Prediction model for obstetric anal sphincter injury using machine learning

Factors Associated with Obstetric Anal Sphincter Injury During Vacuum-Assisted Vaginal Delivery

INTRODUCTION AND HYPOTHESIS

Obstetric anal sphincter injury (OASI) is a major complication associated with vacuum-assisted vaginal delivery (VAVD). The aim of this study was to evaluate risk factors related to vacuum extraction that are associated with OASI.

METHODS

This was a case-control study performed at a tertiary university teaching hospital. Included were patients aged 18-45 years who had a singleton pregnancy resulting in a live, term, VAVD. The study group consisted of women diagnosed with OASI following vacuum extraction. The control group included women following VAVD without OASI. Matching at a ratio of 1:2 was performed. Groups were compared regarding demographic, obstetric. and labor-related parameters, specifically focusing on variables related to the vacuum procedure itself.

RESULTS

One hundred and ten patients within the study group and 212 within the control group were included in the final analysis. Patients in the OASI group were more likely to undergo induction of labor, use of oxytocin during labor, increased second stage of labor, higher likelihood of the operator being a resident, increased number of pulls, procedure lasting under 10 min, occipito-posterior head position at vacuum initiation, episiotomy, increased neonatal head circumference, and birthweight. Multivariate logistic regression analysis revealed that increased week of gestation (OR 1.67, 95% CI 1.25-2.22, p < 0.001), unsupervised resident performing the procedure (OR 4.63, 95% CI 2.17-9.90), p < 0.001), indication of VAVD being fetal distress (OR 2.72, 95% CI 1.04-7.10, p = 0.041), and length of procedure under 10 min (OR 4.75, 95% CI 1.53-14.68, p = 0.007) were associated with OASI. Increased maternal age was associated with lower risk of OASI (OR 0.9, 95% CI 0.84-0.98, p = 0.012).

CONCLUSIONS

When performing VAVD, increased week of gestation, unsupervised resident performing the procedure, fetal distress as vacuum indication, and vacuum procedure under 10 min were associated with OASI. In contrast, increased maternal age was shown to be a protective factor.

The prevention of perineal trauma during vaginal birth

Perineal trauma after vaginal birth is common, with approximately 9 of 10 women being affected. Second-degree perineal tears are twice as likely to occur in primiparous births, with a incidence of 40%. The incidence of obstetrical anal sphincter injury is approximately 3%, with a significantly higher rate in primiparous than in multiparous women (6% vs 2%). Obstetrical anal sphincter injury is a significant risk factor for the development of anal incontinence, with approximately 10% of women developing symptoms within a year following vaginal birth. Obstetrical anal sphincter injuries have significant medicolegal implications and contribute greatly to healthcare costs. For example, in 2013 and 2014, the economic burden of obstetrical anal sphincter injuries in the United Kingdom ranged between £3.7 million (with assisted vaginal birth) and £9.8 million (with spontaneous vaginal birth). In the United States, complications associated with trauma to the perineum incurred costs of approximately $83 million between 2007 and 2011. It is therefore crucial to focus on improvements in clinical care to reduce this risk and minimize the development of perineal trauma, particularly obstetrical anal sphincter injuries. Identification of risk factors allows modification of obstetrical practice with the aim of reducing the rate of perineal trauma and its attendant associated morbidity. Risk factors associated with second-degree perineal trauma include increased fetal birthweight, operative vaginal birth, prolonged second stage of labor, maternal birth position, and advanced maternal age. With obstetrical anal sphincter injury, risk factors include induction of labor, augmentation of labor, epidural, increased fetal birthweight, fetal malposition (occiput posterior), midline episiotomy, operative vaginal birth, Asian ethnicity, and primiparity. Obstetrical practice can be modified both antenatally and intrapartum. The evidence suggests that in the antenatal period, perineal massage can be commenced in the third trimester of pregnancy to increase muscle elasticity and allow stretching of the perineum during birth, thereby reducing the risk of tearing or need for episiotomy. With regard to the intrapartum period, there is a growing body of evidence from the United Kingdom, Norway, and Denmark suggesting that the implementation of quality improvement initiatives including the training of clinicians in manual perineal protection and mediolateral episiotomy can reduce the incidence of obstetrical anal sphincter injury. With episiotomy, the International Federation of Gynecology and Obstetrics recommends restrictive rather than routine use of episiotomy. This is particularly the case with unassisted vaginal births. However, there is a role for episiotomy, specifically mediolateral or lateral, with assisted vaginal births. This is specifically the case with nulliparous vacuum and forceps births, given that the use of mediolateral or lateral episiotomy has been shown to significantly reduce the incidence of obstetrical anal sphincter injury in these groups by 43% and 68%, respectively. However, the complications associated with episiotomy including perineal pain, dyspareunia, and sexual dysfunction should be acknowledged. Despite considerable research, interventions for reducing the risk of perineal trauma remain a subject of controversy. In this review article, we present the available data on the prevention of perineal trauma by describing the risk factors associated with perineal trauma and interventions that can be implemented to prevent perineal trauma, in particular obstetrical anal sphincter injury.

Prediction models for perineal lacerations during childbirth: A systematic review and critical appraisal

BACKGROUND

Perineal lacerations could lead to substantial morbidities for women. A reliable prediction model for perineal lacerations has the potential to guide the prevention. Although several prediction models have been developed to estimate the risk of perineal lacerations, especially third- and fourth-degree perineal lacerations, the evidence about the model quality and clinical applicability is scarce.

OBJECTIVES

To systematically review and critically appraise the existing prediction models for perineal lacerations.

METHODS

Seven databases (PubMed, Embase, The Cochrane Library, Cumulative Index to Nursing and Allied Health Literature, SinoMed, China National Knowledge Infrastructure, and Wanfang Data) were systematically searched from inception to July 2022. Studies that developed prediction models for perineal lacerations or performed external validation of existing models were considered eligible to include in the systematic review. Two reviewers independently conducted data extraction according to the Checklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies. The risk of bias and the applicability of the included models were assessed with the Prediction Model Risk of Bias Assessment Tool. A narrative synthesis was performed to summarize the characteristics, risk of bias, and performance of existing models.

RESULTS

Of 4345 retrieved studies, 14 studies with 22 prediction models for perineal lacerations were included. The included models mainly aimed to estimate the risk of third- and fourth-degree perineal lacerations. The top five predictors used were operative vaginal birth (72.7 %), parity/previous vaginal birth (63.6 %), race/ethnicity (59.1 %), maternal age (50.0 %), and episiotomy (40.1 %). Internal and external validation was performed in 12 (54.5 %) and seven (31.8 %) models, respectively. 13 studies (92.9 %) assessed model discrimination, with the c-index ranging from 0.636 to 0.830. Seven studies (50.0 %) evaluated the model calibration using the Hosmer-Lemeshow test, Brier score, or calibration curve. The results indicated that most of the models had fairly good calibration. All the included models were at higher risk of bias mainly due to unclear or inappropriate methods for handling missing data and continuous predictors, external validation, and model performance evaluation. Six models (27.3 %) showed low concerns about applicability.

CONCLUSIONS

The existing models for perineal lacerations were poorly validated and evaluated, among which only two have the potential for clinical use: one for women undergoing vaginal birth after cesarean delivery, and the other one for all women undergoing vaginal birth. Future studies should focus on robust external validation of existing models and the development of novel models for second-degree perineal laceration.

PROSPERO REGISTRATION NUMBER

CRD42022349786.

TWEETABLE ABSTRACT

The existing models for perineal lacerations during childbirth need external validation and updating. Tools are needed for second-degree perineal laceration.

Machine learning and disease prediction in obstetrics

Machine learning technologies and translation of artificial intelligence tools to enhance the patient experience are changing obstetric and maternity care. An increasing number of predictive tools have been developed with data sourced from electronic health records, diagnostic imaging and digital devices. In this review, we explore the latest tools of machine learning, the algorithms to establish prediction models and the challenges to assess fetal well-being, predict and diagnose obstetric diseases such as gestational diabetes, pre-eclampsia, preterm birth and fetal growth restriction. We discuss the rapid growth of machine learning approaches and intelligent tools for automated diagnostic imaging of fetal anomalies and to asses fetoplacental and cervix function using ultrasound and magnetic resonance imaging. In prenatal diagnosis, we discuss intelligent tools for magnetic resonance imaging sequencing of the fetus, placenta and cervix to reduce the risk of preterm birth. Finally, the use of machine learning to improve safety standards in intrapartum care and early detection of complications will be discussed. The demand for technologies to enhance diagnosis and treatment in obstetrics and maternity should improve frameworks for patient safety and enhance clinical practice.

Birthweight difference between deliveries and the risk of obstetric anal sphincter injury in parous women

INTRODUCTION AND HYPOTHESIS

While obstetric anal sphincter injury (OASI) is less frequent in parous compared to nulliparous women, it remains a major concern affecting quality of life of women worldwide. The aim of this study was to evaluate the association between birthweight (BW) difference between deliveries and risk of OASI in parous women.

METHODS

We performed a retrospective case-control study including parous women with at least one previous vaginal delivery who were diagnosed with OASI. The control group consisted of parous women who did not have OASI during vaginal delivery. Controls were matched in a 1:2 ratio by year of birth, maternal age, and parity. Medical history, obstetric background, and current labor-related data were compared. Further univariate and multivariable analyses were performed, assessing for risk factors for OASI.

RESULTS

One hundred eight parous women who had a diagnosis of OASI and a control group of 216 parturients who delivered without OASI were included in the final analysis. Differences between the current BW and the preceding and maximal previous BW were evaluated. There were significantly higher rates of women who had a larger neonate with > 500 g difference between the current and previous BW in the OASI group than in those with no OASI (28.7% vs. 12.30%, respectively; p < 0.001). Following a multivariable analysis for the dependent parameter of OASI, the following parameters were found to be independently associated with OASI outcome: previous operative vaginal delivery, BW ≥ 90th percentile, and current BW ≥ 500 g compared to previous maximal BW.

CONCLUSIONS

In parous women, neonatal BW increase between deliveries of > 500 g is associated with OASI.

Risk factors for obstetric anal sphincter injury recurrence: A systematic review and meta-analysis

BACKGROUND

Women with previous obstetric anal sphincter injuries (OASIs) are at a higher risk of recurrence in the subsequent pregnancy, which may lead to the development or worsening of anal incontinence. Due to a lack of evidence, few recommendations can be made about the factors that may affect the risk of OASI recurrence.

OBJECTIVE

We sought to conduct a systematic review and meta-analysis to investigate potential risk factors for recurrent OASIs.

SEARCH STRATEGY

Studies up to May 2019 were identified from PubMed, Scopus, Cochrane Library, and ISI Web of Science.

SELECTION CRITERIA

Studies assessing the impact of risk factors on OASI recurrence in subsequent pregnancies were included. Reviews, letters to the editor, conference abstracts, book chapters, guidelines, Cochrane reviews, and expert opinions were excluded.

DATA COLLECTION AND ANALYSIS

Data were extracted by two independent reviewers. Odds ratio and standardized mean difference were chosen as effect measures. Pooled estimates were calculated using the random-effects model.

MAIN RESULTS

The meta-analysis showed that maternal age, gestational age, occiput posterior presentation, oxytocin augmentation, operative delivery, and shoulder dystocia were associated with the risk of recurrent OASIs in the subsequent delivery.

CONCLUSION

Prenatal and intrapartum risk factors are associated with recurrence of OASI. PROSPERO registration no. CRD42020178125.

Introduction to Machine Learning in Obstetrics and Gynecology

In the digital age of the 21st century, we have witnessed an explosion in data matched by remarkable progress in the field of computer science and engineering, with the development of powerful and portable artificial intelligence-powered technologies. At the same time, global connectivity powered by mobile technology has led to an increasing number of connected users and connected devices. In just the past 5 years, the convergence of these technologies in obstetrics and gynecology has resulted in the development of innovative artificial intelligence-powered digital health devices that allow easy and accurate patient risk stratification for an array of conditions spanning early pregnancy, labor and delivery, and care of the newborn. Yet, breakthroughs in artificial intelligence and other new and emerging technologies currently have a slow adoption rate in medicine, despite the availability of large data sets that include individual electronic health records spanning years of care, genomics, and the microbiome. As a result, patient interactions with health care remain burdened by antiquated processes that are inefficient and inconvenient. A few health care institutions have recognized these gaps and, with an influx of venture capital investments, are now making in-roads in medical practice with digital products driven by artificial intelligence algorithms. In this article, we trace the history, applications, and ethical challenges of the artificial intelligence that will be at the forefront of digitally transforming obstetrics and gynecology and medical practice in general.

Obstetric anal sphincter injury following previous vaginal delivery

INTRODUCTION AND HYPOTHESIS

Obstetric anal sphincter injury (OASI) is a debilitating complication of vaginal delivery. The aim of this study was to identify risk factors for OASI in women with a previous vaginal delivery. We further attempted to detect specific risk factors for severe OASI in this subgroup.

METHODS

We conducted a retrospective cohort study between 2003 and 2019. The study group included women who had a singleton, live, vertex, vaginal delivery at term and who also had at least one previous vaginal delivery. The control group included women with at least one previous vaginal delivery without OASI. General medical history, obstetric history, and ante-, intra- and post-partum data were collected and compared between groups.

RESULTS

Following implementation of the inclusion criteria, 79,176 women were included. Allocation to study groups was according to OASI occurrence: 135 patients (0.2%) had a third- or fourth-degree perineal tear, while 79,041 patients (99.8%) had no such injury. Multivariate analysis revealed that one previous vaginal delivery, birthweight ≥ 3900 g (90th percentile), vacuum-assisted vaginal delivery and episiotomy were associated with increased risk of OASI. Comparison of more severe OASI (3C and 4th-degree) cases to the control group showed similar results with the addition of prolonged second stage and younger age to risk factors associated with severe OASI while episiotomy was no longer significant.

CONCLUSION

In women with a previous vaginal delivery, one vs. two or more previous vaginal deliveries, increased birthweight, vacuum-assisted vaginal delivery and episiotomy are risk factors for OASI.