Your Daily Vaccine Update
Using AI to understand long COVID-19
A recent multicentric study conducted in low- and middle-income countries (LMICs) utilized advanced deep learning techniques to analyze the impact of long COVID and vaccination, and to develop a risk calculator. The study included 2,445 participants aged 18 and older who tested positive for COVID-191.
Deep learning methods helped the researchers to sift through vast amounts of patient data, identify key patterns, and create predictive models for long COVID symptoms and the impact of vaccination.
The study revealed several key findings regarding long COVID6666:
• A significant proportion of patients (68.1%) experienced symptoms lasting longer than two weeks.
• The most frequently reported symptoms included loss of smell (46.8%), dry cough (40.1%), loss of taste (37.8%), headaches (37.2%), and sore throat (28.9%).
• A high percentage of patients also reported depression (47.7%) and chronic fatigue (6.5%).
• Vaccination was associated with a lower likelihood of experiencing prolonged COVID-19 symptoms, chronic fatigue syndrome, and depression.
• The findings highlight a substantial burden of long-term symptoms like chronic fatigue and depression affecting many individuals after COVID-19 infection.
To me this illustrates one of the potential applications of AI to help improve health in lower- and middle-income countries. AI can allow investigators to extend limited resources by making it possible to analyze large data bases more easily. It also illustrates the value of vaccines. Although vaccinated individuals who got infected also experienced long COVID-19, these individuals had a lower probability of experiencing prolonged symptoms.
During the COVID-19 pandemic an estimated 200,000 Americans died because they did not get vaccinated. This was an avoidable tragedy.
Vaccines are safe and effective and are are perhaps our most powerful public health tool.
This is a public access article. Shaheen, A., Shaheen, N., Long COVID Collaboration Study Group in the LMICS, Shoib, S., Saeed, F., Buhari, M., Bharmauria, V., & Flouty, O. (2025). Deep learning analysis of long COVID and vaccine impact in low- and middle-income countries (LMICS), development of a risk calculator in a multicentric study.
Frontiers in Public Health, 13:1416273.
doi: 10.3389/fpubh.2025.1416273 12
Richard Mahoney
Adjunct Professor
National School of Tropical Medicine
Baylor College of Medicine