TY - JOUR
T1 - Practical Strategies for Extreme Missing Data Imputation in Dementia Diagnosis
AU - McCombe, Niamh
AU - Liu, Shuo
AU - Ding, Xuemei
AU - Prasad, Girijesh
AU - Bucholc, Magda
AU - Finn, David P.
AU - Todd, Stephen
AU - McClean, Paula L.
AU - Wong-Lin, Kongfatt
N1 - Publisher Copyright:
© 2013 IEEE.
PY - 2022/2/1
Y1 - 2022/2/1
N2 - Accurate computational models for clinical decision support systems require clean and reliable data but, in clinical practice, data are often incomplete. Hence, missing data could arise not only from training datasets but also test datasets which could consist of a single undiagnosed case, an individual. This work addresses the problem of extreme missingness in both training and test data by evaluating multiple imputation and classification workflows based on both diagnostic classification accuracy and computational cost. Extreme missingness is defined as having ∼50% of the total data missing in more than half the data features. In particular, we focus on dementia diagnosis due to long time delays, high variability, high attrition rates and lack of practical data imputation strategies in its diagnostic pathway. We identified and replicated the extreme missingness structure of data from a real-world memory clinic on a larger open dataset, with the original complete data acting as ground truth. Overall, we found that computational cost, but not accuracy, varies widely for various imputation and classification approaches. Particularly, we found that iterative imputation on the training dataset combined with a reduced-feature classification model provides the best approach, in terms of speed and accuracy. Taken together, this work has elucidated important factors to be considered when developing a predictive model for a dementia diagnostic support system.
AB - Accurate computational models for clinical decision support systems require clean and reliable data but, in clinical practice, data are often incomplete. Hence, missing data could arise not only from training datasets but also test datasets which could consist of a single undiagnosed case, an individual. This work addresses the problem of extreme missingness in both training and test data by evaluating multiple imputation and classification workflows based on both diagnostic classification accuracy and computational cost. Extreme missingness is defined as having ∼50% of the total data missing in more than half the data features. In particular, we focus on dementia diagnosis due to long time delays, high variability, high attrition rates and lack of practical data imputation strategies in its diagnostic pathway. We identified and replicated the extreme missingness structure of data from a real-world memory clinic on a larger open dataset, with the original complete data acting as ground truth. Overall, we found that computational cost, but not accuracy, varies widely for various imputation and classification approaches. Particularly, we found that iterative imputation on the training dataset combined with a reduced-feature classification model provides the best approach, in terms of speed and accuracy. Taken together, this work has elucidated important factors to be considered when developing a predictive model for a dementia diagnostic support system.
KW - ADNI data
KW - Alzheimer's disease classification
KW - Clinical decision support systems
KW - data imputation
KW - data quality
KW - dementia
KW - machine learning
KW - medical expert systems
KW - missing data
UR - http://www.scopus.com/inward/record.url?scp=85111026812&partnerID=8YFLogxK
U2 - 10.1109/JBHI.2021.3098511
DO - 10.1109/JBHI.2021.3098511
M3 - Article
SN - 2168-2194
VL - 26
SP - 818
EP - 827
JO - IEEE Journal of Biomedical and Health Informatics
JF - IEEE Journal of Biomedical and Health Informatics
IS - 2
ER -