Phil Kalina has extensive experience curating, wrangling, and modeling data in healthcare and other domains; then testing and validating those models. This experience, together with his education and training as a mathematician and statistician, has well prepared him to contribute to DATA, LLC's research and training programs.

Phil was a software developer who advanced to Manager of Research and Development at Amherst Associates, the highly successful pioneer of decision support systems for hospitals. Today Amherst Associates is subsumed into McKesson Corporation. In 1988, Ernst and Young recruited him to be a senior manager in their national office (in Cleveland, Ohio) of what was then the largest healthcare consulting practice in the United States. He managed a department with responsibility for developing and maintaining a suite of healthcare software applications including budgeting tools, a system to optimize nurse staffing, and a tool to assist with medical records coding.

After further coursework in machine learning at the University of Massachusetts, Phil became a machine learning and statistics consultant. In a wide variety of projects he harmonized data, then used machine learning and other techniques to build and validate classification and prediction models for healthcare. These include a Bayesian model to predict survival of mesothelioma patients, a study of factors which contribute to development of Clostridioides difficile colitis as a complication after colon resection, and, for the office of the Assistant Secretary for Planning and Evaluation (ASPE) at the Department of Health and Human Services, a meta-analysis of surveys of small physician practices to uncover factors which influence their adoption of electronic health records.