Search

BackgroundOxygen saturation (Spo2) screening has not led to earlier detection of critical congenital heart disease (CCHD). Adding pulse oximetry features (ie, perfusion data and radiofemoral pulse delay) may improve CCHD detection, especially coarctation of the aorta (CoA). We developed and tested a machine learning (ML) pulse oximetry algorithm to enhance CCHD detection.Methods and resultsSix sites prospectively enrolled newborns with and without CCHD and recorded simultaneous pre- and postductal pulse oximetry. We focused on models at 1 versus 2 time points and with/without pulse delay for our ML algorithms. The sensitivity, specificity, and area under the receiver operating characteristic curve were compared between the Spo2-alone and ML algorithms. A total of 523 newborns were enrolled (no CHD, 317; CHD, 74; CCHD, 132, of whom 21 had isolated CoA). When applying the Spo2-alone algorithm to all patients, 26.2% of CCHD would be missed. We narrowed the sample to patients with both 2 time point measurements and pulse-delay data (no CHD, 65; CCHD, 14) to compare ML performance. Among these patients, sensitivity for CCHD detection increased with both the addition of pulse delay and a second time point. All ML models had 100% specificity. With a 2-time-points+pulse-delay model, CCHD sensitivity increased to 92.86% (P=0.25) compared with Spo2 alone (71.43%), and CoA increased to 66.67% (P=0.5) from 0. The area under the receiver operating characteristic curve for CCHD and CoA detection significantly improved (0.96 versus 0.83 for CCHD, 0.83 versus 0.48 for CoA; both P=0.03) using the 2-time-points+pulse-delay model compared with Spo2 alone.ConclusionsML pulse oximetry that combines oxygenation, perfusion data, and pulse delay at 2 time points may improve detection of CCHD and CoA within 48 hours after birth.RegistrationURL: https://www.clinicaltrials.gov/study/NCT04056104?term=NCT04056104&rank=1; Unique identifier: NCT04056104.

The efficacy of supervised deep learning in medical image analyses, particularly in pathology, is hindered by the necessity for extensive manual annotations. Annotating images at the gigapixel level manually proves to be a highly labor-intensive and time-consuming task. Semi-supervised learning (SSL) has emerged as a promising approach that leverages unlabeled data to reduce labeling efforts. In this work, we introduce Semi-Path, a practical SSL framework enhanced with active learning (AL) for gigapixel pathology tasks. Unlike existing methods that treat SSL and AL as independent components where AL incurs significant computational complexity to SSL, we propose a deep fusion of SSL and AL into a unified framework. Our framework introduces Informative Active Annotation (IAA) that employs a SSL-AL iterative structure to effectively extract knowledge from unlabeled pathology data. This structure significantly minimizes labeling efforts and computational complexity. Then, we propose Adaptive Pseudo-Labeling (APL) to address heterogeneity in class distribution, and prediction difficulty that are often observed in real-world pathology tasks. We evaluate Semi-Path on pathology image classification and segmentation tasks over three datasets that include WSIs from breast, colorectal, and brain tissues. The experimental results demonstrate the consistent superiority of Semi-Path over state-of-the-art methods.

Estimation of temporospatial clinical features of gait (CFs), such as step count and length, step duration, step frequency, gait speed, and distance traveled, is an important component of community-based mobility evaluation using wearable accelerometers. However, accurate unsupervised computerized measurement of CFs of individuals with Duchenne muscular dystrophy (DMD) who have progressive loss of ambulatory mobility is difficult due to differences in patterns and magnitudes of acceleration across their range of attainable gait velocities. This paper proposes a novel calibration method. It aims to detect steps, estimate stride lengths, and determine travel distance. The approach involves a combination of clinical observation, machine-learning-based step detection, and regression-based stride length prediction. The method demonstrates high accuracy in children with DMD and typically developing controls (TDs) regardless of the participants level of ability. Fifteen children with DMD and fifteen TDs underwent supervised clinical testing across a range of gait speeds using 10 m or 25 m run/walk (10 MRW, 25 MRW), 100 m run/walk (100 MRW), 6-min walk (6 MWT), and free-walk (FW) evaluations while wearing a mobile-phone-based accelerometer at the waist near the bodys center of mass. Following calibration by a trained clinical evaluator, CFs were extracted from the accelerometer data using a multi-step machine-learning-based process and the results were compared to ground-truth observation data. Model predictions vs. observed values for step counts, distance traveled, and step length showed a strong correlation (Pearsons r = -0.9929 to 0.9986, p < 0.0001). The estimates demonstrated a mean (SD) percentage error of 1.49% (7.04%) for step counts, 1.18% (9.91%) for distance traveled, and 0.37% (7.52%) for step length compared to ground-truth observations for the combined 6 MWT, 100 MRW, and FW tasks. Our study findings indicate that a single waist-worn accelerometer calibrated to an individuals stride characteristics using our methods accurately measures CFs and estimates travel distances across a common range of gait speeds in both DMD and TD peers.

Fluid bolus therapy (FBT) is fundamental to the management of circulatory shock in critical care but balancing the benefits and toxicities of FBT has proven challenging in individual patients. Improved predictors of the hemodynamic response to a fluid bolus, commonly referred to as a fluid challenge, are needed to limit non-beneficial fluid administration and to enable automated clinical decision support and patient-specific precision critical care management. In this study we retrospectively analyzed data from 394 fluid boluses from 58 pigs subjected to either hemorrhagic or distributive shock. All animals had continuous blood pressure and cardiac output monitored throughout the study. Using this data, we developed a machine learning (ML) model to predict the hemodynamic response to a fluid challenge using only arterial blood pressure waveform data as the input. A Random Forest binary classifier referred to as the ML fluid responsiveness algorithm (MLFRA) was trained to detect fluid responsiveness (FR), defined as a ≥ 15% change in cardiac stroke volume after a fluid challenge. We then compared its performance to pulse pressure variation, a commonly used metric of FR. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC), confusion matrix metrics, and calibration curves plotting predicted probabilities against observed outcomes. Across multiple train/test splits and feature selection methods designed to assess performance in the setting of small sample size conditions typical of large animal experiments, the MLFRA achieved an average AUROC, recall (sensitivity), specificity, and precision of 0.82, 0.86, 0.62. and 0.76, respectively. In the same datasets, pulse pressure variation had an AUROC, recall, specificity, and precision of 0.73, 0.91, 0.49, and 0.71, respectively. The MLFRA was generally well-calibrated across its range of predicted probabilities and appeared to perform equally well across physiologic conditions. These results suggest that ML, using only inputs from arterial blood pressure monitoring, may substantially improve the accuracy of predicting FR compared to the use of pulse pressure variation. If generalizable, these methods may enable more effective, automated precision management of critically ill patients with circulatory shock.

Accurate and scalable quantification of amyloid-β (Aβ) pathology is crucial for deeper disease phenotyping and furthering research in Alzheimer Disease (AD). This multidisciplinary study addresses the current limitations on neuropathology by leveraging a machine learning (ML) pipeline to perform a granular quantification of Aβ deposits and assess their distribution in the temporal lobe. Utilizing 131 whole-slide-images from consecutive autopsied cases at the University of California Davis Alzheimer Disease Research Center, our objectives were threefold: (1) Validate an automatic workflow for Aβ deposit quantification in white matter (WM) and gray matter (GM); (2) define the distributions of different Aβ deposit types in GM and WM, and (3) investigate correlates of Aβ deposits with dementia status and the presence of mixed pathology. Our methodology highlights the robustness and efficacy of the ML pipeline, demonstrating proficiency akin to experts' evaluations. We provide comprehensive insights into the quantification and distribution of Aβ deposits in the temporal GM and WM revealing a progressive increase in tandem with the severity of established diagnostic criteria (NIA-AA). We also present correlations of Aβ load with clinical diagnosis as well as presence/absence of mixed pathology. This study introduces a reproducible workflow, showcasing the practical use of ML approaches in the field of neuropathology, and use of the output data for correlative analyses. Acknowledging limitations, such as potential biases in the ML model and current ML classifications, we propose avenues for future research to refine and expand the methodology. We hope to contribute to the broader landscape of neuropathology advancements, ML applications, and precision medicine, paving the way for deep phenotyping of AD brain cases and establishing a foundation for further advancements in neuropathological research.

Cardiovascular disease (CVD) is largely preventable, and the leading cause of death for men and women. Though women have increased life expectancy compared to men, there are marked sex disparities in prevalence and risk of CVD-associated mortality and dementia. Yet, the basis for these and female-male differences is not completely understood. It is increasingly recognized that heart and brain health represent a lifetime of exposures to shared risk factors (including obesity, hyperlipidemia, diabetes, and hypertension) that compromise cerebrovascular health. We describe the process and resources for establishing a new research Center for Women's Cardiovascular and Brain Health at the University of California, Davis as a model for: (1) use of the cy pres principle for funding science to improve health; (2) transdisciplinary collaboration to leapfrog progress in a convergence science approach that acknowledges and addresses social determinants of health; and (3) training the next generation of diverse researchers. This may serve as a blueprint for future Centers in academic health institutions, as the cy pres mechanism for funding research is a unique mechanism to leverage residual legal settlement funds to catalyze the pace of scientific discovery, maximize innovation, and promote health equity in addressing society's most vexing health problems.

Background: The association between cancer and venous thromboembolism (VTE) is well-established with cancer patients accounting for approximately 20% of all VTE incidents. In this paper, we have performed a comparison of machine learning (ML) methods to traditional clinical scoring models for predicting the occurrence of VTE in a cancer patient population, identified important features (clinical biomarkers) for ML model predictions, and examined how different approaches to reducing the number of features used in the model impact model performance. Methods: We have developed an ML pipeline including three separate feature selection processes and applied it to routine patient care data from the electronic health records of 1910 cancer patients at the University of California Davis Medical Center. Results: Our ML-based prediction model achieved an area under the receiver operating characteristic curve of 0.778 ± 0.006 (mean ± SD) when trained on a set of 15 features. This result is comparable with the model performance when trained on all features in our feature pool [0.779 ± 0.006 (mean ± SD) with 29 features]. Our result surpasses the most validated clinical scoring system for VTE risk assessment in cancer patients by 16.1%. We additionally found cancer stage information to be a useful predictor after all performed feature selection processes despite not being used in existing score-based approaches. Conclusion: From these findings, we observe that ML can offer new insights and a significant improvement over the most validated clinical VTE risk scoring systems in cancer patients. The results of this study also allowed us to draw insight into our feature pool and identify the features that could have the most utility in the context of developing an efficient ML classifier. While a model trained on our entire feature pool of 29 features significantly outperformed the traditionally used clinical scoring system, we were able to achieve an equivalent performance using a subset of only 15 features through strategic feature selection methods. These results are encouraging for potential applications of ML to predicting cancer-associated VTE in clinical settings such as in bedside decision support systems where feature availability may be limited.

Dicrotic Notch (DN), one of the most significant and indicative features of the arterial blood pressure (ABP) waveform, becomes less pronounced and thus harder to identify as a matter of aging and pathological vascular stiffness. Generalizable and automatic DN identification for such edge cases is even more challenging in the presence of unexpected ABP waveform deformations that happen due to internal and external noise sources or pathological conditions that cause hemodynamic instability. We propose a physics-aware approach, named Physiowise (PW), that first employs a cardiovascular model to augment the original ABP waveform and reduce unexpected deformations, then apply a set of predefined rules on the augmented signal to find DN locations. We have tested the proposed method on in-vivo data gathered from 14 pigs under hemorrhage and sepsis study. Our result indicates 52% overall mean error improvement with 16% higher detection accuracy within the lowest permitted error range of 30ms. An additional hybrid methodology is also proposed to allow combining augmentation with any application-specific user-defined rule set.

Computational machine learning (ML)-based frameworks could be advantageous for scalable analyses in neuropathology. A recent deep learning (DL) framework has shown promise in automating the processes of visualizing and quantifying different types of amyloid-β deposits as well as segmenting white matter (WM) from gray matter (GM) on digitized immunohistochemically stained slides. However, this framework has only been trained and evaluated on amyloid-β-stained slides with minimal changes in preanalytic variables. In this study, we evaluated select preanalytical variables including magnification, compression rate, and storage format using three digital slides scanners (Zeiss Axioscan Z1, Leica Aperio AT2, and Leica Aperio GT 450), on over 60 whole slide images, in a cohort of 14 cases having a spectrum of amyloid-β deposits. We conducted statistical comparisons of preanalytic variables with repeated measures analysis of variance evaluating the outputs of two DL frameworks for segmentation and object classification tasks. For both WM/GM segmentation and amyloid-β plaque classification tasks, there were statistical differences with respect to scanner types (p

In this paper, we study the L 1 /L 2 minimization on the gradient for imaging applications. Several recent works have demonstrated that L 1 /L 2 is better than the L 1 norm when approximating the L 0 norm to promote sparsity. Consequently, we postulate that applying L 1 /L 2 on the gradient is better than the classic total variation (the L 1 norm on the gradient) to enforce the sparsity of the image gradient. Numerically, we design a specific splitting scheme, under which we can prove subsequential and global convergence for the alternating direction method of multipliers (ADMM) under certain conditions. Experimentally, we demonstrate visible improvements of L 1 /L 2 over L 1 and other nonconvex regularizations for image recovery from low-frequency measurements and two medical applications of MRI and CT reconstruction. Finally, we reveal some empirical evidence on the superiority of L 1 /L 2 over L 1 when recovering piecewise constant signals from low-frequency measurements to shed light on future works.

As neurodegenerative disease pathological hallmarks have been reported in both grey matter (GM) and white matter (WM) with different density distributions, automating the segmentation process of GM/WM would be extremely advantageous for aiding in neuropathologic deep phenotyping. Standard segmentation methods typically involve manual annotations, where a trained researcher traces the delineation of GM/WM in ultra-high-resolution Whole Slide Images (WSIs). This method can be time-consuming and subjective, preventing a scalable analysis on pathology images. This paper proposes an automated segmentation pipeline (BrainSec) combining a Convolutional Neural Network (CNN) module for segmenting GM/WM regions and a post-processing module to remove artifacts/residues of tissues. The final output generates XML annotations that can be visualized via Aperio ImageScope. First, we investigate two baseline models for medical image segmentation: FCN, and U-Net. Then we propose a patch-based approach, BrainSec, to classify the GM/WM/background regions. We demonstrate BrainSec is robust and has reliable performance by testing it on over 180 WSIs that incorporate numerous unique cases as well as distinct neuroanatomic brain regions. We also apply gradient-weighted class activation mapping (Grad-CAM) to interpret the segmentation masks and provide relevant explanations and insights. In addition, we have integrated BrainSec with an existing Amyloid-β pathology classification model into a unified framework (without incurring significant computation complexity) to identify pathologies, visualize their distributions, and quantify each type of pathologies in segmented GM/WM regions, respectively.

Critical Congenital Heart Disease (CCHD) screening that only uses oxygen saturation (SpO2), measured by pulse oximetry, fails to detect an estimated 900 US newborns annually. The addition of other pulse oximetry features such as perfusion index (PIx), heart rate, pulse delay and photoplethysmography characteristics may improve detection of CCHD, especially those with systemic blood flow obstruction such as Coarctation of the Aorta (CoA). To comprehensively study the most relevant features associated with CCHD, we investigated interpretable machine learning (ML) algorithms by using Recursive Feature Elimination (RFE) to identify an optimal subset of features. We then incorporated the trained ML models into the current SpO2-alone screening algorithm. Our proposed enhanced CCHD screening system, which adds the ML model, improved sensitivity by approximately 10 percentage points compared to the current standard SpO2-alone method with minimal to no impact on specificity.Clinical relevance- This establishes proof of concept for a ML algorithm that combines pulse oximetry features to improve detection of CCHD with little impact on false positive rate.

As early intervention is highly effective for young children with autism spectrum disorder (ASD), it is imperative to make accurate diagnosis as early as possible. ASD has often been associated with atypical visual attention and eye gaze data can be collected at a very early age. An automatic screening tool based on eye gaze data that could identify ASD risk offers the opportunity for intervention before the full set of symptoms is present. In this paper, we propose two machine learning methods, synthetic saccade approach and image based approach, to automatically classify ASD given children's eye gaze data collected from free-viewing tasks of natural images. The first approach uses a generative model of synthetic saccade patterns to represent the baseline scan-path from a typical non-ASD individual and combines it with the real scan-path as well as other auxiliary data as inputs to a deep learning classifier. The second approach adopts a more holistic image-based approach by feeding the input image and a sequence of fixation maps into a convolutional or recurrent neural network. Using a publicly-accessible collection of children's gaze data, our experiments indicate that the ASD prediction accuracy reaches 67.23% accuracy on the validation dataset and 62.13% accuracy on the test dataset.

To develop and characterize a machine learning algorithm to discriminate acute respiratory distress syndrome from other causes of respiratory failure using only ventilator waveform data.DesignRetrospective, observational cohort study.SettingAcademic medical center ICU.PatientsAdults admitted to the ICU requiring invasive mechanical ventilation, including 50 patients with acute respiratory distress syndrome and 50 patients with primary indications for mechanical ventilation other than hypoxemic respiratory failure.InterventionsNone.Measurements and main resultsPressure and flow time series data from mechanical ventilation during the first 24-hours after meeting acute respiratory distress syndrome criteria (or first 24-hr of mechanical ventilation for non-acute respiratory distress syndrome patients) were processed to extract nine physiologic features. A random forest machine learning algorithm was trained to discriminate between the patients with and without acute respiratory distress syndrome. Model performance was assessed using the area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value. Analyses examined performance when the model was trained using data from the first 24 hours and tested using withheld data from either the first 24 hours (24/24 model) or 6 hours (24/6 model). Area under the receiver operating characteristic curve, sensitivity, specificity, positive predictive value, and negative predictive value were 0.88, 0.90, 0.71, 0.77, and 0.90 (24/24); and 0.89, 0.90, 0.75, 0.83, and 0.83 (24/6).ConclusionsUse of machine learning and physiologic information derived from raw ventilator waveform data may enable acute respiratory distress syndrome screening at early time points after intubation. This approach, combined with traditional diagnostic criteria, could improve timely acute respiratory distress syndrome recognition and enable automated clinical decision support, especially in settings with limited availability of conventional diagnostic tests and electronic health records.

IntroductionAccess to patient medical data is critical to building a real-time data analytic pipeline for improving care providers' ability to detect, diagnose, and prognosticate diseases. Critical congenital heart disease (CCHD) is a common group of neonatal life-threatening defects that must be promptly diagnosed to minimize morbidity and mortality. CCHD can be diagnosed both prenatally and postnatally. However, despite current screening practices involving oxygen saturation analysis, timely diagnosis is missed in approximately 900 infants with CCHD annually in the USA and can benefit from increased data processing capabilities. Adding non-invasive perfusion measurements to oxygen saturation data can improve the timeliness and fidelity of CCHD diagnostics. However, real-time monitoring and interpretation of non-invasive perfusion data are currently limited.MethodsTo address this challenge, we created a hardware and software architecture utilizing a Pi-top™ for collecting, visualizing, and storing dual oxygen saturation, perfusion indices, and photoplethysmography data. Data aggregation in our system is automated and all data files are coded with unique study identifiers to facilitate research purposes.ResultsUsing this system, we have collected data from 190 neonates, 130 presumably without and 60 with congenital heart disease, in total comprising 1665 min of information. From these data, we are able to extract non-invasive perfusion features such as perfusion index, radiofemoral delay, and slope of systolic rise or diastolic fall.ConclusionThis data collection and waveform analysis is relatively inexpensive and can be used to enhance future CCHD screening algorithms.

Future healthcare systems will rely heavily on clinical decision support systems (CDSS) to improve the decision-making processes of clinicians. To explore the design of future CDSS, we developed a research-focused CDSS for the management of patients in the intensive care unit that leverages Internet of Things (IoT) devices capable of collecting streaming physiologic data from ventilators and other medical devices. We then created machine learning (ML) models that could analyze the collected physiologic data to determine if the ventilator was delivering potentially harmful therapy and if a deadly respiratory condition, acute respiratory distress syndrome (ARDS), was present. We also present work to aggregate these models into a mobile application that can provide responsive, real-time alerts of changes in ventilation to providers. As illustrated in the recent COVID-19 pandemic, being able to accurately predict ARDS in newly infected patients can assist in prioritizing care. We show that CDSS may be used to analyze physiologic data for clinical event recognition and automated diagnosis, and we also highlight future research avenues for hospital CDSS.

Clinical decision support systems (CDSS) will play increasing role in improving quality of medical care for critically ill patients. However, due to limitations in current informatics infrastructure, CDSS do not always have complete information on state of supporting physiologic monitoring devices, which can limit input data available to CDSS. This is especially true in use case of mechanical ventilation (MV), where current CDSS have no knowledge of critical ventilation settings, such as ventilation mode. To enable MV CDSS make accurate recommendations related to ventilator mode, we developed a highly performant machine learning model that is able to perform per-breath classification of five of most widely used ventilation modes in USA with average F1-score of 97.52%. We also show how our approach makes methodologic improvements over previous work and is highly robust to missing data caused by software/sensor error.

As the majority of Internet traffic today is attributed to content-centric applications, there has been ever-increasing demand for highly scalable and efficient content delivery. An accurate prediction on future content consumption is essential for such demand. To address such an issue, this paper introduces a new computational approach, Content Network (CN) that can capture the relations among contents, and its potential applications. We conduct a measurement study to investigate how contents are inter-related from the viewpoint of content spreading on one of the popular BitTorrent portals: The Pirate Bay. Based on the large-scale dataset that contains 18 K torrents and 9 M users, we construct the CN and investigate its structural properties. Our key finding is that contents in the same community in the CN (i) belong to the same content category with 94% probability, (ii) are uploaded by the same content publisher with 76% probability, and (iii) have the similar titles with 51% probability, which implies that contents in the same community collectively contain common (shared) interests of users. Our trace-driven study demonstrates that the proposed CN model is useful in (i) content recommendation for increasing sales and (ii) content caching for networking efficiency. We believe our work can provide an important insight for content stakeholders, e.g., content providers for efficient publishing strategies, network engineers for networking efficiency, or content marketers for accurate recommendation.

Learning and exploring the connectivity of unknown networks represent an important problem in practical applications of communication networks and social-media networks. Modeling large-scale networks as connected graphs is highly desirable to extract their connectivity information among nodes to visualize network topology, disseminate data, and improve routing efficiency. This paper investigates a simple measurement model in which a small subset of source nodes collect hop distance information from networked nodes in order to generate a virtual coordinate system (VCS) for networks of unknown topology. We establish the VCS to define logical distance among nodes based on principal component analysis and to determine connectivity relationship and effective routing methods. More importantly, we present a robust analytical algorithm to derive the VCS against practical issues of missing and corrupted measurements. We also develop a connectivity inference method which classifies nodes into layers based on the hop distances and derives partial information on network connectivity.

In this paper, we propose the Programmable LInk Metric Identification (ProgLIMI) infrastructure for software-defined networking (SDN) networks. ProgLIMI identifies round-trip link metrics (RTLMs) from accumulated end-to-end metrics of selected measurement paths by leveraging the flexible routing control capability of SDN networks. ProgLIMI mainly solves three sub-problems: 1) monitor placement; 2) linearly independent measurement path construction; and 3) flow rule design. To reduce measurement cost, ProgLIMI tries to minimize the number of required monitors and flow rules. In this paper, we address the three sub-problems for both full and hybrid SDN networks. For full SDN networks, ProgLIMI can achieve full RTLM identification using only one monitor and two flow rules in each SDN switch. In contrast, the RTLM identification in hybrid SDN networks is more complicated due to the routing constraint of hybrid SDN networks. We first prove that the monitor placement problem in hybrid SDN networks is NP-hard. We then formulate the monitor placement and measurement path selection problem in hybrid SDN networks and propose a greedy heuristic algorithm to solve the problem efficiently. Our evaluations on both physical testbed and simulation platform reveal that ProgLIMI can accurately identify the RTLMs (delay and loss rate). Besides, ProgLIMI is also resource efficient, i.e., it only requires two flow rules in each SDN switch and a small number of monitors, and the extra probing traffic load incurred by ProgLIMI is also low.

BACKGROUND:As healthcare increasingly digitizes, streaming waveform data is being made available from an variety of sources, but there still remains a paucity of performant clinical decision support systems. For example, in the intensive care unit (ICU) existing automated alarm systems typically rely on simple thresholding that result in frequent false positives. Recurrent false positive alerts create distrust of alarm mechanisms that can be directly detrimental to patient health. To improve patient care in the ICU, we need alert systems that are both pervasive, and accurate so as to be informative and trusted by providers. OBJECTIVE:We aimed to develop a machine learning-based classifier to detect abnormal waveform events using the use case of mechanical ventilation waveform analysis, and the detection of harmful forms of ventilation delivery to patients. We specifically focused on detecting injurious subtypes of patient-ventilator asynchrony (PVA). METHODS:Using a dataset of breaths recorded from 35 different patients, we used machine learning to create computational models to automatically detect, and classify two types of injurious PVA, double trigger asynchrony (DTA), breath stacking asynchrony (BSA). We examined the use of synthetic minority over-sampling technique (SMOTE) to overcome class imbalance problems, varied methods for feature selection, and use of ensemble methods to optimize the performance of our model. RESULTS:We created an ensemble classifier that is able to accurately detect DTA at a sensitivity/specificity of 0.960/0.975, BSA at sensitivity/specificity of 0.944/0.987, and non-PVA events at sensitivity/specificity of .967/.980. CONCLUSIONS:Our results suggest that it is possible to create a high-performing machine learning-based model for detecting PVA in mechanical ventilator waveform data in spite of both intra-patient, and inter-patient variability in waveform patterns, and the presence of clinical artifacts like cough and suction procedures. Our work highlights the importance of addressing class imbalance in clinical data sets, and the combined use of statistical methods and expert knowledge in feature selection.

In this paper, we propose an intelligent framework for Traffic Matrix (TM) inference in Software Defined Networks (SDN) where the Ternary Content Addressable Memory (TCAM) entries of switches are partitioned into two parts to: 1) effectively aggregate part of incoming flows for aggregate measurements, and 2) de-aggregate and directly measure the most informative flows for per-flow measurements. These measurements are then processed to effectively estimate the size of network flows. Under hard resource constraints of limited TCAM sizes, we show how to design the optimal and efficient-compressed flow aggregation matrices. We propose an optimal Multi-Armed Bandit (MAB) based algorithm to adaptively measure the most rewarding flows. We evaluate the performance of our framework using real traffic traces from different network environments and by considering two main applications: TM estimation and Heavy Hitter (HH) detection. Moreover, we have implemented a prototype of our framework in Mininet to demonstrate its effectiveness.

With the attractive feature of guaranteeing maximum network throughput, backpressure routing has been widely used in wireless communication networks. Motivated by the backpressure routing, in this paper, we propose a delay-based traffic signal control algorithm in transportation networks. We prove that this delay-based control achieves optimal throughput performance, same as the queue-based traffic signal control in the literature. However, a vehicle at a lane whose queue length remains very small may be excessively delayed under the queue-based signal control. Our delay-based backpressure control can deal with the excessive delays and achieve better fairness with respect to delay while still guaranteeing throughput optimality. Moreover, a general weighted control scheme combining the queue-based and delay-based schemes is also investigated, to provide a more flexible control according to the quality of service requirements. Numerical results explore their performance under both homogeneous and heterogeneous traffic scenarios.

We consider the quantitative group testing problem where the objective is to identify defective items in a given population based on results of tests performed on subsets of the population. Under the quantitative group testing model, the result of each test reveals the number of defective items in the tested group. The minimum number of tests achievable by nested test plans was established by Aigner and Schughart in 1985 within a minimax framework. The optimal nested test plan offering this performance, however, was not obtained. In this paper, we establish the optimal nested test plan in a closed form. This optimal nested test plan is also order optimal among all test plans as the population size approaches infinity. Using heavy-hitter detection as a case study, we show via simulation examples orders of magnitude improvement of the group testing approach over two prevailing sampling-based approaches in detection accuracy and counter consumption. Other applications include anomaly detection and wideband spectrum sensing in cognitive radio systems.

A key requirement for network management is the accurate and reliable monitoring of relevant network characteristics. In today's large-scale networks, this is a challenging task due to the scarcity of network measurement resources and the hard constraints that this imposes. This paper proposes a new framework, called SNIPER, which leverages the flexibility provided by Software-Defined Networking (SDN) to design the optimal observation or measurement matrix that can lead to the best achievable estimation accuracy using Matrix Completion (MC) techniques. To cope with the complexity of designing large-scale optimal observation matrices, we use the Evolutionary Optimization Algorithms (EOA) which directly target the ultimate estimation accuracy as the optimization objective function. We evaluate the performance of SNIPER using both synthetic and real network measurement traces from different network topologies and by considering two main applications for per-flow size and delay estimations. Our results show that SNIPER can be applied to a variety of network performance measurements under hard resource constraints. For example, by measuring only 8.8% of all per-flow path delays in Harvard network [1], congested paths can be detected with probability of 0.94. To demonstrate the feasibility of our framework, we also have implemented a prototype of SNIPER in Mininet.

In real traffic networks, travellers’ route choice is affected by traffic control strategies. In this research, we capture the interaction between travellers’ route choice and traffic signal control in a coherent framework. For travellers’ route choice, a VANET (Vehicular Ad hoc NETwork) is considered, where travellers have access to the real-time traffic information through V2V/V2I (Vehicle to Vehicle/Vehicle to Infrastructure) infrastructures and make route choice decisions at each intersection using hyper-path trees. We test our algorithm and control strategy by simulation in OmNet++ (A network communication simulator) and SUMO (Simulation of Urban MObility) under several scenarios. The simulation results show that with the proposed dynamic routing, the overall travel cost significantly decreases. It is also shown that the proposed adaptive signal control reduces the average delay effectively, as well as reduces the fluctuation of the average speed within the whole network.

The rise of location-based services has enabled many opportunities for content service providers to optimize the content delivery to user's wireless devices based on her location. Since the sharing precise location remains a major privacy concern among the users, certain location-based services rely on contextual location (e.g. residence, work, etc.) as opposed to acquiring user's exact physical location. In this paper, we present PACL (Privacy-Aware Contextual Localizer) model, which can learn user's contextual location just by passively monitoring user's network traffic. PACL can discern a set of vital attributes (statistical and application-based) from user's network traffic, and predict user's contextual location with a very high accuracy. We design and evaluate PACL using real-world network traces of over 1700 users with over 100GB of total data. Our results show that PACL, when built using the Bayesian Network machine learning algorithm, can predict user's contextual location with the accuracy of around 89%.