Search

The under-5 mortality rate (U5MR), a critical health indicator, is typically estimated from household surveys in lower and middle income countries. Spatio-temporal disaggregation of household survey data can lead to highly variable estimates of U5MR, necessitating the usage of smoothing models which borrow information across space and time. The assumptions of common smoothing models may be unrealistic when certain time periods or regions are expected to have shocks in mortality relative to their neighbors, which can lead to oversmoothing of U5MR estimates. In this paper, we develop a spatial and temporal smoothing approach based on Gaussian Markov random field models which incorporate knowledge of these expected shocks in mortality. We demonstrate the potential for these models to improve upon alternatives not incorporating knowledge of expected shocks in a simulation study. We apply these models to estimate U5MR in Rwanda at the national level from 1985-2019, a time period which includes the Rwandan civil war and genocide., Comment: 59 pages

Robust and reliable anonymization of chest radiographs constitutes an essential step before publishing large datasets of such for research purposes. The conventional anonymization process is carried out by obscuring personal information in the images with black boxes and removing or replacing meta-information. However, such simple measures retain biometric information in the chest radiographs, allowing patients to be re-identified by a linkage attack. Therefore, there is an urgent need to obfuscate the biometric information appearing in the images. We propose the first deep learning-based approach (PriCheXy-Net) to targetedly anonymize chest radiographs while maintaining data utility for diagnostic and machine learning purposes. Our model architecture is a composition of three independent neural networks that, when collectively used, allow for learning a deformation field that is able to impede patient re-identification. Quantitative results on the ChestX-ray14 dataset show a reduction of patient re-identification from 81.8% to 57.7% (AUC) after re-training with little impact on the abnormality classification performance. This indicates the ability to preserve underlying abnormality patterns while increasing patient privacy. Lastly, we compare our proposed anonymization approach with two other obfuscation-based methods (Privacy-Net, DP-Pix) and demonstrate the superiority of our method towards resolving the privacy-utility trade-off for chest radiographs., Comment: Accepted at MICCAI 2023

Estimating the true mortality burden of COVID-19 for every country in the world is a difficult, but crucial, public health endeavor. Attributing deaths, direct or indirect, to COVID-19 is problematic. A more attainable target is the "excess deaths", the number of deaths in a particular period, relative to that expected during "normal times", and we estimate this for all countries on a monthly time scale for 2020 and 2021. The excess mortality requires two numbers, the total deaths and the expected deaths, but the former is unavailable for many countries, and so modeling is required for these countries. The expected deaths are based on historic data and we develop a model for producing expected estimates for all countries and we allow for uncertainty in the modeled expected numbers when calculating the excess. We describe the methods that were developed to produce the World Health Organization (WHO) excess death estimates. To achieve both interpretability and transparency we developed a relatively simple overdispersed Poisson count framework, within which the various data types can be modeled. We use data from countries with national monthly data to build a predictive log-linear regression model with time-varying coefficients for countries without data. For a number of countries, subnational data only are available, and we construct a multinomial model for such data, based on the assumption that the fractions of deaths in sub-regions remain approximately constant over time. Based on our modeling, the point estimate for global excess mortality, over 2020-2021, is 14.9 million, with a 95% credible interval of (13.3, 16.6) million. This leads to a point estimate of the ratio of excess deaths to reported COVID-19 deaths of 2.75, which is a huge discrepancy.

Merging datafiles containing information on overlapping sets of entities is a challenging task in the absence of unique identifiers, and is further complicated when some entities are duplicated in the datafiles. Most approaches to this problem have focused on linking two files assumed to be free of duplicates, or on detecting which records in a single file are duplicates. However, it is common in practice to encounter scenarios that fit somewhere in between or beyond these two settings. We propose a Bayesian approach for the general setting of multifile record linkage and duplicate detection. We use a novel partition representation to propose a structured prior for partitions that can incorporate prior information about the data collection processes of the datafiles in a flexible manner, and extend previous models for comparison data to accommodate the multifile setting. We also introduce a family of loss functions to derive Bayes estimates of partitions that allow uncertain portions of the partitions to be left unresolved. The performance of our proposed methodology is explored through extensive simulations. Code implementing the methodology is available at https://github.com/aleshing/multilink ., Comment: 63 pages

Chest radiography is the most common radiographic examination performed in daily clinical practice for the detection of various heart and lung abnormalities. The large amount of data to be read and reported, with more than 100 studies per day for a single radiologist, poses a challenge in consistently maintaining high interpretation accuracy. The introduction of large-scale public datasets has led to a series of novel systems for automated abnormality classification. However, the labels of these datasets were obtained using natural language processed medical reports, yielding a large degree of label noise that can impact the performance. In this study, we propose novel training strategies that handle label noise from such suboptimal data. Prior label probabilities were measured on a subset of training data re-read by 4 board-certified radiologists and were used during training to increase the robustness of the training model to the label noise. Furthermore, we exploit the high comorbidity of abnormalities observed in chest radiography and incorporate this information to further reduce the impact of label noise. Additionally, anatomical knowledge is incorporated by training the system to predict lung and heart segmentation, as well as spatial knowledge labels. To deal with multiple datasets and images derived from various scanners that apply different post-processing techniques, we introduce a novel image normalization strategy. Experiments were performed on an extensive collection of 297,541 chest radiographs from 86,876 patients, leading to a state-of-the-art performance level for 17 abnormalities from 2 datasets. With an average AUC score of 0.880 across all abnormalities, our proposed training strategies can be used to significantly improve performance scores., Comment: Accepted in Medical Image Analysis (MedIA). arXiv admin note: text overlap with arXiv:1905.06362

With the rise and ever-increasing potential of deep learning techniques in recent years, publicly available medical datasets became a key factor to enable reproducible development of diagnostic algorithms in the medical domain. Medical data contains sensitive patient-related information and is therefore usually anonymized by removing patient identifiers, e.g., patient names before publication. To the best of our knowledge, we are the first to show that a well-trained deep learning system is able to recover the patient identity from chest X-ray data. We demonstrate this using the publicly available large-scale ChestX-ray14 dataset, a collection of 112,120 frontal-view chest X-ray images from 30,805 unique patients. Our verification system is able to identify whether two frontal chest X-ray images are from the same person with an AUC of 0.9940 and a classification accuracy of 95.55%. We further highlight that the proposed system is able to reveal the same person even ten and more years after the initial scan. When pursuing a retrieval approach, we observe an mAP@R of 0.9748 and a precision@1 of 0.9963. Furthermore, we achieve an AUC of up to 0.9870 and a precision@1 of up to 0.9444 when evaluating our trained networks on external datasets such as CheXpert and the COVID-19 Image Data Collection. Based on this high identification rate, a potential attacker may leak patient-related information and additionally cross-reference images to obtain more information. Thus, there is a great risk of sensitive content falling into unauthorized hands or being disseminated against the will of the concerned patients. Especially during the COVID-19 pandemic, numerous chest X-ray datasets have been published to advance research. Therefore, such data may be vulnerable to potential attacks by deep learning-based re-identification algorithms., Comment: Published in Scientific Reports

The problem of estimating the size of a population based on a subset of individuals observed across multiple data sources is often referred to as capture-recapture or multiple-systems estimation. This is fundamentally a missing data problem, where the number of unobserved individuals represents the missing data. As with any missing data problem, multiple-systems estimation requires users to make an untestable identifying assumption in order to estimate the population size from the observed data. If an appropriate identifying assumption cannot be found for a data set, no estimate of the population size should be produced based on that data set, as models with different identifying assumptions can produce arbitrarily different population size estimates -- even with identical observed data fits. Approaches to multiple-systems estimation often do not explicitly specify identifying assumptions. This makes it difficult to decouple the specification of the model for the observed data from the identifying assumption and to provide justification for the identifying assumption. We present a re-framing of the multiple-systems estimation problem that leads to an approach which decouples the specification of the observed-data model from the identifying assumption, and discuss how common models fit into this framing. This approach takes advantage of existing software and facilitates various sensitivity analyses. We demonstrate our approach in a case study estimating the number of civilian casualties in the Kosovo war. Code used to produce this manuscript is available at https://github.com/aleshing/central-role-of-identifying-assumptions., Comment: 58 pages. The material presented in Appendix A previously appeared in an unpublished preprint written by the first author: arXiv:2008.09865

Latent class models have recently become popular for multiple-systems estimation in human rights applications. However, it is currently unknown when a given family of latent class models is identifiable in this context. We provide necessary and sufficient conditions on the number of latent classes needed for a family of latent class models to be identifiable. Along the way we provide a mechanism for verifying identifiability in a class of multiple-systems estimation models that allow for individual heterogeneity., Comment: 8 pages

Chest X-ray (CXR) is the most common examination for fast detection of pulmonary abnormalities. Recently, automated algorithms have been developed to classify multiple diseases and abnormalities in CXR scans. However, because of the limited availability of scans containing nodules and the subtle properties of nodules in CXRs, state-of-the-art methods do not perform well on nodule classification. To create additional data for the training process, standard augmentation techniques are applied. However, the variance introduced by these methods are limited as the images are typically modified globally. In this paper, we propose a method for local feature augmentation by extracting local nodule features using a generative inpainting network. The network is applied to generate realistic, healthy tissue and structures in patches containing nodules. The nodules are entirely removed in the inpainted representation. The extraction of the nodule features is processed by subtraction of the inpainted patch from the nodule patch. With arbitrary displacement of the extracted nodules in the lung area across different CXR scans and further local modifications during training, we significantly increase the nodule classification performance and outperform state-of-the-art augmentation methods., Comment: Accepted at MICCAI MLMI 2020

Radar for indoor monitoring is an emerging area of research and development, covering and supporting different health and wellbeing applications of smart homes, assisted living, and medical diagnosis. We report on a successful RF sensing system for home monitoring applications. The system recognizes Activities of Daily Living(ADL) and detects unique motion characteristics, using data processing and training algorithms. We also examine the challenges of continuously monitoring various human activities which can be categorized into translation motions (active mode) and in-place motions (resting mode). We use the range-map, offered by a range-Doppler radar, to obtain the transition time between these two categories, characterized by changing and constant range values, respectively. This is achieved using the Radon transform that identifies straight lines of different slopes in the range-map image. Over the in-place motion time intervals, where activities have insignificant or negligible range swath, power threshold of the radar return micro-Doppler signatures,which is employed to define the time-spans of individual activities with insignificant or negligible range swath. Finding both the transition times and the time-spans of the different motions leads to improved classifications, as it avoids decisions rendered over time windows covering mixed activities., Comment: 12 pages

We consider radar classifications of Activities of Daily Living (ADL) which can prove beneficial in fall detection, analysis of daily routines, and discerning physical and cognitive human conditions. We focus on contiguous motion classifications which follow and commensurate with the human ethogram of possible motion sequences. Contiguous motions can be closely connected with no clear time gap separations. In the proposed motion classification approach, we utilize the Radon transform applied to the radar range-map to detect the translation motion, whereas an energy detector is used to provide the onset and offset times of in-place motions, such as sitting down and standing up. It is shown that motion classifications give different results when performed forward and backward in time. The number of classes, thereby classification rates, considered by a classifier, is made variable depending on the current motion state and the possible transitioning activities in and out of the state. Motion examples are provided to delineate the performance of the proposed approach under typical sequences of human motions., Comment: Master Thesis

The current accessibility to large medical datasets for training convolutional neural networks is tremendously high. The associated dataset labels are always considered to be the real "ground truth". However, the labeling procedures often seem to be inaccurate and many wrong labels are integrated. This may have fatal consequences on the performance of both training and evaluation. In this paper, we show the impact of label noise in the training set on a specific medical problem based on chest X-ray images. With a simple one-class problem, the classification of tuberculosis, we measure the performance on a clean evaluation set when training with label-corrupt data. We develop a method to compete with incorrectly labeled data during training by randomly attacking labels on individual epochs. The network tends to be robust when flipping correct labels for a single epoch and initiates a good step to the optimal minimum on the error surface when flipping noisy labels. On a baseline with an AUC (Area under Curve) score of 0.924, the performance drops to 0.809 when 30% of our training data is misclassified. With our approach the baseline performance could almost be maintained, the performance raised to 0.918., Comment: Accepted at BVM 2020

We perform classification of activities of daily living (ADL) using a Frequency-Modulated Continuous Waveform (FMCW) radar. In particular, we consider contiguous motions that are inseparable in time. Both the micro-Doppler signature and range-map are used to determine transitions from translation (walking) to in-place motions and vice versa, as well as to provide motion onset and the offset times. The possible classes of activities post and prior to the translation motion can be separately handled by forward and background classifiers. The paper describes ADL in terms of states and transitioning actions, and sets a framework to deal with separable and inseparable contiguous motions. It is shown that considering only the physically possible classes of motions stemming from the current motion state improves classification rates compared to incorporating all ADL for any given time.

The interpretation of chest radiographs is an essential task for the detection of thoracic diseases and abnormalities. However, it is a challenging problem with high inter-rater variability and inherent ambiguity due to inconclusive evidence in the data, limited data quality or subjective definitions of disease appearance. Current deep learning solutions for chest radiograph abnormality classification are typically limited to providing probabilistic predictions, relying on the capacity of learning models to adapt to the high degree of label noise and become robust to the enumerated causal factors. In practice, however, this leads to overconfident systems with poor generalization on unseen data. To account for this, we propose an automatic system that learns not only the probabilistic estimate on the presence of an abnormality, but also an explicit uncertainty measure which captures the confidence of the system in the predicted output. We argue that explicitly learning the classification uncertainty as an orthogonal measure to the predicted output, is essential to account for the inherent variability characteristic of this data. Experiments were conducted on two datasets of chest radiographs of over 85,000 patients. Sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC, e.g., by 8% to 0.91 with an expected rejection rate of under 25%. Eliminating training samples using uncertainty-driven bootstrapping, enables a significant increase in robustness and accuracy. In addition, we present a multi-reader study showing that the predictive uncertainty is indicative of reader errors., Comment: Accepted for presentation at MICCAI 2019