SWIFT: A deep learning approach to prediction of hypoxemic events in critically-Ill patients using SpO2 waveform prediction.
Ontology highlight
ABSTRACT:
SUBMITTER: Annapragada AV
PROVIDER: S-EPMC8730462 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description: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 (SpO 2 W aveform I CU F orecasting T echnique), a deep learning model that predicts blood oxygen saturation (SpO 2 ) waveforms 5 and 30 minutes in the future using only prior SpO 2 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 SpO 2 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.
| S-EPMC7941630 | biostudies-literature
Project description:BackgroundThe rapid development in big data analytics and the data-rich environment of intensive care units together provide unprecedented opportunities for medical breakthroughs in the field of critical care. We developed and validated a machine learning-based model, the Pediatric Risk of Mortality Prediction Tool (PROMPT), for real-time prediction of all-cause mortality in pediatric intensive care units.MethodsUtilizing two separate retrospective observational cohorts, we conducted model development and validation using a machine learning algorithm with a convolutional neural network. The development cohort comprised 1445 pediatric patients with 1977 medical encounters admitted to intensive care units from January 2011 to December 2017 at Severance Hospital (Seoul, Korea). The validation cohort included 278 patients with 364 medical encounters admitted to the pediatric intensive care unit from January 2016 to November 2017 at Samsung Medical Center.ResultsUsing seven vital signs, along with patient age and body weight on intensive care unit admission, PROMPT achieved an area under the receiver operating characteristic curve in the range of 0.89-0.97 for mortality prediction 6 to 60 h prior to death. Our results demonstrated that PROMPT provided high sensitivity with specificity and outperformed the conventional severity scoring system, the Pediatric Index of Mortality, in predictive ability. Model performance was indistinguishable between the development and validation cohorts.ConclusionsPROMPT is a deep model-based, data-driven early warning score tool that can predict mortality in critically ill children and may be useful for the timely identification of deteriorating patients.
| S-EPMC6694497 | biostudies-literature
Project description:The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.
| S-EPMC7363899 | biostudies-literature
Project description:ObjectivesCritically ill patients with coronavirus disease 2019 have variable mortality. Risk scores could improve care and be used for prognostic enrichment in trials. We aimed to compare machine learning algorithms and develop a simple tool for predicting 28-day mortality in ICU patients with coronavirus disease 2019.DesignThis was an observational study of adult patients with coronavirus disease 2019. The primary outcome was 28-day inhospital mortality. Machine learning models and a simple tool were derived using variables from the first 48 hours of ICU admission and validated externally in independent sites and temporally with more recent admissions. Models were compared with a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 using the area under the receiver operating characteristic curve and calibration.SettingSixty-eight U.S. ICUs.PatientsAdults with coronavirus disease 2019 admitted to 68 ICUs in the United States between March 4, 2020, and June 29, 2020.InterventionsNone.Measurements and main resultsThe study included 5,075 patients, 1,846 (36.4%) of whom died by day 28. eXtreme Gradient Boosting had the highest area under the receiver operating characteristic curve in external validation (0.81) and was well-calibrated, while k-nearest neighbors were the lowest performing machine learning algorithm (area under the receiver operating characteristic curve 0.69). Findings were similar with temporal validation. The simple tool, which was created using the most important features from the eXtreme Gradient Boosting model, had a significantly higher area under the receiver operating characteristic curve in external validation (0.78) than the Sequential Organ Failure Assessment score (0.69), National Early Warning Score (0.60), and CURB-65 (0.65; p < 0.05 for all comparisons). Age, number of ICU beds, creatinine, lactate, arterial pH, and Pao2/Fio2 ratio were the most important predictors in the eXtreme Gradient Boosting model.ConclusionseXtreme Gradient Boosting had the highest discrimination overall, and our simple tool had higher discrimination than a modified Sequential Organ Failure Assessment score, National Early Warning Score, and CURB-65 on external validation. These models could be used to improve triage decisions and clinical trial enrichment.
| S-EPMC8378790 | biostudies-literature
Project description:Traditional methods for assessing illness severity and predicting in-hospital mortality among critically ill patients require time-consuming, error-prone calculations using static variable thresholds. These methods do not capitalize on the emerging availability of streaming electronic health record data or capture time-sensitive individual physiological patterns, a critical task in the intensive care unit. We propose a novel acuity score framework (DeepSOFA) that leverages temporal measurements and interpretable deep learning models to assess illness severity at any point during an ICU stay. We compare DeepSOFA with SOFA (Sequential Organ Failure Assessment) baseline models using the same model inputs and find that at any point during an ICU admission, DeepSOFA yields significantly more accurate predictions of in-hospital mortality. A DeepSOFA model developed in a public database and validated in a single institutional cohort had a mean AUC for the entire ICU stay of 0.90 (95% CI 0.90-0.91) compared with baseline SOFA models with mean AUC 0.79 (95% CI 0.79-0.80) and 0.85 (95% CI 0.85-0.86). Deep models are well-suited to identify ICU patients in need of life-saving interventions prior to the occurrence of an unexpected adverse event and inform shared decision-making processes among patients, providers, and families regarding goals of care and optimal resource utilization.
| S-EPMC6372608 | biostudies-literature
Project description:Study objectiveTriage quickly identifies critically ill patients, facilitating timely interventions. Many emergency departments (EDs) use emergency severity index (ESI) or abnormal vital sign triggers to guide triage. However, both use fixed thresholds, and false activations are costly. Prior approaches using machinelearning have relied on information that is often unavailable during the triage process. We examined whether deep-learning approaches could identify critically ill patients only using data immediately available at triage.MethodsWe conducted a retrospective, cross-sectional study at an urban tertiary care center, from January 1, 2012-January 1, 2020. De-identified triage information included structured (age, sex, initial vital signs) and textual (chief complaint) data, with critical illness (mortality or ICU admission within 24 hours) as the outcome. Four progressively complex deep-learning models were trained and applied to triage information from all patients. We compared the accuracy of the models against ESI as the standard diagnostic test, using area under the receiver-operator curve (AUC).ResultsA total of 445,925 patients were included, with 60,901 (13.7%) critically ill. Vital sign thresholds identified critically ill patients with AUC 0.521 (95% confidence interval [CI] = 0.519-0.522), and ESI <3 demonstrated AUC 0.672 (95% CI = 0.671-0.674), logistic regression classified patients with AUC 0.803 (95% CI = 0.802-0.804), 2-layer neural network with structured data with AUC 0.811 (95% CI = 0.807-0.815), gradient tree boosting with AUC 0.820 (95% CI = 0.818-0.821), and the neural network model with textual data with AUC 0.851 (95% CI = 0.849-0.852). All successive increases in AUC were statistically significant.ConclusionDeep-learning techniques represent a promising method of augmenting triage, even with limited information. Further research is needed to determine if improved predictions yield clinical and operational benefits.
| S-EPMC7593422 | biostudies-literature
Project description:BACKGROUND:Acute respiratory failure is the leading reason for intensive care unit (ICU) admission in immunocompromised patients, and the need for invasive mechanical ventilation has become a major clinical endpoint in randomized controlled trials (RCTs). However, data are lacking on whether intubation is an objective criteria that is used unbiasedly across centers. This study explores how this outcome varies across ICUs. METHODS:Hierarchical models and permutation procedures for testing multiple random effects were applied on both data from an observational cohort (the TRIAL-OH study: 703 patients, 17 ICUs) and a randomized controlled trial (the HIGH trial: 776 patients, 31 ICUs) to characterize ICU variation in intubation risk across centers. RESULTS:The crude intubation rate varied across ICUs from 29 to 80% in the observational cohort and from 0 to 86% in the RCT. This center effect on the mean ICU intubation rate was statistically significant, even after adjustment on individual patient characteristics (observational cohort: p value?=?0.013, median OR 1.48 [1.30-1.72]; RCT: p value 0.004, median OR 1.51 [1.36-1.68]). Two ICU-level characteristics were associated with intubation risk (the annual rate of intubation procedure per center and the time from respiratory symptoms to ICU admission) and could partly explain this center effect. In the RCT that controlled for the use of high-flow oxygen therapy, we did not find significant variation in the effect of oxygenation strategy on intubation risk across centers, despite a significant variation in the need for invasive mechanical ventilation. CONCLUSION:Intubation rates varied considerably among ICUs, even after adjustment on individual characteristics.
| S-EPMC6731598 | biostudies-literature
Project description:Sepsis is defined by life-threatening organ dysfunction during infection and is the leading cause of death in hospitals. During sepsis, there is a high risk that new onset of atrial fibrillation (AF) can occur, which is associated with significant morbidity and mortality. Consequently, early prediction of AF during sepsis would allow testing of interventions in the intensive care unit (ICU) to prevent AF and its severe complications. In this paper, we present a novel automated AF prediction algorithm for critically ill sepsis patients using electrocardiogram (ECG) signals. From the heart rate signal collected from 5-min ECG, feature extraction is performed using the traditional time, frequency, and nonlinear domain methods. Moreover, variable frequency complex demodulation and tunable Q-factor wavelet-transform-based time-frequency methods are applied to extract novel features from the heart rate signal. Using a selected feature subset, several machine learning classifiers, including support vector machine (SVM) and random forest (RF), were trained using only the 2001 Computers in Cardiology data set. For testing the proposed method, 50 critically ill ICU subjects from the Medical Information Mart for Intensive Care (MIMIC) III database were used in this study. Using distinct and independent testing data from MIMIC III, the SVM achieved 80% sensitivity, 100% specificity, 90% accuracy, 100% positive predictive value, and 83.33% negative predictive value for predicting AF immediately prior to the onset of AF, while the RF achieved 88% AF prediction accuracy. When we analyzed how much in advance we can predict AF events in critically ill sepsis patients, the algorithm achieved 80% accuracy for predicting AF events 10 min early. Our algorithm outperformed a state-of-the-art method for predicting AF in ICU patients, further demonstrating the efficacy of our proposed method. The annotations of patients' AF transition information will be made publicly available for other investigators. Our algorithm to predict AF onset is applicable for any ECG modality including patch electrodes and wearables, including Holter, loop recorder, and implantable devices.
| S-EPMC8391773 | biostudies-literature
Project description:Cerebrovascular events (CVE) are among the most feared complications of transcatheter aortic valve replacement (TAVR). CVE appear difficult to predict due to their multifactorial origin incompletely explained by clinical predictors. We aimed to build a deep learning-based predictive tool for TAVR-related CVE. Integrated clinical and imaging characteristics from consecutive patients enrolled into a prospective TAVR registry were analysed. CVE comprised any strokes and transient ischemic attacks. Predictive variables were selected by recursive feature reduction to train an autoencoder predictive model. Area under the curve (AUC) represented the model's performance to predict 30-day CVE. Among 2279 patients included between 2007 and 2019, both clinical and imaging data were available in 1492 patients. Median age was 83 years and STS score was 4.6%. Acute (< 24 h) and subacute (day 2-30) CVE occurred in 19 (1.3%) and 36 (2.4%) patients, respectively. The occurrence of CVE was associated with an increased risk of death (HR [95% CI] 2.62 [1.82-3.78]). The constructed predictive model uses less than 107 clinical and imaging variables and has an AUC of 0.79 (0.65-0.93). TAVR-related CVE can be predicted using a deep learning-based predictive algorithm. The model is implemented online for broad usage.
| S-EPMC8455675 | biostudies-literature
Project description:OBJECTIVE:Guidelines recommend that encephalopathic critically ill children undergo continuous electroencephalographic (CEEG) monitoring for electrographic seizure (ES) identification and management. However, limited data exist on antiseizure medication (ASM) safety for ES treatment in critically ill children. METHODS:We performed a single-center prospective observational study of encephalopathic critically ill children undergoing CEEG. Clinical and EEG features and ASM utilization patterns were evaluated. We determined the incidence, types, and risk factors for adverse events associated with ASM administration. RESULTS:A total of 472 consecutive critically ill children undergoing CEEG were enrolled. ES occurred in 131 children (28%). Clinicians administered ASM to 108 children with ES (82%). ES terminated after the initial ASM in 38% of patients who received one ASM, after the second ASM in 35% of patients who received two ASMs, after the third ASM in 50% of patients who received three ASMs, and after the fourth ASM in 53% of patients who received four ASMs. Thirty patients (28%) received anesthetic infusions for ES management. Adverse events occurred in 18 patients (17%). Adverse effects were expected and resolved in all patients, and they were generally serious (in 15 patients) and definitely related (in 12 patients). Adverse events were rare in patients with acute symptomatic seizures requiring only one to two ASMs for treatment, but were more common in children with epilepsy, ictal-interictal continuum EEG patterns, or patients requiring more extensive ASM management. SIGNIFICANCE:ES ceased after one ASM in only 38% of critically ill children but ceased after two ASMs in 73% of critically ill children. Thus, ES management was often accomplished with readily available medications, but optimization of multistep ES management strategies might be beneficial. Adverse events were rare and manageable in children with acute symptomatic seizures requiring only one to two ASMs for treatment. Future studies are needed to determine whether management of acute symptomatic ES improves neurobehavioral outcomes.
| S-EPMC6786930 | biostudies-literature