TY - GEN
T1 - Novel Feature Selection for Artificial Intelligence Using Item Response Theory for Mortality Prediction
AU - Kline, Adrienne
AU - Kline, Theresa
AU - Hossein Abad, Zahra Shakeri
AU - Lee, Joon
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/7
Y1 - 2020/7
N2 - Feature selection is a critical component in supervised machine learning classification analyses. Extraneous features introduce noise and inefficiencies into the system leading to a need for feature reduction techniques. Many feature reduction models use the end-classification results in the feature reduction process, committing a circular error. Item Response Theory (IRT) examines the characteristics of features independent of the end-classification results, and provides high levels of information regarding feature utility. A two-parameter dichotomous IRT model was used to analyze 18 features from an intensive care unit data set with 2520 cases. The classification results showed that the features selected via IRT were comparable to that using more traditional machine learning approaches. Strengths and limitations of the IRT selection protocol are discussed.
AB - Feature selection is a critical component in supervised machine learning classification analyses. Extraneous features introduce noise and inefficiencies into the system leading to a need for feature reduction techniques. Many feature reduction models use the end-classification results in the feature reduction process, committing a circular error. Item Response Theory (IRT) examines the characteristics of features independent of the end-classification results, and provides high levels of information regarding feature utility. A two-parameter dichotomous IRT model was used to analyze 18 features from an intensive care unit data set with 2520 cases. The classification results showed that the features selected via IRT were comparable to that using more traditional machine learning approaches. Strengths and limitations of the IRT selection protocol are discussed.
UR - http://www.scopus.com/inward/record.url?scp=85090999127&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090999127&partnerID=8YFLogxK
U2 - 10.1109/EMBC44109.2020.9175403
DO - 10.1109/EMBC44109.2020.9175403
M3 - Conference contribution
C2 - 33019275
AN - SCOPUS:85090999127
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 5729
EP - 5732
BT - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society, EMBC 2020
Y2 - 20 July 2020 through 24 July 2020
ER -