MedElevator Войти в исследования
← Поиск публикаций

DOI 10.1016/j.compbiomed.2022.105615

Медицинская библиотека · Computers in biology and medicine · 2022

ISW-LM: An intensive symptom weight learning mechanism for early COVID-19 diagnosis.

Fang Lingling, Liang Xiyue

СтатьяПоддержка исследования: вне правительства СШАПеревод в очереди

Аннотация

The novel coronavirus disease 2019 (COVID-19) pandemic has severely impacted the world. The early diagnosis of COVID-19 and self-isolation can help curb the spread of the virus. Besides, a simple and accurate diagnostic method can help in making rapid decisions for the treatment and isolation of patients. The analysis of patient characteristics, case trajectory, comorbidities, symptoms, diagnosis, and outcomes will be performed in the model. In this paper, a symptom-based machine learning (ML) model with a new learning mechanism called Intensive Symptom Weight Learning Mechanism (ISW-LM) is proposed. The proposed model designs three new symptoms' weight functions to identify the most relevant symptoms used to diagnose and classify COVID-19. To verify the efficiency of the proposed model, multiple laboratory and clinical datasets containing epidemiological symptoms and blood tests are used. Experiments indicate that the importance of COVID-19 infection symptoms varies between countries and regions. In most datasets, the most frequent and significant predictive symptoms for diagnosing COVID-19 are fever, sore throat, and cough. The experiment also compares the state-of-the-art methods with the proposed method, which shows that the proposed model has a high accuracy rate of up to 97.1711%. The positive results indicate that the proposed learning mechanism can help clinicians quickly diagnose and screen patients for COVID-19 at an early stage.

Для цитирования: Fang Lingling, Liang Xiyue. ISW-LM: An intensive symptom weight learning mechanism for early COVID-19 diagnosis.. Computers in biology and medicine. 2022. DOI: 10.1016/j.compbiomed.2022.105615.

Предметные рубрики MeSH

Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…

История · было → стало

Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.

Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.