PMID- 33916679
OWN - NLM
STAT- MEDLINE
DCOM- 20210503
LR  - 20210503
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 21
IP  - 7
DP  - 2021 Apr 3
TI  - Optimization of Imminent Labor Prediction Systems in Women with Threatened 
      Preterm Labor Based on Electrohysterography.
LID - 10.3390/s21072496 [doi]
LID - 2496
AB  - Preterm birth is the leading cause of death in newborns and the survivors are 
      prone to health complications. Threatened preterm labor (TPL) is the most common 
      cause of hospitalization in the second half of pregnancy. The current methods 
      used in clinical practice to diagnose preterm labor, the Bishop score or cervical 
      length, have high negative predictive values but not positive ones. In this work 
      we analyzed the performance of computationally efficient classification 
      algorithms, based on electrohysterographic recordings (EHG), such as random 
      forest (RF), extreme learning machine (ELM) and K-nearest neighbors (KNN) for 
      imminent labor (<7 days) prediction in women with TPL, using the 50th or 
      10th-90th percentiles of temporal, spectral and nonlinear EHG parameters with and 
      without obstetric data inputs. Two criteria were assessed for the classifier 
      design: F1-score and sensitivity. RF(F1_2) and ELM(F1_2) provided the highest 
      F1-score values in the validation dataset, (88.17 +/- 8.34% and 90.2 +/- 4.43%) with 
      the 50th percentile of EHG and obstetric inputs. ELM(F1_2) outperformed RF(F1_2) 
      in sensitivity, being similar to those of ELM(Sens) (sensitivity optimization). 
      The 10th-90th percentiles did not provide a significant improvement over the 50th 
      percentile. KNN performance was highly sensitive to the input dataset, with a 
      high generalization capability.
FAU - Prats-Boluda, Gema
AU  - Prats-Boluda G
AUID- ORCID: 0000-0002-9362-5055
AD  - Centro de Investigacion e Innovacion en Bioingenieria, Universitat Politecnica de 
      Valencia, 46022 Valencia, Spain.
FAU - Pastor-Tronch, Julio
AU  - Pastor-Tronch J
AUID- ORCID: 0000-0002-7245-6790
AD  - Centro de Investigacion e Innovacion en Bioingenieria, Universitat Politecnica de 
      Valencia, 46022 Valencia, Spain.
FAU - Garcia-Casado, Javier
AU  - Garcia-Casado J
AUID- ORCID: 0000-0003-1410-2721
AD  - Centro de Investigacion e Innovacion en Bioingenieria, Universitat Politecnica de 
      Valencia, 46022 Valencia, Spain.
FAU - Monfort-Ortiz, Rogelio
AU  - Monfort-Ortiz R
AD  - Servicio de Obstetricia, Hospital Universitario y Politecnico de La Fe, 46026 
      Valencia, Spain.
FAU - Perales Marin, Alfredo
AU  - Perales Marin A
AUID- ORCID: 0000-0002-2221-2560
AD  - Servicio de Obstetricia, Hospital Universitario y Politecnico de La Fe, 46026 
      Valencia, Spain.
FAU - Diago, Vicente
AU  - Diago V
AD  - Servicio de Obstetricia, Hospital Universitario y Politecnico de La Fe, 46026 
      Valencia, Spain.
FAU - Roca Prats, Alba
AU  - Roca Prats A
AD  - Servicio de Obstetricia, Hospital Universitario y Politecnico de La Fe, 46026 
      Valencia, Spain.
FAU - Ye-Lin, Yiyao
AU  - Ye-Lin Y
AD  - Centro de Investigacion e Innovacion en Bioingenieria, Universitat Politecnica de 
      Valencia, 46022 Valencia, Spain.
LA  - eng
GR  - RTI2018-094449-A-I00-AR/Spanish Ministry of Economy and Competitiveness, the 
      European Regional Development Fund/
GR  - AICO/2019/220/Generalitat Valenciana/
PT  - Journal Article
DEP - 20210403
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
SB  - IM
MH  - Algorithms
MH  - Female
MH  - Humans
MH  - Infant, Newborn
MH  - *Labor, Obstetric
MH  - *Obstetric Labor, Premature/diagnosis
MH  - Pregnancy
MH  - *Premature Birth/diagnosis
MH  - Uterus
PMC - PMC8038321
OTO - NOTNLM
OT  - K-nearest neighbors
OT  - electrohysterogram
OT  - extreme learning machine
OT  - imminent labor prediction
OT  - random forest
OT  - tocolytic therapy
OT  - uterine myoelectrical activity
COIS- The authors declare no conflict of interest.
EDAT- 2021/05/01 06:00
MHDA- 2021/05/04 06:00
PMCR- 2021/04/03
CRDT- 2021/04/30 01:04
PHST- 2021/02/17 00:00 [received]
PHST- 2021/03/29 00:00 [revised]
PHST- 2021/03/30 00:00 [accepted]
PHST- 2021/04/30 01:04 [entrez]
PHST- 2021/05/01 06:00 [pubmed]
PHST- 2021/05/04 06:00 [medline]
PHST- 2021/04/03 00:00 [pmc-release]
AID - s21072496 [pii]
AID - sensors-21-02496 [pii]
AID - 10.3390/s21072496 [doi]
PST - epublish
SO  - Sensors (Basel). 2021 Apr 3;21(7):2496. doi: 10.3390/s21072496.