PMID- 27441291
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20160721
LR  - 20200930
IS  - 2405-8440 (Print)
IS  - 2405-8440 (Electronic)
IS  - 2405-8440 (Linking)
VI  - 2
IP  - 6
DP  - 2016 Jun
TI  - Screening for post 32-week preterm birth risk: how helpful is routine perinatal 
      data collection?
PG  - e00119
LID - 10.1016/j.heliyon.2016.e00119 [doi]
LID - e00119
AB  - BACKGROUND: Preterm birth is a clinical event significant but difficult to 
      predict. Biomarkers such as fetal fibronectin and cervical length are effective, 
      but the often are used only for women with clinically suspected preterm risk. It 
      is unknown whether routinely collected data can be used in early pregnancy to 
      stratify preterm birth risk by identifying asymptomatic women. This paper tries 
      to determine the value of the Victorian Perinatal Data Collection (VPDC) dataset 
      in predicting preterm birth and screening for invasive tests. METHODS: 
      De-identified VPDC report data from 2009 to 2013 were extracted for patients from 
      Barwon Health in Victoria. Logistic regression models with elastic-net 
      regularization were fitted to predict 37-week preterm, with the VPDC antenatal 
      variables as predictors. The models were also extended with two additional 
      variables not routinely noted in the VPDC: previous preterm birth and partner 
      smoking status, testing the hypothesis that these two factors add prediction 
      accuracy. Prediction performance was evaluated using a number of metrics, 
      including Brier scores, Nagelkerke's R(2), c statistic. RESULTS: Although the 
      predictive model utilising VPDC data had a low overall prediction performance, it 
      had a reasonable discrimination (c statistic 0.646 [95% CI: 0.596-0.697] for 
      37-week preterm) and good calibration (goodness-of-fit p = 0.61). On a decision 
      threshold of 0.2, a Positive Predictive Value (PPV) of 0.333 and a negative 
      predictive value (NPV) of 0.941 were achieved. Data on previous preterm and 
      partner smoking did not significantly improve prediction. CONCLUSIONS: For 
      multiparous women, the routine data contains information comparable to some 
      purposely-collected data for predicting preterm risk. But for nulliparous women, 
      the routine data contains insufficient data related to antenatal complications.
FAU - Luo, Wei
AU  - Luo W
AD  - Centre for Pattern Recognition and Data Analytics, Deakin University, Australia.
FAU - Huning, Emily Y-S
AU  - Huning EY
AD  - Womens & Children's Services, Barwon Health - The Geelong Hospital, Australia.
FAU - Tran, Truyen
AU  - Tran T
AD  - Centre for Pattern Recognition and Data Analytics, Deakin University, Australia; 
      Department of Computing, Curtin University, Australia.
FAU - Phung, Dinh
AU  - Phung D
AD  - Centre for Pattern Recognition and Data Analytics, Deakin University, Australia.
FAU - Venkatesh, Svetha
AU  - Venkatesh S
AD  - Centre for Pattern Recognition and Data Analytics, Deakin University, Australia.
LA  - eng
PT  - Journal Article
DEP - 20160601
PL  - England
TA  - Heliyon
JT  - Heliyon
JID - 101672560
PMC - PMC4946290
OTO - NOTNLM
OT  - Medicine
EDAT- 2016/07/22 06:00
MHDA- 2016/07/22 06:01
PMCR- 2016/06/01
CRDT- 2016/07/22 06:00
PHST- 2015/12/30 00:00 [received]
PHST- 2016/03/31 00:00 [revised]
PHST- 2016/05/23 00:00 [accepted]
PHST- 2016/07/22 06:00 [entrez]
PHST- 2016/07/22 06:00 [pubmed]
PHST- 2016/07/22 06:01 [medline]
PHST- 2016/06/01 00:00 [pmc-release]
AID - S2405-8440(15)30601-0 [pii]
AID - e00119 [pii]
AID - 10.1016/j.heliyon.2016.e00119 [doi]
PST - epublish
SO  - Heliyon. 2016 Jun 1;2(6):e00119. doi: 10.1016/j.heliyon.2016.e00119. eCollection 
      2016 Jun.