This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these template messages) The topic of this article may not meet Wikipedia's notability guidelines for products and services. Please help to demonstrate the notability of the topic by citing reliable secondary sources that are independent of the topic and provide significant coverage of it beyond a mere trivial mention. If notability cannot be shown, the article is likely to be merged, redirected, or deleted.Find sources: "EuResist" – news · newspapers · books · scholar · JSTOR (July 2019) (Learn how and when to remove this template message)This article needs additional citations for verification. Please help improve this article by adding citations to reliable sources. Unsourced material may be challenged and removed.Find sources: "EuResist" – news · newspapers · books · scholar · JSTOR (February 2020) (Learn how and when to remove this template message) (Learn how and when to remove this template message)
EuResist
Initial release2006
Operating systemCross-platform
Websitewww.euresist.org

EuResist is an international project designed to improve the treatment of HIV patients by developing a computerized system that can recommend optimal treatment based on the patient's clinical and genomic data.[1][2]

The project is part of the Virtual Physiological Human framework, funded by the European Commission. It started in 2006 with the formation of a consortium of several research institutes and hospitals in Europe and Israel. The consortium completed its commitment to the European Commission near the end of 2008, at which time the system became available online. A non-profit organization was consequently established by the main partners to maintain and improve the system.

In 2009, the EuResist project was named as a Computerworld honors program laureate.[3]

Background

AIDS is a disease caused by the HIV retrovirus, which progressively reduces the effectiveness of the immune system, leading to infections and ultimately death.

More than 30 different drugs exist for treating HIV patients. Antiretroviral drugs can disrupt the virus's replication process causing its numbers to decrease dramatically. While the virus cannot be eradicated completely, in small numbers it is harmless. Usually a patient is given a combination of three or four drugs, a treatment known as highly active antiretroviral therapy, or HAART. The main reason such a treatment might fail is the development of mutated strands of the virus, resistant to one or more of the prescribed drugs.

Thus an important consideration when choosing treatment for a patient is to prescribe those drugs to which the particular patient's virus strands are most susceptible. One way to achieve that is to extract virus samples from the patient's blood and test them against all possible drugs. Since this process is lengthy and costly, computerized systems have been developed to predict virus resistance based on its genotype. The treating physician samples virus genotype sequences from the patient's blood and provides this data to a computerized system. The system then responds with drug recommendations.

Such systems are limited in accuracy, depending on the amount of data used for their creation, its quality and the richness of mathematical models used for the actual prediction. Prior to EuResist, such systems had several common characteristics that negatively impacted their accuracy:[4]

EuResist overview

EuResist sought to create a more accurate HIV treatment prediction system by collecting a large database of in vivo data (clinical and genomic records of real treatments of HIV patients and their consequences), and by using an array of prediction models instead of just one.

The database was created by merging local databases of various clinics across Europe. This database is thought to be the largest of its kind in the world. For each patient, it includes various personal and demographic details such as gender, age, country of origin, genomic sequencing of HIV found in the patient's blood, records of the drugs prescribed, and the changes in the amount of virus in the blood following these treatments.

This data was used to train an array of prediction models, created by using various contemporary machine learning techniques, among them Bayesian networks, logistic regression, and others.

A web interface allows physicians to specify patients' clinical and genomic data. This data is sent to the prediction engines, and the combined response, which is displayed to the physician, includes various suggested treatments and a prediction of their effect on the amount of HIV in the blood.

The EuResist system was tested and compared with its predecessors by feeding it with historical data on patients for which treatment results are known. The developers of EuResist, who conducted this test, reported an improved performance over the previous state-of-the-art system.

History

EuResist started in 2006 as a consortium funded by the European Union as part of the Virtual Physiological Human FP-6 framework. The partners of this consortium were:

The consortium completed its commitment to the European Union in late 2008, at which time the EuResist system became available on line. The first five partners mentioned above continued to form a non-profit organization that maintains the system, expands the database with new clinical and genomical records and updates the prediction engines accordingly. As of mid-2010, an average of 600 queries are submitted to the EuResist system every quarter.

Recognition

On June 1, 2009, EuResist received a Computerworld honors program laureate award, a global program honoring individuals and organizations that use information technology to benefit society.[3]

References

  1. ^ Sharma, Deepak; Priyadarshini, Pragya; Vrati, Sudhanshu (2015-02-01). "Unraveling the Web of Viroinformatics: Computational Tools and Databases in Virus Research". Journal of Virology. 89 (3): 1489–1501. doi:10.1128/JVI.02027-14. ISSN 0022-538X. PMC 4300767. PMID 25428870.
  2. ^ Fischetti, Mark. "Predictive Modeling Warns Drivers One Hour before Jams Occur". Scientific American. Retrieved 2020-10-01.
  3. ^ a b "Computerworld Honors Program - 2009 Finalists". www.cwhonors.org. Archived from the original on 2013-07-18. Retrieved 2010-08-25.
  4. ^ Rosen-Zvi, Michal; Altmann, Andre; Prosperi, Mattia; Aharoni, Ehud; Neuvirth, Hani; Sönnerborg, Anders; Schülter, Eugen; Struck, Daniel; Peres, Yardena; Incardona, Francesca; Kaiser, Rolf; Zazzi, Maurizio; Lengauer, Thomas (1 July 2008). "Selecting anti-HIV therapies based on a variety of genomic and clinical factors". Bioinformatics. 24 (13): i399–i406. doi:10.1093/bioinformatics/btn141. PMC 2718619. PMID 18586740 – via bioinformatics.oxfordjournals.org.