1
|
Shi Q, Wang Q, Tian S, Wang Q, Lv C. Assessment of different sonographic cervical measures to predict labor induction outcomes: a systematic review and meta-analysis. Quant Imaging Med Surg 2023; 13:8462-8477. [PMID: 38106269 PMCID: PMC10722025 DOI: 10.21037/qims-23-507] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2023] [Accepted: 10/12/2023] [Indexed: 12/19/2023]
Abstract
Background Induction of labor (IOL) is a common obstetric approach to start or encourage uterine contractions to achieve a vaginal birth. It is recommended when continuing the pregnancy may be more dangerous for the mother or baby. Different ultrasonographic measures, such as cervical length, have been investigated as possible predictors of the outcomes of IOL. This meta-analysis aimed to assess the accuracy of ultrasound measurements in anticipating successful IOL. Methods The study conducted a thorough search on three databases (PubMed, Scopus, and Web of Science) until 04 March 2023, to find clinical studies published in English that reported different sonographic cervical measures and their ability to predict IOL outcomes. The chosen studies were stratified based on the type of indicator reported, and a meta-analysis was conducted to determine the best indicator for both successful and failed induction. The risk of bias and concerns about the applicability of the included studies was evaluated using the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) method. Results This study analyzed 57 studies with 9,338 patients. Cervical length is moderately effective in predicting successful IOL, with pooled sensitivity (SN) and specificity (SP) of 0.67 and 0.70, respectively. However, cervical length had a pooled SN and SP of 0.70 and 0.61 for predicting failed IOL. The posterior cervical angle was found to have a higher pooled SN and SP of 0.79 and 0.73 for predicting successful IOL. Fetal head-perineum distance demonstrated moderate accuracy with a pooled SN, SP, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and area under the curve of 0.58, 0.66, 1.95, 0.36, 5.33, and 0.9992, respectively, for predicting successful IOL. Conclusions Fetal head-perineum distance was the most effective predictor for successful IOL compared to cervical length, which only had a moderate predictive ability. Shortening of cervical length was not a useful indicator for successful IOL. On the other hand, the posterior cervical angle was the most reliable factor for predicting failed induction. The study's findings can aid in developing more effective management strategies for IOL.
Collapse
Affiliation(s)
- Qian Shi
- Department of Ultrasound Diagnosis and Treatment, The Second Affiliated Hospital of Shandong First Medical University, Tai'an, China
| | - Qing Wang
- Department of Ultrasound Diagnosis and Treatment, The Second Affiliated Hospital of Shandong First Medical University, Tai'an, China
| | - Shuangyan Tian
- Department of Ultrasound Diagnosis and Treatment, The Second Affiliated Hospital of Shandong First Medical University, Tai'an, China
| | - Qianqian Wang
- Department of Ultrasound Diagnosis and Treatment, The Second Affiliated Hospital of Shandong First Medical University, Tai'an, China
| | - Chunju Lv
- Department of Ultrasound Diagnosis and Treatment, The Second Affiliated Hospital of Shandong First Medical University, Tai'an, China
| |
Collapse
|
2
|
Mbata MK, Boesing M, Lüthi-Corridori G, Jaun F, Vetter G, Gröbli-Stäheli J, Leuppi-Taegtmeyer AB, Frey Tirri B, Leuppi JD. The Correct Indication to Induce Labour in a Swiss Cantonal Hospital. J Clin Med 2023; 12:6515. [PMID: 37892653 PMCID: PMC10607527 DOI: 10.3390/jcm12206515] [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: 08/28/2023] [Revised: 10/04/2023] [Accepted: 10/12/2023] [Indexed: 10/29/2023] Open
Abstract
BACKGROUND Induction of labour (IOL) is a way to stimulate the onset of labour using mechanical and pharmacological methods. IOL is one of the most frequently performed obstetric procedures worldwide. We aimed to determine compliance with guidelines and to investigate factors associated with the success of labour. METHODS In this retrospective, observational study, we analysed all induced deliveries in a Swiss hospital between January 2020 and December 2022. RESULTS Out of 1705 deliveries, 349 women underwent IOL, and 278 were included in this study, with an average age of 32 years (range 19-44 years). Most of the women were induced for missed deadlines (20.1%), the premature rupture of membranes (16.5%), and gestational diabetes mellitus (9.3%), and there was a good adherence to the guideline, especially with the indication and IOL monitoring (100%). However, an improvement needs to be made in measuring and documenting the Bishop score (41%). The success of labour was associated with multiparity (81.8% vs. 62.4% p = 0.001) and maternal non-obesity (73.4 vs. 54.1% p = 0.026). CONCLUSIONS An improvement is needed in the measurement and documentation of the Bishop score. Further research is needed to confirm the found associations between parity, obesity, and the success of IOL.
Collapse
Affiliation(s)
- Munachimso Kizito Mbata
- University Institute of Internal Medicine, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
- Faculty of Medicine, University of Basel, Klingelbergstrasse 61, 4056 Basel, Switzerland
| | - Maria Boesing
- University Institute of Internal Medicine, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
- Faculty of Medicine, University of Basel, Klingelbergstrasse 61, 4056 Basel, Switzerland
| | - Giorgia Lüthi-Corridori
- University Institute of Internal Medicine, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
- Faculty of Medicine, University of Basel, Klingelbergstrasse 61, 4056 Basel, Switzerland
| | - Fabienne Jaun
- University Institute of Internal Medicine, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
- Faculty of Medicine, University of Basel, Klingelbergstrasse 61, 4056 Basel, Switzerland
| | - Grit Vetter
- Department of Gynaecology and Obstetrics, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
| | - Jeanette Gröbli-Stäheli
- Department of Gynaecology and Obstetrics, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
| | - Anne B. Leuppi-Taegtmeyer
- Faculty of Medicine, University of Basel, Klingelbergstrasse 61, 4056 Basel, Switzerland
- Hospital Pharmacy, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
- Department of Patient Safety, Medical Directorate, University Hospital Basel, Schanzenstrasse 55, 4056 Basel, Switzerland
| | - Brigitte Frey Tirri
- Department of Gynaecology and Obstetrics, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
| | - Jörg D. Leuppi
- University Institute of Internal Medicine, Cantonal Hospital Baselland, Rheinstrasse 26, 4410 Liestal, Switzerland
- Faculty of Medicine, University of Basel, Klingelbergstrasse 61, 4056 Basel, Switzerland
| |
Collapse
|
3
|
Assemie MA, Mihiret GT, Mekonnen C, Petrucka P, Getaneh T, Ashebir W. Outcomes and Associated Factors of Induction of Labor in East Gojjam Zone, Northwest Ethiopia: A Multicenter Cross-Sectional Study. Obstet Gynecol Int 2023; 2023:6910063. [PMID: 37351527 PMCID: PMC10284654 DOI: 10.1155/2023/6910063] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/22/2022] [Revised: 05/30/2023] [Accepted: 06/05/2023] [Indexed: 06/24/2023] Open
Abstract
Background Induction of labor is the initiation of uterine contractions by artificial methods once the fetus has reached viability and prior to spontaneous onset of labor with the aim of achieving vaginal delivery. Although induction of labor is a critical life-saving intervention that potentially reduces adverse pregnancy outcomes, sometimes it has undesirable consequences for the health of the mother and/or the fetus. Hence, this study aimed to evaluate the outcomes and associated factors of labor induction. Methods An institution-based cross-sectional study was conducted from February 25 to May 25, 2020, among women undergoing induction at East Gojjam zone public hospitals in northwest Ethiopia. A structured interviewer-administered questionnaire was used to collect data from a sample of 411 mothers who were selected using a systematic random sampling technique. Stata/se™ Version 14 statistical software was used to analyze the data. Multivariable binary logistic regression was used to determine the potential factors affecting successful labor induction. Adjusted odds ratios with their 95% CI intervals were used to declare the strength of the association, and a variable with p value <0.05 was considered to have statistical significance. Results The prevalence of successful induction of labor was 70.3% (65.6, 74.7). The favorable Bishop score ((CI 3.90, 1.63-9.29); p value = 0.002), the intermediate Bishop score ((CI 3.53, 2.15-5.82); p value = 0.001), labor induction using oxytocin with cervical ripening ((CI 2.60, 1.21-5.63); p value = 0.015), and urban residence ((CI 0.48, 0.30-0.78); p value = 0.003) were associated with successful induction of labor. Conclusion These findings strongly suggest that cervical conditions are important determinants for the success of labor induction. Therefore, healthcare providers should confirm the favorability of the cervical status (using Bishop score) as a strict prerequisite before actual labor induction, and special consideration should be given to those pregnant women who reside in urban areas.
Collapse
Affiliation(s)
- Moges Agazhe Assemie
- Department of Public Health, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Getachew Tilaye Mihiret
- Department of Midwifery, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Chernet Mekonnen
- Department of Midwifery, Debre Markos Comprehensive Specialized Hospital, Debre Markos, Ethiopia
| | - Pammla Petrucka
- College of Nursing, University of Saskatchewan, Saskatoon, Canada
| | - Temesgen Getaneh
- Department of Midwifery, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| | - Wassachew Ashebir
- Department of Public Health, College of Health Sciences, Debre Markos University, Debre Markos, Ethiopia
| |
Collapse
|
4
|
Farah FQ, Aynalem GL, Seyoum AT, Gedef GM. The prevalence and associated factors of success of labor induction in Hargeisa maternity hospitals, Hargeisa Somaliland 2022: a hospital-based cross-sectional study. BMC Pregnancy Childbirth 2023; 23:437. [PMID: 37312039 DOI: 10.1186/s12884-023-05655-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2023] [Accepted: 04/27/2023] [Indexed: 06/15/2023] Open
Abstract
BACKGROUND The induction of labor is an artificial initiation of labor and has become one of the most common interventions in modern obstetrics to improve maternal and neonatal health. Understanding the prevalence and pregnancy outcomes following labor inductions is crucial in regions with high rates of maternal mortality and morbidity because of insufficient access to comprehensive emergency obstetric care. Therefore, this study aimed to assess the prevalence and associated factors of the success of induction of labor in Hargeisa maternity hospital Somaliland. METHODS A hospital-based cross-sectional study was employed among 453 women in Hargeisa maternity hospitals, Somaliland from January 1st to March 30th, 2022. Data were entered using Epi data version 4.6 and analyzed by using SPSS version 25. Bivariable and multivariable logistic regression were used to identify the associated factors with the success of labor induction and an odds ratio with a 95% confidence interval was used to measure the strength of the association. A P-value of ≤ 0.05 was considered statistically significant in multivariate analysis. RESULTS Of a total of 453 study participants who had undergone induction of labor, 349 (77%) of them had successful induction of labor with a 95% CI: 73%, 81%. Favorable Bishop score (AOR = 3.45, 95% CI: 1.98, 5.99), time from the start of induction to delivery < 12 h (AOR = 4.01, 95% CI: 2.16, 7.450), non-reassuring fetal heart rate pattern (AOR = 0.42, 95% CI: 0.22, 0.78) and amniotic fluid change to meconium (AOR = 0.43, 95% CI: 0.23, 0.79) were significantly associated with the success of labor induction. CONCLUSION This study implies that three out of four women who underwent induction had successful induction of labor. Favorable bishop score, time from the start of induction to delivery < 12 h, non-reassuring fetal heart rate pattern, and amniotic fluid change to meconium were significantly associated with the success of labor induction. The hospital should establish a clear bishop scoring system and there should be a strict follow-up on the condition of the fetal heartbeat and take corrective actions as needed. The factors related to healthcare facilities and providers need to be addressed by additional prospective studies.
Collapse
Affiliation(s)
| | - Getie Lake Aynalem
- School of Midwifery, College of Medicine and Health Science, University of Gondar, Gondar, Ethiopia
| | - Asmra Tesfahun Seyoum
- School of Midwifery, College of Medicine and Health Science, University of Gondar, Gondar, Ethiopia
| | - Getachew Muluye Gedef
- School of Midwifery, College of Medicine and Health Science, University of Gondar, Gondar, Ethiopia.
| |
Collapse
|
5
|
Laikemariam M, Aklilu A, Waltengus F, Addis M, Gezimu W, Baye F, Getaneh T. Adverse neonatal outcomes and associated factors among mothers who gave birth through induced and spontaneous labor in public hospitals of Awi zone, Northwest Ethiopia: a comparative cross-sectional study. BMC Pregnancy Childbirth 2023; 23:307. [PMID: 37131132 PMCID: PMC10152696 DOI: 10.1186/s12884-023-05631-4] [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: 11/05/2022] [Accepted: 04/21/2023] [Indexed: 05/04/2023] Open
Abstract
BACKGROUND Adverse neonatal outcomes are one of the most common causes of neonatal mortality and morbidity. Empirical evidence across the world shows that induction of labor potentiates adverse neonatal outcomes. In Ethiopia, there has been limited data that compares the frequency of adverse neonatal outcomes between induced and spontaneous labor. OBJECTIVES To compare the prevalence of adverse neonatal outcomes between induced and spontaneous labor and to determine associated factors among women who gave birth in public hospitals of Awi Zone, Northwest Ethiopia. METHODS A comparative cross-sectional study was conducted at Awi Zone public hospitals from May 1 to June 30, 2022. A simple random sampling technique was employed to select 788 (260 induced and 528 spontaneous) women. The collected data were analyzed using statistical package for social science (SPSS) software version 26. The Chi-square test and an independent t-test were used for categorical and continuous variables, respectively. A binary logistic regression was used to assess the association between the outcome and explanatory variables. In the bivariate analysis, a p-value ≤ 0.2 at a 95% confidence interval was used to consider the variables in the multivariate analysis. Finally, statistical significance was stated at a p-value of less than 0.05. RESULT The adverse neonatal outcomes among women who gave birth through induced labor were 41.1%, whereas spontaneous labor was 10.3%. The odds of adverse neonatal outcomes in induced labor were nearly two times higher than in spontaneous labor (AOR = 1.89, 95% CI: 1.11-3.22). No education (AOR = 2.00, 95% CI: 1.56, 6.44), chronic disease (AOR = 3.99, 95% CI: 1.87, 8.52), male involvement (AOR = 2.23, 95% CI: 1.23, 4.06), preterm birth (AOR = 9.83, 95% CI: 8.74, 76.37), operative delivery (AOR = 8.60, 95% CI: 4.63, 15.90), cesarean section (AOR = 4.17, 95% CI: 1.94, 8.95), and labor complications (AOR = 5.16, 95% CI: 2.90, 9.18) were significantly associated factors with adverse neonatal outcomes. CONCLUSION AND RECOMMENDATION Adverse neonatal outcomes in the study area were higher. Composite adverse neonatal outcomes were significantly higher in induced labor compared to spontaneous labor. Therefore, it is important to anticipate the possible adverse neonatal outcomes and plan management strategies while conducting every labor induction.
Collapse
Affiliation(s)
- Melaku Laikemariam
- Department of Midwifery, College of Health Science, Debre Markos University, Debre Markos, Ethiopia.
| | - Almaz Aklilu
- Department of Midwifery, School of Health Sciences, College of Medicine and Health Science, Bahr Dar University, Bahr Dar, Ethiopia
| | - Fikadu Waltengus
- Department of Midwifery, School of Health Sciences, College of Medicine and Health Science, Bahr Dar University, Bahr Dar, Ethiopia
| | - Melkamu Addis
- Department of Midwifery, College of Health Science, Debre Markos University, Debre Markos, Ethiopia
| | - Wubishet Gezimu
- Department of Nursing, College of Health Science, Mettu University, Mettu, Ethiopia
| | - Fekadu Baye
- Department of Midwifery, College of Health Science, Debre Markos University, Debre Markos, Ethiopia
| | - Temesgen Getaneh
- Department of Midwifery, College of Health Science, Debre Markos University, Debre Markos, Ethiopia
| |
Collapse
|
6
|
Willy D, Schmitz R, Klockenbusch W, Köster HA, Willy K, Braun J, Möllers M, Oelmeier K. Perinatal Outcome and Its Association with Blood Pressure Levels in Women with Preeclampsia. J Clin Med 2022; 11:jcm11216334. [PMID: 36362562 PMCID: PMC9654839 DOI: 10.3390/jcm11216334] [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: 08/28/2022] [Revised: 10/15/2022] [Accepted: 10/22/2022] [Indexed: 11/16/2022] Open
Abstract
Background: Timing and mode of delivery in women with preeclampsia remains challenging, often balancing the risk of severe maternal complications and preterm delivery with its risks for the newborn. It is known that women with very high blood pressure levels in pregnancy have more unfavourable outcomes, but there is little data on neonatal outcome in these cases and the effect of the delivery mode. Methods: We included 158 preeclamptic women in our single-centre retrospective cohort study. Patients were divided into three subgroups depending on blood pressure levels, and delivery mode as well as neonatal outcomes were analysed. Furthermore, the effect of gestational age at delivery was assessed. Results: Maternal blood pressure levels correlated negatively with gestational age at delivery (p = 0.007) and positively with delivery via caesarean section (p = 0.003). Induction of labour was more frequent in women with lower blood pressure levels (p = 0.008) and higher gestational age (p < 0.001). If labour was induced, vaginal delivery was achieved equally often in all gestational ages. Neonatal outcome appears to be more favourable after vaginal delivery compared to planned caesarean section (p < 0.001). Conclusions: Induction of labour should be discussed generously in preeclamptic women, even if blood pressure levels are high and/or gestational age is young, as success rates seem to be adequate and neonatal outcome is more favourable after vaginal delivery. Large prospective trials are needed to better evaluate success rates, risks and complications of induced labour and the effects of delivery mode on neonatal outcome in preeclampsia.
Collapse
Affiliation(s)
- Daniela Willy
- Department of Obstetrics and Gynecology, University Hospital Münster, 48149 Münster, Germany
- Correspondence: ; Tel.: +49-251-83-44165; Fax: +49-251-83-48210
| | - Ralf Schmitz
- Department of Obstetrics and Gynecology, University Hospital Münster, 48149 Münster, Germany
| | - Walter Klockenbusch
- Department of Obstetrics and Gynecology, University Hospital Münster, 48149 Münster, Germany
| | - Helen Ann Köster
- Department of Obstetrics and Gynecology, University Hospital Münster, 48149 Münster, Germany
| | - Kevin Willy
- Department of Cardiology, University Hospital Münster, 48149 Münster, Germany
| | - Janina Braun
- Department of Obstetrics and Gynecology, University Hospital Münster, 48149 Münster, Germany
| | - Mareike Möllers
- Department of Obstetrics and Gynecology, University Hospital Münster, 48149 Münster, Germany
| | - Kathrin Oelmeier
- Department of Obstetrics and Gynecology, University Hospital Münster, 48149 Münster, Germany
| |
Collapse
|
7
|
Mebratu A, Assefa DG, Zeleke ED, Mengistu N, Woldesenbet TT, Aynalem A, Sefa A, Mellesse D, Tilahun R, Seifu W, Bayisa Y, Meshesha MD, Wudneh A, Ayele GM, Demisse B, Kabthymer RH, Alemu A, Abebe Eshetu M, Mahamed AA, Temesgen T, Funga ML, Eritero AC, Aregawi S, Wodaynew T, Figa Z, Molla W. Failed induction of labor and associated factors among women delivered in Jigjiga University Sheik Hassan Yabare Referral Hospital: a cross-sectional study. Curr Med Res Opin 2022; 38:1655-1662. [PMID: 35852409 DOI: 10.1080/03007995.2022.2103959] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
OBJECTIVE This study was aimed to assess the magnitude of failed induction of labor and associated factors among mothers delivered in Eastern Ethiopia. METHODS An institutional-based cross-sectional study was carried out among 364 women who had induction of labor at Jigjiga University, Sheik Hassan Yabare Referral Hospital from 2018 to 2021. A checklist was used to collect the data from the women's chart. To isolate independent predictors related to failed induction of labor, multivariate logistic regression analyses were performed. RESULT The magnitude of failed induction of labor was 36.8% (95% CI: 31.8, 42.0). Age (AOR = 3.2; CI: 1.78, 5.75), rural residency (AOR = 2.28; CI:1.29, 4.01), para (AOR = 2.76; CI: 1.55, 4.91), gestational age (AOR = 2.65; CI: 1.44, 4.89), multiple pregnancy (AOR = 2.36; CI: 1.01, 5.55), premature rapture of membrane (AOR = 4.88; CI: 2.33, 10.21), pregnancy-induced hypertension (AOR = 5.11; CI: 2.67, 9.79), and bishop score (AOR = 1.95; CI: 1.15, 3.32) were significantly associated with failed induction of labor. CONCLUSION The magnitude of failed induction of labor was relatively high in the study setting. Failed induction of labor was significantly associated with age, rural residency, primipara, gestational age, multiple pregnancy, premature rapture of membrane, PIH, and bishop score less than six. Prior to initiating the induction of labor, proper pelvis assessment and cervical ripening for bishop score might be considered. Beside to this, adherence to locally available induction protocols and guidelines might also be needed.
Collapse
Affiliation(s)
| | | | | | | | | | | | - Ahmedin Sefa
- Department of Nursing, Dilla University, Dilla, Ethiopia
| | - Dawit Mellesse
- Department of Midwifery, Dire Dawa University, Dire Dawa, Ethiopia
| | - Ruth Tilahun
- Department of Midwifery, Dilla University, Dilla, Ethiopia
| | - Wubareg Seifu
- School of Public Health, Jigjiga University, Jigjiga, Ethiopia
| | | | | | | | | | - Biniyam Demisse
- School of Nursing, Arbaminch University, Arbaminch, Ethiopia
| | | | - Asrat Alemu
- Department of Midwifery, Dilla University, Dilla, Ethiopia
| | | | | | | | | | | | - Saron Aregawi
- School of Public Health, Dilla University, Dilla, Ethiopia
| | | | - Zerihun Figa
- Department of Midwifery, Dilla University, Dilla, Ethiopia
| | | |
Collapse
|
8
|
Tarimo CS, Bhuyan SS, Zhao Y, Ren W, Mohammed A, Li Q, Gardner M, Mahande MJ, Wang Y, Wu J. Prediction of low Apgar score at five minutes following labor induction intervention in vaginal deliveries: machine learning approach for imbalanced data at a tertiary hospital in North Tanzania. BMC Pregnancy Childbirth 2022; 22:275. [PMID: 35365129 PMCID: PMC8976377 DOI: 10.1186/s12884-022-04534-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/18/2021] [Accepted: 02/28/2022] [Indexed: 11/18/2022] Open
Abstract
Background Prediction of low Apgar score for vaginal deliveries following labor induction intervention is critical for improving neonatal health outcomes. We set out to investigate important attributes and train popular machine learning (ML) algorithms to correctly classify neonates with a low Apgar scores from an imbalanced learning perspective. Methods We analyzed 7716 induced vaginal deliveries from the electronic birth registry of the Kilimanjaro Christian Medical Centre (KCMC). 733 (9.5%) of which constituted of low (< 7) Apgar score neonates. The ‘extra-tree classifier’ was used to assess features’ importance. We used Area Under Curve (AUC), recall, precision, F-score, Matthews Correlation Coefficient (MCC), balanced accuracy (BA), bookmaker informedness (BM), and markedness (MK) to evaluate the performance of the selected six (6) machine learning classifiers. To address class imbalances, we examined three widely used resampling techniques: the Synthetic Minority Oversampling Technique (SMOTE) and Random Oversampling Examples (ROS) and Random undersampling techniques (RUS). We applied Decision Curve Analysis (DCA) to evaluate the net benefit of the selected classifiers. Results Birth weight, maternal age, and gestational age were found to be important predictors for the low Apgar score following induced vaginal delivery. SMOTE, ROS and and RUS techniques were more effective at improving “recalls” among other metrics in all the models under investigation. A slight improvement was observed in the F1 score, BA, and BM. DCA revealed potential benefits of applying Boosting method for predicting low Apgar scores among the tested models. Conclusion There is an opportunity for more algorithms to be tested to come up with theoretical guidance on more effective rebalancing techniques suitable for this particular imbalanced ratio. Future research should prioritize a debate on which performance indicators to look up to when dealing with imbalanced or skewed data. Supplementary Information The online version contains supplementary material available at 10.1186/s12884-022-04534-0.
Collapse
Affiliation(s)
- Clifford Silver Tarimo
- Department of Epidemiology and Health Statistics, College of Public Health, Zhengzhou University, 100 Kexue Avenue, Zhengzhou, 450001, Henan, China.,Department of Science and Laboratory Technology, Dar es Salaam Institute of Technology, P.O. Box 2958, Dar es Salaam, Tanzania
| | - Soumitra S Bhuyan
- Rutgers University-New Brunswick, Edward J. Bloustein, School of Planning and Public Policy, New Brunswick, USA
| | - Yizhen Zhao
- Luoyang Orthopedic Traumatological Hospital of Henan Province, Luoyang, China
| | - Weicun Ren
- Department of Epidemiology and Health Statistics, College of Public Health, Zhengzhou University, 100 Kexue Avenue, Zhengzhou, 450001, Henan, China.,College of Sanquan, Xinxiang Medical University, Xinxiang, People's Republic of China
| | - Akram Mohammed
- Center for Biomedical Informatics, University of Tennessee Health Science Center, Memphis, TN, USA
| | - Quanman Li
- Department of Epidemiology and Health Statistics, College of Public Health, Zhengzhou University, 100 Kexue Avenue, Zhengzhou, 450001, Henan, China
| | - Marilyn Gardner
- Department of Public Health, Western Kentucky University, 1906 College Heights Blvd, Bowling Green, KY, 42101, USA
| | - Michael Johnson Mahande
- Institute of Public Health, Kilimanjaro Christian Medical University College, P.O. Box 2240, Moshi, Tanzania
| | - Yuhui Wang
- Centre for Financial and Corporate Integrity, Coventry University, Coventry, UK
| | - Jian Wu
- Department of Epidemiology and Health Statistics, College of Public Health, Zhengzhou University, 100 Kexue Avenue, Zhengzhou, 450001, Henan, China. .,Henan Province Engineering Research Center of Health Economics & Health Technology Assessment, Henan Province, China.
| |
Collapse
|