4
BackgroundLarge curated data sets are required to leverage speech-based tools in health care. These are costly to produce, resulting in increased interest in data sharing. As speech can potentially identify speakers (ie, voiceprints), sharing recordings raises privacy concerns. This is especially relevant when working with patient data protected under the Health Insurance Portability and Accountability Act.ObjectiveWe aimed to determine the reidentification risk for speech recordings, without reference to demographics or metadata, in clinical data sets considering both the size of the search space (ie, the number of comparisons that must be considered when reidentifying) and the nature of the speech recording (ie, the type of speech task).MethodsUsing a state-of-the-art speaker identification model, we modeled an adversarial attack scenario in which an adversary uses a large data set of identified speech (hereafter, the known set) to reidentify as many unknown speakers in a shared data set (hereafter, the unknown set) as possible. We first considered the effect of search space size by attempting reidentification with various sizes of known and unknown sets using VoxCeleb, a data set with recordings of natural, connected speech from >7000 healthy speakers. We then repeated these tests with different types of recordings in each set to examine whether the nature of a speech recording influences reidentification risk. For these tests, we used our clinical data set composed of recordings of elicited speech tasks from 941 speakers.ResultsWe found that the risk was inversely related to the number of comparisons an adversary must consider (ie, the search space), with a positive linear correlation between the number of false acceptances (FAs) and the number of comparisons (r=0.69; P<.001). The true acceptances (TAs) stayed relatively stable, and the ratio between FAs and TAs rose from 0.02 at 1 × 105 comparisons to 1.41 at 6 × 106 comparisons, with a near 1:1 ratio at the midpoint of 3 × 106 comparisons. In effect, risk was high for a small search space but dropped as the search space grew. We also found that the nature of a speech recording influenced reidentification risk, with nonconnected speech (eg, vowel prolongation: FA/TA=98.5; alternating motion rate: FA/TA=8) being harder to identify than connected speech (eg, sentence repetition: FA/TA=0.54) in cross-task conditions. The inverse was mostly true in within-task conditions, with the FA/TA ratio for vowel prolongation and alternating motion rate dropping to 0.39 and 1.17, respectively.ConclusionsOur findings suggest that speaker identification models can be used to reidentify participants in specific circumstances, but in practice, the reidentification risk appears small. The variation in risk due to search space size and type of speech task provides actionable recommendations to further increase participant privacy and considerations for policy regarding public release of speech recordings.
Loading PDF
SHARE dataset - for the article "Inequalities in Utilization of Institutional Care Among Older People in Estonia"
The SHARE wave 6 dataset includes the variables necessary to produce the results included into the article "Inequalities in Utilization of Institutional Care Among Older People in Estonia"
Read more3Databases, Core: Sociology
Databases, Core: Sociology
93Design and Evaluation of Metaphor Processing Systems
System design and evaluation methodologies receive significant attention in natural language processing (NLP), with the systems typically being evaluated on a common task and against shared data sets. This enables direct system comparison and facilitates progress in the field. However, computational work on metaphor is considerably more fragmented than similar research efforts in other areas of NLP and semantics. Recent years have seen a growing interest in computational modeling of metaphor, with many new statistical techniques opening routes for improving system accuracy and robustness. However, the lack of a common task definition, shared data set, and evaluation strategy makes the methods hard to compare, and thus hampers our progress as a community in this area. The goal of this article is to review the system features and evaluation strategies that have been proposed for the metaphor processing task, and to analyze their benefits and downsides, with the aim of identifying the desired properties of metaphor processing systems and a set of requirements for their evaluation.
Read more8Cancer Radiomic and Perfusion Imaging Automated Framework: Validation on Musculoskeletal Tumors.
Limitations from commercial software applications prevent the implementation of a robust and cost-efficient high-throughput cancer imaging radiomic feature extraction and perfusion analysis workflow. This study aimed to develop and validate a cancer research computational solution using open-source software for vendor- and sequence-neutral high-throughput image processing and feature extraction. The Cancer Radiomic and Perfusion Imaging (CARPI) automated framework is a Python-based software application that is vendor- and sequence-neutral. CARPI uses contour files generated using an application of the user's choice and performs automated radiomic feature extraction and perfusion analysis. This workflow solution was validated using two clinical data sets, one consisted of 40 pelvic chondrosarcomas and 42 sacral chordomas with a total of 82 patients, and a second data set consisted of 26 patients with undifferentiated pleomorphic sarcoma (UPS) imaged at multiple points during presurgical treatment. Three hundred sixteen volumetric contour files were processed using CARPI. The application automatically extracted 107 radiomic features from multiple magnetic resonance imaging sequences and seven semiquantitative perfusion parameters from time-intensity curves. Statistically significant differences (P < .00047) were found in 18 of 107 radiomic features in chordoma versus chondrosarcoma, including six first-order and 12 high-order features. In UPS postradiation, the apparent diffusion coefficient mean increased 41% in good responders (P = .0017), while firstorder_10Percentile (P = .0312) was statistically significant between good and partial/nonresponders. The CARPI processing of two clinical validation data sets confirmed the software application's ability to differentiate between different types of tumors and help predict patient response to treatment on the basis of radiomic features. Benchmark comparison with five similar open-source solutions demonstrated the advantages of CARPI in the automated perfusion feature extraction, relational database generation, and graphic report export features, although lacking a user-friendly graphical user interface and predictive model building.
Read more4Orthogonality defect and reduced search-space size for solving integer least-squares problems
In the context of ambiguity resolution (AR) of global navigation satellite systems (GNSS), decorrelation among entries of an ambiguity vector, integer ambiguity search, and ambiguity validations are three standard procedures for solving integer least-squares problems. This paper contributes to AR issues from three aspects. Firstly, the orthogonality defect is introduced as a new measure of the performance of ambiguity decorrelation methods and compared with the decorrelation number and with the condition number, which are currently used as the judging criterion to measure the correlation of ambiguity variance---covariance matrix. Numerically, the orthogonality defect demonstrates slightly better performance as a measure of the correlation between decorrelation impact and computational efficiency than the condition number measure. Secondly, the paper examines the relationship of the decorrelation number, the condition number, the orthogonality defect, and the size of the ambiguity search space with the ambiguity search candidates and search nodes. The size of the ambiguity search space can be properly estimated if the ambiguity matrix is decorrelated well, which is shown to be a significant parameter in the ambiguity search progress. Thirdly, a new ambiguity resolution scheme is proposed to improve ambiguity search efficiency through the control of the size of the ambiguity search space. The new AR scheme combines the LAMBDA search and validation procedures together, which results in a much smaller size of the search space and higher computational efficiency while retaining the same AR validation outcomes. In fact, the new scheme can deal with the case there are only one candidate, while the existing search methods require at least two candidates. If there are more than one candidate, the new scheme turns to the usual ratio-test procedure. Experimental results indicate that this combined method can indeed improve ambiguity search efficiency for both the single constellation and dual constellations, respectively, showing the potential for processing high-dimension integer parameters in multi-GNSS environment.
Read more
132Knowledge Mining from Clinical Datasets Using Rough Sets and Backpropagation Neural Network
The availability of clinical datasets and knowledge mining methodologies encourages the researchers to pursue research in extracting knowledge from clinical datasets. Different data mining techniques have been used for mining rules, and mathematical models have been developed to assist the clinician in decision making. The objective of this research is to build a classifier that will predict the presence or absence of a disease by learning from the minimal set of attributes that has been extracted from the clinical dataset. In this work rough set indiscernibility relation method with backpropagation neural network (RS-BPNN) is used. This work has two stages. The first stage is handling of missing values to obtain a smooth data set and selection of appropriate attributes from the clinical dataset by indiscernibility relation method. The second stage is classification using backpropagation neural network on the selected reducts of the dataset. The classifier has been tested with hepatitis, Wisconsin breast cancer, and Statlog heart disease datasets obtained from the University of California at Irvine (UCI) machine learning repository. The accuracy obtained from the proposed method is 97.3%, 98.6%, and 90.4% for hepatitis, breast cancer, and heart disease, respectively. The proposed system provides an effective classification model for clinical datasets.
Read more1Economic Grand Rounds: Financial Burden of Medical Care and Risk of Forgoing Care Among Europeans With Depressive Symptoms
Little is known about the financial burden of individuals with depressive symptoms. This study explored that burden, using data from the Survey of Health, Ageing, and Retirement in Europe. To assess the association between depressive symptoms and the individuals' financial burden for medical care and whether they forwent medical care because of costs, logistic regressions were performed that adjusted for age, gender, marital status, education, and chronic diseases. A total of 16,696 noninstitutionalized individuals aged 50-79 years were included in the study. Individuals with depressive symptoms and those without such symptoms bore a similar financial burden. However, individuals with depressive symptoms were at increased risk of forgoing care because of costs, which may worsen their health and financial situation
Read more18Inverse tracing of fire source in a single room based on CFD simulation and deep learning
Inverse tracing of fire source in a single room based on CFD simulation and deep learning
37On the sensitivity of the location, size and shape of the GPS ambiguity search space to certain changes in the stochastic model
In this contribution we analyse in a qualitative sense for the geometry-free model the dependency of the location, the size and the shape of the ambiguity search space on different factors of the stochastic model. For this purpose a rather general stochastic model is used. It includes time-correlation, cross-correlation, satellite elevation dependency and the use of an a priori weighted ionospheric model, having the ionosphere-fixed model and the ionosphere-float model as special cases. It is shown that the location is invariant for changes in the cofactor matrix of the phase observables. This also holds true for the cofactor matrix of the code observables in the ionosphere-float case. As for time-correlation and satellite elevation dependency, it is shown that they only affect the size of the search space, but not its shape and orientation. It is also shown that the least-squares ambiguities, their variance matrix and its determinant, for, respectively, the ionosphere-fixed model, the ionosphere-float model and the ionosphere-weighted model, are all related through the same scalar weighted mean, the weight of which is governed by the variance ratio of the ionospheric delays and the code observables. A closed-form expression is given for the area of the search space in which all contributing factors are easily recognized. From it one can infer by how much the area gets blown up when the ionospheric spatial decorrelation increases. This multiplication factor is largest when one switches from the ionosphere-fixed model to the ionosphere-float model, in which case it is approximately equal to the ratio of the standard deviation of phase with that of code. The area gives an indication of the number of grid points inside the search space.
Read more168What makes some problems really hard: Explorations in the problem space of difficulty
What makes some problems really hard: Explorations in the problem space of difficulty
1Self-synchronization for spread spectrum audio watermarks after time scale modification
De-synchronizing operations such as insertion, deletion, and warping pose significant challenges for watermarking. Because these operations are not typical for classical communications, watermarking techniques such as spread spectrum can perform poorly. Conversely, specialized synchronization solutions can be challenging to analyze/ optimize. This paper addresses desynchronization for blind spread spectrum watermarks, detected without reference to any unmodified signal, using the robustness properties of short blocks. Synchronization relies on dynamic time warping to search over block alignments to find a sequence with maximum correlation to the watermark. This differs from synchronization schemes that must first locate invariant features of the original signal, or estimate and reverse desynchronization before detection. Without these extra synchronization steps, analysis for the proposed scheme builds on classical SS concepts and allows characterizes the relationship between the size of search space (number of detection alignment tests) and intrinsic robustness (continuous search space region covered by each individual detection test). The critical metrics that determine the search space, robustness, and performance are: time-frequency resolution of the watermarking transform, and blocklength resolution of the alignment. Simultaneous robustness to (a) MP3 compression, (b) insertion/deletion, and (c) time-scale modification is also demonstrated for a practical audio watermarking scheme developed in the proposed framework.
Read more127Assessing Surgical Quality Using Administrative and Clinical Data Sets: A Direct Comparison of the University HealthSystem Consortium Clinical Database and the National Surgical Quality Improvement Program Data Set
The use of "clinical" versus "administrative" data sets for health care quality assessment continues to be debated. This study directly compares the University HealthSystem Consortium Clinical Database (UHC CDB) and the National Surgical Quality Improvement Program (NSQIP) in terms of their assessment of complications and death for 26 322 surgery patients using analyses of variance, correlation, and multivariable logistic regression. The NSQIP had more variables with significant correlation with outcomes. The NSQIP was better at predicting death (c-index 0.94 vs 0.90, P < .05) and complications (c-index 0.78 vs 0.76, P = .07), especially for higher risk patients. The UHC CDB missed and misclassified several major complications. The data sets are similar in their explanatory power relative to outcomes, but the clinical data set is better, particularly at identifying higher risk patients and specific complications. It should prove more useful for initiating and monitoring clinical process improvements because of more clinically relevant variables.
Read more6Accurate Diagnosis of Alzheimer's Disease Using Specific Breath Volatile Organic Compounds.
Whether volatile organic compounds (VOCs) from exhaled breath can be used as a novel biomarker for Alzheimer's disease (AD) diagnosis is unclear. To determine the significantly distinctive VOCs for AD, a total of 970 participants were enrolled, including 60 individuals in data set 1 (AD, 30; controls, 30), 164 individuals in data set 2 (AD, 82; controls, 82), 637 individuals in data set 3 (AD, 31; controls, 606), and 109 individuals in data set 4 (frontotemporal dementia, 19; vascular dementia, 21; Parkinson's disease, 69). The participants in data sets 1, 2, and 4 were from Xiangya Hospital, Central South University. Participants in data set 3 were from a two-year follow-up cohort. VOCs in breath and plasma, neuropsychological scores, plasma p-tau181 levels, metabolites in plasma, and brain functional connectivity were detected. We found that six VOCs were significantly different between the two groups in data set 1 and were verified in data set 2 and data set 3. Ethanol (m/z = 46) and pyrrole (m/z = 67) presented AUC values of 0.907 and 0.895 in data sets 1 and 2 (clinical data sets) and 0.849 and 0.974 in data set 3 (community data set), respectively. The six VOCs were associated with cognitive decline as reflected by neuropsychological tests; five of them were correlated with plasma p-tau181, and these five plasma VOCs were consistently altered as breath VOCs. Correlation between metabolites and five VOCs in plasma was noted, and the five VOCs may originate from blood metabolites. Moreover, four breath VOCs were associated with altered brain connectivity. In conclusion, specific breath VOCs may be used as biomarkers for AD detection.
Read more45Signal quality in cardiorespiratory monitoring
This focus issue of Physiological Measurement follows the 38th Annual International Computing in Cardiology (CinC) Conference, hosted in Hangzhou, China in September 2011 by Zhejiang University. Each year, the NIH-sponsored PhysioNet resource (http://physionet.org/) runs an open competition lasting several months, aimed at encouraging the development of solutions to an unsolved or poorly solved problem in biomedicine, in most cases making use of relevant clinical and experimental data provided freely by PhysioNet. Participants in these annual challenges discuss their diverse approaches to the Challenge problems during dedicated scientific sessions at CinC. The topics of these PhysioNet/CinC Challenges range from physiologic signal processing and analysis to forecasting and modelling clinically important events and processes.
Read more48How We Fall Apart: Similarities of Human Aging in 10 European Countries.
We analyze human aging-understood as health deficit accumulation-for a panel of European individuals, using four waves of the Survey of Health, Aging and Retirement in Europe (SHARE data set) and constructing a health deficit index. Results from log-linear regressions suggest that, on average, elderly European men and women develop approximately 2.5% more health deficits from one birthday to the next. In nonlinear regressions (akin to the Gompertz-Makeham model), however, we find much greater rates of aging and large differences between men and women as well as between countries. Interestingly, these differences follow a particular regularity (akin to the compensation effect of mortality) and suggest an age at which average health deficits converge for men and women and across countries. This age, which may be associated with human life span, is estimated as 102 ± 2.6 years.
Read more
Copyright 2026 Cactus Communications. All rights reserved.
