Using data available in the ICU in real-time, Artificial Intelligence Sepsis Expert can accurately predict the onset of sepsis in an ICU patient 4-12 hours prior to clinical recognition. A prospective study is necessary to determine the clinical utility of the proposed sepsis prediction model.
Elevated loop gain, consequent to hypersensitive ventilatory control, is a primary nonanatomical cause of obstructive sleep apnoea (OSA) but it is not possible to quantify this in the clinic. Here we provide a novel method to estimate loop gain in OSA patients using routine clinical polysomnography alone. We use the concept that spontaneous ventilatory fluctuations due to apnoeas/hypopnoeas (disturbance) result in opposing changes in ventilatory drive (response) as determined by loop gain (response/disturbance). Fitting a simple ventilatory control model (including chemical and arousal contributions to ventilatory drive) to the ventilatory pattern of OSA reveals the underlying loop gain. Following mathematical-model validation, we critically tested our method in patients with OSA by comparison with a standard (continuous positive airway pressure (CPAP) drop method), and by assessing its ability to detect the known reduction in loop gain with oxygen and acetazolamide. Our method quantified loop gain from baseline polysomnography (correlation versus CPAP-estimated loop gain: n=28; r=0.63, p<0.001), detected the known reduction in loop gain with oxygen (n=11; mean±SEM change in loop gain (ΔLG) −0.23±0.08, p=0.02) and acetazolamide (n=11; ΔLG −0.20±0.06, p=0.005), and predicted the OSA response to loop gain-lowering therapy. We validated a means to quantify the ventilatory control contribution to OSA pathogenesis using clinical polysomnography, enabling identification of likely responders to therapies targeting ventilatory control.
Clinical data management systems typically provide caregiver teams with useful information, derived from large, sometimes highly heterogeneous, data sources that are often changing dynamically. Over the last decade there has been a significant surge in interest in using these data sources, from simply re-using the standard clinical databases for event prediction or decision support, to including dynamic and patient-specific information into clinical monitoring and prediction problems. However, in most cases, commercial clinical databases have been designed to document clinical activity for reporting, liability and billing reasons, rather than for developing new algorithms. With increasing excitement surrounding “secondary use of medical records” and “Big Data” analytics, it is important to understand the limitations of current databases and what needs to change in order to enter an era of “precision medicine.” This review article covers many of the issues involved in the collection and preprocessing of critical care data. The three challenges in critical care are considered: compartmentalization, corruption, and complexity. A range of applications addressing these issues are covered, including the modernization of static acuity scoring; on-line patient tracking; personalized prediction and risk assessment; artifact detection; state estimation; and incorporation of multimodal data sources such as genomic and free text data.
Existing HRV toolboxes do not include standardized preprocessing, signal quality indices (for noisy segment removal), and abnormal rhythm detection and are therefore likely to lead to significant errors in the presence of moderate to high noise or arrhythmias. We therefore describe the inclusion of validated tools to address these issues. We also make recommendations for default values and testing/reporting.
A, White DP. A simplified method for determining phenotypic traits in patients with obstructive sleep apnea. J Appl Physiol 114: 911-922, 2013. First published January 24, 2013 doi:10.1152/japplphysiol.00747.2012.-We previously published a method for measuring several physiological traits causing obstructive sleep apnea (OSA). The method, however, had a relatively low success rate (76%) and required mathematical modeling, potentially limiting its application. This paper presents a substantial revision of that technique. To make the measurements, continuous positive airway pressure (CPAP) was manipulated during sleep to quantify 1) eupneic ventilatory demand, 2) the level of ventilation at which arousals begin to occur, 3) ventilation off CPAP (nasal pressure ϭ 0 cmH 2O) when the pharyngeal muscles are activated during sleep, and 4) ventilation off CPAP when the pharyngeal muscles are relatively passive. These traits could be determined in all 13 participants (100% success rate). There was substantial intersubject variability in the reduction in ventilation that individuals could tolerate before having arousals (difference between ventilations #1 and #2 ranged from 0.7 to 2.9 liters/min) and in the amount of ventilatory compensation that individuals could generate (difference between ventilations #3 and #4 ranged from Ϫ0.5 to 5.5 liters/min). Importantly, the measurements accurately reflected clinical metrics; the difference between ventilations #2 and #3, a measure of the gap that must be overcome to achieve stable breathing during sleep, correlated with the apneahypopnea index (r ϭ 0.9, P Ͻ 0.001). An additional procedure was added to the technique to measure loop gain (sensitivity of the ventilatory control system), which allowed arousal threshold and upper airway gain (response of the upper airway to increasing ventilatory drive) to be quantified as well. Of note, the traits were generally repeatable when measured on a second night in 5 individuals. This technique is a relatively simple way of defining mechanisms underlying OSA and could potentially be used in a clinical setting to individualize therapy. pathophysiology of sleep apnea; loop gain; pharyngeal critical closing pressure; upper airway; arousal threshold RECENT EVIDENCE SUGGESTS that obstructive sleep apnea (OSA) is a multifactorial disorder. Contributing factors include a small or collapsible pharyngeal airway (9, 12, 23), a high loop gain (large ventilatory response to a ventilatory disturbance) (2,11,21,25,26,31), poor pharyngeal muscle responsiveness during sleep (5, 14 -16, 20, 27, 29), and a low respiratory arousal threshold (13, 28). The relative contribution of these traits varies substantially between individuals (24, 30).Despite the multifactorial nature of OSA, common therapies [continuous positive airway pressure (CPAP), upper airway surgery, dental appliances] are directed at only one trait: the abnormal airway anatomy. Moreover, the most effective treatment, CPAP, has an acceptance rate of only ϳ50% (8, 17). We believe that if the tr...
Misdosing medications with sensitive therapeutic windows, such as heparin, can place patients at unnecessary risk, increase length of hospital stay, and lead to wasted hospital resources. In this work, we present a clinician-in-the-loop sequential decision making framework, which provides an individualized dosing policy adapted to each patient's evolving clinical phenotype. We employed retrospective data from the publicly available MIMIC II intensive care unit database, and developed a deep reinforcement learning algorithm that learns an optimal heparin dosing policy from sample dosing trails and their associated outcomes in large electronic medical records. Using separate training and testing datasets, our model was observed to be effective in proposing heparin doses that resulted in better expected outcomes than the clinical guidelines. Our results demonstrate that a sequential modeling approach, learned from retrospective data, could potentially be used at the bedside to derive individualized patient dosing policies.
BackgroundThe detection of change in magnitude of directional coupling between two non-linear time series is a common subject of interest in the biomedical domain, including studies involving the respiratory chemoreflex system. Although transfer entropy is a useful tool in this avenue, no study to date has investigated how different transfer entropy estimation methods perform in typical biomedical applications featuring small sample size and presence of outliers.MethodsWith respect to detection of increased coupling strength, we compared three transfer entropy estimation techniques using both simulated time series and respiratory recordings from lambs. The following estimation methods were analyzed: fixed-binning with ranking, kernel density estimation (KDE), and the Darbellay-Vajda (D-V) adaptive partitioning algorithm extended to three dimensions. In the simulated experiment, sample size was varied from 50 to 200, while coupling strength was increased. In order to introduce outliers, the heavy-tailed Laplace distribution was utilized. In the lamb experiment, the objective was to detect increased respiratory-related chemosensitivity to O2 and CO2 induced by a drug, domperidone. Specifically, the separate influence of end-tidal PO2 and PCO2 on minute ventilation (trueV˙E) before and after administration of domperidone was analyzed.ResultsIn the simulation, KDE detected increased coupling strength at the lowest SNR among the three methods. In the lamb experiment, D-V partitioning resulted in the statistically strongest increase in transfer entropy post-domperidone for PO2MathClass-rel→trueV˙E. In addition, D-V partitioning was the only method that could detect an increase in transfer entropy for PCO2→trueV˙E, in agreement with experimental findings.ConclusionsTransfer entropy is capable of detecting directional coupling changes in non-linear biomedical time series analysis featuring a small number of observations and presence of outliers. The results of this study suggest that fixed-binning, even with ranking, is too primitive, and although there is no clear winner between KDE and D-V partitioning, the reader should note that KDE requires more computational time and extensive parameter selection than D-V partitioning. We hope this study provides a guideline for selection of an appropriate transfer entropy estimation method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.