The Diagnostic Value of a Multivariate Logistic Regression Analysis Model with Transvaginal Power Doppler Ultrasonography for the Prediction of Ectopic Pregnancy

Zy, Chen; Jh, Liu; K, Liang; Wx, Liang; Ma, Siddiqui; Gj, Zeng; Sy, Xiao; Jg, He

doi:10.1177/147323001204000119

Cited by 13 publications

(15 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ultrasound can be used to locate a pregnancy anatomically and to see if the fetus is alive. In general, a gestational sac can be consistently identified by TVS at a cut-off level of serum β-hCG is 2000 IU/L, which is known as the discriminatory zone [ 119 , 120 ].…”

Section: Resultsmentioning

confidence: 99%

Ectopic pregnancy secondary to in vitro fertilisation-embryo transfer: pathogenic mechanisms and management strategies

Refaat

Dalton

Ledger

2015

Reprod Biol Endocrinol

110

108

View full text Add to dashboard Cite

BackgroundEctopic pregnancy (EP) is the leading cause of maternal morbidity and mortality during the first trimester and the incidence increases dramatically with in vitro fertilisation and embryo transfer (IVF-ET). The co-existence of an EP with a viable intrauterine pregnancy (IUP) is known as heterotopic pregnancy (HP) affecting about 1% of patients during assisted conception. EP/HP can cause significant morbidity and occasional mortality and represent diagnostic and therapeutic challenges, particularly during fertility treatment. Many risk factors related to IVF-ET techniques and the cause of infertility have been documented. The combination of transvaginal ultrasound (TVS) and serum human chorionic gonadotrophin (hCG) is the most reliable diagnostic tool, with early diagnosis of EP/HP permitting conservative management. This review describes the risk factors, diagnostic modalities and treatment approaches of EP/HP during IVF-ET and also their impact on subsequent fertility treatment.MethodsThe scientific literature was searched for studies investigating EP/HP during IVF-ET. Publications in English and within the past 6 years were mostly selected.ResultsA history of tubal infertility, pelvic inflammatory disease and specific aspects of embryo transfer technique are the most significant risk factors for later EP. Early measurement of serum hCG and performance of TVS by an expert operator as early as gestational week 5 can identify cases of possible EP. These women should be closely monitored with repeated ultrasound and hCG measurement until a diagnosis is reached. Treatment must be customised to the clinical condition and future fertility requirements of the patient. In cases of HP, the viable IUP can be preserved in the majority of cases but requires early detection of HP. No apparent negative impact of the different treatment approaches for EP/HP on subsequent IVF-ET, except for risk of recurrence.ConclusionsEP/HP are tragic events in a couple’s reproductive life, and the earlier the diagnosis the better the prognosis. Due to the increase incidence following IVF-ET, there is a compelling need to develop a diagnostic biomarker/algorithm that can predict pregnancy outcome with high sensitivity and specificity before IVF-ET to prevent and/or properly manage those who are at higher risk of EP/HP.

show abstract

Section: Resultsmentioning

confidence: 99%

Ectopic pregnancy secondary to in vitro fertilisation-embryo transfer: pathogenic mechanisms and management strategies

Refaat

Dalton

Ledger

2015

Reprod Biol Endocrinol

110

108

View full text Add to dashboard Cite

show abstract

“…Currently, LR and ANN are the most widely used models in biomedicine [8], [14], [19]. LR can generate excellent models and can serve as a commonly accepted statistical tool.…”

Section: Discussionmentioning

confidence: 99%

“…These models may aid the clinician in the decision-making process regarding clinical admission, early prevention, early clinical diagnosis, and application of clinical therapies. Most previous prediction models were developed using univariate or multivariate logistic regression (LR) analysis [8], [9]. An artificial neural network (ANN) refers to a mathematical model inspired by biological neural networks [10].…”

Section: Introductionmentioning

confidence: 99%

Comparison of Prediction Model for Cardiovascular Autonomic Dysfunction Using Artificial Neural Network and Logistic Regression Analysis

Tang

Liu²,

Zeng

et al. 2013

PLoS ONE

View full text Add to dashboard Cite

BackgroundThis study aimed to develop the artificial neural network (ANN) and multivariable logistic regression (LR) analyses for prediction modeling of cardiovascular autonomic (CA) dysfunction in the general population, and compare the prediction models using the two approaches.Methods and MaterialsWe analyzed a previous dataset based on a Chinese population sample consisting of 2,092 individuals aged 30–80 years. The prediction models were derived from an exploratory set using ANN and LR analysis, and were tested in the validation set. Performances of these prediction models were then compared.ResultsUnivariate analysis indicated that 14 risk factors showed statistically significant association with the prevalence of CA dysfunction (P<0.05). The mean area under the receiver-operating curve was 0.758 (95% CI 0.724–0.793) for LR and 0.762 (95% CI 0.732–0.793) for ANN analysis, but noninferiority result was found (P<0.001). The similar results were found in comparisons of sensitivity, specificity, and predictive values in the prediction models between the LR and ANN analyses.ConclusionThe prediction models for CA dysfunction were developed using ANN and LR. ANN and LR are two effective tools for developing prediction models based on our dataset.

show abstract

“…Currently, LR and ANN are the most widely used models in biomedicine [11,16,18]. LR can generate excellent models and can serve as a commonly accepted statistical tool.…”

Section: Discussionmentioning

confidence: 99%

Artificial neural network models for prediction of cardiovascular autonomic dysfunction in general Chinese population

Liu¹,

Tang

Zeng

et al. 2013

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

BackgroundThe present study aimed to develop an artificial neural network (ANN) based prediction model for cardiovascular autonomic (CA) dysfunction in the general population.MethodsWe analyzed a previous dataset based on a population sample consisted of 2,092 individuals aged 30–80 years. The prediction models were derived from an exploratory set using ANN analysis. Performances of these prediction models were evaluated in the validation set.ResultsUnivariate analysis indicated that 14 risk factors showed statistically significant association with CA dysfunction (P < 0.05). The mean area under the receiver-operating curve was 0.762 (95% CI 0.732–0.793) for prediction model developed using ANN analysis. The mean sensitivity, specificity, positive and negative predictive values were similar in the prediction models was 0.751, 0.665, 0.330 and 0.924, respectively. All HL statistics were less than 15.0.ConclusionANN is an effective tool for developing prediction models with high value for predicting CA dysfunction among the general population.

show abstract

The Diagnostic Value of a Multivariate Logistic Regression Analysis Model with Transvaginal Power Doppler Ultrasonography for the Prediction of Ectopic Pregnancy

Abstract: This multivariate predictive logistic regression analysis model has clinical value for the differential diagnosis of early ectopic pregnancy when the pregnancy location is unknown.

Cited by 13 publications

References 20 publications

Ectopic pregnancy secondary to in vitro fertilisation-embryo transfer: pathogenic mechanisms and management strategies

Ectopic pregnancy secondary to in vitro fertilisation-embryo transfer: pathogenic mechanisms and management strategies

Comparison of Prediction Model for Cardiovascular Autonomic Dysfunction Using Artificial Neural Network and Logistic Regression Analysis

Artificial neural network models for prediction of cardiovascular autonomic dysfunction in general Chinese population

Contact Info

Product

Resources

About