ABSTRACT
Background: Prioritizing the patients requiring intensive care may decrease the fatality of coronavirus disease-2019 (COVID-19). Aims and objectives: To develop, validate, and compare two models based on machine-learning methods for predicting patients with COVID-19 requiring intensive care. Materials and methods: In 2021, 506 suspected COVID-19 patients, with clinical presentations along with radiographic findings, were laboratory confirmed and included in the study. The primary end-point was patients with COVID-19 requiring intensive care, defined as actual admission to the intensive care unit (ICU). The data were randomly partitioned into training and testing sets (70% and 30%, respectively) without overlapping. A decision-tree algorithm and multivariate logistic regression were performed to develop the models for predicting the cases based on their first 24 hours data. The predictive performance of the models was compared based on the area under the receiver operating characteristic curve (AUC), sensitivity, and accuracy of the models. Results: A 10-fold cross-validation decision-tree model predicted cases requiring intensive care with the AUC, accuracy, and sensitivity of 97%, 98%, and 94.74%, respectively. The same values in the machine-learning logistic regression model were 75%, 85.62%, and 55.26%, respectively. Creatinine, smoking, neutrophil/lymphocyte ratio, temperature, respiratory rate, partial thromboplastin time, white blood cell, Glasgow Coma Scale (GCS), dizziness, international normalized ratio, O2 saturation, C-reactive protein, diastolic blood pressure (DBP), and dry cough were the most important predictors. Conclusion: In an Iranian population, our decision-based machine-learning method offered an advantage over logistic regression for predicting patients requiring intensive care. This method can support clinicians in decision-making, using patients' early data, particularly in low- and middle-income countries where their resources are as limited as Iran. How to cite this article: Sabetian G, Azimi A, Kazemi A, Hoseini B, Asmarian N, Khaloo V, et al. Prediction of Patients with COVID-19 Requiring Intensive Care: A Cross-sectional Study based on Machine-learning Approach from Iran. Indian J Crit Care Med 2022;26(6):688-695. Ethics approval: This study was approved by the Ethical Committee of Shiraz University of Medical Sciences (IR.SUMS.REC.1399.018).
ABSTRACT
Endotracheal tube (ETT) obstruction, either complete or partial, is a serious life threatening complication in intubated patients. Therefore, implementing a practical method to diagnose this condition is vital. Alteration in respiratory sound signals caused by ETT occlusion can be used for early detection of obstruction. This study is aimed to assess changes in respiratory sound signals after creation of different types of tubal obstruction in an animal model experiment. Artificial internal obstructions were created in three different sizes and three different locations by stitching pieces of smaller tubes in ETTs with internal diameter of 8 mm. A microphone was used to record respiratory sounds during both spontaneous breathing and mechanical ventilation in seven anesthetized dogs. The sound intensity levels produced by different grades and degrees of obstructions were measured and compared with those in non-obstructed tubes. During spontaneous breathing, significant decrease in sound intensity level was detected even with the lowest grades of obstruction (p = 0.003, 0.001, and 0.002, proximal, middle and distal obstructions, respectively). However, in mechanical ventilation, significant decrease in sound intensity was observed only in distal tubal obstruction (p = 0.037). The difference among levels of sound intensity produced by different obstruction locations of occlusion was not statistically significant (p ≥ 0.090). Data analysis revealed that sound intensity level decreased significantly when the degree of obstruction increased. In addition, this change in sound level was not related to the location of obstruction. The decrease in sound intensity changes can be used to detect ETT obstruction. However, further studies are needed for clinical application.
