1
|
Castán Larraz B, Esteban LM, Castán Mateo S, Chóliz Ezquerro M, Calvo Torres J, Esteban-Escaño J, Rodríguez Solanilla B, Cisneros Gimeno A, Savirón-Cornudella R. The utility of fetal heart rate deceleration's descending slope in searching for a non-National Institute of Child Health and Human Development parameter for the detection of fetal acidosis. Int J Gynaecol Obstet 2024; 166:859-870. [PMID: 38441244 DOI: 10.1002/ijgo.15454] [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: 11/11/2023] [Revised: 02/10/2024] [Accepted: 02/18/2024] [Indexed: 07/18/2024]
Abstract
OBJECTIVE To identify new parameters predicting fetal acidemia. METHODS A retrospective case-control study in a cohort of deliveries from a tertiary referral hospital-based cohort deliveries in Zaragoza, Spain between 2018 and 2021 was performed. To predict fetal acidemia, the NICHD categorizations and non-NICHD parameters were analyzed in the electronic fetal monitoring (EFM). Those included total reperfusion time, total deceleration area and the slope of the descending limb of the fetal heart rate of the last deceleration curve. The accuracy of the parameters was evaluated using the specificity for (80%, 85%, 90%, 95%) sensitivity and the area under the receiver operating characteristic curve (AUC). RESULTS A total of 10 362 deliveries were reviewed, with 224 cases and 278 controls included in the study. The NICHD categorizations showed reasonable discriminatory ability (AUC = 0.727). The non-NICHD parameters measured during the 30-min fetal monitoring, total deceleration area (AUC = 0.807, 95% CI: 0.770, 0.845) and total reperfusion time (AUC = 0.750, 95% CI: 0.707, 0.792), exhibited higher discriminatory ability. The slope of the descending limb of the fetal heart rate of the last deceleration curve had the best AUC value (0.853, 95% CI: 0.816, 0.889). The combination of total deceleration area or total reperfusion time with the slope demonstrated high discriminatory ability (AUC = 0.908, 95% CI: 0.882, 0.933; specificities of 71.6% and 72.7% for a sensitivity of 90%). CONCLUSIONS The slope of the descending limb of the fetal heart rate of the last deceleration curve is the strongest predictor of fetal acidosis, but its combination with the total reperfusion time shows better clinical utility.
Collapse
Affiliation(s)
- Berta Castán Larraz
- Department of Obstetrics and Gynecology, Hospital Universitario Miguel Servet, Zaragoza, Spain
| | - Luis Mariano Esteban
- Department of Applied Mathematics, Escuela Universitaria Politécnica de La Almunia, Institute for Biocomputation and Physics of Complex Systems (BIFI), Universidad de Zaragoza, Zaragoza, Spain
| | - Sergio Castán Mateo
- Department of Obstetrics and Gynecology, Hospital Universitario Miguel Servet, Zaragoza, Spain
| | | | - Javier Calvo Torres
- Department of Obstetrics and Gynecology, Hospital Clínico San Carlos, Madrid, Spain
| | - Javier Esteban-Escaño
- Department of Electronic Engineering and Communications, Escuela Universitaria Politécnica de La Almunia, Universidad de Zaragoza, Zaragoza, Spain
| | | | - Ana Cisneros Gimeno
- Departamento de Anatomía e Histología Humanas, Facultad de Medicina, Universidad de Zaragoza, Zaragoza, Spain
| | - Ricardo Savirón-Cornudella
- Department of Obstetrics and Gynecology, Hospital Clínico San Carlos, Madrid, Spain
- Instituto de Investigación Sanitaria San Carlos (IdISSC), Universidad Complutense, Madrid, Spain
| |
Collapse
|
2
|
Ben M'Barek I, Ben M'Barek B, Jauvion G, Holmström E, Agman A, Merrer J, Ceccaldi PF. Large-scale analysis of interobserver agreement and reliability in cardiotocography interpretation during labor using an online tool. BMC Pregnancy Childbirth 2024; 24:136. [PMID: 38355457 PMCID: PMC10865637 DOI: 10.1186/s12884-024-06322-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Accepted: 02/05/2024] [Indexed: 02/16/2024] Open
Abstract
BACKGROUND While the effectiveness of cardiotocography in reducing neonatal morbidity is still debated, it remains the primary method for assessing fetal well-being during labor. Evaluating how accurately professionals interpret cardiotocography signals is essential for its effective use. The objective was to evaluate the accuracy of fetal hypoxia prediction by practitioners through the interpretation of cardiotocography signals and clinical variables during labor. MATERIAL AND METHODS We conducted a cross-sectional online survey, involving 120 obstetric healthcare providers from several countries. One hundred cases, including fifty cases of fetal hypoxia, were randomly assigned to participants who were invited to predict the fetal outcome (binary criterion of pH with a threshold of 7.15) based on the cardiotocography signals and clinical variables. After describing the participants, we calculated (with a 95% confidence interval) the success rate, sensitivity and specificity to predict the fetal outcome for the whole population and according to pH ranges, professional groups and number of years of experience. Interobserver agreement and reliability were evaluated using the proportion of agreement and Cohen's kappa respectively. RESULTS The overall ability to predict a pH level below 7.15 yielded a success rate of 0.58 (95% CI 0.56-0.60), a sensitivity of 0.58 (95% CI 0.56-0.60) and a specificity of 0.63 (95% CI 0.61-0.65). No significant difference in the success rates was observed with respect to profession and number of years of experience. The success rate was higher for the cases with a pH level below 7.05 (0.69) and above 7.20 (0.66) compared to those falling between 7.05 and 7.20 (0.48). The proportion of agreement between participants was good (0.82), with an overall kappa coefficient indicating substantial reliability (0.63). CONCLUSIONS The use of an online tool enabled us to collect a large amount of data to analyze how practitioners interpret cardiotocography data during labor. Despite a good level of agreement and reliability among practitioners, the overall accuracy is poor, particularly for cases with a neonatal pH between 7.05 and 7.20. Factors such as profession and experience level do not present notable impact on the accuracy of the annotations. The implementation and use of a computerized cardiotocography analysis software has the potential to enhance the accuracy to detect fetal hypoxia, especially for ambiguous cardiotocography tracings.
Collapse
Affiliation(s)
- Imane Ben M'Barek
- Service de Gynécologie Obstétrique, Assistance Publique Hôpitaux de Paris - Hôpital Beaujon, 100 boulevard du Général Leclerc, Clichy La Garenne, France.
- Université Paris Cité, 75006, Paris, France.
- Health Simulation Department, iLumens, Université Paris Cité, Paris, France.
| | | | | | - Emilia Holmström
- Service de Gynécologie Obstétrique, Assistance Publique Hôpitaux de Paris - Hôpital Beaujon, 100 boulevard du Général Leclerc, Clichy La Garenne, France
- Université Paris Cité, 75006, Paris, France
| | - Antoine Agman
- Service de Gynécologie Obstétrique, Assistance Publique Hôpitaux de Paris - Hôpital Beaujon, 100 boulevard du Général Leclerc, Clichy La Garenne, France
| | - Jade Merrer
- AP-HP.Nord-Université Paris Cité, Hôpital Universitaire Robert Debré, Unité d'épidémiologie clinique, 1426, InsermParis, CIC, France
| | - Pierre-François Ceccaldi
- Service de Gynécologie-Obstétrique et Médecine de la reproduction, Hôpital Foch, 40 Rue Worth, 92150, Suresnes, France
| |
Collapse
|
3
|
Ekengård F, Cardell M, Herbst A. CTG interpretation templates affect residents' decision making. Eur J Obstet Gynecol Reprod Biol 2023; 285:148-152. [PMID: 37120910 DOI: 10.1016/j.ejogrb.2023.04.022] [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: 02/15/2023] [Revised: 04/14/2023] [Accepted: 04/24/2023] [Indexed: 05/02/2023]
Abstract
OBJECTIVE To study whether a revision of CTG guidelines and educational program influenced the perceived need for intervention by residents in obstetrics and gynecology. A secondary aim was to study the sensitivity and specificity of the classification pathological after classification by residents using two different guidelines in identifying neonates with acidemia. STUDY DESIGN Cardiotocograms, CTGs, from 223 neonates with acidemia at birth (cord blood pH < 7.05 at vaginal birth or second stage cesarean, or pH < 7.10 at first stage cesarean) were included, as well as 223 CTGs from neonates with cord blood pH ≥ 7.15. Two separate groups of residents, who each were educated in and had clinical experience only from either of the two different guidelines, SWE09 and SWE17, classified the patterns according to the at the time current template and judged whether the patterns indicated an intervention. Sensitivity, specificity, and agreement were calculated. RESULTS Residents using SWE09 found indication to intervene in a higher proportion of neonates with acidemia (84.8%) than residents using SWE17 (75.8%; p = 0.002), as well as in cases without acidemia (29.6% vs 22.4%; p = 0.038). Among residents using SWE09 the perceived need for intervention had a sensitivity of 85% and a specificity of 70% to identify acidemia. With SWE17 the corresponding rates were 76% and 78%. The sensitivity to identify neonates with acidemia by classification pathological was 91% with SWE09 and 72% with SWE17. The specificity was 53% and 76% respectively. The agreement rate between perception of indication to intervene and classification pathological using the SWE09 was κ 0.73, moderate, and with the SWE17 κ 0.77, moderate. The agreement on subjective perception of necessity to intervene between users of the two templates was weak to moderate, κ 0.60, and on classification pathological weak, κ 0.47. CONCLUSION The perceived need for intervention by residents interpreting CTGs was significantly affected by the guidelines in use. The difference in decisions were less pronounced than the difference in classification. The sensitivity for both perceived need for intervention and for classification pathological to identify acidosis was higher with SWE09, and the specificity higher with SWE17, when assessed by the two comparable groups of residents.
Collapse
Affiliation(s)
- Frida Ekengård
- Department of Obstetrics and Gynecology Skåne University Hospital, Institution of Clinical Sciences Lund, Lund University, Sweden; Study Conducted in Malmö and Lund, Sweden.
| | - Monika Cardell
- Department of Obstetrics and Gynecology Skåne University Hospital, Institution of Clinical Sciences Lund, Lund University, Sweden; Study Conducted in Malmö and Lund, Sweden
| | - Andreas Herbst
- Department of Obstetrics and Gynecology Skåne University Hospital, Institution of Clinical Sciences Lund, Lund University, Sweden; Study Conducted in Malmö and Lund, Sweden
| |
Collapse
|
4
|
Comparison of Four Intrapartum Cardiotocography Classifications for Predicting Neonatal Acidemia at Birth. J Pregnancy 2023; 2023:5853889. [PMID: 36814692 PMCID: PMC9940944 DOI: 10.1155/2023/5853889] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2022] [Revised: 01/25/2023] [Accepted: 01/27/2023] [Indexed: 02/17/2023] Open
Abstract
Objective To compare diagnostic values of four intrapartum cardiotocography (CTG) classifications in predicting neonatal acidemia at birth. Methods Retrospective case-control study. Forty-three CTG traces with an umbilical artery pH < 7.00 (study group) and 43 traces with a pH ≥ 7.00 (control group) were analyzed. Inclusion criteria were singleton pregnancy, cephalic presentation, admission to labour ward during active phase of first stage of labour, and gestational age 37+0 to 41+6 weeks. Exclusion criteria were suspected intrauterine growth restriction, oligohydramnios, polyhydramnios, pregestational or gestational insulin-dependent diabetes mellitus, and preeclampsia. Last 30-60 minutes before delivery of CTG traces was classified retrospectively according to four classification systems-International Federation of Gynecology and Obstetrics (FIGO), Royal College of Obstetricians and Gynaecologists (RCOG), National Institute of Child Health and Human Development (NICHD), and the 5-tier system by Parer and Ikeda. Predictive value of each classification for neonatal acidemia was assessed using receiver operating characteristics (ROC) analysis. Results FIGO, RCOG, and NICHD classifications predicted neonatal acidemia with areas under the ROC curves (AUC) of 0.73, 95% confidence interval (CI) 0.63-0.84; 0.72, 95% CI 0.60-0.83; and 0.69, 95% CI 0.57-0.80, respectively. The five-tier system by Parer and Ikeda had significantly better predictive value with an AUC of 0.96, 95% CI 0.91-1.00. Conclusions The 5-tier classification system proposed by Parer and Ikeda for assessing CTG in labour was superior to FIGO, RCOG, and NICHD intrapartum CTG classifications in predicting severe neonatal acidemia at birth.
Collapse
|
5
|
Steer PJ, Yau CWH, Blott M, Lattey K, Nwandison M, Uddin Z, Winter C, Draycott T. A case-control study of the interaction of fetal heart rate abnormalities, fetal growth restriction, meconium in the amniotic fluid and tachysystole, in relation to the outcome of labour. BJOG 2023; 130:286-291. [PMID: 36164836 DOI: 10.1111/1471-0528.17302] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2022] [Revised: 08/05/2022] [Accepted: 08/29/2022] [Indexed: 01/12/2023]
Abstract
OBJECTIVE To quantify the incidence of intrapartum risk factors in labours with an adverse outcome, and compare them with the incidence of the same indicators in a series of consecutive labours without adverse outcome. DESIGN Case-control study. SETTING Twenty-six maternity units in the UK. POPULATION OR SAMPLE Sixty-nine labours with an adverse outcome and 198 labours without adverse outcome. METHODS Observational study. MAIN OUTCOME MEASURES Incidence of risk factors in hourly assessments for 7 hours before birth in the two groups. RESULTS A risk score combining suspected fetal growth restriction, tachysystole, meconium in the amniotic fluid and fetal heart rate abnormalities (baseline rate and variability, presence of decelerations) gave the best indication of likely outcome group. CONCLUSIONS Accurate risk assessment in labour requires fetal heart rate abnormalities to be considered in context with additional intrapartum risk factors.
Collapse
Affiliation(s)
- Philip J Steer
- Academic Department of Obstetrics and Gynaecology, Chelsea and Westminster Hospital, London, UK
| | | | - Maggie Blott
- Department of Obstetrics and Gynaecology, Royal Free London NHS Trust, London, UK
| | | | - Millicent Nwandison
- Department of Obstetrics and Gynaecology, Chelsea and Westminster Hospital, London, UK
| | - Zeenath Uddin
- Department of Women's Health, North Wing St Thomas' Hospital, London, UK
| | - Cathy Winter
- Department of Women and Children's Health, North Bristol NHS Trust, Bristol, UK
| | - Timothy Draycott
- RCOG Vice President for Clinical Quality, Royal College of Obstetricians & Gynaecologists (RCOG), London, UK
| |
Collapse
|
6
|
Monari F, Chiossi G, Ballarini M, Menichini D, Gargano G, Coscia A, Baronciani D, Facchinetti F. Perinatal outcomes in twin late preterm pregnancies: results from an Italian area-based, prospective cohort study. Ital J Pediatr 2022; 48:101. [PMID: 35710441 PMCID: PMC9204959 DOI: 10.1186/s13052-022-01297-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/28/2022] [Accepted: 06/10/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Multiple gestations represent a considerable proportion of pregnancies delivering in the late preterm (LP) period. Only 30% of LP twins are due to spontaneous preterm labor and 70% are medically indicated; among this literature described that 16-50% of indicated LP twin deliveries are non-evidence based. As non-evidence-based delivery indications account for iatrogenic morbidity that could be prevented, the objective of our observational study is to investigate first neonatal outcomes of LP twin pregnancies according to gestational age at delivery, chorionicity and delivery indication, then non evidence-based delivery indications. METHODS Prospective cohort study among twins infants born between 34 + 0 and 36 + 6 weeks, in Emilia Romagna, Italy, during 2013-2015. The primary outcome was a composite of adverse perinatal outcomes. RESULTS Among 346 LP twins, 84 (23.4%) were monochorionic and 262 (75.7%) were dichorionic; spontaneous preterm labor accounted for 85 (24.6%) deliveries, preterm prelabor rupture of membranes for 66 (19.1%), evidence based indicated deliveries were 117 (33.8%), while non-evidence-based indications were 78 (22.5%). When compared to spontaneous preterm labor or preterm prelabor rupture of membranes, pregnancies delivered due to maternal and/or fetal indications were associated with higher maternal age (p < 0.01), higher gestational age at delivery (p < 0.01), Caucasian race (p 0.04), ART use (p < 0.01), gestational diabetes (p < 0.01), vaginal bleeding (p < 0.01), antenatal corticosteroids (p < 0.01), diagnosis of fetal growth restriction (FGR) (p < 0.01), and monochorionic (p < 0.01). Two hundred twenty-six pregnancies (65.3%) had at least one fetus experiencing one composite of adverse perinatal outcome. Multivariate analysis confirmed that delivery indication did not affect the composite of adverse perinatal outcomes; the only characteristic that affect the outcome after controlling for confounding was gestational age at delivery (p < 0.01). Moreover, there was at least one adverse neonatal outcome for 94% of babies born at 34 weeks, for 73% of those born at 35 weeks and for 46% of those born at 36 weeks (p < 0.01). CONCLUSION Our study suggests that the decision to deliver or not twins in LP period should consider gestational age at delivery as the main determinant infants' prognosis. Delivery indications should be accurately considered, to avoid iatrogenic early birth responsible of preventable complications.
Collapse
Affiliation(s)
- Francesca Monari
- Obstetrics and Gynecology Unit, Mother-Infant and Adult Department of Medical and Surgical Sciences, University of Modena and Reggio Emilia, Policlinico di Modena, Via del Pozzo 71, 41125, Modena, Italy.
| | - Giuseppe Chiossi
- Obstetrics and Gynecology Unit, Mother-Infant and Adult Department of Medical and Surgical Sciences, University of Modena and Reggio Emilia, Policlinico di Modena, Via del Pozzo 71, 41125, Modena, Italy
| | - Michela Ballarini
- Obstetrics and Gynecology Unit, Mother-Infant and Adult Department of Medical and Surgical Sciences, University of Modena and Reggio Emilia, Policlinico di Modena, Via del Pozzo 71, 41125, Modena, Italy
| | - Daniela Menichini
- Department of Biomedical, Metabolic and Neural Sciences, International Doctorate School in Clinical and Experimental Medicine, University of Modena and Reggio Emilia, 41125, Modena, Italy
| | - Giancarlo Gargano
- Department of Obstetrics and Pediatrics, Neonatal Intensive Care Unit, Arcispedale Santa Maria Nuova, IRCCS, Reggio Emilia, 42123, Reggio Emilia, Italy
| | - Alessandra Coscia
- Department of Public Health and Pediatrics, Neonatology Unit, Università degli Studi di Torino, 10126, Turin, Italy
| | - Dante Baronciani
- Health Facilities, Technologies and Information Systems Unit, Emilia-Romagna Region, Viale Aldo Moro 21, 40127, Bologna, Italy
| | - Fabio Facchinetti
- Obstetrics and Gynecology Unit, Mother-Infant and Adult Department of Medical and Surgical Sciences, University of Modena and Reggio Emilia, Policlinico di Modena, Via del Pozzo 71, 41125, Modena, Italy
| | | |
Collapse
|
7
|
di Pasquo E, Commare A, Masturzo B, Paolucci S, Cromi A, Montersino B, Germano CM, Attini R, Perrone S, Pisani F, Dall'Asta A, Fieni S, Frusca T, Ghi T. Short-term morbidity and types of intrapartum hypoxia in the newborn with metabolic acidaemia: a retrospective cohort study. BJOG 2022; 129:1916-1925. [PMID: 35244312 PMCID: PMC9541157 DOI: 10.1111/1471-0528.17133] [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: 11/03/2021] [Revised: 02/13/2022] [Accepted: 02/26/2022] [Indexed: 11/30/2022]
Abstract
Objectives To assess labour characteristics in relation to the occurrence of Composite Adverse neonatal Outcome (CAO) within a cohort of fetuses with metabolic acidaemia. Design Retrospective cohort study. Setting Three Italian tertiary maternity units. Population 431 neonates born with acidaemia ≥36 weeks. Methods Intrapartum CTG traces were assigned to one of these four types of labour hypoxia: acute, subacute, gradually evolving and chronic hypoxia. The presence of CAO was defined by the occurrence of at least one of the following: Sarnat Score grade ≥2, seizures, hypothermia and death <7 days from birth. Main outcome measures To compare the type of hypoxia on the intrapartum CTG traces among the acidaemic neonates with and without CAO. Results The occurrence of a CAO was recorded in 15.1% of neonates. At logistic regression analysis, the duration of the hypoxia was the only parameter associated with CAO in the case of an acute or subacute pattern (odds ratio [OR] 1.3; 95% CI 1.02–1.6 and OR 1.04; 95% CI 1.0–1.1, respectively), whereas both the duration of the hypoxic insult and the time from PROM to delivery were associated with CAO in those with a gradually evolving pattern (OR 1.13; 95% CI 1.01–1.3 and OR 1.04; 95% CI 1.0–1.7, respectively). The incidence of CAO was higher in fetuses with chronic antepartum hypoxia than in those showing CTG features of intrapartum hypoxia (64.7 vs. 13.0%; P < 0.001). Conclusions The frequency of CAO seems related to the duration and the type of the hypoxic injury, being higher in fetuses showing CTG features of antepartum chronic hypoxia. Tweetable abstract This study demonstrates that in a large population of neonates with metabolic acidaemia at birth, the overall incidence of short‐term adverse outcome is around 15%. Such risk seems closely correlated to the duration and the type of hypoxic injury, being higher in fetuses admitted in labour with antepartum chronic hypoxia than those experiencing intrapartum hypoxia. This study demonstrates that in a large population of neonates with metabolic acidaemia at birth, the overall incidence of short‐term adverse outcome is around 15%. Such risk seems closely correlated to the duration and the type of hypoxic injury, being higher in fetuses admitted in labour with antepartum chronic hypoxia than those experiencing intrapartum hypoxia.
Collapse
Affiliation(s)
- Elvira di Pasquo
- Unit of Surgical Sciences, Obstetrics and Gynaecology Unit, Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Arianna Commare
- Unit of Surgical Sciences, Obstetrics and Gynaecology Unit, Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Bianca Masturzo
- Division of Obstetrics and Gynaecology, Department of Maternal-Neonatal and Infant Health, Ospedale degli Infermi, University of Turin, Biella, Italy
| | - Sonia Paolucci
- Department of Medicine and Surgery, University of Insubria, Varese, Italy
| | - Antonella Cromi
- Department of Medicine and Surgery, University of Insubria, Varese, Italy
| | - Benedetta Montersino
- Department of Obstetrics and Gynaecology, Città della Salute e della Scienza, Sant'Anna Hospital, Turin, Italy
| | - Chiara M Germano
- Department of Obstetrics and Gynaecology, Città della Salute e della Scienza, Sant'Anna Hospital, Turin, Italy
| | - Rossella Attini
- Department of Obstetrics and Gynaecology, Città della Salute e della Scienza, Sant'Anna Hospital, Turin, Italy
| | | | - Francesco Pisani
- Child Neuropsychiatry Unit, Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Andrea Dall'Asta
- Unit of Surgical Sciences, Obstetrics and Gynaecology Unit, Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Stefania Fieni
- Unit of Surgical Sciences, Obstetrics and Gynaecology Unit, Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Tiziana Frusca
- Unit of Surgical Sciences, Obstetrics and Gynaecology Unit, Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Tullio Ghi
- Unit of Surgical Sciences, Obstetrics and Gynaecology Unit, Department of Medicine and Surgery, University of Parma, Parma, Italy
| |
Collapse
|
8
|
Esteban-Escaño J, Castán B, Castán S, Chóliz-Ezquerro M, Asensio C, Laliena AR, Sanz-Enguita G, Sanz G, Esteban LM, Savirón R. Machine Learning Algorithm to Predict Acidemia Using Electronic Fetal Monitoring Recording Parameters. ENTROPY 2021; 24:e24010068. [PMID: 35052094 PMCID: PMC8775221 DOI: 10.3390/e24010068] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 11/18/2021] [Revised: 12/18/2021] [Accepted: 12/27/2021] [Indexed: 12/17/2022]
Abstract
Background: Electronic fetal monitoring (EFM) is the universal method for the surveillance of fetal well-being in intrapartum. Our objective was to predict acidemia from fetal heart signal features using machine learning algorithms. Methods: A case–control 1:2 study was carried out compromising 378 infants, born in the Miguel Servet University Hospital, Spain. Neonatal acidemia was defined as pH < 7.10. Using EFM recording logistic regression, random forest and neural networks models were built to predict acidemia. Validation of models was performed by means of discrimination, calibration, and clinical utility. Results: Best performance was attained using a random forest model built with 100 trees. The discrimination ability was good, with an area under the Receiver Operating Characteristic curve (AUC) of 0.865. The calibration showed a slight overestimation of acidemia occurrence for probabilities above 0.4. The clinical utility showed that for 33% cutoff point, missing 5% of acidotic cases, 46% of unnecessary cesarean sections could be prevented. Logistic regression and neural networks showed similar discrimination ability but with worse calibration and clinical utility. Conclusions: The combination of the variables extracted from EFM recording provided a predictive model of acidemia that showed good accuracy and provides a practical tool to prevent unnecessary cesarean sections.
Collapse
Affiliation(s)
- Javier Esteban-Escaño
- Department of Electronic Engineering and Communications, Escuela Universitaria Politécnica de La Almunia, Universidad de Zaragoza, Calle Mayor 5, 50100 La Almunia de Doña Godina, Spain;
| | - Berta Castán
- Department of Obstetrics and Gynecology, San Pedro Hospital, Calle Piqueras 98, 26006 Logroño, Spain;
| | - Sergio Castán
- Department of Obstetrics and Gynecology, Miguel Servet University Hospital, Paseo Isabel La Católica 3, 50009 Zaragoza, Spain
- Correspondence: (S.C.); (L.M.E.)
| | - Marta Chóliz-Ezquerro
- Department of Obstetrics, Dexeus University Hospital, Gran Via de Carles III 71-75, 08028 Barcelona, Spain;
| | - César Asensio
- Department of Applied Mathematics, Escuela Universitaria Politécnica de La Almunia, Universidad de Zaragoza, Calle Mayor 5, 50100 La Almunia de Doña Godina, Spain; (C.A.); (A.R.L.)
| | - Antonio R. Laliena
- Department of Applied Mathematics, Escuela Universitaria Politécnica de La Almunia, Universidad de Zaragoza, Calle Mayor 5, 50100 La Almunia de Doña Godina, Spain; (C.A.); (A.R.L.)
| | - Gerardo Sanz-Enguita
- Department of Applied Physics, Escuela Universitaria Politécnica de La Almunia, Universidad de Zaragoza, Calle Mayor 5, 50100 La Almunia de Doña Godina, Spain;
| | - Gerardo Sanz
- Department of Statistical Methods and Institute for Biocomputation and Physics of Complex Systems-BIFI, University of Zaragoza, Calle Pedro Cerbuna 12, 50009 Zaragoza, Spain;
| | - Luis Mariano Esteban
- Department of Applied Mathematics, Escuela Universitaria Politécnica de La Almunia, Universidad de Zaragoza, Calle Mayor 5, 50100 La Almunia de Doña Godina, Spain; (C.A.); (A.R.L.)
- Correspondence: (S.C.); (L.M.E.)
| | - Ricardo Savirón
- Department of Obstetrics and Gynecology, Hospital Clínico San Carlos and Instituto de Investigación Sanitaria San Carlos (IdISSC), Universidad Complutense, Calle del Prof Martín Lagos s/n, 28040 Madrid, Spain;
| |
Collapse
|