Philip Pretorius

Development and validation of an HIV risk scorecard model

This research paper covers the development of an HIV risk scorecard using SAS Enterprise MinerTM. The HIV risk scorecard was developed using the 2007 South African annual antenatal HIV and syphilis seroprevalence data. Antenatal data contains various demographic characteristics for each pregnant woman, such as pregnant womans age, male sexual partners age, race, level of education, gravidity, parity, HIV and syphilis status. The purpose of this research was to use a scorecard to rank the effects of the demographic characteristics on influencing an individuals risk of acquiring an HIV infection, not the probability of being sick. The project encompassed the selection of the data sample, classing, selection of demographic characteristics, fitting of a regression model, generation of weights-of-evidence (WOE), calculation of information values (IVs), creation and validation of an HIV risk scorecard. The educational level and syphilis status of the pregnant women produced information values below 0.05 and were rejected from inclusion in the final HIV risk scorecard. Based on their respective information values, the following four demographic characteristics of the pregnant women were found to be of medium predictive strength and thus included in the final HIV risk scorecard; age, age of male sexual partner, gravidity and parity. The age of the pregnant woman had the highest information value and Gini coefficient. The HIV risk scorecard showed that the risk of contracting an HIV infection increased gradually up to the age of 30 years for females and 34 years old for their male sexual partners. Thereafter, the risk decreased gradually towards the age of 45.

Weight of Evidence M odel : Application in Tracking Changes in HIV Risk Profile Using 10 Year Annual Antenatal HIV Seroprevalence Data

 Abstract—A weight-of-evidence model based on antenatal HIV seroprevalence data is explored to study the effect of demographic characteristics on the risk of acquiring an HIV infection amongst pregnant women in South Africa. Antenatal data obtained from each pregnant woman contains a wealth of information in the form of demographic characteristics. In this research we use weights-of-evidence models (WOE) and information values (IV) as measures of the risk of acquiring an HIV infection to monitor changes in HIV risk over a period of 10 years from 2001 to 2010. The study demonstrated that the risk of acquiring an HIV infection amongst pregnant women in South Africa was higher for the younger women below the age of 28 during the early years of 2001 to 2005. However, during the subsequent years of 2006 to 2010, the risk dropped amongst the younger women with the simultaneous increase amongst the older women over the age of 28. Married women were found to be least at risk of acquiring an HIV infection, while widowed women were observed to be most at risk.

Comparative study of an HIV risk scorecard and regression models to rank effects of demographic characteristics on risk of aquiring an HIV infection

This research paper covers the development of an HIV risk scorecard using SAS Enterprise Miner™. The HIV risk scorecard was developed using the 2007 South African annual antenatal HIV and syphilis seroprevalence data. Limited comparisons are made with a more recent 2010 antenatal database. Antenatal data contains various demographic characteristics for each pregnant woman, such as pregnant womans age, male sexual partners age, population group, level of education, gravidity, parity, HIV and syphilis status. The purpose of this research was to use a scorecard to rank the effects of the demographic characteristics on influencing a pregnant womans risk of acquiring an HIV infection. The project encompassed the selection of the data sample, classing, selection of demographic characteristics, fitting of a regression model, generation of weights-of-evidence (WOE), calculation of information values (IVs), creation and validation of an HIV risk scorecard. The educational level and syphilis status of the pregnant women produced information values below 0.05 and were rejected from inclusion in the final HIV risk scorecard. Based on their respective information values, the following four demographic characteristics of the pregnant women were found to be of medium predictive strength and thus included in the final HIV risk scorecard; pregnant womans age, age of male sexual partner, gravidity and parity. The age of the pregnant woman had the highest information value and Gini coefficient. The final objective of this research was to demonstrate that a binned variable HIV risk scorecard can provide as much risk ranking as any other regression based model.