Recent work has reported that respiratory audio-trained AI classifiers can accurately predict SARS-CoV-2 infection status. Here, we undertake a large-scale study of audio-based AI classifiers, as part of the UK government's pandemic response. We collect a dataset of audio recordings from 67,842 individuals, with linked metadata, of whom 23,514 had positive PCR tests for SARS-CoV-2. In an unadjusted analysis, similar to that in previous works, AI classifiers predict SARS-CoV-2 infection status with high accuracy (ROC-AUC=0.846 However, after matching on measured confounders, such as selfreported symptoms, performance is much weaker (ROC-AUC=0.619 Upon quantifying the utility of audio-based classifiers in practical settings, we find them to be outperformed by predictions based on user-reported symptoms. We make best-practice recommendations for handling recruitment bias, and for assessing audio-based classifiers by their utility in relevant practical settings. Our work provides novel insights into the value of AI audio analysis and the importance of study design and treatment of confounders in AI-enabled diagnostics. The coronavirus disease 2019 (COVID-19) pandemic has been estimated by the World Health Organization (WHO) to have caused 14.9 million excess deaths over the 2020-2021 period (link). Table S1 summarises nine highly cited datasets and corresponding classification performance. Here, we analyse the largest PCR-validated dataset collected to date in the field of audio-based COVID-19 screening (ABCS). We design and specify an analysis plan in advance, to investigate whether using audio-based classifiers can improve the accuracy of COVID-19 screening over using self-reported symptoms. Our contribution is as follows: - We collect a respiratory acoustic dataset of 67,842 individuals with linked PCR test outcomes, including 23,514 who tested positive for COVID-19.

Introduction: Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater. Methods: We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research. Results: We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future. Discussion: ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

An open-ended time series refers to a series of data points indexed in time order without an end. Such a time series can be found everywhere due to the prevalence of Internet of Things. Providing lightweight and real-time anomaly detection for open-ended time series is highly desirable to industry and organizations since it allows immediate response and avoids potential financial loss. In the last few years, several real-time time series anomaly detection approaches have been introduced. However, they might exhaust system resources when they are applied to open-ended time series for a long time. To address this issue, in this paper we propose RePAD2, a lightweight real-time anomaly detection approach for open-ended time series by improving its predecessor RePAD, which is one of the state-of-the-art anomaly detection approaches. We conducted a series of experiments to compare RePAD2 with RePAD and another similar detection approach based on real-world time series datasets, and demonstrated that RePAD2 can address the mentioned resource exhaustion issue while offering comparable detection accuracy and slightly less time consumption.

Detecting Out-of-distribution (OOD) inputs have been a critical issue for neural networks in the open world. However, the unstable behavior of OOD detection along the optimization trajectory during training has not been explored clearly. In this paper, we first find the performance of OOD detection suffers from overfitting and instability during training: 1) the performance could decrease when the training error is near zero, and 2) the performance would vary sharply in the final stage of training. Based on our findings, we propose Average of Pruning (AoP), consisting of model averaging and pruning, to mitigate the unstable behaviors. Specifically, model averaging can help achieve a stable performance by smoothing the landscape, and pruning is certified to eliminate the overfitting by eliminating redundant features. Comprehensive experiments on various datasets and architectures are conducted to verify the effectiveness of our method.

In this paper we define, implement, and investigate a simplicial complex construction for computing persistent homology of Euclidean point cloud data, which we call the Delaunay-Rips complex (DR). Assigning the Vietoris-Rips weights to simplices, DR experiences speed-up in the persistence calculations by only considering simplices that appear in the Delaunay triangulation of the point cloud. We document and compare a Python implementation of DR with other simplicial complex constructions for generating persistence diagrams. By imposing sufficient conditions on point cloud data, we are able to theoretically justify the stability of the persistence diagrams produced using DR. When the Delaunay triangulation of the point cloud changes under perturbations of the points, we prove that DR-produced persistence diagrams exhibit instability. Since we cannot guarantee that real-world data will satisfy our stability conditions, we demonstrate the practical robustness of DR for persistent homology in comparison with other simplicial complexes in machine learning applications. We find in our experiments that using DR for an ML-TDA pipeline performs comparatively well as using other simplicial complex constructions.

The extent to which advanced waveform analysis of non-invasive physiological signals can diagnose levels of hypovolemia remains insufficiently explored. The present study explores the discriminative ability of a deep learning (DL) framework to classify levels of ongoing hypovolemia, simulated via novel dynamic lower body negative pressure (LBNP) model among healthy volunteers. We used a dynamic LBNP protocol as opposed to the traditional model, where LBNP is applied in a predictable step-wise, progressively descending manner. This dynamic LBNP version assists in circumventing the problem posed in terms of time dependency, as in real-life pre-hospital settings, intravascular blood volume may fluctuate due to volume resuscitation. A supervised DL-based framework for ternary classification was realized by segmenting the underlying noninvasive signal and labeling segments with corresponding LBNP target levels. The proposed DL model with two inputs was trained with respective time-frequency representations extracted on waveform segments to classify each of them into blood volume loss: Class 1 (mild); Class 2 (moderate); or Class 3 (severe). At the outset, the latent space derived at the end of the DL model via late fusion among both inputs assists in enhanced classification performance. When evaluated in a 3-fold cross-validation setup with stratified subjects, the experimental findings demonstrated PPG to be a potential surrogate for variations in blood volume with average classification performance, AUROC: 0.8861, AUPRC: 0.8141, $F1$-score:72.16%, Sensitivity:79.06 %, and Specificity:89.21 %. Our proposed DL algorithm on PPG signal demonstrates the possibility of capturing the complex interplay in physiological responses related to both bleeding and fluid resuscitation using this challenging LBNP setup.

We propose FedScore, a privacy-preserving federated learning framework for scoring system generation across multiple sites to facilitate cross-institutional collaborations. The FedScore framework includes five modules: federated variable ranking, federated variable transformation, federated score derivation, federated model selection and federated model evaluation. To illustrate usage and assess FedScore's performance, we built a hypothetical global scoring system for mortality prediction within 30 days after a visit to an emergency department using 10 simulated sites divided from a tertiary hospital in Singapore. We employed a pre-existing score generator to construct 10 local scoring systems independently at each site and we also developed a scoring system using centralized data for comparison. We compared the acquired FedScore model's performance with that of other scoring models using the receiver operating characteristic (ROC) analysis. The FedScore model achieved an average area under the curve (AUC) value of 0.763 across all sites, with a standard deviation (SD) of 0.020. We also calculated the average AUC values and SDs for each local model, and the FedScore model showed promising accuracy and stability with a high average AUC value which was closest to the one of the pooled model and SD which was lower than that of most local models. This study demonstrates that FedScore is a privacy-preserving scoring system generator with potentially good generalizability.

Mitigating algorithmic bias is a critical task in the development and deployment of machine learning models. While several toolkits exist to aid machine learning practitioners in addressing fairness issues, little is known about the strategies practitioners employ to evaluate model fairness and what factors influence their assessment, particularly in the context of text classification. Two common approaches of evaluating the fairness of a model are group fairness and individual fairness. We run a study with Machine Learning practitioners (n=24) to understand the strategies used to evaluate models. Metrics presented to practitioners (group vs. individual fairness) impact which models they consider fair. Participants focused on risks associated with underpredicting/overpredicting and model sensitivity relative to identity token manipulations. We discover fairness assessment strategies involving personal experiences or how users form groups of identity tokens to test model fairness. We provide recommendations for interactive tools for evaluating fairness in text classification.

Deep learning-based models generalize better to unknown data samples after being guided "where to look" by incorporating human perception into training strategies. We made an observation that the entropy of the model's salience trained in that way is lower when compared to salience entropy computed for models training without human perceptual intelligence. Thus the question: does further increase of model's focus, by lowering the entropy of model's class activation map, help in further increasing the performance? In this paper we propose and evaluate several entropy-based new loss function components controlling the model's focus, covering the full range of the level of such control, from none to its "aggressive" minimization. We show, using a problem of synthetic face detection, that improving the model's focus, through lowering entropy, leads to models that perform better in an open-set scenario, in which the test samples are synthesized by unknown generative models. We also show that optimal performance is obtained when the model's loss function blends three aspects: regular classification, low-entropy of the model's focus, and human-guided saliency.

With the swift advancement of deep learning, state-of-the-art algorithms have been utilized in various social situations. Nonetheless, some algorithms have been discovered to exhibit biases and provide unequal results. The current debiasing methods face challenges such as poor utilization of data or intricate training requirements. In this work, we found that the backdoor attack can construct an artificial bias similar to the model bias derived in standard training. Considering the strong adjustability of backdoor triggers, we are motivated to mitigate the model bias by carefully designing reverse artificial bias created from backdoor attack. Based on this, we propose a backdoor debiasing framework based on knowledge distillation, which effectively reduces the model bias from original data and minimizes security risks from the backdoor attack. The proposed solution is validated on both image and structured datasets, showing promising results. This work advances the understanding of backdoor attacks and highlights its potential for beneficial applications. The code for the study can be found at \url{https://anonymous.4open.science/r/DwB-BC07/}.