A Minimalist Method Toward Severity Assessment and Progression Monitoring of Obstructive Sleep Apnea on the Edge

Artificial Intelligence-enabled applications on edge devices have the potential to revolutionize disease detection and monitoring in future smart health (sHealth) systems. In this study, we investigated a minimalist approach for the severity classification, severity estimation, and progression monitoring of obstructive sleep apnea (OSA) in a home environment using wearables. We used the recursive feature elimination technique to select the best feature set of 70 features from a total of 200 features extracted from polysomnogram. We used a multi-layer perceptron model to investigate the performance of OSA severity classification with all the ranked features to a subset of features available from either Electroencephalography or Heart Rate Variability (HRV) and time duration of SpO2 level. The results indicate that using only computationally inexpensive features from HRV and SpO2, an area under the curve of 0.91 and an accuracy of 83.97% can be achieved for the severity classification of OSA. For estimation of the apnea-hypopnea index, the accuracy of RMSE = 4.6 and R-squared value = 0.71 have been achieved in the test set using only ranked HRV and SpO2 features. The Wilcoxon-signed-rank test indicates a significant change (p < 0.05) in the selected feature values for a progression in the disease over 2.5 years. The method has the potential for integration with edge computing for deployment on everyday wearables. This may facilitate the preliminary severity estimation, monitoring, and management of OSA patients and reduce associated healthcare costs as well as the prevalence of untreated OSA.

A p−V Diagram Based Fault Identification for Compressor Valve by Means of Linear Discrimination Analysis

The pressure-volume diagram (p−V diagram) is an established method for analyzing the thermodynamic process in the cylinder of a reciprocating compressor as well as the fault of its core components including valves. The failure of suction/discharge valves is the most common cause of unscheduled shutdowns, and undetected failure may lead to catastrophic accidents. Although researchers have investigated fault classification by various estimation techniques and case studies, few have looked deeper into the barriers and pathways to realize the level determination of faults. The initial stage of valve failure is characterized in the form of mild leakage; if this is identified at this period, more serious accidents can be prevented. This study proposes a fault diagnosis and severity estimation method of the reciprocating compressor valve by virtue of features extracted from the p−V diagram. Four-dimensional characteristic variables consisting of the pressure ratio, process angle coefficient, area coefficient, and process index coefficient are extracted from the p−V diagram. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were applied to establish the diagnostic model, where PCA realizes feature amplification and projection, then LDA implements feature dimensionality reduction and failure prediction. The method was validated by the diagnosis of various levels of severity of valve leakage in a reciprocating compressor, and further, applied in the diagnosis of two actual faults: Mild leakage caused by the cracked valve plate in a reciprocating compressor, and serious leakage caused by the deformed valve in a hydraulically driven piston compressor for a hydrogen refueling station (HRS).

Disease Progression Detection via Deep Sequence Learning of Successive Radiographic Scans

The highly rapid spread of the current pandemic has quickly overwhelmed hospitals all over the world and motivated extensive research to address a wide range of emerging problems. The unforeseen influx of COVID-19 patients to hospitals has made it inevitable to deploy a rapid and accurate triage system, monitor progression, and predict patients at higher risk of deterioration in order to make informed decisions regarding hospital resource management. Disease detection in radiographic scans, severity estimation, and progression and prognosis prediction have been extensively studied with the help of end-to-end methods based on deep learning. The majority of recent works have utilized a single scan to determine severity or predict progression of the disease. In this paper, we present a method based on deep sequence learning to predict improvement or deterioration in successive chest X-ray scans and build a mathematical model to determine individual patient disease progression profile using successive scans. A deep convolutional neural network pretrained on a diverse lung disease dataset was used as a feature extractor to generate the sequences. We devised three strategies for sequence modeling in order to obtain both fine-grained and coarse-grained features and construct sequences of different lengths. We also devised a strategy to quantify positive or negative change in successive scans, which was then combined with age-related risk factors to construct disease progression profile for COVID-19 patients. The age-related risk factors allowed us to model rapid deterioration and slower recovery in older patients. Experiments conducted on two large datasets showed that the proposed method could accurately predict disease progression. With the best feature extractor, the proposed method was able to achieve AUC of 0.98 with the features obtained from radiographs. Furthermore, the proposed patient profiling method accurately estimated the health profile of patients.

Attention to Fires: Multi-Channel Deep Learning Models for Wildfire Severity Prediction

Wildfires are one of the natural hazards that the European Union is actively monitoring through the Copernicus EMS Earth observation program which continuously releases public information related to such catastrophic events. Such occurrences are the cause of both short- and long-term damages. Thus, to limit their impact and plan the restoration process, a rapid intervention by authorities is needed, which can be enhanced by the use of satellite imagery and automatic burned area delineation methodologies, accelerating the response and the decision-making processes. In this context, we analyze the burned area severity estimation problem by exploiting a state-of-the-art deep learning framework. Experimental results compare different model architectures and loss functions on a very large real-world Sentinel2 satellite dataset. Furthermore, a novel multi-channel attention-based analysis is presented to uncover the prediction behaviour and provide model interpretability. A perturbation mechanism is applied to an attention-based DS-UNet to evaluate the contribution of different domain-driven groups of channels to the severity estimation problem.

Development of mine-blast trauma severity score for lower extremities in men

This study presented the results of the analysis of existing approaches to the assessment of the severity of lower extremity injuries protected with explosion-proof shoes in case of mine-explosive ammunition explosion. An increasing number of mine explosives are used in modern local wars and armed conflicts. At present, more than 110 million mines are planted and activated. Every year, nearly 10 thousand individuals are killed by explosive demolitions, and more than 20 thousand civilians sustain injuries. The necessity to clear minefields and to destroy located ammunition increases the risks of mine clearance specialists to mine-blast trauma of the lower extremities. To reduce the likelihood of severe trauma in this population, developing effective blast protective equipment, such as anti-mine boots, is necessary. The effectiveness evaluation of protective boots requires special methodology that should comprise relevant methods of mine-blast trauma severity estimation. Mine-blast trauma is a special type of surgical pathology where the injured individual has extremity avulsion or multiple injuries to extremity tissues accompanied by severe impairment of body functions. Almost all available domestic classifications of mine-explosive wounds have a pronounced clinical orientation, and foreign ones have terminologies that are not accepted in Russia and cannot be fully used for assessment purposes. The modified working classification, in the form of a rating scale, showed not only the characteristics of a given blast trauma but also the criteria of trauma severity estimation and feasibility of exposure to blast trauma. The results of the study demonstrated the potential for its use to estimate the protective features of mine clearance specialist boots when exposed to charge explosion, as well as recommendations to include this classification in documenting the science and technology that deal with the general specifications of protective equipment for specialists at the project stage.

Multiple-Choice Question Answering Models for Automatic Depression Severity Estimation

Depression is one of the most prevalent mental health diseases. Although there are effective treatments, the main problem relies on providing early and effective risk detection. Medical experts use self-reporting questionnaires to elaborate their diagnosis, but these questionnaires have some limitations. Social stigmas and the lack of awareness often negatively affect the success of these self-report questionnaires. This article aims to describe techniques to automatically estimate the depression severity from users on social media. We explored the use of pre-trained language models over the subject’s writings. We addressed the task “Measuring the Severity of the Signs of Depression” of eRisk 2020, an initiative in the CLEF Conference. In this task, participants have to fill the Beck Depression Questionnaire (BDI-II). Our proposal explores the application of pre-trained Multiple-Choice Question Answering (MCQA) models to predict user’s answers to the BDI-II questionnaire using their posts on social media. These MCQA models are built over the BERT (Bidirectional Encoder Representations from Transformers) architecture. Our results showed that multiple-choice question answering models could be a suitable alternative for estimating the depression degree, even when small amounts of training data are available (20 users).