Personalized Assessment of Mortality Risk and Hospital Stay Duration in Hospitalized Patients with COVID-19 Treated with Remdesivir: A Machine Learning Approach DOI Open Access

Antonio Ramón,

Andrés Bas Castillo,

Santiago Herrero González

и другие.

Опубликована: Фев. 24, 2024

Despite widespread vaccination, early treatments, and improved understanding of the disease, effects SARS-CoV-2 infection remain significant worldwide. Many patients still suffer from severe COVID-19, necessitating admission to intensive care units. Remdesivir is a primary treatment option among viral RNA polymerase inhibitors for hospitalized patients. However, there lack studies examining factors influencing its effectiveness in this context. We conducted retrospective study throughout 2022, analyzing clinical, laboratory, sociodemographic data 252 COVID-19 treated with remdesivir. Six machine learning algorithms were compared validated predict associated loss clinical benefit remdesivir terms mortality hospital stay. Data extracted electronic health records. The eXtreme Gradient Boost (XGB) method achieved highest balanced accuracy both (95.45%) stay (94.24%). Factors worse outcomes use included limitation life support treatment, need ventilatory (especially invasive mechanical ventilation) on day 14 after first dose remdesivir, lymphopenia, low levels albumin hemoglobin, presence flu and/or coinfection, cough. number doses vaccine, patchy lung density, bilateral pulmonary radiological status, comorbidities, oxygen therapy, troponin lactate dehydrogenase levels, asthenia. These findings highlight XGB as strong candidate accurately categorizing undergoing treatment.

Язык: Английский

Personalized Assessment of Mortality Risk and Hospital Stay Duration in Hospitalized Patients with COVID-19 Treated with Remdesivir: A Machine Learning Approach DOI Open Access

Antonio Ramón,

Andrés Bas,

Santiago Herrero

и другие.

Journal of Clinical Medicine, Год журнала: 2024, Номер 13(7), С. 1837 - 1837

Опубликована: Март 22, 2024

Background: Despite advancements in vaccination, early treatments, and understanding of SARS-CoV-2, its impact remains significant worldwide. Many patients require intensive care due to severe COVID-19. Remdesivir, a key treatment option among viral RNA polymerase inhibitors, lacks comprehensive studies on factors associated with effectiveness. Methods: We conducted retrospective study 2022, analyzing data from 252 hospitalized COVID-19 treated remdesivir. Six machine learning algorithms were compared predict influencing remdesivir’s clinical benefits regarding mortality hospital stay. Results: The extreme gradient boost (XGB) method showed the highest accuracy for both (95.45%) stay (94.24%). Factors worse outcomes terms included limitations life support, ventilatory support needs, lymphopenia, low albumin hemoglobin levels, flu and/or coinfection, cough. For stay, vaccine doses, lung density, pulmonary radiological status, comorbidities, oxygen therapy, troponin, lactate dehydrogenase asthenia. Conclusions: These findings underscore XGB’s effectiveness accurately categorizing undergoing remdesivir treatment.

Язык: Английский

Процитировано

2
Personalized Assessment of Mortality Risk and Hospital Stay Duration in Hospitalized Patients with COVID-19 Treated with Remdesivir: A Machine Learning Approach DOI Open Access

Antonio Ramón,

Andrés Bas Castillo,

Santiago Herrero González

и другие.

Опубликована: Фев. 24, 2024

Despite widespread vaccination, early treatments, and improved understanding of the disease, effects SARS-CoV-2 infection remain significant worldwide. Many patients still suffer from severe COVID-19, necessitating admission to intensive care units. Remdesivir is a primary treatment option among viral RNA polymerase inhibitors for hospitalized patients. However, there lack studies examining factors influencing its effectiveness in this context. We conducted retrospective study throughout 2022, analyzing clinical, laboratory, sociodemographic data 252 COVID-19 treated with remdesivir. Six machine learning algorithms were compared validated predict associated loss clinical benefit remdesivir terms mortality hospital stay. Data extracted electronic health records. The eXtreme Gradient Boost (XGB) method achieved highest balanced accuracy both (95.45%) stay (94.24%). Factors worse outcomes use included limitation life support treatment, need ventilatory (especially invasive mechanical ventilation) on day 14 after first dose remdesivir, lymphopenia, low levels albumin hemoglobin, presence flu and/or coinfection, cough. number doses vaccine, patchy lung density, bilateral pulmonary radiological status, comorbidities, oxygen therapy, troponin lactate dehydrogenase levels, asthenia. These findings highlight XGB as strong candidate accurately categorizing undergoing treatment.

Язык: Английский

Процитировано

1