A new machine learning study has discovered that the most effective drug combinations for preventing COVID-19 from recurring are different for every patient.
The study used real-world data from a Chinese hospital and found that characteristics like age, weight, and other illnesses can influence the efficacy of different drug combinations in reducing recurrence rates.
The study has been published in the journal Frontiers in Artificial Intelligence.
The Significance of Chinese Data
The fact that this data came from China is significant for two reasons. Firstly, in China, doctors could prescribe up to eight different drugs for COVID-19 patients at the start of the pandemic.
This enabled the analysis of a broader range of drug combinations. Secondly, discharged COVID-19 patients in China have to quarantine in a government-run hotel, which allows for a systematic study of reinfection rates.
How Different People Need Different Treatments
The virus that causes COVID-19 can suppress the immune system and cause excessive inflammation.
Because of this, people who had weaker immune systems before they got COVID-19 might need immune-boosting drugs to fight the virus effectively.
On the other hand, younger people’s immune systems can overreact to the infection, leading to severe inflammation and even death. These people may require immune suppressants as part of their treatment.
The study found that different demographic groups had better success with different drug combinations, depending on how their immune systems responded to the virus.
A Step Towards Personalized Medicine
The traditional approach to testing drug effectiveness involves clinical trials where participants with similar disease conditions and characteristics are randomly assigned to treatment or control groups.
However, this method does not account for other medical conditions that could influence how the drug works for different subgroups of people.
To overcome this challenge, the researchers in this study developed a technique that matched people with similar characteristics who were receiving different treatment combinations.
This approach allowed them to generalize the effectiveness of different treatment combinations in various subgroups.
This study illustrates the potential of machine learning and artificial intelligence in advancing personalized medicine, where treatment is tailored to the individual patient’s characteristics.
In the future, these technologies are expected to have even greater impacts in the field of medicine.
If you care about COVID, please read studies about new evidence on rare blood clots after COVID-19 vaccination, and how diets could help manage post-COVID syndrome.
For more information about COVID, please see recent studies about how having had COVID-19 may harm your cognitive abilities, and results showing new antiviral drug combo could effectively treat COVID-19.
The study was published in Frontiers in Artificial Intelligence.
Copyright © 2023 Knowridge Science Report. All rights reserved.
