-
Journal of Medical Internet Research Apr 2022The applications of artificial intelligence (AI) processes have grown significantly in all medical disciplines during the last decades. Two main types of AI have been... (Review)
Review
BACKGROUND
The applications of artificial intelligence (AI) processes have grown significantly in all medical disciplines during the last decades. Two main types of AI have been applied in medicine: symbolic AI (eg, knowledge base and ontologies) and nonsymbolic AI (eg, machine learning and artificial neural networks). Consequently, AI has also been applied across most obstetrics and gynecology (OB/GYN) domains, including general obstetrics, gynecology surgery, fetal ultrasound, and assisted reproductive medicine, among others.
OBJECTIVE
The aim of this study was to provide a systematic review to establish the actual contributions of AI reported in OB/GYN discipline journals.
METHODS
The PubMed database was searched for citations indexed with "artificial intelligence" and at least one of the following medical subject heading (MeSH) terms between January 1, 2000, and April 30, 2020: "obstetrics"; "gynecology"; "reproductive techniques, assisted"; or "pregnancy." All publications in OB/GYN core disciplines journals were considered. The selection of journals was based on disciplines defined in Web of Science. The publications were excluded if no AI process was used in the study. Review, editorial, and commentary articles were also excluded. The study analysis comprised (1) classification of publications into OB/GYN domains, (2) description of AI methods, (3) description of AI algorithms, (4) description of data sets, (5) description of AI contributions, and (6) description of the validation of the AI process.
RESULTS
The PubMed search retrieved 579 citations and 66 publications met the selection criteria. All OB/GYN subdomains were covered: obstetrics (41%, 27/66), gynecology (3%, 2/66), assisted reproductive medicine (33%, 22/66), early pregnancy (2%, 1/66), and fetal medicine (21%, 14/66). Both machine learning methods (39/66) and knowledge base methods (25/66) were represented. Machine learning used imaging, numerical, and clinical data sets. Knowledge base methods used mostly omics data sets. The actual contributions of AI were method/algorithm development (53%, 35/66), hypothesis generation (42%, 28/66), or software development (3%, 2/66). Validation was performed on one data set (86%, 57/66) and no external validation was reported. We observed a general rising trend in publications related to AI in OB/GYN over the last two decades. Most of these publications (82%, 54/66) remain out of the scope of the usual OB/GYN journals.
CONCLUSIONS
In OB/GYN discipline journals, mostly preliminary work (eg, proof-of-concept algorithm or method) in AI applied to this discipline is reported and clinical validation remains an unmet prerequisite. Improvement driven by new AI research guidelines is expected. However, these guidelines are covering only a part of AI approaches (nonsymbolic) reported in this review; hence, updates need to be considered.
Topics: Artificial Intelligence; Female; Gynecology; Humans; Obstetrics; Periodicals as Topic; Pregnancy
PubMed: 35297766
DOI: 10.2196/35465 -
American Journal of Obstetrics and... Aug 2022To update a previously published systematic review and perform a meta-analysis on the risk factors for primary pelvic organ prolapse and prolapse recurrence. (Meta-Analysis)
Meta-Analysis Review
OBJECTIVE
To update a previously published systematic review and perform a meta-analysis on the risk factors for primary pelvic organ prolapse and prolapse recurrence.
DATA SOURCES
PubMed and Embase were systematically searched. We searched from July 1, 2014 until July 5, 2021. The previous search was from inception until August 4, 2014.
STUDY ELIGIBILITY CRITERIA
Randomized controlled trials and cross-sectional and cohort studies conducted in the Western developed countries that reported on multivariable analysis of risk factors for primary prolapse or prolapse recurrence were included. The definition of prolapse was based on anatomic references, and prolapse recurrence was defined as anatomic recurrence after native tissue repair. Studies on prolapse recurrence with a median follow-up of ≥1 year after surgery were included.
METHODS
Quality assessment was performed with the Newcastle-Ottawa Scale. Data from the previous review and this review were combined into forest plots, and meta-analyses were performed where possible. If the data could not be pooled, "confirmed risk factors" were identified if ≥2 studies reported a significant association in multivariable analysis.
RESULTS
After screening, 14 additional studies were selected-8 on the risk factors for primary prolapse and 6 on prolapse recurrence. Combined with the results from the previous review, 27 studies met the inclusion criteria, representing the data of 47,429 women. Not all studies could be pooled because of heterogeneity. Meta-analyses showed that birthweight (n=3, odds ratio, 1.04; 95% confidence interval, 1.02-1.06), age (n=3, odds ratio, 1.34; 95% confidence interval, 1.23-1.47), body mass index (n=2, odds ratio, 1.75; 95% confidence interval, 1.17-2.62), and levator defect (n=2, odds ratio, 3.99; 95% confidence interval, 2.57-6.18) are statistically significant risk factors, and cesarean delivery (n=2, pooled odds ratio, 0.08; 95% confidence interval, 0.03-0.20) and smoking (n=3, odds ratio, 0.59; 95% confidence interval, 0.46-0.75) are protective factors for primary prolapse. Parity, vaginal delivery, and levator hiatal area are identified as "confirmed risk factors." For prolapse recurrence, preoperative prolapse stage (n=5, odds ratio, 2.68; 95% confidence interval, 1.93-3.73) and age (n=2, odds ratio, 3.48; 95% confidence interval, 1.99-6.08) are statistically significant risk factors.
CONCLUSION
Vaginal delivery, parity, birthweight, age, body mass index, levator defect, and levator hiatal area are risk factors, and cesarean delivery and smoking are protective factors for primary prolapse. Preoperative prolapse stage and younger age are risk factors for prolapse recurrence after native tissue surgery.
Topics: Birth Weight; Cross-Sectional Studies; Delivery, Obstetric; Female; Humans; Pelvic Organ Prolapse; Pregnancy; Risk Factors
PubMed: 35500611
DOI: 10.1016/j.ajog.2022.04.046 -
International Urogynecology Journal Sep 2020Most vaginal births are associated with trauma to the perineum. The morbidity associated with perineal trauma can be significant, especially when it leads to third- and... (Meta-Analysis)
Meta-Analysis Review
INTRODUCTION AND HYPOTHESIS
Most vaginal births are associated with trauma to the perineum. The morbidity associated with perineal trauma can be significant, especially when it leads to third- and fourth-degree perineal tears. We hypothesized that antenatal perineal massage could decrease the incidence of perineal trauma, particularly severe perineal tears and other postpartum complications.
METHODS
We searched four different databases from inception until August 2019 for the available trials. We included randomized controlled trials (RCTs) which assessed the effect of antenatal perineal massage (intervention group) versus control group (no antenatal perineal massage) in perineal trauma patients. Data were extracted from eligible studies and meta-analyzed using RevMan software. Primary outcomes were the risk of episiotomies and perineal tears. Secondary outcomes were perineal pain, second stage of labor duration, wound healing, anal incontinence, and Apgar scores at 1 and 5 min.
RESULTS
Eleven RCTs with 3467 patients were analyzed. Women who received antenatal perineal massage had significantly lower incidence of episiotomies (RR = 0.79, 95% CI [0.72, 0.87], p < 0.001) and perineal tears (RR = 0.79, 95% CI [0.67, 0.94], p = 0.007), particularly the risk of third- and fourth-degree perineal tears (p = 0.03). Better wound healing and less perineal pain were evident in the antenatal perineal massage group. Antenatal perineal massage reduced the second stage of labor duration (p = 0.005) and anal incontinence (p = 0.003) with significant improvement in Apgar scores at 1 and 5 min (p = 0.01 and p = 0.02).
CONCLUSIONS
Antenatal perineal massage is associated with a lower risk of severe perineal trauma and postpartum complications.
Topics: Delivery, Obstetric; Episiotomy; Female; Humans; Massage; Morbidity; Obstetric Labor Complications; Perineum; Postpartum Period; Pregnancy; Randomized Controlled Trials as Topic
PubMed: 32399905
DOI: 10.1007/s00192-020-04302-8 -
Journal of Thrombosis and Haemostasis :... Aug 2020Thromboelastography (TEG) and rotational thromboelastometry (ROTEM) are point-of-care viscoelastic devices that use whole blood samples to assess coagulation and... (Review)
Review
Thromboelastography (TEG) and rotational thromboelastometry (ROTEM) are point-of-care viscoelastic devices that use whole blood samples to assess coagulation and fibrinolysis. These devices have been studied extensively in cardiac surgery, but there is limited robust evidence supporting its use in obstetrics. The hesitancy toward its routine use in obstetrics may be due to the current lack of randomized controlled trials and large observational studies. The study aims to systematically review studies that investigated TEG/ROTEM use in pregnancy or peripartum, and to provide recommendations for future studies to fill current research gaps. We performed a systematic review of studies on viscoelastic testing in obstetrics. Included studies were original research, used TEG or ROTEM during pregnancy or peripartum, and published in English. Ninety-three studies, spanning 31 years from 1989 to 2020 and with a total of 32,817 participants, were included. Sixty-two (66.7%) of the studies used TEG and 31 (33.3%) used ROTEM. To date, there are a total of two randomized controlled trials on TEG/ROTEM use in obstetrics. ROTEM may be used to guide transfusion therapy for postpartum hemorrhage. TEG and ROTEM can detect the hypercoagulable changes associated with pregnancy. Variability between study protocols and results suggests the need for future large prospective high-quality studies with standardized protocols to investigate the utility of TEG/ROTEM in assessing risk for thrombosis and hemorrhage as well as in guiding prophylaxis and treatment in obstetric patients. This review identifies the gaps and provides concrete recommendations for future studies to fill those gaps.
Topics: Blood Coagulation Disorders; Blood Transfusion; Female; Humans; Obstetrics; Pregnancy; Prospective Studies; Thrombelastography
PubMed: 32356929
DOI: 10.1111/jth.14882 -
Acta Obstetricia Et Gynecologica... Apr 2018A randomized controlled trial is a prospective, comparative, quantitative study/experiment performed under controlled conditions with random allocation of interventions... (Review)
Review
A randomized controlled trial is a prospective, comparative, quantitative study/experiment performed under controlled conditions with random allocation of interventions to comparison groups. The randomized controlled trial is the most rigorous and robust research method of determining whether a cause-effect relation exists between an intervention and an outcome. High-quality evidence can be generated by performing an randomized controlled trial when evaluating the effectiveness and safety of an intervention. Furthermore, randomized controlled trials yield themselves well to systematic review and meta-analysis providing a solid base for synthesizing evidence generated by such studies. Evidence-based clinical practice improves patient outcomes and safety, and is generally cost-effective. Therefore, randomized controlled trials are becoming increasingly popular in all areas of clinical medicine including perinatology. However, designing and conducting an randomized controlled trial, analyzing data, interpreting findings and disseminating results can be challenging as there are several practicalities to be considered. In this review, we provide simple descriptive guidance on planning, conducting, analyzing and reporting randomized controlled trials.
Topics: Gynecology; Humans; Obstetrics; Randomized Controlled Trials as Topic; Research Design
PubMed: 29377058
DOI: 10.1111/aogs.13309 -
American Journal of Obstetrics and... May 2023Green-stained amniotic fluid, often referred to as meconium-stained amniotic fluid, is present in 5% to 20% of patients in labor and is considered an obstetric hazard.... (Review)
Review
Green-stained amniotic fluid, often referred to as meconium-stained amniotic fluid, is present in 5% to 20% of patients in labor and is considered an obstetric hazard. The condition has been attributed to the passage of fetal colonic content (meconium), intraamniotic bleeding with the presence of heme catabolic products, or both. The frequency of green-stained amniotic fluid increases as a function of gestational age, reaching approximately 27% in post-term gestation. Green-stained amniotic fluid during labor has been associated with fetal acidemia (umbilical artery pH <7.00), neonatal respiratory distress, and seizures as well as cerebral palsy. Hypoxia is widely considered a mechanism responsible for fetal defecation and meconium-stained amniotic fluid; however, most fetuses with meconium-stained amniotic fluid do not have fetal acidemia. Intraamniotic infection/inflammation has emerged as an important factor in meconium-stained amniotic fluid in term and preterm gestations, as patients with these conditions have a higher rate of clinical chorioamnionitis and neonatal sepsis. The precise mechanisms linking intraamniotic inflammation to green-stained amniotic fluid have not been determined, but the effects of oxidative stress in heme catabolism have been implicated. Two randomized clinical trials suggest that antibiotic administration decreases the rate of clinical chorioamnionitis in patients with meconium-stained amniotic fluid. A serious complication of meconium-stained amniotic fluid is meconium aspiration syndrome. This condition develops in 5% of cases presenting with meconium-stained amniotic fluid and is a severe complication typical of term newborns. Meconium aspiration syndrome is attributed to the mechanical and chemical effects of aspirated meconium coupled with local and systemic fetal inflammation. Routine naso/oropharyngeal suctioning and tracheal intubation in cases of meconium-stained amniotic fluid have not been shown to be beneficial and are no longer recommended in obstetrical practice. A systematic review of randomized controlled trials suggested that amnioinfusion may decrease the rate of meconium aspiration syndrome. Histologic examination of the fetal membranes for meconium has been invoked in medical legal litigation to time the occurrence of fetal injury. However, inferences have been largely based on the results of in vitro experiments, and extrapolation of such findings to the clinical setting warrants caution. Fetal defecation throughout gestation appears to be a physiologic phenomenon based on ultrasound as well as in observations in animals.
Topics: Infant, Newborn; Pregnancy; Female; Humans; Meconium Aspiration Syndrome; Meconium; Amniotic Fluid; Chorioamnionitis; Pregnancy Complications; Inflammation; Heme
PubMed: 37012128
DOI: 10.1016/j.ajog.2022.11.1283 -
Obstetrics and Gynecology Feb 2020To systematically review the effectiveness of telehealth interventions for improving obstetric and gynecologic health outcomes.
OBJECTIVE
To systematically review the effectiveness of telehealth interventions for improving obstetric and gynecologic health outcomes.
DATA SOURCES
We conducted a comprehensive search for primary literature in ClinicalTrials.gov, Cochrane Library, Cochrane Collaboration Registry of Controlled Trials, EMBASE, PubMed, and MEDLINE.
METHODS OF STUDY SELECTION
Qualifying primary studies had a comparison group, were conducted in countries ranked very high on the United Nations Human Development Index, published in English, and evaluated obstetric and gynecologic health outcomes. Cochrane Collaboration's tool and ROBINS-I tool were used for assessing risk of bias. Summary of evidence tables were created using the United States Preventive Services Task Force Summary of Evidence Table for Evidence Reviews.
TABULATION, INTEGRATION, RESULTS
Of the 3,926 published abstracts identified, 47 met criteria for inclusion and included 31,967 participants. Telehealth interventions overall improved obstetric outcomes related to smoking cessation and breastfeeding. Telehealth interventions decreased the need for high-risk obstetric monitoring office visits while maintaining maternal and fetal outcomes. One study found reductions in diagnosed preeclampsia among women with gestational hypertension. Telehealth interventions were effective for continuation of oral and injectable contraception; one text-based study found increased oral contraception rates at 6 months. Telehealth provision of medication abortion services had similar clinical outcomes compared with in-person care and improved access to early abortion. Few studies suggested utility for telehealth to improve notification of sexually transmitted infection test results and app-based intervention to improve urinary incontinence symptoms.
CONCLUSION
Telehealth interventions were associated with improvements in obstetric outcomes, perinatal smoking cessation, breastfeeding, early access to medical abortion services, and schedule optimization for high-risk obstetrics. Further well-designed studies are needed to examine these interventions and others to generate evidence that can inform decisions about implementation of newer telehealth technologies into obstetrics and gynecology practice.
Topics: Female; Gynecology; Humans; Obstetrics; Pregnancy; Prenatal Care; Quality of Health Care; Randomized Controlled Trials as Topic; Telemedicine
PubMed: 31977782
DOI: 10.1097/AOG.0000000000003646 -
Current Opinion in Obstetrics &... Dec 2012This review aims to provide an update on the recent evidence concerning exercise during pregnancy including effects for mother and fetus and the types, frequency,... (Review)
Review
PURPOSE OF REVIEW
This review aims to provide an update on the recent evidence concerning exercise during pregnancy including effects for mother and fetus and the types, frequency, intensity, duration and rate of progression of exercise performed.
RECENT FINDINGS
Exercises during pregnancy are associated with higher cardiorespiratory fitness, prevention of urinary incontinence and low back pain, reduced symptoms of depression, gestational weight gain control, and for cases of gestational diabetes, reduced number of women who required insulin. There is no association with reduction in birth weight or preterm birth rate. The type of exercise shows no difference on results, and its intensity should be mild or moderate for previous sedentary women and moderate to high for active women. The exercise recommendations still are based on the current guidelines on moderate-intensity, low-impact, aerobic exercise at least three times a week. Yet, new guidelines propose increasing weekly physical-activity expenditure while incorporating vigorous exercise and adding light strength training to the exercise routine of healthy pregnant women. In the case of other chronic diseases like hypertension, there are still few data, and therefore more studies should be performed to assess the safety of the intervention.
SUMMARY
Physical exercise is beneficial for women during pregnancy and also in the postpartum period; it is not associated with risks for the newborn and can lead to changes in lifestyle that imply long-term benefits.
Topics: Delivery, Obstetric; Exercise; Female; Fetal Development; Guidelines as Topic; Humans; Labor, Obstetric; Pregnancy; Pregnancy Outcome; Prevalence
PubMed: 23014142
DOI: 10.1097/GCO.0b013e328359f131 -
Reproductive Biomedicine Online Jan 2021This study aimed to investigate the association of adenomyosis with fertility, pregnancy and neonatal outcomes. An electronic search was conducted using the MEDLINE,... (Meta-Analysis)
Meta-Analysis
This study aimed to investigate the association of adenomyosis with fertility, pregnancy and neonatal outcomes. An electronic search was conducted using the MEDLINE, PubMed and Cochrane databases up to April 2020. Seventeen observational studies were included. Adenomyosis was significantly associated with a lower clinical pregnancy rate (odds ratio [OR] 0.69; 95% confidence interval [CI] 0.51-0.94) and higher miscarriage rate (OR 2.17; 95% CI 1.25-3.79) after treatment with assisted reproductive technology (ART). The lower clinical pregnancy rate was more significant in the subgroup of patients with short down-regulation protocols. Similar associations were recorded after age adjustment. Adenomyosis was also significantly associated with an increased risk of pre-eclampsia, preterm delivery, Caesarean section, fetal malpresentation, small for gestational age infancy and post-partum haemorrhage, which was confirmed after correction for age and mode of conception. In conclusion, adenomyosis is associated with negative effects on fertility after ART. The potentially protective role of the ultra-long down-regulation protocols needs further evaluation in randomized controlled studies. Adenomyosis is also associated (independently of the mode of conception) with adverse pregnancy and neonatal outcomes. Proper counselling prior to ART and close monitoring of pregnancy in patients with adenomyosis should be recommended.
Topics: Adenomyosis; Female; Fertility; Humans; Infant, Newborn; Infertility, Female; Pregnancy; Pregnancy Complications; Pregnancy Outcome; Pregnancy Rate; Reproductive Techniques, Assisted
PubMed: 33191131
DOI: 10.1016/j.rbmo.2020.09.023 -
Anesthesia and Analgesia Nov 2017It is widely believed that the choice between isobaric bupivacaine and hyperbaric bupivacaine formulations alters the block characteristics for the conduct of surgery... (Meta-Analysis)
Meta-Analysis Review
BACKGROUND
It is widely believed that the choice between isobaric bupivacaine and hyperbaric bupivacaine formulations alters the block characteristics for the conduct of surgery under spinal anesthesia. The aim of this study was to systematically review the comparative evidence regarding the effectiveness and safety of the 2 formulations when used for spinal anesthesia for adult noncesarean delivery surgery.
METHODS
Key electronic databases were searched for randomized controlled trials, excluding cesarean delivery surgeries under spinal anesthesia, without any language or date restrictions. The primary outcome measure for this review was the failure of spinal anesthesia. Two independent reviewers selected the studies and extracted the data. Results were expressed as relative risk (RR) or mean differences (MDs) with 95% confidence intervals (CIs).
RESULTS
Seven hundred fifty-one studies were identified between 1946 and 2016. After screening, there were 16 randomized controlled clinical trials, including 724 participants, that provided data for the meta-analysis. The methodological reporting of most studies was poor, and appropriate judgment of their individual risk of bias elements was not possible. There was no difference between the 2 drugs regarding the need for conversion to general anesthesia (RR, 0.60; 95% CI, 0.08-4.41; P = .62; I = 0%), incidence of hypotension (RR, 1.15; 95% CI, 0.69-1.92; P = .58; I = 0%), nausea/vomiting (RR, 0.29; 95% CI, 0.06-1.32; P = .11; I = 7%), or onset of sensory block (MD = 1.7 minutes; 95% CI, -3.5 to 0.1; P = .07; I = 0%). The onset of motor block (MD = 4.6 minutes; 95% CI, 7.5-1.7; P = .002; I = 78%) was significantly faster with hyperbaric bupivacaine. Conversely, the duration of motor (MD = 45.2 minutes; 95% CI, 66.3-24.2; P < .001; I = 87%) and sensory (MD = 29.4 minutes; 95% CI, 15.5-43.3; P < .001; I = 73%) block was longer with isobaric bupivacaine.
CONCLUSIONS
Both hyperbaric bupivacaine and isobaric bupivacaine provided effective anesthesia with no difference in the failure rate or adverse effects. The hyperbaric formulation allows for a relatively rapid motor block onset, with shorter duration of motor and sensory block. The isobaric formulation has a slower onset and provides a longer duration of both sensory and motor block. Nevertheless, the small sample size and high heterogeneity involving these outcomes suggest that all the results should be treated with caution.
Topics: Anesthesia, Obstetrical; Anesthesia, Spinal; Anesthetics, Local; Bupivacaine; Chi-Square Distribution; Delivery, Obstetric; Drug Compounding; Female; Humans; Motor Activity; Odds Ratio; Pain Measurement; Pain Threshold; Pregnancy; Risk Factors; Time Factors; Treatment Outcome
PubMed: 28708665
DOI: 10.1213/ANE.0000000000002254