TY - JOUR
T1 - Responsible Imputation of Missing Speech Perception Testing Data & Analysis of 4,739 Observations and Predictors of Performance
AU - Pavelchek, Cole
AU - Lee, David S.
AU - Walia, Amit
AU - Michelson, Andrew P.
AU - Ortmann, Amanda
AU - Gentile, Brynn
AU - Herzog, Jacques A.
AU - Buchman, Craig A.
AU - Shew, Matthew A.
N1 - Funding Information:
Source of Funding: Research reported in this publication was supported by the National Institute of Deafness and Other Communication Disorders (NIDCD) within the National Institutes of Health (NIH), through the “Development of Clinician/Researchers in Academic ENT” training grant, award number T32DC000022. The content is solely the responsibility of the authors and does not necessarily represent the official view of the NIH. Research reported in this publication was supported, in part, by the National Center for Advancing Translational Sciences of the National Institutes of Health under Award Number UL1 TR002345. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.
Funding Information:
The Washington University cochlear implant data registry used for data generation and analysis was supported by the Foundation for Barnes-Jewish Hospital.
Publisher Copyright:
© 2023 Wolters Kluwer Health, Inc. All rights reserved.
PY - 2023/7/1
Y1 - 2023/7/1
N2 - Objective To address outcome heterogeneity in cochlear implant (CI) research, we built imputation models using multiple imputation by chained equations (MICEs) and K-nearest neighbors (KNNs) to convert between four common open-set testing scenarios: Consonant-Nucleus-Consonant word (CNCw), Arizona Biomedical (AzBio) in quiet, AzBio +5, and AzBio +10. We then analyzed raw and imputed data sets to evaluate factors affecting CI outcome variability. Study Design Retrospective cohort study of a national CI database (HERMES) and a nonoverlapping single-institution CI database. Setting Multi-institutional (32 CI centers). Patients Adult CI recipients (n = 4,046 patients). Main Outcome Measure(s) Mean absolute error (MAE) between imputed and observed speech perception scores. Results Imputation models of preoperative speech perception measures demonstrate a MAE of less than 10% for feature triplets of CNCw/AzBio in quiet/AzBio +10 (MICE: MAE, 9.52%; 95% confidence interval [CI], 9.40-9.64; KNN: MAE, 8.93%; 95% CI, 8.83-9.03) and AzBio in quiet/AzBio +5/AzBio +10 (MICE: MAE, 8.85%; 95% CI, 8.68-9.02; KNN: MAE, 8.95%; 95% CI, 8.74-9.16) with one feature missing. Postoperative imputation can be safely performed with up to four of six features missing in a set of CNCw and AzBio in quiet at 3, 6, and 12 months postcochlear implantation using MICE (MAE, 9.69%; 95% CI, 9.63-9.76). For multivariable analysis of CI performance prediction, imputation increased sample size by 72%, from 2,756 to 4,739, with marginal change in adjusted R2 (0.13 raw, 0.14 imputed). Conclusions Missing data across certain sets of common speech perception tests may be safely imputed, enabling multivariate analysis of one of the largest CI outcomes data sets to date.
AB - Objective To address outcome heterogeneity in cochlear implant (CI) research, we built imputation models using multiple imputation by chained equations (MICEs) and K-nearest neighbors (KNNs) to convert between four common open-set testing scenarios: Consonant-Nucleus-Consonant word (CNCw), Arizona Biomedical (AzBio) in quiet, AzBio +5, and AzBio +10. We then analyzed raw and imputed data sets to evaluate factors affecting CI outcome variability. Study Design Retrospective cohort study of a national CI database (HERMES) and a nonoverlapping single-institution CI database. Setting Multi-institutional (32 CI centers). Patients Adult CI recipients (n = 4,046 patients). Main Outcome Measure(s) Mean absolute error (MAE) between imputed and observed speech perception scores. Results Imputation models of preoperative speech perception measures demonstrate a MAE of less than 10% for feature triplets of CNCw/AzBio in quiet/AzBio +10 (MICE: MAE, 9.52%; 95% confidence interval [CI], 9.40-9.64; KNN: MAE, 8.93%; 95% CI, 8.83-9.03) and AzBio in quiet/AzBio +5/AzBio +10 (MICE: MAE, 8.85%; 95% CI, 8.68-9.02; KNN: MAE, 8.95%; 95% CI, 8.74-9.16) with one feature missing. Postoperative imputation can be safely performed with up to four of six features missing in a set of CNCw and AzBio in quiet at 3, 6, and 12 months postcochlear implantation using MICE (MAE, 9.69%; 95% CI, 9.63-9.76). For multivariable analysis of CI performance prediction, imputation increased sample size by 72%, from 2,756 to 4,739, with marginal change in adjusted R2 (0.13 raw, 0.14 imputed). Conclusions Missing data across certain sets of common speech perception tests may be safely imputed, enabling multivariate analysis of one of the largest CI outcomes data sets to date.
KW - Cochlear implant outcomes
KW - Imputation
KW - Machine learning
KW - Speech perception tests
UR - http://www.scopus.com/inward/record.url?scp=85163329346&partnerID=8YFLogxK
U2 - 10.1097/MAO.0000000000003903
DO - 10.1097/MAO.0000000000003903
M3 - Article
C2 - 37231531
AN - SCOPUS:85163329346
SN - 1531-7129
VL - 44
SP - E369-E378
JO - Otology and Neurotology
JF - Otology and Neurotology
IS - 6
ER -