1
|
Nieto-Del-Amor F, Ye-Lin Y, Monfort-Ortiz R, Diago-Almela VJ, Modrego-Pardo F, Martinez-de-Juan JL, Hao D, Prats-Boluda G. Automatic semantic segmentation of EHG recordings by deep learning: An approach to a screening tool for use in clinical practice. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 254:108317. [PMID: 38996804 DOI: 10.1016/j.cmpb.2024.108317] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/15/2024] [Revised: 07/03/2024] [Accepted: 07/04/2024] [Indexed: 07/14/2024]
Abstract
BACKGROUND AND OBJECTIVE Preterm delivery is an important factor in the disease burden of the newborn and infants worldwide. Electrohysterography (EHG) has become a promising technique for predicting this condition, thanks to its high degree of sensitivity. Despite the technological progress made in predicting preterm labor, its use in clinical practice is still limited, one of the main barriers being the lack of tools for automatic signal processing without expert supervision, i.e. automatic screening of motion and respiratory artifacts in EHG records. Our main objective was thus to design and validate an automatic system of segmenting and screening the physiological segments of uterine origin in EHG records for robust characterization of uterine myoelectric activity, predicting preterm labor and help to promote the transferability of the EHG technique to clinical practice. METHODS For this, we combined 300 EHG recordings from the TPEHG DS database and 69 EHG recordings from our own database (Ci2B-La Fe) of women with singleton gestations. This dataset was used to train and evaluate U-Net, U-Net++, and U-Net 3+ for semantic segmentation of the physiological and artifacted segments of EHG signals. The model's predictions were then fine-tuned by post-processing. RESULTS U-Net 3+ outperformed the other models, achieving an area under the ROC curve of 91.4 % and an average precision of 96.4 % in detecting physiological activity. Thresholds from 0.6 to 0.8 achieved precision from 93.7 % to 97.4 % and specificity from 81.7 % to 94.5 %, detecting high-quality physiological segments while maintaining a trade-off between recall and specificity. Post-processing improved the model's adaptability by fine-tuning both the physiological and corrupted segments, ensuring accurate artifact detection while maintaining physiological segment integrity in EHG signals. CONCLUSIONS As automatic segmentation proved to be as effective as double-blind manual segmentation in predicting preterm labor, this automatic segmentation tool fills a crucial gap in the existing preterm delivery prediction system workflow by eliminating the need for double-blind segmentation by experts and facilitates the practical clinical use of EHG. This work potentially contributes to the early detection of authentic preterm labor women and will allow clinicians to design individual patient strategies for maternal health surveillance systems and predict adverse pregnancy outcomes.
Collapse
Affiliation(s)
- Félix Nieto-Del-Amor
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València (Ci2B), Valencia 46022, Spain
| | - Yiyao Ye-Lin
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València (Ci2B), Valencia 46022, Spain; BJUT-UPV Joint Research Laboratory in Biomedical Engineering, China
| | | | | | | | - Jose L Martinez-de-Juan
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València (Ci2B), Valencia 46022, Spain; BJUT-UPV Joint Research Laboratory in Biomedical Engineering, China
| | - Dongmei Hao
- Faculty of Environment and Life, Beijing University of Technology, Beijing International Science and Technology Cooperation Base for Intelligent Physiological Measurement and Clinical Transformation, Beijing 100124, China; BJUT-UPV Joint Research Laboratory in Biomedical Engineering, China
| | - Gema Prats-Boluda
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València (Ci2B), Valencia 46022, Spain; BJUT-UPV Joint Research Laboratory in Biomedical Engineering, China.
| |
Collapse
|
2
|
Jager F. An open dataset with electrohysterogram records of pregnancies ending in induced and cesarean section delivery. Sci Data 2023; 10:669. [PMID: 37783671 PMCID: PMC10545725 DOI: 10.1038/s41597-023-02581-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Accepted: 09/20/2023] [Indexed: 10/04/2023] Open
Abstract
The existing non-invasive automated preterm birth prediction methods rely on the use of uterine electrohysterogram (EHG) records coming from spontaneous preterm and term deliveries, and are indifferent to term induced and cesarean section deliveries. In order to enhance current publicly available pool of term EHG records, we developed a new EHG dataset, Induced Cesarean EHG DataSet (ICEHG DS), containing 126 30-minute EHG records, recorded early (23rd week), and/or later (31st week) during pregnancy, of those pregnancies that were expected to end in spontaneous term delivery, but ended in induced or cesarean section delivery. The records were collected at the University Medical Center Ljubljana, Ljubljana, Slovenia. The dataset includes 38 and 43, early and later, induced; 11 and 8, early and later, cesarean; and 13 and 13, early and later, induced and cesarean EHG records. This dataset enables better understanding of the underlying physiological mechanisms involved during pregnancies ending in induced and cesarean deliveries, and provides a robust and more realistic assessment of the performance of automated preterm birth prediction methods.
Collapse
Affiliation(s)
- Franc Jager
- Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, 1000, Ljubljana, Slovenia.
| |
Collapse
|
3
|
Mohammadi Far S, Beiramvand M, Shahbakhti M, Augustyniak P. Prediction of Preterm Labor from the Electrohysterogram Signals Based on Different Gestational Weeks. SENSORS (BASEL, SWITZERLAND) 2023; 23:5965. [PMID: 37447815 DOI: 10.3390/s23135965] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/19/2023] [Revised: 06/15/2023] [Accepted: 06/22/2023] [Indexed: 07/15/2023]
Abstract
Timely preterm labor prediction plays an important role for increasing the chance of neonate survival, the mother's mental health, and reducing financial burdens imposed on the family. The objective of this study is to propose a method for the reliable prediction of preterm labor from the electrohysterogram (EHG) signals based on different pregnancy weeks. In this paper, EHG signals recorded from 300 subjects were split into 2 groups: (I) those with preterm and term labor EHG data that were recorded prior to the 26th week of pregnancy (referred to as the PE-TE group), and (II) those with preterm and term labor EHG data that were recorded after the 26th week of pregnancy (referred to as the PL-TL group). After decomposing each EHG signal into four intrinsic mode functions (IMFs) by empirical mode decomposition (EMD), several linear and nonlinear features were extracted. Then, a self-adaptive synthetic over-sampling method was used to balance the feature vector for each group. Finally, a feature selection method was performed and the prominent ones were fed to different classifiers for discriminating between term and preterm labor. For both groups, the AdaBoost classifier achieved the best results with a mean accuracy, sensitivity, specificity, and area under the curve (AUC) of 95%, 92%, 97%, and 0.99 for the PE-TE group and a mean accuracy, sensitivity, specificity, and AUC of 93%, 90%, 94%, and 0.98 for the PL-TL group. The similarity between the obtained results indicates the feasibility of the proposed method for the prediction of preterm labor based on different pregnancy weeks.
Collapse
Affiliation(s)
| | - Matin Beiramvand
- Faculty of Information Technology and Communication, Tampere University, 33100 Tampere, Finland
| | - Mohammad Shahbakhti
- Biomedical Engineering Institute, Kaunas University of Technology, 51423 Kaunas, Lithuania
| | | |
Collapse
|
4
|
Diaz-Martinez A, Monfort-Ortiz R, Ye-Lin Y, Garcia-Casado J, Nieto-Tous M, Nieto-Del-Amor F, Diago-Almela V, Prats-Boluda G. Uterine myoelectrical activity as biomarker of successful induction with Dinoprostone: Influence of parity. Biocybern Biomed Eng 2023. [DOI: 10.1016/j.bbe.2022.12.004] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/06/2023]
|
5
|
Pirnar Ž, Jager F, Geršak K. Characterization and separation of preterm and term spontaneous, induced, and cesarean EHG records. Comput Biol Med 2022; 151:106238. [PMID: 36343404 DOI: 10.1016/j.compbiomed.2022.106238] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/24/2022] [Revised: 09/30/2022] [Accepted: 10/22/2022] [Indexed: 12/27/2022]
Abstract
To improve the understanding of the underlying physiological processes that lead to preterm birth, and different term delivery modes, we quantitatively characterized and assessed the separability of the sets of early (23rd week) and later (31st week) recorded, preterm and term spontaneous, induced, cesarean, and induced-cesarean electrohysterogram (EHG) records using several of the most widely used non-linear features extracted from the EHG signals. Linearly modeled temporal trends of the means of the median frequencies (MFs), and of the means of the peak amplitudes (PAs) of the normalized power spectra of the EHG signals, along pregnancy (from early to later recorded records), derived from a variety of frequency bands, revealed that for the preterm group of records, in comparison to all other term delivery groups, the frequency spectrum of the frequency band B0L (0.08-0.3 Hz) shifts toward higher frequencies, and that the spectrum of the newly identified frequency band B0L' (0.125-0.575 Hz), which approximately matches the Fast Wave Low band, becomes stronger. The most promising features to separate between the later preterm group and all other later term delivery groups appear to be MF (p=1.1⋅10-5) in the band B0L of the horizontal signal S3, and PA (p=2.4⋅10-8) in the band B0L' (S3). Moreover, the PA in the band B0L' (S3) showed the highest power to individually separate between the later preterm group and any other later term delivery group. Furthermore, the results suggest that in preterm pregnancies the resting maternal heart rate decreases between the 23rd and 31st week of gestation.
Collapse
Affiliation(s)
- Žiga Pirnar
- Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, 1000 Ljubljana, Slovenia
| | - Franc Jager
- Faculty of Computer and Information Science, University of Ljubljana, Večna pot 113, 1000 Ljubljana, Slovenia.
| | - Ksenija Geršak
- Faculty of Medicine, University of Ljubljana, Vrazov trg 2, 1000 Ljubljana, Slovenia; University Medical Center Ljubljana, Zaloška cesta 2, 1000 Ljubljana, Slovenia
| |
Collapse
|
6
|
Paljk Likar I, Becic E, Pezdirc N, Gersak K, Lucovnik M, Trojner Bregar A. Comparison of Oxytocin vs. Carbetocin Uterotonic Activity after Caesarean Delivery Assessed by Electrohysterography: A Randomised Trial. SENSORS (BASEL, SWITZERLAND) 2022; 22:8994. [PMID: 36433591 PMCID: PMC9698977 DOI: 10.3390/s22228994] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/29/2022] [Revised: 11/11/2022] [Accepted: 11/19/2022] [Indexed: 06/16/2023]
Abstract
Electrohysterography has been used for monitoring uterine contractility in pregnancy and labour. Effective uterine contractility is crucial for preventing postpartum haemorrhage. The objective of our study was to compare postpartum electrohysterograms in women receiving oxytocin vs. carbetocin for postpartum haemorrhage prevention after caesarean delivery. The trial is registered at ClinicalTrials.gov with the identifier NCT04201665. We included 64 healthy women with uncomplicated singleton pregnancies at term scheduled for caesarean section after one previous caesarean section. After surgery, a 15 min electrohysterogram was obtained after which women were randomised to receive either five IU of oxytocin intravenously or 100 μg of carbetocin intramuscularly. A 30 min electrohysterogram was performed two hours after drug application. Changes in power density spectrum peak frequency of electrohysterogram pseudo-bursts were analysed. A significant reduction in power density spectrum peak frequency in the first two hours was observed after carbetocin but not after oxytocin (median = 0.07 (interquartile range (IQR): 0.87 Hz) compared to median = -0.63 (IQR: 0.20) Hz; p = 0.004). Electrohysterography can be used for objective comparison of uterotonic effects. We found significantly higher power density spectrum peak frequency two hours after oxytocin compared to carbetocin.
Collapse
Affiliation(s)
- Ivana Paljk Likar
- Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia
- Division of Obstetrics and Gynecology, Department of Perinatology, University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia
| | - Emra Becic
- Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia
| | - Neza Pezdirc
- Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia
| | - Ksenija Gersak
- Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia
- Division of Obstetrics and Gynecology, Department of Perinatology, University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia
| | - Miha Lucovnik
- Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia
- Division of Obstetrics and Gynecology, Department of Perinatology, University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia
| | - Andreja Trojner Bregar
- Faculty of Medicine, University of Ljubljana, 1000 Ljubljana, Slovenia
- Division of Obstetrics and Gynecology, Department of Perinatology, University Medical Centre Ljubljana, 1000 Ljubljana, Slovenia
| |
Collapse
|
7
|
Albaladejo-Belmonte M, Prats-Boluda G, Ye Lin Y, Garfield RE, Garcia-Casado J. Uterine slow wave: directionality and changes with imminent delivery. Physiol Meas 2022; 43. [PMID: 35896091 DOI: 10.1088/1361-6579/ac84c0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/02/2022] [Accepted: 07/27/2022] [Indexed: 11/11/2022]
Abstract
OBJECTIVE The slow wave (SW) of the electrohysterogram (EHG) may contain relevant information on the electrophysiological condition of the uterus throughout pregnancy and labor. Our aim was to assess differences in the SW as regards the imminence of labor and the directionality of uterine myoelectrical activity. APPROACH The SW of the EHG was extracted from the signals of the Icelandic 16-electrode EHG database in the bandwidth [5, 30] mHz and its power, spectral content, complexity and synchronization between the horizontal (X) and vertical (Y) directions were characterized by the root mean square (RMS), dominant frequency (domF), sample entropy (SampEn) and maximum cross-correlation (CCmax) of the signals, respectively. Significant differences between parameters at time-to-delivery (TTD) ≤7 vs. >7 days and between the horizontal vs. vertical directions were assessed. MAIN RESULTS The SW power significantly increased in both directions as labor approached (TTD≤7d vs. >7d (mean±SD): x= 0.12±0.10 vs. 0.08±0.06mV; y= 0.12±0.09 vs. 0.08±0.05mV), as well as the dominant frequency in the horizontal direction (= 9.1±1.3 vs. 8.5±1.2mHz) and the synchronization between both directions (= 0.44±0.16 vs. 0.36±0.14). Furthermore, its complexity decreased in the vertical direction (= 6.13·10-2±8.7·10-3 vs. 6.50·10-2±8.3·10-3), suggesting a higher cell-to-cell electrical coupling. Whereas there were no differences between the SW features in both directions in the general population, statistically significant differences were obtained between them in individuals in many cases. SIGNIFICANCE Our results suggest that the SW of the EHG is related to bioelectrical events in the uterus and could provide objective information to clinicians in challenging obstetric scenarios.
Collapse
Affiliation(s)
- Monica Albaladejo-Belmonte
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, Edif. 8B, Camino de Vera SN, Valencia, Valencia, 46022, SPAIN
| | - Gema Prats-Boluda
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, Edif. 8B, Camino de Vera SN, Valencia, Valencia, 46022, SPAIN
| | - Yiyao Ye Lin
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, Edif. 8B, Camino de Vera SN, Valencia, Valencia, 46022, SPAIN
| | - Robert Edward Garfield
- The University of Arizona College of Medicine Tucson, 1501 N Campbell Ave, Tucson, AZ 85724, USA, Tucson, Arizona, 85724-5018, UNITED STATES
| | - Javier Garcia-Casado
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, Edif. 8B, Camino de Vera SN, Valencia, Valencia, 46022, SPAIN
| |
Collapse
|
8
|
Nieto-del-Amor F, Prats-Boluda G, Garcia-Casado J, Diaz-Martinez A, Diago-Almela VJ, Monfort-Ortiz R, Hao D, Ye-Lin Y. Combination of Feature Selection and Resampling Methods to Predict Preterm Birth Based on Electrohysterographic Signals from Imbalance Data. SENSORS 2022; 22:s22145098. [PMID: 35890778 PMCID: PMC9319575 DOI: 10.3390/s22145098] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/13/2022] [Revised: 07/01/2022] [Accepted: 07/05/2022] [Indexed: 02/01/2023]
Abstract
Due to its high sensitivity, electrohysterography (EHG) has emerged as an alternative technique for predicting preterm labor. The main obstacle in designing preterm labor prediction models is the inherent preterm/term imbalance ratio, which can give rise to relatively low performance. Numerous studies obtained promising preterm labor prediction results using the synthetic minority oversampling technique. However, these studies generally overestimate mathematical models’ real generalization capacity by generating synthetic data before splitting the dataset, leaking information between the training and testing partitions and thus reducing the complexity of the classification task. In this work, we analyzed the effect of combining feature selection and resampling methods to overcome the class imbalance problem for predicting preterm labor by EHG. We assessed undersampling, oversampling, and hybrid methods applied to the training and validation dataset during feature selection by genetic algorithm, and analyzed the resampling effect on training data after obtaining the optimized feature subset. The best strategy consisted of undersampling the majority class of the validation dataset to 1:1 during feature selection, without subsequent resampling of the training data, achieving an AUC of 94.5 ± 4.6%, average precision of 84.5 ± 11.7%, maximum F1-score of 79.6 ± 13.8%, and recall of 89.8 ± 12.1%. Our results outperformed the techniques currently used in clinical practice, suggesting the EHG could be used to predict preterm labor in clinics.
Collapse
Affiliation(s)
- Félix Nieto-del-Amor
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (J.G.-C.); (A.D.-M.); (Y.Y.-L.)
| | - Gema Prats-Boluda
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (J.G.-C.); (A.D.-M.); (Y.Y.-L.)
- Correspondence:
| | - Javier Garcia-Casado
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (J.G.-C.); (A.D.-M.); (Y.Y.-L.)
| | - Alba Diaz-Martinez
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (J.G.-C.); (A.D.-M.); (Y.Y.-L.)
| | | | - Rogelio Monfort-Ortiz
- Servicio de Obstetricia, H.U.P. La Fe, 46026 Valencia, Spain; (V.J.D.-A.); (R.M.-O.)
| | - Dongmei Hao
- Faculty of Environment and Life, Beijing University of Technology, Beijing International Science and Technology Cooperation Base for Intelligent Physiological Measurement and Clinical Transformation, Beijing 100124, China;
| | - Yiyao Ye-Lin
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (J.G.-C.); (A.D.-M.); (Y.Y.-L.)
| |
Collapse
|
9
|
Almeida M, Mouriño H, Batista AG, Russo S, Esgalhado F, dos Reis CRP, Serrano F, Ortigueira M. Electrohysterography extracted features dependency on anthropometric and pregnancy factors. Biomed Signal Process Control 2022. [DOI: 10.1016/j.bspc.2022.103556] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/02/2022]
|
10
|
Nieto-del-Amor F, Beskhani R, Ye-Lin Y, Garcia-Casado J, Diaz-Martinez A, Monfort-Ortiz R, Diago-Almela VJ, Hao D, Prats-Boluda G. Assessment of Dispersion and Bubble Entropy Measures for Enhancing Preterm Birth Prediction Based on Electrohysterographic Signals. SENSORS 2021; 21:s21186071. [PMID: 34577278 PMCID: PMC8471282 DOI: 10.3390/s21186071] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 06/28/2021] [Revised: 09/06/2021] [Accepted: 09/08/2021] [Indexed: 11/16/2022]
Abstract
One of the remaining challenges for the scientific-technical community is predicting preterm births, for which electrohysterography (EHG) has emerged as a highly sensitive prediction technique. Sample and fuzzy entropy have been used to characterize EHG signals, although they require optimizing many internal parameters. Both bubble entropy, which only requires one internal parameter, and dispersion entropy, which can detect any changes in frequency and amplitude, have been proposed to characterize biomedical signals. In this work, we attempted to determine the clinical value of these entropy measures for predicting preterm birth by analyzing their discriminatory capacity as an individual feature and their complementarity to other EHG characteristics by developing six prediction models using obstetrical data, linear and non-linear EHG features, and linear discriminant analysis using a genetic algorithm to select the features. Both dispersion and bubble entropy better discriminated between the preterm and term groups than sample, spectral, and fuzzy entropy. Entropy metrics provided complementary information to linear features, and indeed, the improvement in model performance by including other non-linear features was negligible. The best model performance obtained an F1-score of 90.1 ± 2% for testing the dataset. This model can easily be adapted to real-time applications, thereby contributing to the transferability of the EHG technique to clinical practice.
Collapse
Affiliation(s)
- Félix Nieto-del-Amor
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (R.B.); (J.G.-C.); (A.D.-M.); (G.P.-B.)
| | - Raja Beskhani
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (R.B.); (J.G.-C.); (A.D.-M.); (G.P.-B.)
| | - Yiyao Ye-Lin
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (R.B.); (J.G.-C.); (A.D.-M.); (G.P.-B.)
- Correspondence:
| | - Javier Garcia-Casado
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (R.B.); (J.G.-C.); (A.D.-M.); (G.P.-B.)
| | - Alba Diaz-Martinez
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (R.B.); (J.G.-C.); (A.D.-M.); (G.P.-B.)
| | - Rogelio Monfort-Ortiz
- Servicio de Obstetricia, H.U.P. La Fe, 46026 Valencia, Spain; (R.M.-O.); (V.J.D.-A.)
| | | | - Dongmei Hao
- Faculty of Environment and Life, Beijing University of Technology, Beijing International Science and Technology Cooperation Base for Intelligent Physiological Measurement and Clinical Transformation, Beijing 100124, China;
| | - Gema Prats-Boluda
- Centro de Investigación e Innovación en Bioingeniería, Universitat Politècnica de València, 46022 Valencia, Spain; (F.N.-d.-A.); (R.B.); (J.G.-C.); (A.D.-M.); (G.P.-B.)
| |
Collapse
|
11
|
Preterm-term birth classification using EMD-based time-domain features of single-channel electrohysterogram data. Phys Eng Sci Med 2021; 44:1151-1159. [PMID: 34463948 DOI: 10.1007/s13246-021-01051-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/28/2021] [Accepted: 08/26/2021] [Indexed: 10/20/2022]
Abstract
Preterm birth anticipation is a crucial task that can reduce both the rate and the complications of preterm birth. Electrohysterogram (EHG) or uterine electromyogram (EMG) data have shown that they can provide useful information for preterm birth anticipation. Four distinct time-domain features (mean absolute value, average amplitude change, difference in absolute standard deviation value, and log detector) that are commonly applied to EMG signal processing were utilized and investigated in this study. A single channel of EHG data was decomposed into its constituent components (i.e., into intrinsic mode functions) by using empirical mode decomposition (EMD) before their time-domain features were extracted. The time-domain features of the intrinsic mode functions of the EHG data associated with preterm and term births were applied for preterm-term birth classification by using a support vector machine with a radial basis function. The preterm-term birth classifications were validated by using 10-fold cross validation. From the computational results, it was shown that excellent preterm-term birth classification can be achieved by using single-channel EHG data. The computational results further suggested that the best overall performance concerning preterm-term birth classification was obtained when thirteen (out of sixteen) EMD-based time-domain features were applied. The best accuracy, sensitivity, specificity, and [Formula: see text]-score achieved were 0.9382, 0.9130, 0.9634, and 0.9366, respectively.
Collapse
|
12
|
Optimized Feature Subset Selection Using Genetic Algorithm for Preterm Labor Prediction Based on Electrohysterography. SENSORS 2021; 21:s21103350. [PMID: 34065847 PMCID: PMC8151582 DOI: 10.3390/s21103350] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 03/05/2021] [Revised: 04/23/2021] [Accepted: 05/07/2021] [Indexed: 11/17/2022]
Abstract
Electrohysterography (EHG) has emerged as an alternative technique to predict preterm labor, which still remains a challenge for the scientific-technical community. Based on EHG parameters, complex classification algorithms involving non-linear transformation of the input features, which clinicians found difficult to interpret, were generally used to predict preterm labor. We proposed to use genetic algorithm to identify the optimum feature subset to predict preterm labor using simple classification algorithms. A total of 203 parameters from 326 multichannel EHG recordings and obstetric data were used as input features. We designed and validated 3 base classifiers based on k-nearest neighbors, linear discriminant analysis and logistic regression, achieving F1-score of 84.63 ± 2.76%, 89.34 ± 3.5% and 86.87 ± 4.53%, respectively, for incoming new data. The results reveal that temporal, spectral and non-linear EHG parameters computed in different bandwidths from multichannel recordings provide complementary information on preterm labor prediction. We also developed an ensemble classifier that not only outperformed base classifiers but also reduced their variability, achieving an F1-score of 92.04 ± 2.97%, which is comparable with those obtained using complex classifiers. Our results suggest the feasibility of developing a preterm labor prediction system with high generalization capacity using simple easy-to-interpret classification algorithms to assist in transferring the EHG technique to clinical practice.
Collapse
|
13
|
Optimization of Imminent Labor Prediction Systems in Women with Threatened Preterm Labor Based on Electrohysterography. SENSORS 2021; 21:s21072496. [PMID: 33916679 PMCID: PMC8038321 DOI: 10.3390/s21072496] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/17/2021] [Revised: 03/29/2021] [Accepted: 03/30/2021] [Indexed: 12/30/2022]
Abstract
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. RFF1_2 and ELMF1_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. ELMF1_2 outperformed RFF1_2 in sensitivity, being similar to those of ELMSens (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.
Collapse
|