2 articles
Currently, extensive research has shown that almost all published prediction models are poorly studied and have significant limitations, leading to their predictive performance often being overestimated. Additionally, there is still no universally accepted scoring system, primarily due to the need for adaptation to heterogeneous patient samples (including patient numbers, clinical profiles, and risk factors) and/or ongoing differences in the organization of healthcare systems across various countries.
This is a narrative literature review. A bibliographic search was conducted in the PubMed, Hinari, SpringerLink, National Center for Biotechnology Information, and Medline databases. Articles published between 2000 and 2024 were selected based on keyword combinations such as "artificial intelligence", "prediction model", "algorithm", "machine learning", and "COVID-19". Information on machine learning predictive models was selected and processed to identify characteristics that can be used to predict diagnosis, severity, length of hospital stay, ICU admission, treatment, vaccination, and mortality in COVID-19 patients. After processing the data according to the search criteria, 125 full-text articles were identified. The final bibliography includes 52 relevant sources, which were considered representative of the literature on this synthesis article topic.
Artificial intelligence techniques are increasingly being used to predict outcomes in COVID-19 patients, particularly in estimating mortality among individuals infected with SARS-CoV-2, which can rapidly and effectively support clinical decision-making. According to the analysis of multiple studies, strong predictors of mortality in COVID-19 patients include advanced age, male gender, comorbidities, reduced levels of calcium, albumin, red blood cells, and oxygen saturation, as well as lymphopenia, elevated blood urea nitrogen, creatinine, lactate dehydrogenase, D-dimers, neutrophils, interleukin-6, procalcitonin, bilirubin, ferritin, aspartate aminotransferase, and troponin.
Artificial intelligence techniques provide potential advantages over conventional assessment methods. The information obtained from machine learning and deep learning algorithms, including easily accessible and interpretable data, can assist healthcare workers in making accurate decisions for the appropriate and timely care of COVID- 19 patients. This can improve patient outcomes, reduce the burden on healthcare systems, and ultimately decrease mortality rates.
The Coronavirus Disease 2019 (COVID-19) pandemic presented a significant challenge for global society, leaving a profound impact across the board. Although COVID-19 cases are still reported, they are no longer at previously high levels. One of the key tools in combating the pandemic was Artificial Intelligence (AI), which played a vital and advancing role throughout the pandemic. AI contributed significantly to the gradual reduction in COVID-19 cases. Effective coordination of the pandemic response, timely management, and the integration of AI into the medical system were crucial factors in achieving success.
A comprehensive literature review focusing on publications from 2019 to 2024 was conducted using Google Scholar, PubMed, and Science Direct. Twenty publications were selected for their relevance to AI in the COVID-19 response, based on criteria such as accessibility, language, and publication type.
The review focused on the significant role of AI during the COVID-19 pandemic, highlighting its impact on public health and medical systems. In countries like the USA, China, and South Korea, AI was crucial in tracking the virus, predicting infection trends, and optimizing resource allocation. AI models helped identify outbreak hotspots and enabled targeted interventions, while natural language processing efficiently managed extensive data. Conversely, in countries such as Brazil, Mexico, India, and many African nations, AI was used less extensively due to limitations in technological infrastructure and data availability. The pandemic drove a closer integration of AI with medical services, streamlining processes and saving time. AI also enhanced laboratory efficiency and supported the development of new medications and vaccines. Despite its potential, the uneven adoption highlighted disparities in technological readiness and resource allocation during the crisis.
The COVID-19 pandemic has once again highlighted that we live in an era of advanced technology and underscores the need for closer integration between healthcare systems and artificial intelligence. This integration allows for more effective and timely management of current and future health challenges. AI contributes to a more rapid and high-quality response to emergencies, providing innovative solutions for both existing and upcoming challenges.