PMID- 37932660
OWN - NLM
STAT- MEDLINE
DCOM- 20231108
LR  - 20231121
IS  - 1471-2288 (Electronic)
IS  - 1471-2288 (Linking)
VI  - 23
IP  - 1
DP  - 2023 Nov 6
TI  - Missing data imputation, prediction, and feature selection in diagnosis of 
      vaginal prolapse.
PG  - 259
LID - 10.1186/s12874-023-02079-0 [doi]
LID - 259
AB  - BACKGROUND: Data loss often occurs in the collection of clinical data. Directly 
      discarding the incomplete sample may lead to low accuracy of medical diagnosis. A 
      suitable data imputation method can help researchers make better use of valuable 
      medical data. METHODS: In this paper, five popular imputation methods including 
      mean imputation, expectation-maximization (EM) imputation, K-nearest neighbors 
      (KNN) imputation, denoising autoencoders (DAE) and generative adversarial 
      imputation nets (GAIN) are employed on an incomplete clinical data with 28,274 
      cases for vaginal prolapse prediction. A comprehensive comparison study for the 
      performance of these methods has been conducted through certain classification 
      criteria. It is shown that the prediction accuracy can be greatly improved by 
      using the imputed data, especially by GAIN. To find out the important risk 
      factors to this disease among a large number of candidate features, three 
      variable selection methods: the least absolute shrinkage and selection operator 
      (LASSO), the smoothly clipped absolute deviation (SCAD) and the broken adaptive 
      ridge (BAR) are implemented in logistic regression for feature selection on the 
      imputed datasets. In pursuit of our primary objective, which is accurate 
      diagnosis, we employed diagnostic accuracy (classification accuracy) as a pivotal 
      metric to assess both imputation and feature selection techniques. This 
      assessment encompassed seven classifiers (logistic regression (LR) classifier, 
      random forest (RF) classifier, support machine classifier (SVC), extreme gradient 
      boosting (XGBoost) , LASSO classifier, SCAD classifier and Elastic Net 
      classifier)enhancing the comprehensiveness of our evaluation. RESULTS: The 
      proposed framework imputation-variable selection-prediction is quite suitable to 
      the collected vaginal prolapse datasets. It is observed that the original dataset 
      is well imputed by GAIN first, and then 9 most significant features were selected 
      using BAR from the original 67 features in GAIN imputed dataset, with only 
      negligible loss in model prediction. BAR is superior to the other two variable 
      selection methods in our tests. CONCLUDES: Overall, combining the imputation, 
      classification and variable selection, we achieve good interpretability while 
      maintaining high accuracy in computer-aided medical diagnosis.
CI  - (c) 2023. The Author(s).
FAU - Fan, Mingxuan
AU  - Fan M
AD  - Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application 
      for Data Science, BNU-HKBU United International College, Zhuhai, 519087, China.
FAU - Peng, Xiaoling
AU  - Peng X
AD  - Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application 
      for Data Science, BNU-HKBU United International College, Zhuhai, 519087, China.
FAU - Niu, Xiaoyu
AU  - Niu X
AD  - Department of Gynecology and Obstetrics, West China Second University Hospital, 
      Sichuan University, Chengdu, 610064, China. niuxy@scu.edu.cn.
AD  - Key Laboratory of Birth Defects and Related Diseases of Women and Children 
      (Sichuan University), Ministry of Education, Chengdu, 610064, China. 
      niuxy@scu.edu.cn.
FAU - Cui, Tao
AU  - Cui T
AD  - Department of Gynecology and Obstetrics, West China Second University Hospital, 
      Sichuan University, Chengdu, 610064, China. cuitao8012@163.com.
AD  - Key Laboratory of Birth Defects and Related Diseases of Women and Children 
      (Sichuan University), Ministry of Education, Chengdu, 610064, China. 
      cuitao8012@163.com.
FAU - He, Qiaolin
AU  - He Q
AD  - School of Mathematics, Sichuan University, Chengdu, 610064, China.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20231106
PL  - England
TA  - BMC Med Res Methodol
JT  - BMC medical research methodology
JID - 100968545
SB  - IM
MH  - Female
MH  - Humans
MH  - *Uterine Prolapse
MH  - Diagnosis, Computer-Assisted
MH  - Logistic Models
PMC - PMC10629145
OTO - NOTNLM
OT  - Classification
OT  - Diagnosis of vaginal prolapse
OT  - Feature selection
OT  - Generative adversarial imputation
OT  - Missing data imputation
COIS- The authors declare no competing interests.
EDAT- 2023/11/07 00:42
MHDA- 2023/11/08 06:45
PMCR- 2023/11/06
CRDT- 2023/11/06 23:50
PHST- 2023/06/10 00:00 [received]
PHST- 2023/10/24 00:00 [accepted]
PHST- 2023/11/08 06:45 [medline]
PHST- 2023/11/07 00:42 [pubmed]
PHST- 2023/11/06 23:50 [entrez]
PHST- 2023/11/06 00:00 [pmc-release]
AID - 10.1186/s12874-023-02079-0 [pii]
AID - 2079 [pii]
AID - 10.1186/s12874-023-02079-0 [doi]
PST - epublish
SO  - BMC Med Res Methodol. 2023 Nov 6;23(1):259. doi: 10.1186/s12874-023-02079-0.