arXiv subjects

Gari D. Clifford

Publications and source records attributed to Gari D. Clifford.

At least 37 records · Page 2Linked to original sources

arXiv2024

Benchmarking changepoint detection algorithms on cardiac time series

The pattern of state changes in a biomedical time series can be related to health or disease. This work presents a principled approach for selecting a changepoint detection algorithm for a specific task, such as disease classification. Eight key algorithms were compared, and the performance of each algorithm was evaluated as a function of temporal tolerance, noise, and abnormal conduction (ectopy) on realistic artificial cardiovascular time series data. All algorithms were applied to real data (cardiac time series of 22 patients with REM-behavior disorder (RBD) and 15 healthy controls) using the parameters selected on artificial data. Finally, features were derived from the detected changepoints to classify RBD patients from healthy controls using a K-Nearest Neighbors approach. On artificial data, Modified Bayesian Changepoint Detection algorithm provided superior positive predictive value for state change identification while Recursive Mean Difference Maximization (RMDM) achieved the highest true positive rate. For the classification task, features derived from the RMDM algorithm provided the highest leave one out cross validated accuracy of 0.89 and true positive rate of 0.87. Automatically detected changepoints provide useful information about subject's physiological state which cannot be directly observed. However, the choice of change point detection algorithm depends on the nature of the underlying data and the downstream application, such as a classification task. This work represents the first time change point detection algorithms have been compared in a meaningful way and utilized in a classification task, which demonstrates the effect of changepoint algorithm choice on application performance.

cs.LG↗

arXiv2024

ECG-Image-Kit: A Synthetic Image Generation Toolbox to Facilitate Deep Learning-Based Electrocardiogram Digitization

Cardiovascular diseases are a major cause of mortality globally, and electrocardiograms (ECGs) are crucial for diagnosing them. Traditionally, ECGs are printed on paper. However, these printouts, even when scanned, are incompatible with advanced ECG diagnosis software that require time-series data. Digitizing ECG images is vital for training machine learning models in ECG diagnosis and to leverage the extensive global archives collected over decades. Deep learning models for image processing are promising in this regard, although the lack of clinical ECG archives with reference time-series data is challenging. Data augmentation techniques using realistic generative data models provide a solution. We introduce ECG-Image-Kit, an open-source toolbox for generating synthetic multi-lead ECG images with realistic artifacts from time-series data. The tool synthesizes ECG images from real time-series data, applying distortions like text artifacts, wrinkles, and creases on a standard ECG paper background. As a case study, we used ECG-Image-Kit to create a dataset of 21,801 ECG images from the PhysioNet QT database. We developed and trained a combination of a traditional computer vision and deep neural network model on this dataset to convert synthetic images into time-series data for evaluation. We assessed digitization quality by calculating the signal-to-noise ratio (SNR) and compared clinical parameters like QRS width, RR, and QT intervals recovered from this pipeline, with the ground truth extracted from ECG time-series. The results show that this deep learning pipeline accurately digitizes paper ECGs, maintaining clinical parameters, and highlights a generative approach to digitization. This toolbox currently supports data augmentation for the 2024 PhysioNet Challenge, focusing on digitizing and classifying paper ECG images.

cs.CV↗

arXiv2024

A Data-Driven Gaussian Process Filter for Electrocardiogram Denoising

Objective: Gaussian Processes (GP)-based filters, which have been effectively used for various applications including electrocardiogram (ECG) filtering can be computationally demanding and the choice of their hyperparameters is typically ad hoc. Methods: We develop a data-driven GP filter to address both issues, using the notion of the ECG phase domain -- a time-warped representation of the ECG beats onto a fixed number of samples and aligned R-peaks, which is assumed to follow a Gaussian distribution. Under this assumption, the computation of the sample mean and covariance matrix is simplified, enabling an efficient implementation of the GP filter in a data-driven manner, with no ad hoc hyperparameters. The proposed filter is evaluated and compared with a state-of-the-art wavelet-based filter, on the PhysioNet QT Database. The performance is evaluated by measuring the signal-to-noise ratio (SNR) improvement of the filter at SNR levels ranging from -5 to 30dB, in 5dB steps, using additive noise. For a clinical evaluation, the error between the estimated QT-intervals of the original and filtered signals is measured and compared with the benchmark filter. Results: It is shown that the proposed GP filter outperforms the benchmark filter for all the tested noise levels. It also outperforms the state-of-the-art filter in terms of QT-interval estimation error bias and variance. Conclusion: The proposed GP filter is a versatile technique for preprocessing the ECG in clinical and research applications, is applicable to ECG of arbitrary lengths and sampling frequencies, and provides confidence intervals for its performance.

eess.SP↗

arXiv2024

Point-of-Care Real-Time Signal Quality for Fetal Doppler Ultrasound Using a Deep Learning Approach

In this study, we present a deep learning framework designed to integrate with our previously developed system that facilitates large-scale 1D fetal Doppler data collection, aiming to enhance data quality. This system, tailored for traditional Indigenous midwives in low-resource communities, leverages a cost-effective Android phone to improve the quality of recorded signals. We have shown that the Doppler data can be used to identify fetal growth restriction, hypertension, and other concerning issues during pregnancy. However, the quality of the signal is dependent on many factors, including radio frequency interference, position of the fetus, maternal body habitus, and usage of the Doppler by the birth attendants. In order to provide instant feedback to allow correction of the data at source, a signal quality metric is required that can run in real-time on the mobile phone. In this study, 191 DUS signals with durations mainly in the range between 5 to 10 minutes were evaluated for quality and classified into five categories: Good, Poor, (Radiofrequency) Interference, Talking, and Silent, at a resolution of 3.75 seconds. A deep neural network was trained on each 3.75-second segment from these recordings and validated using five-fold cross-validation. An average micro F1 = 97.4\% and macro F1 = 94.2\% were achieved, with F1 = 99.2\% for `Good' quality data. These results indicate that the algorithm, which will now be implemented in the midwives' app, should allow a significant increase in the quality of data at the time of capture.

eess.SP↗

arXiv2023

A Survey on Blood Pressure Measurement Technologies: Addressing Potential Sources of Bias

Regular blood pressure (BP) monitoring in clinical and ambulatory settings plays a crucial role in the prevention, diagnosis, treatment, and management of cardiovascular diseases. Recently, the widespread adoption of ambulatory BP measurement devices has been driven predominantly by the increased prevalence of hypertension and its associated risks and clinical conditions. Recent guidelines advocate for regular BP monitoring as part of regular clinical visits or even at home. This increased utilization of BP measurement technologies has brought up significant concerns, regarding the accuracy of reported BP values across settings. In this survey, focusing mainly on cuff-based BP monitoring technologies, we highlight how BP measurements can demonstrate substantial biases and variances due to factors such as measurement and device errors, demographics, and body habitus. With these inherent biases, the development of a new generation of cuff-based BP devices which use artificial-intelligence (AI) has significant potential. We present future avenues where AI-assisted technologies can leverage the extensive clinical literature on BP-related studies together with the large collections of BP records available in electronic health records. These resources can be combined with machine learning approaches, including deep learning and Bayesian inference, to remove BP measurement biases and to provide individualized BP-related cardiovascular risk indexes.

physics.med-ph↗

arXiv2023

A Feasibility Study on Indoor Localization and Multi-person Tracking Using Sparsely Distributed Camera Network with Edge Computing

Camera-based activity monitoring systems are becoming an attractive solution for smart building applications with the advances in computer vision and edge computing technologies. In this paper, we present a feasibility study and systematic analysis of a camera-based indoor localization and multi-person tracking system implemented on edge computing devices within a large indoor space. To this end, we deployed an end-to-end edge computing pipeline that utilizes multiple cameras to achieve localization, body orientation estimation and tracking of multiple individuals within a large therapeutic space spanning $1700m^2$, all while maintaining a strong focus on preserving privacy. Our pipeline consists of 39 edge computing camera systems equipped with Tensor Processing Units (TPUs) placed in the indoor space's ceiling. To ensure the privacy of individuals, a real-time multi-person pose estimation algorithm runs on the TPU of the computing camera system. This algorithm extracts poses and bounding boxes, which are utilized for indoor localization, body orientation estimation, and multi-person tracking. Our pipeline demonstrated an average localization error of 1.41 meters, a multiple-object tracking accuracy score of 88.6\%, and a mean absolute body orientation error of 29\degree. These results shows that localization and tracking of individuals in a large indoor space is feasible even with the privacy constrains.

cs.CV↗

arXiv2023

Indoor Localization using Bluetooth and Inertial Motion Sensors in Distributed Edge and Cloud Computing Environment

Spatial navigation of indoor space usage patterns reveals important cues about the cognitive health of individuals. In this work, we present a low-cost, scalable, open-source edge computing system using Bluetooth Low Energy (BLE) and Inertial Measurement Unit sensors (IMU) for tracking indoor movements for a large indoor facility (over 1600 m^2) that was designed to facilitate therapeutic activities for individuals with Mild Cognitive Impairment. The facility is instrumented with 39 edge computing systems with an on-premise fog server, and subjects carry BLE beacon and IMU sensors on-body. We proposed an adaptive trilateration approach that considers the temporal density of hits from the BLE beacon to surrounding edge devices to handle inconsistent coverage of edge devices in large spaces with varying signal strength that leads to intermittent detection of beacons. The proposed BLE-based localization is further enhanced by fusing with an IMU-based tracking method using a dead-reckoning technique. Our experiment results, achieved in a real clinical environment, suggest that an ordinary medical facility can be transformed into a smart space that enables automatic assessment of the individual patients' movements.

cs.HC↗

arXiv2023

Beyond Heart Murmur Detection: Automatic Murmur Grading from Phonocardiogram

Objective: Murmurs are abnormal heart sounds, identified by experts through cardiac auscultation. The murmur grade, a quantitative measure of the murmur intensity, is strongly correlated with the patient's clinical condition. This work aims to estimate each patient's murmur grade (i.e., absent, soft, loud) from multiple auscultation location phonocardiograms (PCGs) of a large population of pediatric patients from a low-resource rural area. Methods: The Mel spectrogram representation of each PCG recording is given to an ensemble of 15 convolutional residual neural networks with channel-wise attention mechanisms to classify each PCG recording. The final murmur grade for each patient is derived based on the proposed decision rule and considering all estimated labels for available recordings. The proposed method is cross-validated on a dataset consisting of 3456 PCG recordings from 1007 patients using a stratified ten-fold cross-validation. Additionally, the method was tested on a hidden test set comprised of 1538 PCG recordings from 442 patients. Results: The overall cross-validation performances for patient-level murmur gradings are 86.3% and 81.6% in terms of the unweighted average of sensitivities and F1-scores, respectively. The sensitivities (and F1-scores) for absent, soft, and loud murmurs are 90.7% (93.6%), 75.8% (66.8%), and 92.3% (84.2%), respectively. On the test set, the algorithm achieves an unweighted average of sensitivities of 80.4% and an F1-score of 75.8%. Conclusions: This study provides a potential approach for algorithmic pre-screening in low-resource settings with relatively high expert screening costs. Significance: The proposed method represents a significant step beyond detection of murmurs, providing characterization of intensity which may provide a enhanced classification of clinical outcomes.

q-bio.QM↗

arXiv2021

Mythological Medical Machine Learning: Boosting the Performance of a Deep Learning Medical Data Classifier Using Realistic Physiological Models

Objective: To determine if a realistic, but computationally efficient model of the electrocardiogram can be used to pre-train a deep neural network (DNN) with a wide range of morphologies and abnormalities specific to a given condition - T-wave Alternans (TWA) as a result of Post-Traumatic Stress Disorder, or PTSD - and significantly boost performance on a small database of rare individuals. Approach: Using a previously validated artificial ECG model, we generated 180,000 artificial ECGs with or without significant TWA, with varying heart rate, breathing rate, TWA amplitude, and ECG morphology. A DNN, trained on over 70,000 patients to classify 25 different rhythms, was modified the output layer to a binary class (TWA or no-TWA, or equivalently, PTSD or no-PTSD), and transfer learning was performed on the artificial ECG. In a final transfer learning step, the DNN was trained and cross-validated on ECG from 12 PTSD and 24 controls for all combinations of using the three databases. Main results: The best performing approach (AUROC = 0.77, Accuracy = 0.72, F1-score = 0.64) was found by performing both transfer learning steps, using the pre-trained arrhythmia DNN, the artificial data and the real PTSD-related ECG data. Removing the artificial data from training led to the largest drop in performance. Removing the arrhythmia data from training provided a modest, but significant, drop in performance. The final model showed no significant drop in performance on the artificial data, indicating no overfitting. Significance: In healthcare, it is common to only have a small collection of high-quality data and labels, or a larger database with much lower quality (and less relevant) labels. The paradigm presented here, involving model-based performance boosting, provides a solution through transfer learning on a large realistic artificial database, and a partially relevant real database.

cs.LG↗

arXiv2021

HRnV-Calc: A software package for heart rate n-variability and heart rate variability analysis

Objective: Heart rate variability (HRV) has been proven to be an important indicator of physiological status for numerous applications. Despite the progress and active developments made in HRV metric research over the last few decades, the representation of the heartbeat sequence upon which HRV is based has received relatively little attention. The recently introduced heart rate n-variability (HRnV) offers an alternative to R-to-R peak interval representations which complements conventional HRV analysis by considering HRV behavior on varying scales. Although HRnV has been shown to improve triage in pilot studies, there is currently no open and standard software to support future research of HRnV and its broader clinical applications. We aimed to develop an open, reliable, and easy to use software package implementing HRnV for further research and improvements of HRnV. This package has been designed to facilitate collaborative investigations between clinicians and researchers to study HRnV in various contexts and applications. Approach: We developed an open-source software, HRnV-Calc, based on the PhysioNet Cardiovascular Signal Toolbox (PCST), which features comprehensive graphical user interfaces (GUIs) for HRnV and HRV analysis. Main results: While preserving the core functionalities and performance of PCST, HRnV-Calc enables step-by-step manual inspection and configuration of HRV and HRnV analysis, so that results can be debugged, easily interpreted, and integrated to downstream applications. Significance: The open-source HRnV-Calc software, an accessible and standardized HRV and HRnV analysis platform, enhances the scope of HRV assessment and is designed to assist in future improvements and applications of HRnV and related research.

cs.CE↗

arXiv2021

Privacy-Preserving Eye-tracking Using Deep Learning

The expanding usage of complex machine learning methods like deep learning has led to an explosion in human activity recognition, particularly applied to health. In particular, as part of a larger body sensor network system, face and full-body analysis is becoming increasingly common for evaluating health status. However, complex models which handle private and sometimes protected data, raise concerns about the potential leak of identifiable data. In this work, we focus on the case of a deep network model trained on images of individual faces. Full-face video recordings taken from 493 individuals undergoing an eye-tracking based evaluation of neurological function were used. Outputs, gradients, intermediate layer outputs, loss, and labels were used as inputs for a deep network with an added support vector machine emission layer to recognize membership in the training data. The inference attack method and associated mathematical analysis indicate that there is a low likelihood of unintended memorization of facial features in the deep learning model. In this study, it is showed that the named model preserves the integrity of training data with reasonable confidence. The same process can be implemented in similar conditions for different models.

cs.CV↗

arXiv2021

An Analysis Of Protected Health Information Leakage In Deep-Learning Based De-Identification Algorithms

The increasing complexity of algorithms for analyzing medical data, including de-identification tasks, raises the possibility that complex algorithms are learning not just the general representation of the problem, but specifics of given individuals within the data. Modern legal frameworks specifically prohibit the intentional or accidental distribution of patient data, but have not addressed this potential avenue for leakage of such protected health information. Modern deep learning algorithms have the highest potential of such leakage due to complexity of the models. Recent research in the field has highlighted such issues in non-medical data, but all analysis is likely to be data and algorithm specific. We, therefore, chose to analyze a state-of-the-art free-text de-identification algorithm based on LSTM (Long Short-Term Memory) and its potential in encoding any individual in the training set. Using the i2b2 Challenge Data, we trained, then analyzed the model to assess whether the output of the LSTM, before the compression layer of the classifier, could be used to estimate the membership of the training data. Furthermore, we used different attacks including membership inference attack method to attack the model. Results indicate that the attacks could not identify whether members of the training data were distinguishable from non-members based on the model output. This indicates that the model does not provide any strong evidence into the identification of the individuals in the training data set and there is not yet empirical evidence it is unsafe to distribute the model for general use.

cs.LG↗

arXiv2021

Late fusion of machine learning models using passively captured interpersonal social interactions and motion from smartphones predicts decompensation in heart failure

Objective: Worldwide, heart failure (HF) is a major cause of morbidity and mortality and one of the leading causes of hospitalization. Early detection of HF symptoms and pro-active management may reduce adverse events. Approach: Twenty-eight participants were monitored using a smartphone app after discharge from hospitals, and each clinical event during the enrollment (N=110 clinical events) was recorded. Motion, social, location, and clinical survey data collected via the smartphone-based monitoring system were used to develop and validate an algorithm for predicting or classifying HF decompensation events (hospitalizations or clinic visit) versus clinic monitoring visits in which they were determined to be compensated or stable. Models based on single modality as well as early and late fusion approaches combining patient-reported outcomes and passive smartphone data were evaluated. Results: The highest AUCPr for classifying decompensation with a late fusion approach was 0.80 using leave one subject out cross-validation. Significance: Passively collected data from smartphones, especially when combined with weekly patient-reported outcomes, may reflect behavioral and physiological changes due to HF and thus could enable prediction of HF decompensation.

eess.SP↗

arXiv2020

Voting of predictive models for clinical outcomes: consensus of algorithms for the early prediction of sepsis from clinical data and an analysis of the PhysioNet/Computing in Cardiology Challenge 2019

Although there has been significant research in boosting of weak learners, there has been little work in the field of boosting from strong learners. This latter paradigm is a form of weighted voting with learned weights. In this work, we consider the problem of constructing an ensemble algorithm from 70 individual algorithms for the early prediction of sepsis from clinical data. We find that this ensemble algorithm outperforms separate algorithms, especially on a hidden test set on which most algorithms failed to generalize.

cs.LG↗

arXiv2020

Deep Sequence Learning for Accurate Gestational Age Estimation from a $\$$25 Doppler Device

Assessing fetal development is usually carried out by techniques such as ultrasound imaging, which is generally unavailable in rural areas due to the high cost, maintenance, skills and training needed to operate the devices effectively. In this work, we propose a low-cost one-dimensional Doppler-based method for estimating gestational age (GA). Doppler time series were collected from 401 pregnancies between 5 and 9 months GA using a smartphone. The proposed model for GA estimation is based on sequence learning by forming a temporally dependent model using a convolutional long-short-term memory network. Time-frequency features are extracted from Doppler signals and regularized before feeding to the network. The overall mean absolute GA error with respect to the last menstrual period was found to be 0.71 month, which outperforms all previous works.

eess.SP↗

arXiv2020

Using Convolutional Variational Autoencoders to Predict Post-Trauma Health Outcomes from Actigraphy Data

Depression and post-traumatic stress disorder (PTSD) are psychiatric conditions commonly associated with experiencing a traumatic event. Estimating mental health status through non-invasive techniques such as activity-based algorithms can help to identify successful early interventions. In this work, we used locomotor activity captured from 1113 individuals who wore a research grade smartwatch post-trauma. A convolutional variational autoencoder (VAE) architecture was used for unsupervised feature extraction from four weeks of actigraphy data. By using VAE latent variables and the participant's pre-trauma physical health status as features, a logistic regression classifier achieved an area under the receiver operating characteristic curve (AUC) of 0.64 to estimate mental health outcomes. The results indicate that the VAE model is a promising approach for actigraphy data analysis for mental health outcomes in long-term studies.

cs.LG↗

arXiv2020

Remote health monitoring and diagnosis in the time of COVID-19

Coronavirus disease (COVID-19) is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that is rapidly spreading across the globe. The clinical spectrum of SARS-CoV-2 pneumonia ranges from mild to critically ill cases and requires early detection and monitoring, within a clinical environment for critical cases and remotely for mild cases. The fear of contamination in clinical environments has led to a dramatic reduction in on-site referrals for routine care. There has also been a perceived need to continuously monitor non-severe COVID- 19 patients, either from their quarantine site at home, or dedicated quarantine locations (e.g., hotels). Thus, the pandemic has driven incentives to innovate and enhance or create new routes for providing healthcare services at distance. In particular, this has created a dramatic impetus to find innovative ways to remotely and effectively monitor patient health status. In this paper we present a short review of remote health monitoring initiatives taken in 19 states during the time of the pandemic. We emphasize in the discussion particular aspects that are common ground for the reviewed states, in particular the future impact of the pandemic on remote health monitoring and consideration on data privacy.

cs.CY↗

arXiv2020

The Future AI in Healthcare: A Tsunami of False Alarms or a Product of Experts?

Recent significant increases in affordable and accessible computational power and data storage have enabled machine learning to provide almost unbelievable classification and prediction performances compared to well-trained humans. There have been some promising (but limited) results in the complex healthcare landscape, particularly in imaging. This promise has led some individuals to leap to the conclusion that we will solve an ever-increasing number of problems in human health and medicine by applying `artificial intelligence' to `big (medical) data'. The scientific literature has been inundated with algorithms, outstripping our ability to review them effectively. Unfortunately, I argue that most, if not all of these publications or commercial algorithms make several fundamental errors. I argue that because everyone (and therefore every algorithm) has blind spots, there are multiple `best' algorithms, each of which excels on different types of patients or in different contexts. Consequently, we should vote many algorithms together, weighted by their overall performance, their independence from each other, and a set of features that define the context (i.e., the features that maximally discriminate between the situations when one algorithm outperforms another). This approach not only provides a better performing classifier or predictor but provides confidence intervals so that a clinician can judge how to respond to an alert. Moreover, I argue that a sufficient number of (mostly) independent algorithms that address the same problem can be generated through a large international competition/challenge, lasting many months and define the conditions for a successful event. Finally, I propose introducing the requirement for major grantees to run challenges in the final year of funding to maximize the value of research and select a new generation of grantees.

cs.CY↗