scholarly journals SWIFT: A deep learning approach to prediction of hypoxemic events in critically-Ill patients using SpO2 waveform prediction

2021 ◽  
Vol 17 (12) ◽  
pp. e1009712
Author(s):  
Akshaya V. Annapragada ◽  
Joseph L. Greenstein ◽  
Sanjukta N. Bose ◽  
Bradford D. Winters ◽  
Sridevi V. Sarma ◽  
...  
Keyword(s):  
Deep Learning ◽  
Clinical Outcomes ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Blood Oxygen Saturation ◽  
The Future ◽  
Optimal Resource ◽  
Deep Learning Model

Hypoxemia is a significant driver of mortality and poor clinical outcomes in conditions such as brain injury and cardiac arrest in critically ill patients, including COVID-19 patients. Given the host of negative clinical outcomes attributed to hypoxemia, identifying patients likely to experience hypoxemia would offer valuable opportunities for early and thus more effective intervention. We present SWIFT (SpO2 Waveform ICU Forecasting Technique), a deep learning model that predicts blood oxygen saturation (SpO2) waveforms 5 and 30 minutes in the future using only prior SpO2 values as inputs. When tested on novel data, SWIFT predicts more than 80% and 60% of hypoxemic events in critically ill and COVID-19 patients, respectively. SWIFT also predicts SpO2 waveforms with average MSE below .0007. SWIFT predicts both occurrence and magnitude of potential hypoxemic events 30 minutes in the future, allowing it to be used to inform clinical interventions, patient triaging, and optimal resource allocation. SWIFT may be used in clinical decision support systems to inform the management of critically ill patients during the COVID-19 pandemic and beyond.

scholarly journals SWIFT: A Deep Learning Approach to Prediction of Hypoxemic Events in Critically-Ill Patients Using SpO2 Waveform Prediction

2021 ◽  
Author(s):  
Akshaya V. Annapragada ◽  
Joseph L. Greenstein ◽  
Sanjukta N. Bose ◽  
Bradford D. Winters ◽  
Sridevi V. Sarma ◽  
...  
Keyword(s):  
Deep Learning ◽  
Clinical Outcomes ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Clinical Decision Support Systems ◽  
Clinical Decision ◽  
Optimal Resource Allocation ◽  
Blood Oxygen Saturation ◽  
Optimal Resource ◽  
Deep Learning Model

AbstractHypoxemia is a significant driver of mortality and poor clinical outcomes in conditions such as brain injury and cardiac arrest in critically ill patients, including COVID-19 patients. Given the host of negative clinical outcomes attributed to hypoxemia, identifying patients likely to experience hypoxemia would offer valuable opportunities for early and thus more effective intervention. We present SWIFT (SpO2Waveform ICU Forecasting Technique), a deep learning model that predicts blood oxygen saturation (SpO2) waveforms 5 and 30 minutes in the future using only prior SpO2 values as inputs. When tested on novel data, SWIFT predicts more than 80% and 60% of hypoxemic events in critically ill and COVID-19 patients, respectively. SWIFT also predicts SpO2 waveforms with average MSE below .0007. SWIFT provides information on both occurrence and magnitude of potential hypoxemic events 30 minutes in advance, allowing it to be used to inform clinical interventions, patient triaging, and optimal resource allocation. SWIFT may be used in clinical decision support systems to inform the management of critically ill patients during the COVID-19 pandemic and beyond.

scholarly journals Explaining deep neural networks for knowledge discovery in electrocardiogram analysis

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Steven A. Hicks ◽  
Jonas L. Isaksen ◽  
Vajira Thambawita ◽  
Jonas Ghouse ◽  
Gustav Ahlberg ◽  
...  
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Clinical Decision Making ◽  
Medical Knowledge ◽  
Clinical Decision ◽  
Medical Data ◽  
Medical Doctors ◽  
Medical Tests ◽  
Deep Learning Model

AbstractDeep learning-based tools may annotate and interpret medical data more quickly, consistently, and accurately than medical doctors. However, as medical doctors are ultimately responsible for clinical decision-making, any deep learning-based prediction should be accompanied by an explanation that a human can understand. We present an approach called electrocardiogram gradient class activation map (ECGradCAM), which is used to generate attention maps and explain the reasoning behind deep learning-based decision-making in ECG analysis. Attention maps may be used in the clinic to aid diagnosis, discover new medical knowledge, and identify novel features and characteristics of medical tests. In this paper, we showcase how ECGradCAM attention maps can unmask how a novel deep learning model measures both amplitudes and intervals in 12-lead electrocardiograms, and we show an example of how attention maps may be used to develop novel ECG features.

scholarly journals Effect of timing of intubation on clinical outcomes of critically ill patients with COVID-19: a systematic review and meta-analysis of non-randomized cohort studies

Critical Care ◽  
2021 ◽  
Vol 25 (1) ◽  
Author(s):  
Eleni Papoutsi ◽  
Vassilis G. Giannakoulis ◽  
Eleni Xourgia ◽  
Christina Routsi ◽  
Anastasia Kotanidou ◽  
...  
Keyword(s):  
Systematic Review ◽  
Mechanical Ventilation ◽  
Clinical Outcomes ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Meta Analysis ◽  
Mortality And Morbidity ◽  
Icu Admission ◽  
All Cause Mortality ◽  
Detectable Difference

Abstract Background Although several international guidelines recommend early over late intubation of patients with severe coronavirus disease 2019 (COVID-19), this issue is still controversial. We aimed to investigate the effect (if any) of timing of intubation on clinical outcomes of critically ill patients with COVID-19 by carrying out a systematic review and meta-analysis. Methods PubMed and Scopus were systematically searched, while references and preprint servers were explored, for relevant articles up to December 26, 2020, to identify studies which reported on mortality and/or morbidity of patients with COVID-19 undergoing early versus late intubation. “Early” was defined as intubation within 24 h from intensive care unit (ICU) admission, while “late” as intubation at any time after 24 h of ICU admission. All-cause mortality and duration of mechanical ventilation (MV) were the primary outcomes of the meta-analysis. Pooled risk ratio (RR), pooled mean difference (MD) and 95% confidence intervals (CI) were calculated using a random effects model. The meta-analysis was registered with PROSPERO (CRD42020222147). Results A total of 12 studies, involving 8944 critically ill patients with COVID-19, were included. There was no statistically detectable difference on all-cause mortality between patients undergoing early versus late intubation (3981 deaths; 45.4% versus 39.1%; RR 1.07, 95% CI 0.99–1.15, p = 0.08). This was also the case for duration of MV (1892 patients; MD − 0.58 days, 95% CI − 3.06 to 1.89 days, p = 0.65). In a sensitivity analysis using an alternate definition of early/late intubation, intubation without versus with a prior trial of high-flow nasal cannula or noninvasive mechanical ventilation was still not associated with a statistically detectable difference on all-cause mortality (1128 deaths; 48.9% versus 42.5%; RR 1.11, 95% CI 0.99–1.25, p = 0.08). Conclusions The synthesized evidence suggests that timing of intubation may have no effect on mortality and morbidity of critically ill patients with COVID-19. These results might justify a wait-and-see approach, which may lead to fewer intubations. Relevant guidelines may therefore need to be updated.

Evaluation of Delirium in Critically Ill Patients Prescribed Melatonin or Ramelteon

2021 ◽  
pp. 106002802110020
Author(s):  
Natasha Romero ◽  
Kevin M. Dube ◽  
Kenneth E. Lupi ◽  
Jeremy R. DeGrado
Keyword(s):  
Clinical Outcomes ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Receptor Agonist ◽  
Hospital Length ◽  
Hospital Length Of Stay ◽  
Melatonin Receptor ◽  
Observational Cohort ◽  
Impaired Sleep ◽  
Retrospective Observational Cohort Study

Background: An impaired sleep-wake cycle may be one factor that affects the development of delirium in critically ill patients. Several small studies suggest that exogenous melatonin or ramelteon may decrease the incidence and/or duration of delirium. Objective: To compare the effect of prophylactic administration of melatonin, ramelteon, or no melatonin receptor agonist on the development of delirium in the intensive care unit (ICU). Methods: This was a single-center, retrospective, observational cohort study of nondelirious patients in the ICU who received melatonin, ramelteon, or no melatonin receptor agonist. The primary end point was the incidence of delirium. Secondary end points included assessments of daily level of sedation and daily utilization of antipsychotic, sedative, and opioid agents. Results: No difference was observed in the incidence of delirium among the melatonin, ramelteon, and placebo cohorts (18.7% vs 14.3% vs 13.8%; P = 0.77). A difference was observed in the rate of agitation and sedation among the 3 groups, with the greatest observed in the melatonin cohort. Additionally, there was a difference in the use of propofol, dexmedetomidine, and opioids. Overall, there was no difference in clinical outcomes, including duration of mechanical ventilation and ICU or hospital length of stay. Conclusion and Relevance: Therapy with melatonin, ramelteon, and no melatonin receptor agonist resulted in similar rates of delirium in a mixed ICU population. Despite significant differences in agitation, sedation, and medication utilization, there was no differences in the clinical outcomes evaluated.

Obesity, Inflammatory and Thrombotic Markers, and Major Clinical Outcomes in Critically Ill Patients with COVID‐19 in the US

Obesity ◽  
2021 ◽  
Author(s):  
Allon N. Friedman ◽  
John Guirguis ◽  
Raj Kapoor ◽  
Shruti Gupta ◽  
David E. Leaf ◽  
...  
Keyword(s):  
Clinical Outcomes ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
The Us

The Physiological Deep Learner: First application of multitask deep learning to predict hypotension in critically ill patients

2021 ◽  
pp. 102118
Author(s):  
Ményssa Cherifa ◽  
Yannet Interian ◽  
Alice Blet ◽  
Matthieu Resche-Rigon ◽  
Romain Pirrachio
Keyword(s):  
Deep Learning ◽  
Critically Ill ◽  
Critically Ill Patients

scholarly journals Full versus Trophic Feeds in Critically Ill Adults with High and Low Nutritional Risk Scores: A Randomized Controlled Trial

Nutrients ◽  
2020 ◽  
Vol 12 (11) ◽  
pp. 3518
Author(s):  
Chen-Yu Wang ◽  
Pin-Kuei Fu ◽  
Wen-Cheng Chao ◽  
Wei-Ning Wang ◽  
Chao-Hsiu Chen ◽  
...  
Keyword(s):  
Randomized Controlled Trial ◽  
Hospital Stay ◽  
Clinical Outcomes ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Controlled Trial ◽  
Risk Scores ◽  
Nutrition Risk ◽  
Randomized Controlled ◽  
Trophic Feeding

Although energy intake might be associated with clinical outcomes in critically ill patients, it remains unclear whether full or trophic feeding is suitable for critically ill patients with high or low nutrition risk. We conducted a prospective study to determine which feeding energy intakes were associated with clinical outcomes in critically ill patients with high or low nutrition risk. This was an investigator-initiated, single center, single blind, randomized controlled trial. Critically ill patients were allocated to either high or low nutrition risk based on their Nutrition Risk in the Critically Ill score, and then randomized to receive either the full or the trophic feeding. The feeding procedure was administered for six days. No significant differences were observed in hospital, 14-day and 28-day mortalities, the length of ventilator dependency, or ICU and hospital stay among the four groups. There were no associations between energy and protein intakes and hospital, 14-day and 28-day mortalities in any of the four groups. However, protein intake was positively associated with the length of hospital stay and ventilator dependency in patients with low nutrition risk receiving trophic feeding. Full or trophic feeding in critically ill patients showed no associations with clinical outcomes, regardless of nutrition risk.

Timing of renal replacement therapy and clinical outcomes in critically ill patients with severe acute kidney injury

2009 ◽  
Vol 24 (1) ◽  
pp. 129-140 ◽  
Author(s):  
Sean M. Bagshaw ◽  
Shigehiko Uchino ◽  
Rinaldo Bellomo ◽  
Hiroshi Morimatsu ◽  
Stanislao Morgera ◽  
...  
Keyword(s):  
Acute Kidney Injury ◽  
Renal Replacement Therapy ◽  
Replacement Therapy ◽  
Clinical Outcomes ◽  
Critically Ill ◽  
Critically Ill Patients ◽  
Kidney Injury

scholarly journals Early Fever Is Associated With Clinical Outcomes in Patients With Coronavirus Disease

2021 ◽  
Vol 9 ◽  
Author(s):  
Feng-ming Ding ◽  
Yun Feng ◽  
Lei Han ◽  
Yan Zhou ◽  
Yong Ji ◽  
...  
Keyword(s):  
Clinical Outcomes ◽  
Critically Ill ◽  
Symptom Onset ◽  
Critically Ill Patients ◽  
Severe Disease ◽  
Multivariable Analysis ◽  
Reactive Protein ◽  
Increased Temperature ◽  
Kaplan Meier ◽  
Image Improvement

Fever is one of the typical symptoms of coronavirus disease (COVID-19). We aimed to investigate the association between early fever (EF) and clinical outcomes in COVID-19 patients. A total of 1,014 COVID-19 patients at the Leishenshan Hospital were enrolled and classified into the EF and non-EF groups based on whether they had fever within 5 days of symptom onset. Risk factors for clinical outcomes in patients with different levels of disease severity were analyzed using multivariable analyses. Time from symptom onset to symptom alleviation, CT image improvement, and discharge were longer for patients with moderate and severe disease in the EF group than in the non-EF group. Multivariable analysis showed that sex, EF, eosinophil number, C-reactive protein, and IL-6 levels were positively correlated with the time from symptom onset to hospital discharge in moderate cases. The EF patients showed no significant differences in the development of acute respiratory distress syndrome, compared with the non-EF patients. The Kaplan–Meier curve showed no obvious differences in survival between the EF and non-EF patients. However, EF patients with increased temperature showed markedly lower survival than the non-EF patients with increased temperature. EF had no significant impact on the survival of critically ill patients, while an increase in temperature was identified as an independent risk factor. EF appears to be a predictor of longer recovery time in moderate/severe COVID-19 infections. However, its value in predicting mortality needs to be considered for critically ill patients with EF showing increasing temperature.

Sign in / Sign up

Export Citation Format

Share Document