Triage and monitoring of COVID-19 patients in intensive care using unsupervised machine learning.

BACKGROUND: We designed an algorithm to assess COVID-19 patients severity and dynamic intubation needs and predict their length of stay using the breathing frequency (BF) and oxygen saturation (SpO2) signals. METHODS: We recorded the BF and SpO2 signals for confirmed COVID-19 patients admitted to the ICU of a teaching hospital during both the first and subsequent outbreaks of the pandemic in France. An unsupervised machine-learning algorithm (the Gaussian mixture model) was applied to the patients' data for clustering. The algorithm's robustness was ensured by comparing its results against actual intubation rates. We predicted intubation rates using the algorithm every hour, thus conducting a severity evaluation. We designed a S24 severity score that represented the patient's severity over the previous 24 h; the validity of MS24, the maximum S24 score, was checked against rates of intubation risk and prolonged ICU stay. RESULTS: Our sample included 279 patients. . The unsupervised clustering had an accuracy rate of 87.8% for intubation recognition (AUC = 0.94, True Positive Rate 86.5%, true Negative Rate 90.9%). The S24 score of intubated patients was significantly higher than that of non-intubated patients at 48 h before intubation. The MS24 score allowed for the distinguishing between three severity levels with an increased risk of intubation: green (3.4%), orange (37%), and red (77%). A MS24 score over 40 was highly predictive of an ICU stay greater than 5 days at an accuracy rate of 81.0% (AUC = 0.87). CONCLUSIONS: Our algorithm uses simple signals and seems to efficiently visualize the patients' respiratory situations, meaning that it has the potential to assist staffs' in decision-making. Additionally, real-time computation is easy to implement.

Do distinct mind wandering differently disrupt drivers? Interpretation of physiological and behavioral pattern with a data triangulation method.

MW is damaging for tasks requiring sustained and divided attention, for example driving. Recent findings seem to be indicating that off-task thoughts differently disrupt drivers. The present paper delved into characteristics of off-task thoughts to assess their respective detrimental impact on driving. Twenty volunteers had to declare their MW thoughts and get intentionally involved in Problem-Solving Thoughts (PST) according to instructions. Heart rate and oculometric behavior were collected during the two sessions. Results showed that MW and PST led to a fixed gaze. MW might also led to a cognitive effort necessary to switch from task-unrelated to task-related focus. Similarities and differences between intentional and unintentional off-task thoughts were discussed in greater detail. By designing a detection algorithm, it could be possible to detect disruptive MW during risky situations while permitting the mind to wander when the driving demand is low.

Respiration and Heart Rate Modulation Due to Competing Cognitive Tasks While Driving.

Research works on operator monitoring underline the benefit of taking into consideration several signal modalities to improve accuracy for an objective mental state diagnosis. Heart rate (HR) is one of the most utilized systemic measures to assess cognitive workload (CW), whereas, respiration parameters are hardly utilized. This study aims at verifying the contribution of analyzing respiratory signals to extract features to evaluate driver's activity and CW variations in driving. Eighteen subjects participated in the study. The participants carried out two different cognitive tasks requiring different CW demands, a single task as well as a competing cognitive task realized while driving in a simulator. Our results confirm that both HR and breathing rate (BR) increase in driving and are sensitive to CW. However, HR and BR are differently modulated by the CW variations in driving. Specifically, HR is affected by both driving activity and CW, whereas, BR is suitable to evidence a variation of CW only when driving is not required. On the other hand, spectral features characterizing respiratory signal could be also used similarly to HR variability indices to detect high CW episodes. These results hint the use of respiration as an alternative to HR to monitor the driver mental state in autonomic vehicles in order to predict the available cognitive resources if the user has to take over the vehicle.