An artificial neural network model to predict the mortality of COVID-19 patients using routine blood samples at the time of hospital admission: Development and validation study.
Ontology highlight
ABSTRACT:
SUBMITTER: Lin JK
PROVIDER: S-EPMC8284724 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundCOVID-19, which is accompanied by acute respiratory distress, multiple organ failure, and death, has spread worldwide much faster than previously thought. However, at present, it has limited treatments.ObjectiveTo overcome this issue, we developed an artificial intelligence (AI) model of COVID-19, named EDRnet (ensemble learning model based on deep neural network and random forest models), to predict in-hospital mortality using a routine blood sample at the time of hospital admission.MethodsWe selected 28 blood biomarkers and used the age and gender information of patients as model inputs. To improve the mortality prediction, we adopted an ensemble approach combining deep neural network and random forest models. We trained our model with a database of blood samples from 361 COVID-19 patients in Wuhan, China, and applied it to 106 COVID-19 patients in three Korean medical institutions.ResultsIn the testing data sets, EDRnet provided high sensitivity (100%), specificity (91%), and accuracy (92%). To extend the number of patient data points, we developed a web application (BeatCOVID19) where anyone can access the model to predict mortality and can register his or her own blood laboratory results.ConclusionsOur new AI model, EDRnet, accurately predicts the mortality rate for COVID-19. It is publicly available and aims to help health care providers fight COVID-19 and improve patients' outcomes.
| S-EPMC7759509 | biostudies-literature
Project description:BackgroundIdentification of patients with novel coronavirus disease 2019 (COVID-19) requiring hospital admission or at high-risk of in-hospital mortality is essential to guide patient triage and to provide timely treatment for higher risk hospitalized patients.MethodsA retrospective multi-centre (8 hospital) cohort at Beaumont Health, Michigan, USA, reporting on COVID-19 patients diagnosed between 1 March and 1 April 2020 was used for score validation. The COVID-19 Risk of Complications Score was automatically computed by the EHR. Multivariate logistic regression models were built to predict hospital admission and in-hospital mortality using individual variables constituting the score. Validation was performed using both discrimination and calibration.ResultsCompared to Green scores, Yellow Scores (OR: 5.72) and Red Scores (OR: 19.1) had significantly higher odds of admission (both p < .0001). Similarly, Yellow Scores (OR: 4.73) and Red Scores (OR: 13.3) had significantly higher odds of in-hospital mortality than Green Scores (both p < .0001). The cross-validated C-Statistics for the external validation cohort showed good discrimination for both hospital admission (C = 0.79 (95% CI: 0.77-0.81)) and in-hospital mortality (C = 0.75 (95% CI: 0.71-0.78)).ConclusionsThe COVID-19 Risk of Complications Score predicts the need for hospital admission and in-hospital mortality patients with COVID-19. Key points: Can an electronic health record generated risk score predict the risk of hospital admission and in-hospital mortality in patients diagnosed with coronavirus disease 2019 (COVID-19)? In both validation cohorts of 2,025 and 1,290 COVID-19, the cross-validated C-Statistics showed good discrimination for both hospital admission (C = 0.79 (95% CI: 0.77-0.81)) and in-hospital mortality (C = 0.75 (95% CI: 0.71-0.78)), respectively. The COVID-19 Risk of Complications Score may help predict the need for hospital admission if a patient contracts SARS-CoV-2 infection and in-hospital mortality for a hospitalized patient with COVID-19.
| S-EPMC7877986 | biostudies-literature
Project description:IntroductionPrevious studies have shown that patients admitted to the intensive care unit (ICU) after "office hours" are more likely to die. However these results have been challenged by numerous other studies. We therefore analysed this possible relationship between ICU admission time and in-hospital mortality in The Netherlands.MethodsThis article relates time of ICU admission to hospital mortality for all patients who were included in the Dutch national ICU registry (National Intensive Care Evaluation, NICE) from 2002 to 2008. We defined office hours as 08:00-22:00 hours during weekdays and 09:00-18:00 hours during weekend days. The weekend was defined as from Saturday 00:00 hours until Sunday 24:00 hours. We corrected hospital mortality for illness severity at admission using Acute Physiology and Chronic Health Evaluation II (APACHE II) score, reason for admission, admission type, age and gender.ResultsA total of 149,894 patients were included in this analysis. The relative risk (RR) for mortality outside office hours was 1.059 (1.031-1.088). Mortality varied with time but was consistently higher than expected during "off hours" and lower during office hours. There was no significant difference in mortality between different weekdays of Monday to Thursday, but mortality increased slightly on Friday (RR 1.046; 1.001-1.092). During the weekend the RR was 1.103 (1.071-1.136) in comparison with the rest of the week.ConclusionsHospital mortality in The Netherlands appears to be increased outside office hours and during the weekends, even when corrected for illness severity at admission. However, incomplete adjustment for certain confounders might still play an important role. Further research is needed to fully explain this difference.
| S-EPMC2940016 | biostudies-literature
Project description:Early prediction of in-hospital mortality can improve patient outcome. Current prediction models for in-hospital mortality focus mainly on specific pathologies. Structured pathology data is hospital-wide readily available and is primarily used for e.g. financing purposes. We aim to build a predictive model at admission using the International Classification of Diseases (ICD) codes as predictors and investigate the effect of the self-evident DNR ("Do Not Resuscitate") diagnosis codes and palliative care codes. We compare the models using ICD-10-CM codes with Risk of Mortality (RoM) and Charlson Comorbidity Index (CCI) as predictors using the Random Forests modeling approach. We use the Present on Admission flag to distinguish which diagnoses are present on admission. The study is performed in a single center (Ghent University Hospital) with the inclusion of 36 368 patients, all discharged in 2017. Our model at admission using ICD-10-CM codes (AUCROC = 0.9477) outperforms the model using RoM (AUCROC = 0.8797 and CCI (AUCROC = 0.7435). We confirmed that DNR and palliative care codes have a strong impact on the model resulting in a decrease of 7% for the ICD model (AUCROC = 0.8791) at admission. We therefore conclude that a model with a sufficient predictive performance can be derived from structured pathology data, and if real-time available, can serve as a prerequisite to develop a practical clinical decision support system for physicians.
| S-EPMC7316243 | biostudies-literature
Project description:BackgroundPredicting death in a cohort of clinically diverse, multi-condition hospitalized patients is difficult. This frequently hinders timely serious illness care conversations. Prognostic models that can determine 6-month death risk at the time of hospital admission can improve access to serious illness care conversations.ObjectiveThe objective is to determine if the demographic, vital sign, and laboratory data from the first 48 h of a hospitalization can be used to accurately quantify 6-month mortality risk.DesignThis is a retrospective study using electronic medical record data linked with the state death registry.ParticipantsParticipants were 158,323 hospitalized patients within a 6-hospital network over a 6-year period.Main measuresMain measures are the following: the first set of vital signs, complete blood count, basic and complete metabolic panel, serum lactate, pro-BNP, troponin-I, INR, aPTT, demographic information, and associated ICD codes. The outcome of interest was death within 6 months.Key resultsModel performance was measured on the validation dataset. A random forest model-mini serious illness algorithm-used 8 variables from the initial 48 h of hospitalization and predicted death within 6 months with an AUC of 0.92 (0.91-0.93). Red cell distribution width was the most important prognostic variable. min-SIA (mini serious illness algorithm) was very well calibrated and estimated the probability of death to within 10% of the actual value. The discriminative ability of the min-SIA was significantly better than historical estimates of clinician performance.Conclusionmin-SIA algorithm can identify patients at high risk of 6-month mortality at the time of hospital admission. It can be used to improved access to timely, serious illness care conversations in high-risk patients.
| S-EPMC7210334 | biostudies-literature
Project description:COVID-19 is a disease with a variable clinical course ranging from mild symptoms to critical illness, organ failure, and death. Prospective biomarkers may help to predict the severity of an individual's clinical course and mortality risk. We analyzed asymmetric (ADMA) and symmetric dimethylarginine (SDMA) in blood samples from 31 patients hospitalized for COVID-19. We calculated associations of ADMA and SDMA with mortality and organ failure, and we developed a predictive algorithm based upon these biomarkers to predict mortality risk. Nine patients (29%) experienced in-hospital death. SDMA and ADMA serum concentrations were significantly higher at admission in COVID-19 patients who died than in survivors. Cut-offs of 0.90 µmol/L for SDMA (AUC, 0.904, p = 0.0005) and 0.66 µmol/L for ADMA (AUC, 0.874, p = 0.0013) were found in ROC analyses to best discriminate both subgroups of patients. Hazard ratio for in-hospital mortality was 12.2 (95% CI: 2.2-31.2) for SDMA and 6.3 (1.1-14.7) for ADMA above cut-off. Sequential analysis of both biomarkers allowed discriminating a high-risk group (87.5% mortality) from an intermediate-risk group (25% mortality) and a low-risk group (0% mortality). Elevated circulating concentrations of SDMA and ADMA may help to better identify COVID-19 patients with a high risk of in-hospital mortality.
| S-EPMC8110746 | biostudies-literature
Project description:The aim of the study is to develop artificial intelligence (AI) algorithm based on a deep learning model to predict mortality using abbreviate injury score (AIS). The performance of the conventional anatomic injury severity score (ISS) system in predicting in-hospital mortality is still limited. AIS data of 42,933 patients registered in the Korean trauma data bank from four Korean regional trauma centers were enrolled. After excluding patients who were younger than 19 years old and those who died within six hours from arrival, we included 37,762 patients, of which 36,493 (96.6%) survived and 1269 (3.4%) deceased. To enhance the AI model performance, we reduced the AIS codes to 46 input values by organizing them according to the organ location (Region-46). The total AIS and six categories of the anatomic region in the ISS system (Region-6) were used to compare the input features. The AI models were compared with the conventional ISS and new ISS (NISS) systems. We evaluated the performance pertaining to the 12 combinations of the features and models. The highest accuracy (85.05%) corresponded to Region-46 with DNN, followed by that of Region-6 with DNN (83.62%), AIS with DNN (81.27%), ISS-16 (80.50%), NISS-16 (79.18%), NISS-25 (77.09%), and ISS-25 (70.82%). The highest AUROC (0.9084) corresponded to Region-46 with DNN, followed by that of Region-6 with DNN (0.9013), AIS with DNN (0.8819), ISS (0.8709), and NISS (0.8681). The proposed deep learning scheme with feature combination exhibited high accuracy metrics such as the balanced accuracy and AUROC than the conventional ISS and NISS systems. We expect that our trial would be a cornerstone of more complex combination model.
| S-EPMC8651670 | biostudies-literature
Project description:BackgroundIn prevention, sedentary behaviour and physical activity have been associated with risk of cardiovascular disease and mortality. Less is known about associations with utilization of hospital care.AimTo investigate whether physical activity level and sedentary behaviour prior to cardiac ward admission can predict utilization of hospital care and mortality among patients with cardiovascular disease.MethodsLongitudinal observational study including 1148 patients admitted and treated in cardiac wards in two hospitals. Subjective reports of physical activity levels and sedentary time prior to admission were collected during inpatient care and categorized as low, medium or high. The associations between physical activity level and sedentary time with hospital stay, readmission and mortality were analysed using linear, logistic and Cox regressions.ResultsMedian hospital stay was 2.1 days. One higher step in the physical activity level, or lower sedentary time, was related to an approximately 0.9 days shorter hospital stay. Sixty per cent of patients were readmitted to hospital. The risk of being readmitted was lower for individuals reporting high physical activity and low sedentary time (odds ratios ranging between 0.44 and 0.91). A total of 200 deaths occurred during the study. Mortality was lower among those with high and medium physical activity levels and low sedentary time (hazard ratios ranging between 0.36 and 0.90).ConclusionBoth physical activity level and sedentary time during the period preceding hospitalization for cardiac events were predictors of hospital utilization and mortality. This highlights the prognostic value of assessing patients' physical activity and sedentary behaviour.
| S-EPMC7817990 | biostudies-literature
Project description:BackgroundHospitalisation due to acute exacerbations of COPD (AECOPD) is common, and subsequent mortality high. The DECAF score was derived for accurate prediction of mortality and risk stratification to inform patient care. We aimed to validate the DECAF score, internally and externally, and to compare its performance to other predictive tools.MethodsThe study took place in the two hospitals within the derivation study (internal validation) and in four additional hospitals (external validation) between January 2012 and May 2014. Consecutive admissions were identified by screening admissions and searching coding records. Admission clinical data, including DECAF indices, and mortality were recorded. The prognostic value of DECAF and other scores were assessed by the area under the receiver operator characteristic (AUROC) curve.ResultsIn the internal and external validation cohorts, 880 and 845 patients were recruited. Mean age was 73.1 (SD 10.3) years, 54.3% were female, and mean (SD) FEV1 45.5 (18.3) per cent predicted. Overall mortality was 7.7%. The DECAF AUROC curve for inhospital mortality was 0.83 (95% CI 0.78 to 0.87) in the internal cohort and 0.82 (95% CI 0.77 to 0.87) in the external cohort, and was superior to other prognostic scores for inhospital or 30-day mortality.ConclusionsDECAF is a robust predictor of mortality, using indices routinely available on admission. Its generalisability is supported by consistent strong performance; it can identify low-risk patients (DECAF 0-1) potentially suitable for Hospital at Home or early supported discharge services, and high-risk patients (DECAF 3-6) for escalation planning or appropriate early palliation.Trial registration numberUKCRN ID 14214.
| S-EPMC4752621 | biostudies-literature
Project description:Prostate cancer treatment strategies are guided by risk-stratification. This stratification can be difficult in some patients with known comorbidities. New models are needed to guide strategies and determine which patients are at risk of prostate cancer mortality. This article presents a gradient-boosting model to predict the risk of prostate cancer mortality within 10 years after a cancer diagnosis, and to provide an interpretable prediction. This work uses prospective data from the PLCO Cancer Screening and selected patients who were diagnosed with prostate cancer. During follow-up, 8776 patients were diagnosed with prostate cancer. The dataset was randomly split into a training (n = 7021) and testing (n = 1755) dataset. Accuracy was 0.98 (±0.01), and the area under the receiver operating characteristic was 0.80 (±0.04). This model can be used to support informed decision-making in prostate cancer treatment. AI interpretability provides a novel understanding of the predictions to the users.
| S-EPMC8234681 | biostudies-literature