Raoof Nopour, Mostafa Shanbehzadeh, Hadi Kazemi-Arpanahi,
Volume 36, Issue 1 (1-2022)
Abstract
Background: Owing to the shortage of ventilators, there is a crucial demand for an objective and accurate prognosis for 2019 coronavirus disease (COVID-19) critical patients, which may necessitate a mechanical ventilator (MV). This study aimed to construct a predictive model using machine learning (ML) algorithms for frontline clinicians to better triage endangered patients and priorities who would need MV.
Methods: In this retrospective single-center study, the data of 482 COVID-19 patients from February 9, 2020, to December 20, 2020, were analyzed by several ML algorithms including, multi-layer perception (MLP), logistic regression (LR), J-48 decision tree, and Naïve Bayes (NB). First, the most important clinical variables were identified using the Chi-square test at P < 0.01. Then, by comparing the ML algorithms' performance using some evaluation criteria, including TP-Rate, FP-Rate, precision, recall, F-Score, MCC, and Kappa, the best performing one was identified.
Results: Predictive models were trained using 15 validated features, including cough, contusion, oxygen therapy, dyspnea, loss of taste, rhinorrhea, blood pressure, absolute lymphocyte count, pleural fluid, activated partial thromboplastin time, blood glucose, white cell count, cardiac diseases, length of hospitalization, and other underline diseases. The results indicated the J-48 with F-score = 0.868 and AUC = 0.892 yielded the best performance for predicting intubation requirement.
Conclusion: ML algorithms are potentials to improve traditional clinical criteria to forecast the necessity for intubation in COVID-19 in-hospital patients. Such ML-based prediction models may help physicians with optimizing the timing of intubation, better sharing of MV resources and personnel, and increase patient clinical status.
Mirkhoshim Mirsaliyev, Khadisha Kashikova, Aisulu Zholdybayeva, Botakoz Myrzakhmetova, Akmaral Isbasarova, Natalya Petrova, Dana Kozhamberdiyeva,
Volume 37, Issue 1 (2-2023)
Abstract
Background: Research data on hospitalized coronavirus 2019 (COVID-19) survivors indicate the persistence of symptoms, radiological abnormalities, and physiological disorders months after the initial infection. Given the scale of the ongoing pandemic, a substantial number of patients with severe residual pulmonary fibrosis (PF) and oxygen dependence are anticipated. Currently, the search for risk factors associated with the development of fibrotic radiological abnormalities after moderate to severe COVID-19 is underway. Furthermore, the extent to which computed tomography (CT) data correlate with postdischarge symptoms and physical functions remains unclear. This study aimed to characterize patients experiencing persistent pulmonary consequences after hospital discharge. We examined clinical, radiological, and laboratory predictors of pulmonary fibrosis after COVID-19 infection.
Methods: We retrospectively evaluated fibrosis-like lung changes and their prognostic factors in COVID-19 survivors. Our study included 77 patients with laboratory-confirmed COVID-19 who received inpatient treatment at City Clinical Hospital No. 1 in Almaty between November and December 2020. We assessed patients during the acute phase of the disease and again 6 to 8 months after discharge using high-resolution computed tomography (CT). Patients were classified into 2 cohorts based on semi-quantitative analysis of subsequently added tomograms—those with radiological fibrosis-like abnormalities (main group) and those who had recovered (control group).
Results: Parenchymal cords, irregular interfaces, reticulation, and traction bronchiectasis were common CT findings among all COVID-19 patients. Our study focused on patients who developed pulmonary fibrosis within 1 month after the onset of the disease. After 6 to 8 months, fibrosis-like lung changes persisted in 49.35% of patients (leading group), while 50.65% showed disease resolution (control group). Age, body mass index, high interleukin-6 (IL-6) levels, low IO levels, and the need for mechanical ventilation were identified as prognostic indicators for the persistence of pulmonary fibrosis.
Conclusion: Our study revealed that pulmonary function can return to normal in over half of COVID-19 patients 8 months after infection onset. Despite advancements in COVID-19 treatment, there remains a significant knowledge gap in managing long-term effects, especially pulmonary fibrosis. Continued clinical trials and research on post COVID-19 fibrosis are essential to prevent early mortality due to the long-term impacts on these patients.
