Timezone: »

Automated Supervised Feature Selection for Differentiated Patterns of Care
Catherine Wanjiru · William Ogallo · Girmaw Abebe Tadesse · Charles Wachira · Isaiah Onando Mulang' · Aisha Walcott-Bryant

An automated feature selection pipeline was developed using several state-of-the-art feature selection techniques to select optimal features for Differentiating Patterns of Care (DPOC). The pipeline included three types of feature selection techniques; Filters, Wrappers and Embedded methods to select the top K features. Five different datasets with binary dependent variables were used and their different top K optimal features selected. The selected features were tested in the existing multi-dimensional subset scanning (MDSS) where the most anomalous subpopulations, most anomalous subsets, propensity scores, and effect of measures were recorded to test their performance. This performance was compared with four similar metrics gained after using all covariates in the dataset in the MDSS pipeline. We found out that despite the different feature selection techniques used, the data distribution is key to note when determining the technique to use

Author Information

Catherine Wanjiru (Carnegie Mellon University Africa)
William Ogallo (IBM Research)
Girmaw Abebe Tadesse (IBM Research | Africa)
Charles Wachira (IBM Research)
Isaiah Onando Mulang' (IBM Research Africa)
Aisha Walcott-Bryant (IBM Research)

I am a research scientist and manager at IBM Research Africa - Nairobi, Kenya. I lead a team of phenomenal, brilliant researchers and engineers that use AI, Blockchain, and other technologies to develop innovations in Global Health, Water Access and Management, and Climate. I earned my PhD in the Electrical Engineering and Computer Science Department at MIT in robotics, as a member of the Computer Science and Artificial Intelligent lab (CSAIL).

More from the Same Authors