An artificial intelligence system for predicting the deterioration of COVID-19 patients in the emergency department.
Ontology highlight
ABSTRACT:
SUBMITTER: Shamout FE
PROVIDER: S-EPMC8115328 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:The respective value of clinical data and CT examinations in predicting COVID-19 progression is unclear, because the CT scans and clinical data previously used are not synchronized in time. To address this issue, we collected 119 COVID-19 patients with 341 longitudinal CT scans and paired clinical data, and we developed an AI system for the prediction of COVID-19 deterioration. By combining features extracted from CT and clinical data with our system, we can predict whether a patient will develop severe symptoms during hospitalization. Complementary to clinical data, CT examinations show significant add-on values for the prediction of COVID-19 progression in the early stage of COVID-19, especially in the 6th to 8th day after the symptom onset, indicating that this is the ideal time window for the introduction of CT examinations. We release our AI system to provide clinicians with additional assistance to optimize CT usage in the clinical workflow.
| S-EPMC8989658 | biostudies-literature
Project description:BackgroundCOVID-19 may lead to severe disease, requiring intensive care treatment and challenging the capacity of health care systems. The aim of this study was to compare the ability of commonly used scoring systems for sepsis and pneumonia to predict severe COVID-19 in the emergency department.MethodsProspective, observational, single centre study in a secondary/tertiary care hospital in Oslo, Norway. Patients were assessed upon hospital admission using the following scoring systems; quick Sequential Failure Assessment (qSOFA), Systemic Inflammatory Response Syndrome criteria (SIRS), National Early Warning Score 2 (NEWS2), CURB-65 and Pneumonia Severity index (PSI). The ratio of arterial oxygen tension to inspiratory oxygen fraction (P/F-ratio) was also calculated. The area under the receiver operating characteristics curve (AUROC) for each scoring system was calculated, along with sensitivity and specificity for the most commonly used cut-offs. Severe disease was defined as death or treatment in ICU within 14 days.Results38 of 175 study participants developed severe disease, 13 (7%) died and 29 (17%) had a stay at an intensive care unit (ICU). NEWS2 displayed an AUROC of 0.80 (95% confidence interval 0.72-0.88), CURB-65 0.75 (0.65-0.84), PSI 0.75 (0.65-0.84), SIRS 0.70 (0.61-0.80) and qSOFA 0.70 (0.61-0.79). NEWS2 was significantly better than SIRS and qSOFA in predicating severe disease, and with a cut-off of5 points, had a sensitivity and specificity of 82% and 60%, respectively.ConclusionNEWS2 predicted severe COVID-19 disease more accurately than SIRS and qSOFA, but not significantly better than CURB65 and PSI. NEWS2 may be a useful screening tool in evaluating COVID-19 patients during hospital admission.Trial registration: ClinicalTrials.gov Identifier: NCT04345536. (https://clinicaltrials.gov/ct2/show/NCT04345536).
| S-EPMC7577659 | biostudies-literature
Project description:BackgroundWithin the trauma system, the emergency department (ED) is the hospital's first contact and is vital for allocating medical resources. However, there is generally limited information about patients that die in the ED.ObjectiveThe aim of this study was to develop an artificial intelligence (AI) model to predict trauma mortality and analyze pertinent mortality factors for all patients visiting the ED.MethodsWe used the Korean National Emergency Department Information System (NEDIS) data set (N=6,536,306), incorporating over 400 hospitals between 2016 and 2019. We included the International Classification of Disease 10th Revision (ICD-10) codes and chose the following input features to predict ED patient mortality: age, sex, intentionality, injury, emergent symptom, Alert/Verbal/Painful/Unresponsive (AVPU) scale, Korean Triage and Acuity Scale (KTAS), and vital signs. We compared three different feature set performances for AI input: all features (n=921), ICD-10 features (n=878), and features excluding ICD-10 codes (n=43). We devised various machine learning models with an ensemble approach via 5-fold cross-validation and compared the performance of each model with that of traditional prediction models. Lastly, we investigated explainable AI feature effects and deployed our final AI model on a public website, providing access to our mortality prediction results among patients visiting the ED.ResultsOur proposed AI model with the all-feature set achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.9974 (adaptive boosting [AdaBoost], AdaBoost + light gradient boosting machine [LightGBM]: Ensemble), outperforming other state-of-the-art machine learning and traditional prediction models, including extreme gradient boosting (AUROC=0.9972), LightGBM (AUROC=0.9973), ICD-based injury severity scores (AUC=0.9328 for the inclusive model and AUROC=0.9567 for the exclusive model), and KTAS (AUROC=0.9405). In addition, our proposed AI model outperformed a cutting-edge AI model designed for in-hospital mortality prediction (AUROC=0.7675) for all ED visitors. From the AI model, we also discovered that age and unresponsiveness (coma) were the top two mortality predictors among patients visiting the ED, followed by oxygen saturation, multiple rib fractures (ICD-10 code S224), painful response (stupor, semicoma), and lumbar vertebra fracture (ICD-10 code S320).ConclusionsOur proposed AI model exhibits remarkable accuracy in predicting ED mortality. Including the necessity for external validation, a large nationwide data set would provide a more accurate model and minimize overfitting. We anticipate that our AI-based risk calculator tool will substantially aid health care providers, particularly regarding triage and early diagnosis for trauma patients.
| S-EPMC10498319 | biostudies-literature
Project description:ImportanceMultimodal generative artificial intelligence (AI) methodologies have the potential to optimize emergency department care by producing draft radiology reports from input images.ObjectiveTo evaluate the accuracy and quality of AI-generated chest radiograph interpretations in the emergency department setting.Design, setting, and participantsThis was a retrospective diagnostic study of 500 randomly sampled emergency department encounters at a tertiary care institution including chest radiographs interpreted by both a teleradiology service and on-site attending radiologist from January 2022 to January 2023. An AI interpretation was generated for each radiograph. The 3 radiograph interpretations were each rated in duplicate by 6 emergency department physicians using a 5-point Likert scale.Main outcomes and measuresThe primary outcome was any difference in Likert scores between radiologist, AI, and teleradiology reports, using a cumulative link mixed model. Secondary analyses compared the probability of each report type containing no clinically significant discrepancy with further stratification by finding presence, using a logistic mixed-effects model. Physician comments on discrepancies were recorded.ResultsA total of 500 ED studies were included from 500 unique patients with a mean (SD) age of 53.3 (21.6) years; 282 patients (56.4%) were female. There was a significant association of report type with ratings, with post hoc tests revealing significantly greater scores for AI (mean [SE] score, 3.22 [0.34]; P < .001) and radiologist (mean [SE] score, 3.34 [0.34]; P < .001) reports compared with teleradiology (mean [SE] score, 2.74 [0.34]) reports. AI and radiologist reports were not significantly different. On secondary analysis, there was no difference in the probability of no clinically significant discrepancy between the 3 report types. Further stratification of reports by presence of cardiomegaly, pulmonary edema, pleural effusion, infiltrate, pneumothorax, and support devices also yielded no difference in the probability of containing no clinically significant discrepancy between the report types.Conclusions and relevanceIn a representative sample of emergency department chest radiographs, results suggest that the generative AI model produced reports of similar clinical accuracy and textual quality to radiologist reports while providing higher textual quality than teleradiologist reports. Implementation of the model in the clinical workflow could enable timely alerts to life-threatening pathology while aiding imaging interpretation and documentation.
| S-EPMC10556963 | biostudies-literature
Project description:BackgroundArtificial intelligence (AI)-aided analysis of chest CT expedites the quantification of abnormalities and may facilitate the diagnosis and assessment of the prognosis of subjects with COVID-19.ObjectivesThis study investigates the performance of an AI-aided quantification model in predicting the clinical outcomes of hospitalized subjects with COVID-19 and compares it with radiologists' performance.Subjects and methodsA total of 90 subjects with COVID-19 (men, n = 59 [65.6%]; age, 52.9±16.7 years) were recruited in this cross-sectional study. Quantification of the total and compromised lung parenchyma was performed by two expert radiologists using a volumetric image analysis software and compared against an AI-assisted package consisting of a modified U-Net model for segmenting COVID-19 lesions and an off-the-shelf U-Net model augmented with COVID-19 data for segmenting lung volume. The fraction of compromised lung parenchyma (%CL) was calculated. Based on clinical results, the subjects were divided into two categories: critical (n = 45) and noncritical (n = 45). All admission data were compared between the two groups.ResultsThere was an excellent agreement between the radiologist-obtained and AI-assisted measurements (intraclass correlation coefficient = 0.88, P < 0.001). Both the AI-assisted and radiologist-obtained %CLs were significantly higher in the critical subjects (P = 0.009 and 0.02, respectively) than in the noncritical subjects. In the multivariate logistic regression analysis to distinguish the critical subjects, an AI-assisted %CL ≥35% (odds ratio [OR] = 17.0), oxygen saturation level of <88% (OR = 33.6), immunocompromised condition (OR = 8.1), and other comorbidities (OR = 15.2) independently remained as significant variables in the models. Our proposed model obtained an accuracy of 83.9%, a sensitivity of 79.1%, and a specificity of 88.6% in predicting critical outcomes.ConclusionsAI-assisted measurements are similar to quantitative radiologist-obtained measurements in determining lung involvement in COVID-19 subjects.
| S-EPMC10707659 | biostudies-literature
Project description:Early detection of COVID-19 based on chest CT enables timely treatment of patients and helps control the spread of the disease. We proposed an artificial intelligence (AI) system for rapid COVID-19 detection and performed extensive statistical analysis of CTs of COVID-19 based on the AI system. We developed and evaluated our system on a large dataset with more than 10 thousand CT volumes from COVID-19, influenza-A/B, non-viral community acquired pneumonia (CAP) and non-pneumonia subjects. In such a difficult multi-class diagnosis task, our deep convolutional neural network-based system is able to achieve an area under the receiver operating characteristic curve (AUC) of 97.81% for multi-way classification on test cohort of 3,199 scans, AUC of 92.99% and 93.25% on two publicly available datasets, CC-CCII and MosMedData respectively. In a reader study involving five radiologists, the AI system outperforms all of radiologists in more challenging tasks at a speed of two orders of magnitude above them. Diagnosis performance of chest x-ray (CXR) is compared to that of CT. Detailed interpretation of deep network is also performed to relate system outputs with CT presentations. The code is available at https://github.com/ChenWWWeixiang/diagnosis_covid19 .
| S-EPMC7547659 | biostudies-literature
Project description:BackgroundHyperglycemic crises are associated with high morbidity and mortality. Previous studies have proposed methods to predict adverse outcomes of patients in hyperglycemic crises; however, artificial intelligence (AI) has never been used to predict adverse outcomes. We implemented an AI model integrated with the hospital information system (HIS) to clarify whether AI could predict adverse outcomes.MethodsWe included 2,666 patients with hyperglycemic crises from emergency departments (ED) between 2009 and 2018. The patients were randomized into a 70%/30% split for AI model training and testing. Twenty-two feature variables from the electronic medical records were collected. The performance of the multilayer perceptron (MLP), logistic regression, random forest, Light Gradient Boosting Machine (LightGBM), support vector machine (SVM), and K-nearest neighbor (KNN) algorithms was compared. We selected the best algorithm to construct an AI model to predict sepsis or septic shock, intensive care unit (ICU) admission, and all-cause mortality within 1 month. The outcomes between the non-AI and AI groups were compared after implementing the HIS and predicting the hyperglycemic crisis death (PHD) score.ResultsThe MLP had the best performance in predicting the three adverse outcomes, compared with the random forest, logistic regression, SVM, KNN, and LightGBM models. The areas under the curves (AUCs) using the MLP model were 0.852 for sepsis or septic shock, 0.743 for ICU admission, and 0.796 for all-cause mortality. Furthermore, we integrated the AI predictive model with the HIS to assist decision making in real time. No significant differences in ICU admission or all-cause mortality were detected between the non-AI and AI groups. The AI model performed better than the PHD score for predicting all-cause mortality (AUC 0.796 vs. 0.693).ConclusionsA real-time AI predictive model is a promising method for predicting adverse outcomes in ED patients with hyperglycemic crises. Further studies recruiting more patients are warranted.
| S-EPMC10594858 | biostudies-literature
Project description:ObjectiveProning has been shown to improve oxygenation and mortality in certain populations of intubated patients with acute respiratory distress syndrome. Small observational analyses of COVID-19 patients suggest awake proning may lead to clinical improvement. Data on safety and efficacy is lacking. We sought to describe the effect of proning on oxygenation in nonintubated COVID-19 patients. We also evaluated feasibility, safety, and other physiological and clinical outcomes associated with this intervention.MethodsWe conducted a prospective, observational cohort study of nonintubated patients with COVID-19 who underwent proning per an Emergency Department (ED) clinical protocol. Patients with mild to moderate respiratory distress were included. We calculated change in oxygenation by comparing the oxygen saturation to fraction of inspired oxygen ratio (SpO2:FiO2) during the five minutes prior to proning and first 30 min of proning. We also captured data on respiratory rate, duration of proning, need for intubation, intensive care unit admission, survival to discharge.ResultsFifty-two patients were enrolled. Thirty were excluded for not meeting protocol inclusion criteria or missing baseline oxygenation data, leaving 22 for analysis. The SpO2:FiO2 ratio increased by a median of 5 (IQR: 0-15) in the post-proning period compared to the pre-proning period (median: 298 (IQR: 263-352) vs 295 (IQR: 276-350), p = 0.01). Respiratory rate did not change significantly between time periods. No immediate adverse events occurred during proning. Five patients (23%) were intubated within 48 h of admission.ConclusionEarly, awake proning may be feasible in select COVID-19 patients and was associated with improved oxygenation.
| S-EPMC7713606 | biostudies-literature
Project description:BackgroundThe global healthcare burden of COVID-19 continues to rise. There is currently limited information regarding the disease progression and the need for hospitalizations in patients who present to the Emergency Department (ED) with minimal or no symptoms.ObjectivesThis study identifies bounceback rates and timeframes for patients who return to the ED due to COVID-19 after initial discharge on the date of testing.MethodsUsing the NorthShore University Health System's (NSUHS) Enterprise Data Warehouse (EDW), we conducted a retrospective cohort analysis of patients who were tested positive for COVID-19 and were discharged home on the date of testing. A one-month follow-up period was included to ensure the capture of disease progression.ResultsOf 1883 positive cases with initially mild symptoms, 14.6% returned to the ED for complaints related to COVID-19. 56.9% of the mildly symptomatic bounceback patients were discharged on the return visit while 39.5% were admitted to the floor and 3.6% to the ICU. Of the 1120 positive cases with no initial symptoms, only four returned to the ED (0.26%) and only one patient was admitted. Median initial testing occurred on day 3 (2-5.6) of illness, and median ED bounceback occurred on day 9 (6.3-12.7). Our statistical model was unable to identify risk factors for ED bouncebacks.ConclusionCOVID-19 patients diagnosed with mild symptoms on initial presentation have a 14.6% rate of bounceback due to progression of illness.
| S-EPMC8054547 | biostudies-literature
Project description:BackgroundCoronavirus disease 2019 (Covid-19) might present neurological symptoms. We aimed to evaluate the frequency of them at the moment of emergency department (ED) visit and their impact in the prognosis.MethodsRetrospective cohort study including all consecutive hospitalized cases between March 8th and April 11th, 2020. Covid-19 diagnosis was confirmed by polymerase chain reaction test and/or serology. We compared, in patients with and without neurological symptoms on admission, demographic, clinical presentation, and frequency and type of abnormal laboratory values. We analyzed the variables that were associated with in-hospital all-cause mortality by Cox-regression log-rank test.ResultsWe included 576 hospitalized patients, 250 (43.3%) female, aged 67.2 years. At the moment of ED visit, 320 (55.6%) described neurological symptoms, including anosmia (146, 25.3%), myalgia (139, 24.1%), headache (137, 23.8%), and altered mental status (98, 17.0%). Neurological symptoms started the first symptomatic day in 198 (54.2%) cases. Patients with neurological symptoms presented later to the ED (7.9 versus. 6.6 days, p = .019). Only four (0.6%) cases had no typical Covid-19 general symptoms, and only six (1.9%) had a normal laboratory results, for a sensitivity of 98.7% (95% confidence interval (CI): 96.6%-99.6%) and 98.1% (95% CI: 95.7%-99.2%), respectively. In the multivariate Cox-regression of mortality predictors, anosmia (HR: 0.358, 95%CI: 0.140-0.916) and altered mental status (HR: 1.867, 95%CI: 1.162-3.001) were significant.ConclusionNeurological symptoms were the most frequent extrapulmonary symptoms. They were present in half of the Covid-19 patients at the time of the ED visit. Anosmia on admission was an independent predictor of lower in-hospital mortality and altered mental status on admission predicted in-hospital mortality.
| S-EPMC7994975 | biostudies-literature