Focusing on the genotype of the virus and combining this with clinical information about the patient, researchers behind the EU-funded EuResist project developed new mathematical prediction models. According to the researchers, the achievements of EuResist translate into more accuracy, lower treatment-related toxicity and cost savings.
The scientists combined databases from Italy, Sweden and Germany and newly created software. All information is now located in one database with over 18,000 patients, 64,000 therapies and 240,000 viral mode measurements. With this, doctors can predict what would happen if a patient with a certain type of virus and certain viral load is given a certain combination of antiretroviral therapy.
The prediction of future responses to treatment is based on three basic pieces of information: a quantification of the viral load, a definition of the viral genotype, and the viral load after eight weeks of treatment. The researchers then include other information, such as how the virus was transmitted, gender and sexual preference of the person, drug abuser or not.
Three complementary programmes were developed by the project partners. Each uses the same type of mathematical model to classify a given drug combination as successful or unsuccessful, but is fed with different information to account for various aspects of the disease evolution. The researchers evaluated the three engines separately and in combination and found that EuResist’s model was 76 percent accurate.
This is better than the state-of-the-art HIV resistance database at Stanford University, USA. Compared to the existing systems, which calculate only according to single drugs, the new model can account for combinations of therapies.
The project partners have created the network GEIE, a non-profit organisation, to maintain the database and make both it and the predictive programmes available to medical researchers and doctors all over the world.
MEDICA.de; Source: ICT Results