Application of Artificial Neural Networks for Decision Support in Medicine
The emergence of drug resistant pathogens can reduce the efficacy of drugs commonly used to treat infectious diseases. Human immunodeficiency virus (HIV) is particularly sensitive to drug selection pressure, rapidly evolving into drug resistant variants on exposure to anti-HIV drugs. Over 200 mutations within the genetic material of HIV have been shown to be associated with drug resistance to date, and complex mutational patterns have been found in HIV isolates from infected patients exposed to multiple antiretroviral drugs. Genotyping is commonly used in clinical practice as a tool to identify drug resistance mutations in HIV from individual patients. This information is then used to help guide the choice of future therapy for patients whose drug regimen is failing because of the development of drug resistant HIV. Many sets of rules and algorithms are available to predict loss of susceptibility to individual antiretroviral drugs from genotypic data. Although this approach has been helpful, the interpretation of genotypic data remains challenging. We describe here the development and application of ANN models as alternative tools for the interpretation of HIV genotypic drug resistance data.
A large amount of clinical and virological data, from around 30,000 patients treated with antiretroviral drugs, has been collected by the HIV Resistance Response Database Initiative (RDI, www.hivrdi.org) in a centralized database. Treatment change episodes (TCEs) have been extracted from these data and used along with HIV drug resistance mutations as the basic input variables to train ANN models. We performed a series of analyses that have helped define the following: (1) the reliability of ANN predictions for HIV patients receiving routine clinical care; (2) the utility of ANN models to identify effective treatments for patients failing therapy; (3) strategies to increase the accuracy of ANN predictions; and (4) performance of ANN models in comparison to the rules-based methods currently in use.
KeywordsArtificial neural networks decision support HIV infection clinical response antiretroviral therapy.
- 10.Fuller J J, Emmett M, Kessel JW, Price PD, Forsythe, J. H. (2005) A comparison of neural networks for computing predicted probability of survival for trauma victims. WV Med J 101:120–125.Google Scholar
- 12.Papik K, Molnar B, Schaefer R, Dombovari Z, Tulassay Z, Feher J (1995) Application of neural networks in medicine: a review. Diagnostics and Medical Technology 1:538–546.Google Scholar
- 14.Lisboa PJ, Taktak AF (2006) The use of artificial neural networks in decision support in cancer: a systematic review. Neural Netw (Feb 13) (Epub in press).Google Scholar
- 21.Sordo M (2002) Introduction to neural networks in healthcare. Open Clinical. [online] www.openclinical.org/docs/int/neuralnetworks011.pdf.
- 23.The Panel on Clinical Practices for Treatment of HIV Infection Convened by the Department of Health and Social Services. (2006) Guidelines for the use of antiretroviral agents in HIV-1 infected adults and adolescents, October 6, 2005. [online] http://aidsinfo.nih.gov/ContentFiles/AdultandAdolescentGL.pdf.
- 25.Wang D, De Gruttola V, Hammer S, Harrigan R, Larder B, Wegner S, et al., on Behalf of the HIV Resistance Response Database Initiative. (2002). A collaborative HIV resistance response database initiative: predicting virological response using neural network models. Antiviral Therapy 7:S96.Google Scholar
- 26.Wang D, Larder BA, Revell A, Harrigan R, Montaner J, on behalf of the HIV Resistance Response Database Initiative. (2003). A neural network model using clinical cohort data accurately predicts virological response and identifies regimens with increased probability of success in treatment failures. Antiviral Therapy 8:S112.Google Scholar
- 27.Larder BA, Wang D, Revell A, Lane C (2003) Neural network model identified potentially effective drug combinations for patients failing salvage therapy. 2nd IAS conference on HIV pathogenesis and treatment, Paris, July 13–16, poster LB39.Google Scholar
- 28.Larder BA, Wang D, Revell A, Harrigan R, Montaner J, Lane C (2004) Accuracy of neural network models in predicting HIV treatment response from genotype may depend on diversity as well as size of data sets. 11th conference on retroviruses and opportunistic infections, San Francisco, February 8–11, poster 697.Google Scholar
- 29.Revell A, Larder BA, Wang D, Wegner S, Harrigan R, Montaner J, Lane C (2005) Global neural network models are superior to single clinic models as general quantitative predictors of virologic treatment response. 3rd IAS conference on HIV pathogenesis and treatment. July 24–27, Rio de Janeiro, poster WePe12.6C04.Google Scholar
- 30.Wang D, Larder BA, Revell A, Harrigan R, Montaner J, Wegner S, Lane C (2005) Treatment history improves the accuracy of neural networks predicting virologic response to HIV therapy. BioSapiens-viRgil workshop on bioinformatics for viral infections, September 21–23, Caesar Bonn, Germany, poster 20.Google Scholar
- 31.Larder BA, Wang D, Revell A, Harrigan R, Montaner J,Wegner S, Lane C (2005) Treatment history but not previous genotype improves the accuracy of predicting virologic response to HIV therapy. 45th ICAAC, December 16–19. Washington, DC, poster H-1051.Google Scholar
- 32.Larder BA, Wang D, Revell A, Harrigan R, Montaner J, Wegner S, Lane C (2005). Treatment history and adherence information significantly improves prediction of virological response by neural networks. Antiviral Therapy 10:S57.Google Scholar
- 33.Larder BA, Revell A, Wang D, Harrigan R, Montaner J, Wegner S, Lane C (2005) Neural networks are more accurate predictors of virological response to HAART than rules-based genotype interpretation systems. 10th European AIDS conference/EACS, November 17–20, Dublin, poster PE3.4/13Google Scholar