November 2023 in “Advances and Applications in Statistics” In this retrospective study, researchers developed machine learning models to predict mortality risk among 7115 COVID-19 patients in Iran, finding that the random forests model performed best with 96% accuracy and identified factors like intubation and SpO2 as significant predictors.
6 citations
,
October 2024 in “npj Digital Medicine” This study observed that patients with COVID-19 had many conditions and phenotypes that increased post-infection, varying by demographics and infection wave, which could enhance understanding and diagnostics of Long-COVID.
December 2020 in “Research Square (Research Square)” This study found that the AndroCoV Clinical Scoring for COVID-19 Diagnosis is a feasible, sensitive, and cost-effective tool with higher accuracy than most rtPCR-SARS-CoV-2 tests for diagnosing COVID-19.
1 citations
,
February 2024 in “npj digital medicine” This study developed a deep-learning model using unannotated dermatology images from online forums, achieving 49.64% accuracy in classifying 22 skin diseases and 61.76% accuracy in detecting monkeypox, highlighting the potential of these images for skin disease diagnostics in China.
1 citations
,
January 2021 in “medRxiv (Cold Spring Harbor Laboratory)” This study reports that the AndroCoV Clinical Scoring for COVID-19 Diagnosis provides a quicker, more sensitive, and inexpensive alternative to rtPCR-SARS-CoV-2 with an accuracy above 80% in diagnosing COVID-19.
