ICARUS: Minimizing User Effort in Iterative Data Completion

Icarus is an interactive data completion system that shows the user useful subsets for edits. It leverages the database structure to generalize the user's single edit to multiple cells through suggested rules, thereby reducing user effort and time. It is currently being used to complete multiple microbiology datasets at Ohio State's Biomedical Informatics department. We are working on deploying it at Chicago's Northshore Healthcare facility, as well as open sourcing it soon.

Publications

• Protiva Rahman, Courtney Hebert, Arnab Nandi. ICARUS: Minimizing Human Effort in Iterative Data Completion. VLDB'18. [pdf][slides][poster]
• Protiva Rahman, Jian Chen, Courtney Hebert, Preeti Pancholi, Mark Lustberg, Kurt Stevenson, Arnab Nandi. Exploratory Visualizations of Rules for Validation of Expert Decisions. DSIA 2018. [pdf]
• Protiva Rahman, Albert Lai, Courtney Hebert. Parsing Complex Microbiology Data for Secondary Use. AMIA 2016 Poster. [poster][abstract]
• Protiva Rahman, Erinn M. Hade, Arnab Nandi, Preeti Pancholi, Mark Lustberg, Kurt Stevenson, Courtney Hebert. Derivation of Expert Consensus Rules for Missing Antimicrobial Susceptibility Data. AMIA 2018 Poster. [abstract]

Projects that use Icarus

• Courtney M Dewart, Yuan Gao, Protiva Rahman, Awa Mbodj, Erinn M Hade, Kurt Stevenson, Courtney Hebert. Penicillin Allergy and Association with Ciprofloxacin Coverage in Community-onset Urinary Tract Infection. Journal of Infection Control & Hospital Epidemiology 2018.
• Courtney Hebert, Erinn Hade, Protiva Rahman, Mark Lustberg, Kurt Stevenson, Preeti Pancholi. Modeling Likelihood of Coverage for Narrow Spectrum Antibiotics in Patients Hospitalized with Urinary Tract Infections. Open forum infectious diseases 2017.