HIV Lipodystrophy Case Definition using Artificial Neural Network Modelling

Objective A case definition of HIV lipodystrophy has recently been developed from a combination of clinical, metabolic and imaging/body composition variables using logistic regression methods. We aimed to evaluate whether artificial neural networks could improve the diagnostic accuracy. Methods The database of the case-control Lipodystrophy Case Definition Study was split into 504 subjects (265 with and 239 without lipodystrophy) used for training and 284 independent subjects (152 with and 132 without lipodystrophy) used for validation. Back-propagation neural networks with one or two middle layers were trained and validated. Results were compared against logistic regression models using the same information. Results Neural networks using clinical variables only (41 items) achieved consistently superior performance than logistic regression in terms of specificity, overall accuracy and area under the ROC curve. Their average sensitivity and specificity were 72.4 and 71.2%, as compared with 73.0 and 62.9% for logistic regression, respectively (area under the ROC curve, 0.784 vs 0.748). The discriminating performance of the neural networks was largely unaffected when built excluding 13 parameters that patients may not have readily available. The average sensitivity and specificity of the neural networks remained the same when metabolic variables were also considered (total 60 items) without a clear advantage against logistic regression (overall accuracy 71.8%). The performance of networks considering also body composition variables was similar to that of logistic regression (overall accuracy 78.5% for both). Conclusions Neural networks may offer a means to improve the discriminating performance for HIV lipodystrophy, when only clinical data are available and a rapid approximate diagnostic decision is needed. In this context, information on metabolic parameters is apparently not helpful in improving the diagnosis of HIV lipodystrophy, unless imaging and body composition studies are also obtained.

[1]  A. Carr.  An objective case definition of lipodystrophy in HIV-infected adults: a case-control study , 2003, The Lancet.

[2]  R. Bruno,et al.  Evaluation of the Risk Factors Associated with Lipodystrophy Development in a Cohort of HIV-Positive Patients , 2001, Antiviral therapy.

[3]  M. John,et al.  Antiretoviral Therapy and the Lipodystrophy Syndrome, Part 2: Concepts in Aetiopathogenesis , 2000, Antiviral therapy.

[4]  D. Neau,et al.  Lipodystrophy, metabolic disorders, and human immunodeficiency virus infection: Aquitaine Cohort, France, 1999. Groupe d'Epidémiologie Clinique du Syndrome d'Immunodéficience Acquise en Aquitaine. , 2000, Clinical infectious diseases : an official publication of the Infectious Diseases Society of America.

[5]  D. Cooper,et al.  A syndrome of lipoatrophy, lactic acidaemia and liver dysfunction associated with HIV nucleoside analogue therapy: contribution to protease inhibitor-related lipodystrophy syndrome , 2000, AIDS.

[6]  M. Moroni,et al.  Redistribution of body fat in HIV-infected women undergoing combined antiretroviral therapy. , 1999, AIDS.

[7]  David A. Cooper,et al.  A syndrome of peripheral lipodystrophy, hyperlipidaemia and insulin resistance in patients receiving HIV protease inhibitors , 1998, AIDS.

[8]  J J Goedert,et al.  Use of neural networks to model complex immunogenetic associations of disease: human leukocyte antigen impact on the progression of human immunodeficiency virus infection. , 1998, American journal of epidemiology.

[9]  J V Tu,et al.  Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. , 1996, Journal of clinical epidemiology.

[10]  R. Dybowski,et al.  Prediction of outcome in critically ill patients using artificial neural network synthesised by genetic algorithm , 1996, The Lancet.

[11]  W. Baxt.  Application of artificial neural networks to clinical medicine , 1995, The Lancet.

[12]  Rush-Presbyterian-St. Luke's Medical Center and Others v. Hellenic Republic and Others , 1995, International Law Reports.

[13]  Etienne Barnard,et al.  Avoiding false local minima by proper initialization of connections , 1992, IEEE Trans. Neural Networks.

[14]  W. Baxt.  Use of an artificial neural network for the diagnosis of myocardial infarction. , 1991, Annals of internal medicine.

[15]  D. Hosmer,et al.  Applied Logistic Regression , 1991 .

[16]  Robert A. Jacobs,et al.  Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[17]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[18]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.