ABSTRACT
Background: Early prediction of oxygen therapy in patients with coronavirus disease 2019 (COVID-19) is vital for triage. Several machine-learning prognostic models for COVID-19 are currently available. However, external validation of these models has rarely been performed. Therefore, most reported predictive performance is optimistic and has a high risk of bias. This study aimed to develop and validate a model that predicts oxygen therapy needs in the early stages of COVID-19 using a sizable multicenter dataset. Methods: This multicenter retrospective study included consecutive COVID-19 hospitalized patients confirmed by a reverse transcription chain reaction in 11 medical institutions in Fukui, Japan. We developed and validated seven machine-learning models (e.g., penalized logistic regression model) using routinely collected data (e.g., demographics, simple blood test). The primary outcome was the need for oxygen therapy (≥1 L/min or SpO2 ≤ 94%) during hospitalization. C-statistics, calibration slope, and association measures (e.g., sensitivity) evaluated the performance of the model using the test set (randomly selected 20% of data for internal validation). Among these seven models, the machine-learning model that showed the best performance was re-evaluated using an external dataset. We compared the model performances using the A-DROP criteria (modified version of CURB-65) as a conventional method. Results: Of the 396 patients with COVID-19 for the model development, 102 patients (26%) required oxygen therapy during hospitalization. For internal validation, machine-learning models, except for the k-point nearest neighbor, had a higher discrimination ability than the A-DORP criteria (P < 0.01). The XGboost had the highest c-statistic in the internal validation (0.92 vs. 0.69 in A-DROP criteria; P < 0.001). For the external validation with 728 temporal independent datasets (106 patients [15%] required oxygen therapy), the XG boost model had a higher c-statistic (0.88 vs. 0.69 in A-DROP criteria; P < 0.001). Conclusions: Machine-learning models demonstrated a more significant performance in predicting the need for oxygen therapy in the early stages of COVID-19.
ABSTRACT
BACKGROUND: Patients with severe coronavirus disease 2019 (COVID-19) infection require a long period of time to return to work and society due to significant physical weakness even after recovery. Here we report a patient with a history of nephrectomy who developed severe COVID-19 infection associated with muscle weakness but was able to return to society after rehabilitation therapy. CASE PRESENTATION: A Japanese man in his 40s was admitted to the hospital with PCR-based COVID-19 diagnosis. The respiratory condition worsened rapidly and was treated with extracorporeal membrane-assisted ventilation in the intensive case unit. On admission to the Rehabilitation Department on day T + 30 [T: day patient became febrile (38 °C)], he was unable to stand for a long time and used a walker. Rehabilitation therapy was postponed to prevent COVID-19 spread, but the patient was encouraged to exercise during isolation to improve trunk and lower extremity muscle strength. Physical therapy commenced on day T + 49 to improve gait and trunk and lower limb muscle strength. He was able to walk independently and later returned to work following discharge on day T + 53. A computed tomography scan showed an increase in psoas muscle volume from 276 before to 316 cm3 after physical therapy, together with a decrease in whole-body extracellular water:total body weight ratio from 0.394 to 0.389. CONCLUSIONS: We have described the beneficial effects of rehabilitation therapy in a patient with severe COVID-19 infection. In addition to exercise, we believe that nutrition is even more important in increasing skeletal muscle mass. Rehabilitation therapy is recommended to enhance the return of severely ill COVID-19 patients to routine daily activity.
Subject(s)
COVID-19 , COVID-19 Testing , Humans , Male , Muscle Weakness/etiology , Physical Therapy Modalities/adverse effects , Respiration, ArtificialABSTRACT
Background Early prediction of oxygen therapy in patients with coronavirus disease 2019 (COVID-19) is vital for triage. Several machine-learning prognostic models for COVID-19 are currently available. However, external validation of these models has rarely been performed. Therefore, most reported predictive performance is optimistic and has a high risk of bias. This study aimed to develop and validate a model that predicts oxygen therapy needs in the early stages of COVID-19 using a sizable multicenter dataset. Methods This multicenter retrospective study included consecutive COVID-19 hospitalized patients confirmed by a reverse transcription chain reaction in 11 medical institutions in Fukui, Japan. We developed and validated seven machine-learning models (e.g., penalized logistic regression model) using routinely collected data (e.g., demographics, simple blood test). The primary outcome was the need for oxygen therapy (≥1 L/min or SpO2 ≤ 94%) during hospitalization. C-statistics, calibration slope, and association measures (e.g., sensitivity) evaluated the performance of the model using the test set (randomly selected 20% of data for internal validation). Among these seven models, the machine-learning model that showed the best performance was re-evaluated using an external dataset. We compared the model performances using the A-DROP criteria (modified version of CURB-65) as a conventional method. Results Of the 396 patients with COVID-19 for the model development, 102 patients (26%) required oxygen therapy during hospitalization. For internal validation, machine-learning models, except for the k-point nearest neighbor, had a higher discrimination ability than the A-DORP criteria (P < 0.01). The XGboost had the highest c-statistic in the internal validation (0.92 vs. 0.69 in A-DROP criteria;P < 0.001). For the external validation with 728 temporal independent datasets (106 patients [15%] required oxygen therapy), the XG boost model had a higher c-statistic (0.88 vs. 0.69 in A-DROP criteria;P < 0.001). Conclusions Machine-learning models demonstrated a more significant performance in predicting the need for oxygen therapy in the early stages of COVID-19.