Prediction of respiratory decompensation in Covid-19 patients using machine learning: The READY trial

Abstract

Background Currently, physicians are limited in their ability to provide an accurate prognosis for COVID-19 positive patients. Existing scoring systems have been ineffective for identifying patient decompensation. Machine learning (ML) may offer an alternative strategy. A prospectively validated method to predict the need for ventilation in COVID-19 patients is essential to help triage patients, allocate resources, and prevent emergency intubations and their associated risks. Methods In a multicenter clinical trial, we evaluated the performance of a machine learning algorithm for prediction of invasive mechanical ventilation of COVID-19 patients within 24 h of an initial encounter. We enrolled patients with a COVID-19 diagnosis who were admitted to five United States health systems between March 24 and May 4, 2020. Results 197 patients were enrolled in the REspirAtory Decompensation and model for the triage of covid-19 patients: a prospective studY (READY) clinical trial. The algorithm had a higher diagnostic odds ratio (DOR, 12.58) for predicting ventilation than a comparator early warning system, the Modified Early Warning Score (MEWS). The algorithm also achieved significantly higher sensitivity (0.90) than MEWS, which achieved a sensitivity of 0.78, while maintaining a higher specificity (p < 0.05). Conclusions In the first clinical trial of a machine learning algorithm for ventilation needs among COVID-19 patients, the algorithm demonstrated accurate prediction of the need for mechanical ventilation within 24 h. This algorithm may help care teams effectively triage patients and allocate resources. Further, the algorithm is capable of accurately identifying 16% more patients than a widely used scoring system while minimizing false positive results.

Intelligent system for COVID-19 prognosis: a state-of-the-art survey

“… [ 29 ] COVID-19 patients data of Massachusetts, Georgia, and New Jersey. GB (Gradient Boosting) algorithm Text data Better prediction rate [ 30 ] COVID-19 Patient Dataset ML algorithm Text data Good prediction rate [ 31 ] COVID-19 Indian Dataset Support vector Kuhntucker model Text data Better Prediction rate [ 32 ] COVID-19 data from Mindstream-ai ANN Text data Better prediction rate to identify infection is obtained. [ 33 ] COVID-19 Data Logistic Model + Prophet method Time-series data Good prediction rate [ 34 ] CT dataset AD3D-MIL algorithm (A Deep 3D-Multiple Instance Learning) Image data An accuracy of 97.9% is obtained [ 35 ] JHU CSSE database - Text data Good identification rate [ 36 ] Two COVID-19 chest X-ray datasets KNN (K Nearest Neighbor) + Manta-Ray Foraging Optimization (MRFO) Image data 96.09% and 98.09% accuracies is obtained for two datasets respectively [ 37 ] COVID-19 patient data XGB (Extreme Gradient Boosting), Decision Tree (DT), Random Forest (RF), SVM, GBM (Gradient Boosting Machine) Text data ...…”

Predicting Hospitals Hygiene Rate during COVID-19 Pandemic

“…The rate of Hand hygiene compliance almost stands on the method employed for measurement and place of assessment, with differentiation between clinics, intensive care units (ICU) and other places in the medical organisations. Several studies emphasis on that covering medical include its different unites by hand hygiene dispensers is not the ideal way to gain a high level of hygiene compliance [6] [7]. That indicates the importance of using technologies to support decision-makers to allocate hand hygiene dispensers and get the vital data to monitor and manage hygiene systems in an optimal way [8].…”

Predicting the duration of inpatient treatment for COVID-19 patients

“…Разработанная авторами модель машинного обучения продемонстрировала высокую точность (80%) для прогнозирования риска развития ОРДС у пациентов с подозрением на COVID-19 без явных клинических признаков тяжелого течения заболевания [20]. Сегодня также известны методы диагностики COVID-19 с помощью мобильного приложения и на основании одних только симптомов заболевания [21,22], прогнозирования тяжелого течения COVID-19 [23][24][25][26] и летального исхода [27,28]. В мае 2020 г. в журнале Nature Machine Intelligence была опубликована научная статья, в которой был представлен новый, простой и интерпретируемый алгоритм оценки риска смерти больных COVID-19 по уровню лактатдегидрогеназы, количеству лимфоцитов и уровню С-реактивного белка [29].…”