to each half, each analyzed separately using cross-validation and hold-out validation. We selected Super Learner, a nonparametric ensemble-based cross-validated learning method, for advancement to the primary sieve analysis. This method predicted the dichotomous resistance outcome of whether the IC50 neutralization titer of VRC01 for a given Env pseudovirus is right-censored (indicating resistance) with an average validated AUC of 0.868 across the two hold-out datasets. Quantitative log IC50 was predicted with an average validated R2 of 0.355. Features predicting neutralization sensitivity or resistance included 26 surface-accessible residues in the VRC01 and CD4 binding footprints, the length of gp120, the length of Env, the number of cysteines in gp120, the number of cysteines in Env, and 4 potential N-linked glycosylation sites; the top features will be advanced to the primary sieve analysis. This modeling framework may also inform the study of VRC01 in the treatment of HIV-infected persons. [ABSTRACT FROM AUTHOR]

Background: A better understanding of sickle cell anemia (SCA) and improvements in drug therapy and health policy have contributed to the emergence of a large population of adults living with this disease. The mechanisms by which SCA produces adverse effects on the respiratory system of these patients are largely unknown. Fractional-order (FrOr) models have a high potential to improve pulmonary clinical science and could be useful for diagnostic purposes, offering accurate models with an improved ability to mimic nature. Part 2 of this two-part study examines the changes in respiratory mechanics in patients with SCA using the new perspective of the FrOr models. These results are compared with those obtained in traditional forced oscillation (FOT) parameters, investigated in Part 1 of the present study, complementing this first analysis. Methodology/Principal findings: The data consisted of three categories of subjects: controls (n = 23), patients with a normal spirometric exam (n = 21) and those presenting restriction (n = 24). The diagnostic accuracy was evaluated by investigating the area under the receiver operating characteristic curve (AUC). Initially, it was observed that biomechanical changes in SCA included increased values of fractional inertance, as well as damping and hysteresivity (p<0.001). The correlation analysis showed that FrOr parameters are associated with functional exercise capacity (R = -0.57), pulmonary diffusion (R = -0.71), respiratory muscle performance (R = 0.50), pulmonary flows (R = -0.62) and airway obstruction (R = 0.60). Fractional-order modeling showed high diagnostic accuracy in the detection of early respiratory abnormalities (AUC = 0.93), outperforming spirometry (p<0.03) and standard FOT analysis (p<0.01) used in Part 1 of this study. A combination of machine learning methods with fractional-order modeling further improved diagnostic accuracy (AUC = 0.97). Conclusions: FrOr modeling improved our knowledge about the biomechanical abnormalities in adults with SCA. Changes in FrOr parameters are associated with functional exercise capacity decline, abnormal pulmonary mechanics and diffusion. FrOr modeling outperformed spirometric and traditional forced oscillation analyses, showing a high diagnostic accuracy in the diagnosis of early respiratory abnormalities that was further improved by an automatic clinical decision support system. This finding suggested the potential utility of this combination to help identify early respiratory changes in patients with SCA. [ABSTRACT FROM AUTHOR]

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. Results: 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. Conclusion: 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. [ABSTRACT FROM AUTHOR]

Background: Globally, preterm birth is the leading cause of neonatal death with estimated prevalence and associated mortality highest in low- and middle-income countries (LMICs). Accurate identification of preterm infants is important at the individual level for appropriate clinical intervention as well as at the population level for informed policy decisions and resource allocation. As early prenatal ultrasound is commonly not available in these settings, gestational age (GA) is often estimated using newborn assessment at birth. This approach assumes last menstrual period to be unreliable and birthweight to be unable to distinguish preterm infants from those that are small for gestational age (SGA). We sought to leverage machine learning algorithms incorporating maternal factors associated with SGA to improve accuracy of preterm newborn identification in LMIC settings. Methods and findings: This study uses data from an ongoing obstetrical cohort in Lusaka, Zambia that uses early pregnancy ultrasound to estimate GA. Our intent was to identify the best set of parameters commonly available at delivery to correctly categorize births as either preterm (<37 weeks) or term, compared to GA assigned by early ultrasound as the gold standard. Trained midwives conducted a newborn assessment (<72 hours) and collected maternal and neonatal data at the time of delivery or shortly thereafter. New Ballard Score (NBS), last menstrual period (LMP), and birth weight were used individually to assign GA at delivery and categorize each birth as either preterm or term. Additionally, machine learning techniques incorporated combinations of these measures with several maternal and newborn characteristics associated with prematurity and SGA to develop GA at delivery and preterm birth prediction models. The distribution and accuracy of all models were compared to early ultrasound dating. Within our live-born cohort to date (n = 862), the median GA at delivery by early ultrasound was 39.4 weeks (IQR: 38.3–40.3). Among assessed newborns with complete data included in this analysis (n = 468), the median GA by ultrasound was 39.6 weeks (IQR: 38.4–40.3). Using machine learning, we identified a combination of six accessible parameters (LMP, birth weight, twin delivery, maternal height, hypertension in labor, and HIV serostatus) that can be used by machine learning to outperform current GA prediction methods. For preterm birth prediction, this combination of covariates correctly classified >94% of newborns and achieved an area under the curve (AUC) of 0.9796. Conclusions: We identified a parsimonious list of variables that can be used by machine learning approaches to improve accuracy of preterm newborn identification. Our best-performing model included LMP, birth weight, twin delivery, HIV serostatus, and maternal factors associated with SGA. These variables are all easily collected at delivery, reducing the skill and time required by the frontline health worker to assess GA. Trial registration: ClinicalTrials.gov Identifier: [ABSTRACT FROM AUTHOR]

Based on morphology it is often challenging to distinguish between the many different soft tissue sarcoma subtypes. Moreover, outcome of disease is highly variable even between patients with the same disease. Machine learning on transcriptome sequencing data could be a valuable new tool to understand differences between and within entities. Here we used machine learning analysis to identify novel diagnostic and prognostic markers and therapeutic targets for soft tissue sarcomas. Gene expression data was used from the Cancer Genome Atlas, the Genotype-Tissue Expression data and the French Sarcoma Group. We identified three groups of tumors that overlap in their molecular profile as seen with unsupervised t-Distributed Stochastic Neighbor Embedding clustering and a deep neural network. The three groups corresponded to subtypes that are morphologically overlapping. Using a random forest algorithm, we identified novel diagnostic markers for soft tissue sarcoma that distinguished between synovial sarcoma and MPNST, and that we validated using qRT-PCR in an independent series. Next, we identified prognostic genes that are strong predictors of disease outcome when used in a k-nearest neighbor algorithm. The prognostic genes were further validated in expression data from the French Sarcoma Group. One of these, HMMR, was validated in an independent series of leiomyosarcomas using immunohistochemistry on tissue micro array as a prognostic gene for disease-free interval. Furthermore, reconstruction of regulatory networks combined with data from the Connectivity Map showed, amongst others, that HDAC inhibitors could be a potential effective therapy for multiple soft tissue sarcoma subtypes. A viability assay with two HDAC inhibitors confirmed that both leiomyosarcoma and synovial sarcoma are sensitive to HDAC inhibition. In this study we identified novel diagnostic markers, prognostic markers and therapeutic leads from multiple soft tissue sarcoma gene expression datasets. Thus, machine learning algorithms are powerful new tools to improve our understanding of rare tumor entities. [ABSTRACT FROM AUTHOR]

Objective: The rapid proliferation of machine learning research using electronic health records to classify healthcare outcomes offers an opportunity to address the pressing public health problem of adolescent suicidal behavior. We describe the development and evaluation of a machine learning algorithm using natural language processing of electronic health records to identify suicidal behavior among psychiatrically hospitalized adolescents. Methods: Adolescents hospitalized on a psychiatric inpatient unit in a community health system in the northeastern United States were surveyed for history of suicide attempt in the past 12 months. A total of 73 respondents had electronic health records available prior to the index psychiatric admission. Unstructured clinical notes were downloaded from the year preceding the index inpatient admission. Natural language processing identified phrases from the notes associated with the suicide attempt outcome. We enriched this group of phrases with a clinically focused list of terms representing known risk and protective factors for suicide attempt in adolescents. We then applied the random forest machine learning algorithm to develop a classification model. The model performance was evaluated using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and accuracy. Results: The final model had a sensitivity of 0.83, specificity of 0.22, AUC of 0.68, a PPV of 0.42, NPV of 0.67, and an accuracy of 0.47. The terms mostly highly associated with suicide attempt clustered around terms related to suicide, family members, psychiatric disorders, and psychotropic medications. Conclusion: This analysis demonstrates modest success of a natural language processing and machine learning approach to identifying suicide attempt among a small sample of hospitalized adolescents in a psychiatric setting. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

We address gene selection and machine learning methods for cancer classification using microarray gene expression data. Due to the high dimensionality of microarray data, traditional gene selection algorithms are filter-based, focusing on intrinsic properties of the data such as distance, dependency, and correlation. These methods are fast but select far too many genes to use for the classification task. In this work, we present a new hybrid filter-wrapper gene subset selection algorithm that is an improved modification of our prior algorithm. Our proposed method employs interaction information to rank candidate genes to add into a gene subset. It then conditionally adds one gene at a time into the current subset and verifies whether the resultant subset improves the classification performance significantly. Only significant genes are selected, and the candidate gene list is updated every time a gene is added to the subset. Thus, our gene selection algorithm is very dynamic. Experimental results on ten public cancer microarray data sets show that our method consistently outperforms prior gene selection algorithms in terms of classification accuracy, while requiring a small number of selected genes. [ABSTRACT FROM AUTHOR]

Introduction: Aortic distensibility can be calculated using semi-automated methods to segment the aortic lumen on cine CMR (Cardiovascular Magnetic Resonance) images. However, these methods require visual quality control and manual localization of the region of interest (ROI) of ascending (AA) and proximal descending (PDA) aorta, which limit the analysis in large-scale population-based studies. Using 5100 scans from UK Biobank, this study sought to develop and validate a fully automated method to 1) detect and locate the ROIs of AA and PDA, and 2) provide a quality control mechanism. Methods: The automated AA and PDA detection-localization algorithm followed these steps: 1) foreground segmentation; 2) detection of candidate ROIs by Circular Hough Transform (CHT); 3) spatial, histogram and shape feature extraction for candidate ROIs; 4) AA and PDA detection using Random Forest (RF); 5) quality control based on RF detection probability. To provide the ground truth, overall image quality (IQ = 0–3 from poor to good) and aortic locations were visually assessed by 13 observers. The automated algorithm was trained on 1200 scans and Dice Similarity Coefficient (DSC) was used to calculate the agreement between ground truth and automatically detected ROIs. Results: The automated algorithm was tested on 3900 scans. Detection accuracy was 99.4% for AA and 99.8% for PDA. Aorta localization showed excellent agreement with the ground truth, with DSC ≥ 0.9 in 94.8% of AA (DSC = 0.97 ± 0.04) and 99.5% of PDA cases (DSC = 0.98 ± 0.03). AA×PDA detection probabilities could discriminate scans with IQ ≥ 1 from those severely corrupted by artefacts (AUC = 90.6%). If scans with detection probability < 0.75 were excluded (350 scans), the algorithm was able to correctly detect and localize AA and PDA in all the remaining 3550 scans (100% accuracy). Conclusion: The proposed method for automated AA and PDA localization was extremely accurate and the automatically derived detection probabilities provided a robust mechanism to detect low quality scans for further human review. Applying the proposed localization and quality control techniques promises at least a ten-fold reduction in human involvement without sacrificing any accuracy. [ABSTRACT FROM AUTHOR]

In more recent years, a significant increase in the number of available biological experiments has taken place due to the widespread use of massive sequencing data. Furthermore, the continuous developments in the machine learning and in the high performance computing areas, are allowing a faster and more efficient analysis and processing of this type of data. However, biological information about a certain disease is normally widespread due to the use of different sequencing technologies and different manufacturers, in different experiments along the years around the world. Thus, nowadays it is of paramount importance to attain a correct integration of biologically-related data in order to achieve genuine benefits from them. For this purpose, this work presents an integration of multiple Microarray and RNA-seq platforms, which has led to the design of a multiclass study by collecting samples from the main four types of leukemia, quantified at gene expression. Subsequently, in order to find a set of differentially expressed genes with the highest discernment capability among different types of leukemia, an innovative parameter referred to as coverage is presented here. This parameter allows assessing the number of different pathologies that a certain gen is able to discern. It has been evaluated together with other widely known parameters under assessment of an ANOVA statistical test which corroborated its filtering power when the identified genes are subjected to a machine learning process at multiclass level. The optimal tuning of gene extraction evaluated parameters by means of this statistical test led to the selection of 42 highly relevant expressed genes. By the use of minimum-Redundancy Maximum-Relevance (mRMR) feature selection algorithm, these genes were reordered and assessed under the operation of four different classification techniques. Outstanding results were achieved by taking exclusively the first ten genes of the ranking into consideration. Finally, specific literature was consulted on this last subset of genes, revealing the occurrence of practically all of them with biological processes related to leukemia. At sight of these results, this study underlines the relevance of considering a new parameter which facilitates the identification of highly valid expressed genes for simultaneously discerning multiple types of leukemia. [ABSTRACT FROM AUTHOR]

Annotation of foot-contact and foot-off events is the initial step in post-processing for most quantitative gait analysis workflows. If clean force plate strikes are present, the events can be automatically detected. Otherwise, annotation of gait events is performed manually, since reliable automatic tools are not available. Automatic annotation methods have been proposed for normal gait, but are usually based on heuristics of the coordinates and velocities of motion capture markers placed on the feet. These heuristics do not generalize to pathological gait due to greater variability in kinematics and anatomy of patients, as well as the presence of assistive devices. In this paper, we use a data-driven approach to predict foot-contact and foot-off events from kinematic and marker time series in children with normal and pathological gait. Through analysis of 9092 gait cycle measurements we build a predictive model using Long Short-Term Memory (LSTM) artificial neural networks. The best-performing model identifies foot-contact and foot-off events with an average error of 10 and 13 milliseconds respectively, outperforming popular heuristic-based approaches. We conclude that the accuracy of our approach is sufficient for most clinical and research applications in the pediatric population. Moreover, the LSTM architecture enables real-time predictions, enabling applications for real-time control of active assistive devices, orthoses, or prostheses. We provide the model, usage examples, and the training code in an open-source package. [ABSTRACT FROM AUTHOR]

Background: Exhaled aerosols from lungs have unique patterns, and their variation can be correlated to the underlying lung structure and associated abnormities. However, it is challenging to characterize such aerosol patterns and differentiate their difference because of their complexity. This challenge is even greater for small airway diseases, where the disturbance signals are weak. Objectives and methods: The objective of this study is exploiting different feature extraction algorithms to develop a practical classifier to diagnose obstructive lung diseases using exhaled aerosol images. These include proper orthogonal decomposition (POD), principal component analysis (PCA), dynamic mode decomposition (DMD), and DMD with control (DMDC). Aerosol images were generated via physiology-based simulations in one normal and four diseased airway models in G7-9 bronchioles. The image data were classified using both the support vector machine (SVM) and random forest (RF) algorithms. The effectiveness of different features was evaluated by classification accuracy and misclassification rate. Findings: Results show a significantly higher performance using dynamic feature extractions (DMD and DMDC) than static algorithms (POD and PCA). Adding the control variables to DMD further improved classification accuracy. Comparing the classification methods, RF persistently outperformed SVM for all types of features considered. While the performance of RF constantly increased with the number of features retained, the performance of SVM peaked at 50 and decreased thereafter. The 5-class classification accuracy was 94.8% using the DMDC-RF model and 93.0% using the DMD-RF model, both of which were higher than 87.0% in the previous study that used fractal dimension features. Conclusion: Considering that disease progression is inherently a dynamic process, DMD(C)-based feature extraction preserves temporal information and is preferred over POD and PCA. Compared with hand-crafted features like fractals, feature extraction by DMD and DMDC is automatic and more accurate. [ABSTRACT FROM AUTHOR]

Texture analysis is an important topic in Ultrasound (US) image analysis for structure segmentation and tissue classification. In this work a novel approach for US image texture feature extraction is presented. It is mainly based on parametrical modelling of a signal version of the US image in order to process it as data resulting from a dynamical process. Because of the predictive characteristics of such a model representation, good estimations of texture features can be obtained with less data than generally used methods require, allowing higher robustness to low Signal-to-Noise ratio and a more localized US image analysis. The usability of the proposed approach was demonstrated by extracting texture features for segmenting the thyroid in US images. The obtained results showed that features corresponding to energy ratios between different modelled texture frequency bands allowed to clearly distinguish between thyroid and non-thyroid texture. A simple k-means clustering algorithm has been used for separating US image patches as belonging to thyroid or not. Segmentation of thyroid was performed in two different datasets obtaining Dice coefficients over 85%. [ABSTRACT FROM AUTHOR]

Early prediction of the potential for neurological recovery after resuscitation from cardiac arrest is difficult but important. Currently, no clinical finding or combination of findings are sufficient to accurately predict or preclude favorable recovery of comatose patients in the first 24 to 48 hours after resuscitation. Thus, life-sustaining therapy is often continued for several days in patients whose irrecoverable injury is not yet recognized. Conversely, early withdrawal of life-sustaining therapy increases mortality among patients who otherwise might have gone on to recover. In this work, we present Canonical Autocorrelation Analysis (CAA) and Canonical Autocorrelation Embeddings (CAE), novel methods suitable for identifying complex patterns in high-resolution multivariate data often collected in highly monitored clinical environments such as intensive care units. CAE embeds sets of datapoints onto a space that characterizes their latent correlation structures and allows direct comparison of these structures through the use of a distance metric. The methodology may be particularly suitable when the unit of analysis is not just an individual datapoint but a dataset, as for instance in patients for whom physiological measures are recorded over time, and where changes of correlation patterns in these datasets are informative for the task at hand. We present a proof of concept to illustrate the potential utility of CAE by applying it to characterize electroencephalographic recordings from 80 comatose survivors of cardiac arrest, aiming to identify patients who will survive to hospital discharge with favorable functional recovery. Our results show that with very low probability of making a Type 1 error, we are able to identify 32.5% of patients who are likely to have a good neurological outcome, some of whom have otherwise unfavorable clinical characteristics. Importantly, some of these had 5% predicted chance of favorable recovery based on initial illness severity measures alone. Providing this information to support clinical decision-making could motivate the continuation of life-sustaining therapies for these patients. [ABSTRACT FROM AUTHOR]

Type IV secretion systems exist in a number of bacterial pathogens and are used to secrete effector proteins directly into host cells in order to change their environment making the environment hospitable for the bacteria. In recent years, several machine learning algorithms have been developed to predict effector proteins, potentially facilitating experimental verification. However, inconsistencies exist between their results. Previously we analysed the disparate sets of predictive features used in these algorithms to determine an optimal set of 370 features for effector prediction. This study focuses on the best way to use these optimal features by designing three machine learning classifiers, comparing our results with those of others, and obtaining de novo results. We chose the pathogen Legionella pneumophila strain Philadelphia-1, a cause of Legionnaires’ disease, because it has many validated effector proteins and others have developed machine learning prediction tools for it. While all of our models give good results indicating that our optimal features are quite robust, Model 1, which uses all 370 features with a support vector machine, has slightly better accuracy. Moreover, Model 1 predicted 472 effector proteins that are deemed highly probable to be effectors and include 94% of known effectors. Although the results of our three models agree well with those of other researchers, their models only predicted 126 and 311 candidate effectors. [ABSTRACT FROM AUTHOR]

Dementia is a neurological and cognitive condition that affects millions of people around the world. At any given time in the United Kingdom, 1 in 4 hospital beds are occupied by a person with dementia, while about 22% of these hospital admissions are due to preventable causes. In this paper we discuss using Internet of Things (IoT) technologies and in-home sensory devices in combination with machine learning techniques to monitor health and well-being of people with dementia. This will allow us to provide more effective and preventative care and reduce preventable hospital admissions. One of the unique aspects of this work is combining environmental data with physiological data collected via low cost in-home sensory devices to extract actionable information regarding the health and well-being of people with dementia in their own home environment. We have worked with clinicians to design our machine learning algorithms where we focused on developing solutions for real-world settings. In our solutions, we avoid generating too many alerts/alarms to prevent increasing the monitoring and support workload. We have designed an algorithm to detect Urinary Tract Infections (UTI) which is one of the top five reasons of hospital admissions for people with dementia (around 9% of hospital admissions for people with dementia in the UK). To develop the UTI detection algorithm, we have used a Non-negative Matrix Factorisation (NMF) technique to extract latent factors from raw observation and use them for clustering and identifying the possible UTI cases. In addition, we have designed an algorithm for detecting changes in activity patterns to identify early symptoms of cognitive decline or health decline in order to provide personalised and preventative care services. For this purpose, we have used an Isolation Forest (iForest) technique to create a holistic view of the daily activity patterns. This paper describes the algorithms and discusses the evaluation of the work using a large set of real-world data collected from a trial with people with dementia and their caregivers. [ABSTRACT FROM AUTHOR]

Different performance measures are used to assess the behaviour, and to carry out the comparison, of classifiers in Machine Learning. Many measures have been defined on the literature, and among them, a measure inspired by Shannon’s entropy named the Confusion Entropy (CEN). In this work we introduce a new measure, MCEN, by modifying CEN to avoid its unwanted behaviour in the binary case, that disables it as a suitable performance measure in classification. We compare MCEN with CEN and other performance measures, presenting analytical results in some particularly interesting cases, as well as some heuristic computational experimentation. [ABSTRACT FROM AUTHOR]

The high failure rate of therapeutics showing promise in mouse models to translate to patients is a pressing challenge in biomedical science. Though retrospective studies have examined the fidelity of mouse models to their respective human conditions, approaches for prospective translation of insights from mouse models to patients remain relatively unexplored. Here, we develop a semi-supervised learning approach for inference of disease-associated human differentially expressed genes and pathways from mouse model experiments. We examined 36 transcriptomic case studies where comparable phenotypes were available for mouse and human inflammatory diseases and assessed multiple computational approaches for inferring human biology from mouse datasets. We found that semi-supervised training of a neural network identified significantly more true human biological associations than interpreting mouse experiments directly. Evaluating the experimental design of mouse experiments where our model was most successful revealed principles of experimental design that may improve translational performance. Our study shows that when prospectively evaluating biological associations in mouse studies, semi-supervised learning approaches, combining mouse and human data for biological inference, provide the most accurate assessment of human in vivo disease processes. Finally, we proffer a delineation of four categories of model system-to-human “Translation Problems” defined by the resolution and coverage of the datasets available for molecular insight translation and suggest that the task of translating insights from model systems to human disease contexts may be better accomplished by a combination of translation-minded experimental design and computational approaches. [ABSTRACT FROM AUTHOR]

Background: Glaucoma is the leading cause of irreversible blindness worldwide. It is a heterogeneous group of conditions with a common optic neuropathy and associated loss of peripheral vision. Both over and under-diagnosis carry high costs in terms of healthcare spending and preventable blindness. The characteristic clinical feature of glaucoma is asymmetrical optic nerve rim narrowing, which is difficult for humans to quantify reliably. Strategies to improve and automate optic disc assessment are therefore needed to prevent sight loss. Methods: We developed a novel glaucoma detection algorithm that segments and analyses colour photographs to quantify optic nerve rim consistency around the whole disc at 15-degree intervals. This provides a profile of the cup/disc ratio, in contrast to the vertical cup/disc ratio in common use. We introduce a spatial probabilistic model, to account for the optic nerve shape, we then use this model to derive a disc deformation index and a decision rule for glaucoma. We tested our algorithm on two separate image datasets (ORIGA and RIM-ONE). Results: The spatial algorithm accurately distinguished glaucomatous and healthy discs on internal and external validation (AUROC 99.6% and 91.0% respectively). It achieves this using a dataset 100-times smaller than that required for deep learning algorithms, is flexible to the type of cup and disc segmentation (automated or semi-automated), utilises images with missing data, and is correlated with the disc size (p = 0.02) and the rim-to-disc at the narrowest rim (p<0.001, in external validation). Discussion: The spatial probabilistic algorithm is highly accurate, highly data efficient and it extends to any imaging hardware in which the boundaries of cup and disc can be segmented, thus making the algorithm particularly applicable to research into disease mechanisms, and also glaucoma screening in low resource settings. [ABSTRACT FROM AUTHOR]