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.

Machine learning, artificial intelligence, and other modern statistical methods are providing new opportunities to operationalise previously untapped and rapidly growing sources of data for patient benefit. Despite much promising research currently being undertaken, particularly in imaging, the literature as a whole lacks transparency, clear reporting to facilitate replicability, exploration for potential ethical concerns, and clear demonstrations of effectiveness. Among the many reasons why these problems exist, one of the most important (for which we provide a preliminary solution here) is the current lack of best practice guidance specific to machine learning and artificial intelligence. However, we believe that interdisciplinary groups pursuing research and impact projects involving machine learning and artificial intelligence for health would benefit from explicitly addressing a series of questions concerning transparency, reproducibility, ethics, and effectiveness (TREE). The 20 critical questions proposed here provide a framework for research groups to inform the design, conduct, and reporting; for editors and peer reviewers to evaluate contributions to the literature; and for patients, clinicians and policy makers to critically appraise where new findings may deliver patient benefit. Machine learning (ML), artificial intelligence (AI), and other modern statistical methods are providing new opportunities to operationalise previously untapped and rapidly growing sources of data for patient benefit. The potential uses include improving diagnostic accuracy,1 more reliably predicting prognosis,2 targeting treatments,3 and increasing the operational efficiency of health systems.4 Examples of potentially disruptive technology with early promise include image based diagnostic applications of ML/AI, which have shown the most early clinical promise (eg, deep learning based algorithms improving accuracy in diagnosing retinal pathology compared with that of specialist physicians5), or natural language processing used as a tool to extract information from structured and unstructured (that is, free) text embedded in electronic health records.2 Although we are only just …

Gravitational-wave detection strategies are based on a signal analysis technique known as matched filtering. Despite the success of matched filtering, due to its computational cost, there has been recent interest in developing deep convolutional neural networks (CNNs) for signal detection. Designing these networks remains a challenge as most procedures adopt a trial and error strategy to set the hyperparameter values. We propose a new method for hyperparameter optimization based on genetic algorithms (GAs). We compare six different GA variants and explore different choices for the GA-optimized fitness score. We show that the GA can discover high-quality architectures when the initial hyperparameter seed values are far from a good solution as well as refining already good networks. For example, when starting from the architecture proposed by George and Huerta, the network optimized over the 20-dimensional hyperparameter space has 78% fewer trainable parameters while obtaining an 11% increase in accuracy for our test problem. Using genetic algorithm optimization to refine an existing network should be especially useful if the problem context (e.g. statistical properties of the noise, signal model, etc) changes and one needs to rebuild a network. In all of our experiments, we find the GA discovers significantly less complicated networks as compared to the seed network, suggesting it can be used to prune wasteful network structures. While we have restricted our attention to CNN classifiers, our GA hyperparameter optimization strategy can be applied within other machine learning settings.

Subset selection is a valuable tool for interpretable learning, scientific discovery, and data compression. However, classical subset selection is often eschewed due to selection instability, computational bottlenecks, and lack of post-selection inference. We address these challenges from a Bayesian perspective. Given any Bayesian predictive model $\mathcal{M}$, we elicit predictively-competitive subsets using linear decision analysis. The approach is customizable for (local) prediction or classification and provides interpretable summaries of $\mathcal{M}$. A key quantity is the acceptable family of subsets, which leverages the predictive distribution from $\mathcal{M}$ to identify subsets that offer nearly-optimal prediction. The acceptable family spawns new (co-) variable importance metrics based on whether variables (co-) appear in all, some, or no acceptable subsets. Crucially, the linear coefficients for any subset inherit regularization and predictive uncertainty quantification via $\mathcal{M}$. The proposed approach exhibits excellent prediction, interval estimation, and variable selection for simulated data, including $p=400 > n$. These tools are applied to a large education dataset with highly correlated covariates, where the acceptable family is especially useful. Our analysis provides unique insights into the combination of environmental, socioeconomic, and demographic factors that predict educational outcomes, and features highly competitive prediction with remarkable stability.

Cardiovascular diseases and heart failures in particular are the main cause of non-communicable disease mortality in the world. Constant patient monitoring enables better medical treatment as it allows practitioners to react on time and provide the appropriate treatment. Telemedicine can provide constant remote monitoring so patients can stay in their homes, only requiring medical sensing equipment and network connections. A limiting factor for telemedical centers is the amount of patients that can be monitored simultaneously. We aim to increase this amount by implementing a decision support system. This paper investigates a machine learning model to estimate a risk score based on patient vital parameters that allows sorting all cases every day to help practitioners focus their limited capacities on the most severe cases. The model we propose reaches an AUCROC of 0.84, whereas the baseline rule-based model reaches an AUCROC of 0.73. Our results indicate that the usage of deep learning to improve the efficiency of telemedical centers is feasible. This way more patients could benefit from better health-care through remote monitoring.

Due to its relevance in intelligent transportation systems, anomaly detection in traffic videos has recently received much interest. It remains a difficult problem due to a variety of factors influencing the video quality of a real-time traffic feed, such as temperature, perspective, lighting conditions, and so on. Even though state-of-the-art methods perform well on the available benchmark datasets, they need a large amount of external training data as well as substantial computational resources. In this paper, we propose an efficient approach for a video anomaly detection system which is capable of running at the edge devices, e.g., on a roadside camera. The proposed approach comprises a pre-processing module that detects changes in the scene and removes the corrupted frames, a two-stage background modelling module and a two-stage object detector. Finally, a backtracking anomaly detection algorithm computes a similarity statistic and decides on the onset time of the anomaly. We also propose a sequential change detection algorithm that can quickly adapt to a new scene and detect changes in the similarity statistic. Experimental results on the Track 4 test set of the 2021 AI City Challenge show the efficacy of the proposed framework as we achieve an F1-score of 0.9157 along with 8.4027 root mean square error (RMSE) and are ranked fourth in the competition.

How to use classification techniques to support automated manufacturing process design from product specifications. As we saw in our article series on AI in Manufacturing, manufacturing plants offer one of the most complex yet most promising environments to deploy large-scale AI-based solutions. In this article we provide a very concrete use-case where a machine learning algorithm is used to learn from historical production data how to infer the number of necessary manufacturing steps solely based on the basic product specifications. A manufacturer specializes in the custom-production of small mechanical parts. Their customers provide them with specifications of the parts to be produced. The manufacturer must first determine the exact steps to follow to produce these parts and then decide on appropriate price quotations.

This paper studies the construction of p-values for nonparametric outlier detection, taking a multiple-testing perspective. The goal is to test whether new independent samples belong to the same distribution as a reference data set or are outliers. We propose a solution based on conformal inference, a broadly applicable framework which yields p-values that are marginally valid but mutually dependent for different test points. We prove these p-values are positively dependent and enable exact false discovery rate control, although in a relatively weak marginal sense. We then introduce a new method to compute p-values that are both valid conditionally on the training data and independent of each other for different test points; this paves the way to stronger type-I error guarantees. Our results depart from classical conformal inference as we leverage concentration inequalities rather than combinatorial arguments to establish our finite-sample guarantees. Furthermore, our techniques also yield a uniform confidence bound for the false positive rate of any outlier detection algorithm, as a function of the threshold applied to its raw statistics. Finally, the relevance of our results is demonstrated by numerical experiments on real and simulated data.

Universities worldwide are experiencing a surge in enrollments, therefore campus estate managers are seeking continuous data on attendance patterns to optimize the usage of classroom space. As a result, there is an increasing trend to measure classrooms attendance by employing various sensing technologies, among which pervasive WiFi infrastructure is seen as a low cost method. In a dense campus environment, the number of connected WiFi users does not well estimate room occupancy since connection counts are polluted by adjoining rooms, outdoor walkways, and network load balancing. In this paper, we develop machine learning based models to infer classroom occupancy from WiFi sensing infrastructure. Our contributions are three-fold: (1) We analyze metadata from a dense and dynamic wireless network comprising of thousands of access points (APs) to draw insights into coverage of APs, behavior of WiFi connected users, and challenges of estimating room occupancy; (2) We propose a method to automatically map APs to classrooms using unsupervised clustering algorithms; and (3) We model classroom occupancy using a combination of classification and regression methods of varying algorithms. We achieve 84.6% accuracy in mapping APs to classrooms while the accuracy of our estimation for room occupancy is comparable to beam counter sensors with a symmetric Mean Absolute Percentage Error (sMAPE) of 13.10%.

In this paper we propose $\epsilon$-Consistent Mixup ($\epsilon$mu). $\epsilon$mu is a data-based structural regularization technique that combines Mixup's linear interpolation with consistency regularization in the Mixup direction, by compelling a simple adaptive tradeoff between the two. This learnable combination of consistency and interpolation induces a more flexible structure on the evolution of the response across the feature space and is shown to improve semi-supervised classification accuracy on the SVHN and CIFAR10 benchmark datasets, yielding the largest gains in the most challenging low label-availability scenarios. Empirical studies comparing $\epsilon$mu and Mixup are presented and provide insight into the mechanisms behind $\epsilon$mu's effectiveness. In particular, $\epsilon$mu is found to produce more accurate synthetic labels and more confident predictions than Mixup.