Abstract
We compare the performances of a Cox model and a neural network model that are used as prognostic tools for a cohort of people living with AIDS. We modeled disease progression for patients who had AIDS (according to the 1993 CDC definition) in a cohort of 588 patients in California, using data from the ATHOS project. We divided the study population into 10 training and 10 test sets and evaluated the prognostic accuracy of a Cox proportional hazards model and of a neural network model by determining the number of predicted deaths, the sensitivities, specificities, positive predictive values, and negative predictive values for intervals of one year following the diagnosis of AIDS. For the Cox model, we further tested the agreement between a series of binary observations, representing death in one, two, and three years, and a set of estimates which define the probability of survival for those intervals. Both models were able to provide accurate numbers on how many patients were likely to die at each interval, and reasonable individualized estimates for the two- and three-year survival of a given patient, but failed to provide reliable predictions for the first year after diagnosis. There was no evidence that the Cox model performed better than did the neural network model or vice-versa, but the former method had the advantage of providing some insight on which variables were most influential for prognosis. Nevertheless, it is likely that the assumptions required by the Cox model may not be satisfied in all data sets, justifying the use of neural networks in certain cases.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Hanson D. L., Horsburgh C. R., Jr, Fann S. A., Havlik J. A., Thompson S. E., 3rd Survival prognosis of HIV-infected patients. J Acquir Immune Defic Syndr. 1993 Jun;6(6):624–629. [PubMed] [Google Scholar]
- Ingram D. D., Kleinman J. C. Empirical comparisons of proportional hazards and logistic regression models. Stat Med. 1989 May;8(5):525–538. doi: 10.1002/sim.4780080502. [DOI] [PubMed] [Google Scholar]
- Justice A. C., Feinstein A. R., Wells C. K. A new prognostic staging system for the acquired immunodeficiency syndrome. N Engl J Med. 1989 May 25;320(21):1388–1393. doi: 10.1056/NEJM198905253202106. [DOI] [PubMed] [Google Scholar]
- Lubeck D. P., Fries J. F. Health status among persons infected with human immunodeficiency virus. A community-based study. Med Care. 1993 Mar;31(3):269–276. doi: 10.1097/00005650-199303000-00008. [DOI] [PubMed] [Google Scholar]
- Ravdin P. M., Clark G. M. A practical application of neural network analysis for predicting outcome of individual breast cancer patients. Breast Cancer Res Treat. 1992;22(3):285–293. doi: 10.1007/BF01840841. [DOI] [PubMed] [Google Scholar]
- Seage G. R., 3rd, Landers S., Lamb G. A., Epstein A. M. Effect of changing patterns of care and duration of survival on the cost of treating the acquired immunodeficiency syndrome (AIDS). Am J Public Health. 1990 Jul;80(7):835–839. doi: 10.2105/ajph.80.7.835. [DOI] [PMC free article] [PubMed] [Google Scholar]