Mid-Regional Pro-Adrenomedullin, Methemoglobin and Carboxyhemoglobin as Prognosis Biomarkers in Critically Ill Patients with COVID-19: An Observational Prospective Study

Mid-regional pro-adrenomedullin (MR-proADM), methemoglobin (MetHb), and carboxyhemoglobin (COHb) levels have been associated with sepsis. In this study, we assessed the role of this potential biomarkers in critically ill COVID-19 patients. Outcomes were mortality and a combined event (mortality, venous or arterial thrombosis, and orotracheal intubation (OTI)) during a 30-day follow-up. A total of 95 consecutive patients were included, 51.6% required OTI, 12.6% patients died, 8.4% developed VTE, and 3.1% developed arterial thrombosis. MetHb and COHb levels were not associated with mortality nor combined event. Higher MR-proADM levels were found in patients with mortality (median of 1.21 [interquartile range-IQR-0.84;2.33] nmol/L vs. 0.76 [IQR 0.60;1.03] nmol/L, p = 0.011) and combined event (median of 0.91 [IQR 0.66;1.39] nmol/L vs. 0.70 [IQR 0.51;0.82] nmol/L, p < 0.001); the positive likelihood ratio (LR+) and negative likelihood ratio (LR−) for mortality were 2.40 and 0.46, respectively. The LR+ and LR− for combined event were 3.16 and 0.63, respectively. MR-proADM ≥1 nmol/L was the optimal cut-off for mortality and combined event prediction. The predictive capacity of MR-proADM showed an area under the ROC curve of 0.73 (95% CI, 0.62–0.81) and 0.72 (95% CI, 0.62–0.81) for mortality and combined event, respectively. In conclusion, elevated on-admission MR-proADM levels were associated with higher risk of 30-day mortality and 30-day poor outcomes in a cohort of critically ill patients with COVID-19.

An Assessment of Convective Initiation Nowcasting Algorithm within 0-60 Minutes using Himawari-8 Satellite

Convective cloud monitoring since its growth stage primarily related to location and time of the first convective cloud initiated, called convective initiation (CI), could be the primary key in providing an earlier heavy rainfall event prediction. This study aimed to assess the accuracy and lead time of CI nowcasting using Satellite Convection Analysis and Tracking (SATCAST) algorithm in predicting the CI event within 0-60 minutes over Surabaya and surrounding area using Himawari-8 satellite during June-July-August (JJA) period in 2018. Three main processes used in this study were cloud masking, cloud object tracking, and CI nowcasting. Twelve interest fields were utilized as predictors based on six bands of Himawari-8 satellite, which represented cloud physics attributes such as cloud-top height, glaciation, or cooling rate. The verification was conducted by comparing CI prediction to CI location and time based on Surabaya weather radar within the next 0-60 minutes. The algorithm resulted that the prediction could achieve 87.3% of accuracy from the 3449 cloud objects. The prediction had POD, FAR, and CSI scores of 57.1%, 52.2%, and 35.2%, respectively. The 32.3 minutes of averaged lead time prediction indicated that CI nowcasting could detect growing cumulus about 30 minutes prior to the CI event.

Applications of Machine Learning in Ambulatory ECG

The ambulatory ECG (AECG) is an important diagnostic tool for many heart electrophysiology-related cases. AECG covers a wide spectrum of devices and applications. At the core of these devices and applications are the algorithms responsible for signal conditioning, ECG beat detection and classification, and event detections. Over the years, there has been huge progress for algorithm development and implementation thanks to great efforts by researchers, engineers, and physicians, alongside the rapid development of electronics and signal processing, especially machine learning (ML). The current efforts and progress in machine learning fields are unprecedented, and many of these ML algorithms have also been successfully applied to AECG applications. This review covers some key AECG applications of ML algorithms. However, instead of doing a general review of ML algorithms, we are focusing on the central tasks of AECG and discussing what ML can bring to solve the key challenges AECG is facing. The center tasks of AECG signal processing listed in the review include signal preprocessing, beat detection and classification, event detection, and event prediction. Each AECG device/system might have different portions and forms of those signal components depending on its application and the target, but these are the topics most relevant and of greatest concern to the people working in this area.

One-Dimensional Convolutional Auto-Encoder for Predicting Furnace Blowback Events from Multivariate Time Series Process Data—A Case Study

Modern industrial mining and mineral processing applications are characterized by large volumes of historical process data. Hazardous events occurring in these processes compromise process safety and therefore overall viability. These events are recorded in historical data and are often preceded by characteristic patterns. Reconstruction-based data-driven models are trained to reconstruct the characteristic patterns of hazardous event-preceding process data with minimal residuals, facilitating effective event prediction based on reconstruction residuals. This investigation evaluated one-dimensional convolutional auto-encoders as reconstruction-based data-driven models for predicting positive pressure events in industrial furnaces. A simple furnace model was used to generate dynamic multivariate process data with simulated positive pressure events to use as a case study. A one-dimensional convolutional auto-encoder was trained as a reconstruction-based model to recognize the data preceding the hazardous events, and its performance was evaluated by comparing it to a fully-connected auto-encoder as well as a principal component analysis reconstruction model. This investigation found that one-dimensional convolutional auto-encoders recognized event-preceding patterns with lower detection delays, higher specificities, and lower missed alarm rates, suggesting that the one-dimensional convolutional auto-encoder layout is superior to the fully connected auto-encoder layout for use as a reconstruction-based event prediction model. This investigation also found that the nonlinear auto-encoder models outperformed the linear principal component model investigated. While the one-dimensional auto-encoder was evaluated comparatively on a simulated furnace case study, the methodology used in this evaluation can be applied to industrial furnaces and other mineral processing applications. Further investigation using industrial data will allow for a view of the convolutional auto-encoder’s absolute performance as a reconstruction-based hazardous event prediction model.

Multi-Head Spatio-Temporal Attention Mechanism for Urban Anomaly Event Prediction

Timely forecasting the urban anomaly events in advance is of great importance to the city management and planning. However, anomaly event prediction is highly challenging due to the sparseness of data, geographic heterogeneity (e.g., complex spatial correlation, skewed spatial distribution of anomaly events and crowd flows), and the dynamic temporal dependencies. In this study, we propose M-STAP, a novel Multi-head Spatio-Temporal Attention Prediction approach to address the problem of multi-region urban anomaly event prediction. Specifically, M-STAP considers the problem from three main aspects: (1) extracting the spatial characteristics of the anomaly events in different regions, and the spatial correlations between anomaly events and crowd flows; (2) modeling the impacts of crowd flow dynamic of the most relevant regions in each time step on the anomaly events; and (3) employing attention mechanism to analyze the varying impacts of the historical anomaly events on the predicted data. We have conducted extensive experimental studies on the crowd flows and anomaly events data of New York City, Melbourne and Chicago. Our proposed model shows higher accuracy (41.91% improvement on average) in predicting multi-region anomaly events compared with the state-of-the-arts.