Development and clinical validation of real-time artificial intelligence diagnostic companion for fetal ultrasound examination.

OBJECTIVE: Prenatal diagnosis of a rare disease on ultrasound relies on a physician's ability to remember an intractable amount of knowledge. We developed a real-time decision support system (DSS) that suggests, at each step of the examination, the next phenotypic feature to assess, optimizing the diagnostic pathway to the smallest number of possible diagnoses. The objective of this study was to evaluate the performance of this real-time DSS using clinical data. METHODS: This validation study was conducted on a database of 549 perinatal phenotypes collected from two referral centers (one in France and one in the UK). Inclusion criteria were: at least one anomaly was visible on fetal ultrasound after 11 weeks' gestation; the anomaly was confirmed postnatally; an associated rare disease was confirmed or ruled out based on postnatal/postmortem investigation, including physical examination, genetic testing and imaging; and, when confirmed, the syndrome was known by the DSS software. The cases were assessed retrospectively by the software, using either the full phenotype as a single input, or a stepwise input of phenotypic features, as prompted by the software, mimicking its use in a real-life clinical setting. Adjudication of discordant cases, in which there was disagreement between the DSS output and the postnatally confirmed ('ascertained') diagnosis, was performed by a panel of external experts. The proportion of ascertained diagnoses within the software's top-10 differential diagnoses output was evaluated, as well as the sensitivity and specificity of the software to select correctly as its best guess a syndromic or isolated condition. RESULTS: The dataset covered 110/408 (27%) diagnoses within the software's database, yielding a cumulative prevalence of 83%. For syndromic cases, the ascertained diagnosis was within the top-10 list in 93% and 83% of cases using the full-phenotype and stepwise input, respectively, after adjudication. The full-phenotype and stepwise approaches were associated, respectively, with a specificity of 94% and 96% and a sensitivity of 99% and 84%. The stepwise approach required an average of 13 queries to reach the final set of diagnoses. CONCLUSIONS: The DSS showed high performance when applied to real-world data. This validation study suggests that such software can improve perinatal care, efficiently providing complex and otherwise overlooked knowledge to care-providers involved in ultrasound-based prenatal diagnosis. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

The impact of optimal dating on the assessment of fetal growth.

BACKGROUND: The impact of using the Intergrowth (IG) dating formulae in comparison to the commonly used Robinson dating on the evaluation of biometrics and estimated fetal weight (EFW) has not been evaluated. METHODS: Nationwide cross-sectional study of routine fetal ultrasound biometry in low-risk pregnant women whose gestational age (GA) had been previously assessed by a first trimester CRL measurement. We compared the CRL-based GA according to the Robinson formula and the IG formula. We evaluated the fetal biometric measurements as well as the EFW taken later in pregnancy depending on the dating formula used. Mean and standard deviation of the Z scores as well as the number and percentage of cases classified as <3rd, < 10th, >90th and > 97th percentile were compared. RESULTS: Three thousand five hundred twenty-two low-risk women with scans carried out after 18 weeks were included. There were differences of zero, one and 2 days in 642 (18.2%), 2700 (76.7%) and 180 (5%) when GA was estimated based on the Robinson or the IG formula, respectively. The biometry Z scores assessed later in pregnancy were all statistically significantly lower when the Intergrowth-based dating formula was used (p < 10- 4). Likewise, the number and percentage of foetuses classified as <3rd, < 10th, >90th and > 97th percentile demonstrated significant differences. As an example, the proportion of SGA foetuses varied from 3.46 to 4.57% (p = 0.02) and that of LGA foetuses from 17.86 to 13.4% (p < 10- 4). CONCLUSION: The dating formula used has a quite significant impact on the subsequent evaluation of biometry and EFW. We suggest that the combined and homogeneous use of a recent dating standard, together with prescriptive growth standards established on the same low-risk pregnancies, allows an optimal assessment of fetal growth.

Biometric and morphological features on magnetic resonance imaging of fetal bladder in lower urinary tract obstruction: new perspectives for fetal cystoscopy.

OBJECTIVES: Incompatibility between currently available fetoscopes and the anatomical constraints of the distended fetal bladder, with the resulting curvature around the bladder neck, account for most technical difficulties during fetal cystoscopy in lower urinary tract obstruction (LUTO). The aim of this anatomical study was to assess by magnetic resonance imaging (MRI) the variation in three bladder angles (bladder-neck angle (BNA), vesicourethral angle (VUA) and angle between bladder dome and posterior urethra (DUA)), according to gestational age (GA), bladder volume and the presence of LUTO. METHODS: From our fetal medicine database, we retrieved for review 46 MRI examinations of male fetuses between 2015 and 2019, including 17 with LUTO, examined at a mean GA of 28.1 (range, 17.3-35.0) weeks and 29 age-matched controls, examined at 29.9 (range, 21.9-35.0) weeks. We measured bladder volume, bladder-wall thickness and the three bladder angles, and used the Mann-Whitney U-test to compare values between groups. Variations according to GA and bladder volume were determined using analysis of variance (ANOVA). A reliability study was performed using the Bland-Altman method and Lin's correlation coefficient was calculated. RESULTS: Both bladder volume and bladder-wall thickness were significantly greater in the LUTO group (P < 0.01). BNA was significantly larger in LUTO compared with control fetuses: the mean (range) was 127.1° (101.6-161.6°) vs 111.2° (88.5-157.3°) (P < 0.01). DUA averaged 117° and showed no difference between the groups (P = 0.92). No statistical comparison was performed on VUA since this was not measurable in most control fetuses. ANOVA showed no variation of any angle with bladder volume in both LUTO fetuses and control fetuses. BNA in LUTO fetuses was the only angle to vary with GA, being larger after, compared with at or before, 25 weeks (P = 0.04). The reliability study showed an acceptable bias for both intra- and interobserver reproducibility for all three angles. CONCLUSION: The findings that BNA is increased by approximately 15° in fetuses with LUTO and DUA averages 117° could aid in development of a customized fetal cystoscope and help to overcome the current technical challenges of fetal cystoscopy. Copyright © 2019 ISUOG. Published by John Wiley & Sons Ltd.

Implementing the INTERGROWTH-21st fetal growth standards in France: a 'flash study' of the College Français d'Echographie Foetale (CFEF).

OBJECTIVES: To assess potential differences in fetal size between the French population and the international population from the INTERGROWTH-21st (IG-21st ) Project and to measure the impact of switching to the IG-21st reference standards for fetal size. METHODS: This was a nationwide cross-sectional study of fetal ultrasound biometry. Low-risk singleton pregnancies were recruited prospectively within the network of the national French College of Fetal Ultrasound, CFEF, over a 6-week period. Further selection was performed based on the criteria of the IG-21st Project in order to obtain a comparable population. Head circumference (HC) was used as the main fat-free skeletal measure of growth for comparison of French fetal size with that of the IG-21st population. The impact of switching to the IG-21st fetal growth standards was quantified by comparing Z-scores calculated using the IG-21st standards with those calculated using locally derived reference ranges for HC, abdominal circumference (AC) and femur length (FL). RESULTS: Following selection, 4858 cases were analyzed. The distribution of HC demonstrated clear similarity between our French population and the IG-21st population: our observed centile curves closely matched those of IG-21st and the Z-scores were close to 0 across gestational age. The IG-21st standards performed as well as did locally derived charts in terms of screening for small-for-gestational age by AC, while they identified significantly fewer small FL values than were expected and than did the locally derived charts. CONCLUSIONS: Under strict selection criteria, fetal size in France is similar to that of the international population used in the IG-21st Project. The discrepancies in FL are unlikely to impact on prenatal management. Therefore, switching from locally derived reference ranges to the IG-21st standards appears to be a safe option. Copyright © 2016 ISUOG. Published by John Wiley & Sons Ltd.

Sequential fetal serum ß2-microglobulin to predict postnatal renal function in bilateral or low urinary tract obstruction.

OBJECTIVE: Fetal serum ß2-microglobulin has been shown to predict postnatal renal outcome in cases of fetal obstructive uropathy. We assessed the value of serial measurements of fetal serum ß2-microglobulin in the prediction of postnatal renal outcome. METHODS: We retrospectively studied renal outcome in 42 fetuses with bilateral or low urinary tract obstruction that had fetal blood sampling on at least two occasions to assay serum levels of ß2-microglobulin. Amniotic fluid volume at the time of each sampling was recorded. We classified renal outcome as either favorable (when postnatal renal function was normal) or adverse (when postnatal chronic renal failure occurred or when renal dysplasia at autopsy was noted). A ß2-microglobulin cut-off of 5 mg/L and amniotic fluid index of 5 cm were used to predict postnatal renal outcome. RESULTS: Renal outcome was adverse in 28 cases and favorable in 14. In 12 (28.6%) cases, fetal serum ß2-microglobulin concentration differed between the first and last measurement. Prediction of postnatal renal outcome was correct in 11 of these cases based on the last ß2-microglobulin measurement. The sensitivity of ß2-microglobulin in predicting renal outcome was significantly higher (P = 0.005) when using the last rather than the first measurement (96.4% vs 64.3%), with similar specificity for both measurements (85.7% vs 78.6%, non-significant). The sensitivity of amniotic fluid volume was also significantly higher (P = 0.005) when using the last rather than the first measurement (75.0% vs 35.7%), with similar specificity for both measurements (64.3% vs 71.4%, non-significant). CONCLUSION: Sequential measurement of serum ß2-microglobulin, performed for adverse ultrasound findings, such as renal parenchymal abnormality or decreasing amniotic fluid volume, predicts postnatal renal outcome more accurately than does a single assay. This may be due to possible worsening of renal injury with increasing duration of urinary tract obstruction. Copyright © 2016 ISUOG. Published by John Wiley & Sons Ltd.

Pulmonary stenosis in complicated monochorionic twin pregnancies: prevalence, management and outcome.

OBJECTIVE: To review prevalence, management and prognostic factors of pulmonary stenosis (PS) in monochorionic diamniotic (MCDA) pregnancies complicated by twin-to-twin transfusion syndrome (TTTS). METHODS: Retrospective study over the last 10 years in a single referral center. We reviewed fetal echocardiography data of all MC twin cases with diagnosis of isolated PS. We assessed fetoscopy characteristics of those that underwent laser coagulation. We collected data regarding perinatal outcome, neonatal echocardiography and cardiac management. RESULTS: We found 24 cases of isolated PS among 2091 MCDA pregnancies. Among 1052 complicated MCDA that underwent fetal laser surgery, 22 (2.09%) developed PS of which 20 were diagnosed prenatally. Two cases were diagnosed in uncomplicated MCDA pregnancies (0.2%). Four of 22 (18.18%) cases with TTTS showed in utero regression after laser treatment. Thirteen newborns (65%) required valvular dilatation. Peak systolic velocities in the pulmonary artery trunk (PSV-PA) at diagnosis and the interval between the diagnosis of TTTS and that of PS were significantly different (p < 0.001 and p = 0.05 respectively) between PS requiring cardiac intervention and those who did not. CONCLUSION: An elevated PSV-PA at the time of PS diagnosis and a short time-interval between fetoscopic laser surgery and PS diagnosis are predictive of the need for interventional treatment after birth.

Prenatal prediction of pulmonary arterial hypertension in congenital diaphragmatic hernia.

OBJECTIVE: To evaluate the role of prenatal prognostic markers obtained routinely by ultrasound examination and magnetic resonance imaging (MRI) in the prediction of development of postnatal pulmonary arterial hypertension (PAH) in isolated congenital diaphragmatic hernia (CDH). METHODS: One hundred and ten cases of isolated CDH were referred to our fetal medicine unit between January 2004 and April 2013. Mortality and morbidity rates were reviewed for those presenting with postnatal PAH. The following prenatal markers were evaluated as potential predictive factors of PAH: liver position, side of the CDH defect, lung area to head circumference ratio (LHR) and observed/expected LHR (o/e-LHR), which were measured by ultrasound, and observed/expected total fetal lung volume (o/e-TFLV), which was measured by MRI. Univariable logistic regression was used to assess associations. RESULTS: PAH was significantly associated with perinatal mortality and morbidity (P < 0.001). The occurrence of PAH decreased significantly with an increasing LHR, o/e-LHR and o/e-TFLV and was significantly increased for cases with an intrathoracic liver, but not for those with right-sided defects. Univariable regression revealed that o/e-TFLV (odds ratio (OR), 0.9 (95% CI, 0.86-0.95); P < 0.05 for percentage unit change in o/e), LHR (OR, 0.19 (95% CI, 0.09-0.40); P < 0.05 for unit change), o/e-LHR (OR, 0.95 (95% CI, 0.93-0.98); P < 0.05 for percentage unit change in o/e) and liver position (OR, 2.82 (95% CI, 1.13-7.00); P < 0.05 for intrathoracic liver) were significant predictors of subsequent PAH. No differences were found after adjusting for gestational age at delivery. The areas under the receiver-operating characteristics curve were 0.80 and 0.75 for o/e-TFLV and o/e-LHR, respectively. CONCLUSION: In cases of CDH, PAH is associated with high rates of mortality and morbidity. Routinely obtained prenatal markers, usually used for the assessment of pulmonary hypoplasia, are also relevant for the postnatal prediction of PAH.

Optimal risk assessment of small-for-gestational-age fetuses using 31-34-week biometry in a low-risk population.

OBJECTIVE: To compare the performance of traditional growth charts for estimated fetal weight (EFW) and a validated pragmatic probabilistic approach using biometry at 31-34 weeks' gestation to screen for late pregnancy small-for-gestational age (SGA) fetuses in a low-risk population. METHODS: Records of ultrasound biometry at 31-34 weeks were reviewed in 7755 consecutive low-risk women between 2002 and 2011. Fetal malformations, Doppler anomalies and preterm delivery before 37 weeks were excluded. SGA was defined by various percentile cut-offs of birth weight. The probability of SGA was modeled as a function of Z-scores of femur length, abdominal circumference and head circumference. The model was validated on a second independent dataset of 1725 pregnancies from a different screening unit. The screening performance of this probabilistic approach was compared with those of traditional EFW growth charts. The additional value of factoring in maternal characteristics was also ascertained. RESULTS: Using national birth-weight charts, the proportions of newborns at 37-42 weeks with birth weight<3(rd) , <5(th) and<10(th) centiles were 3%, 6% and 12%, respectively, and there was a 2% rate of birth weight<2500 g. For a 10% false-positive rate, a direct probabilistic approach yielded a 51% detection rate of neonates with birth weight<10(th) centile, compared to the 32% and 48% detection rates given by the 10(th) centile cut-off of two reference charts for EFW. Adding maternal characteristics significantly improved detection rate by 2% to 53%. CONCLUSIONS: The suggested validated approach to screening for late SGA fetuses outperforms traditional approaches using growth charts. By adding maternal characteristics, this screening method offers a favorable alternative to customized charts.

Active management of selective intrauterine growth restriction with abnormal Doppler in monochorionic diamniotic twin pregnancies diagnosed in the second trimester of pregnancy.

OBJECTIVE: This study aims to compare outcomes of active management of monochorionic diamniotic twin pregnancies complicated with severe intrauterine growth restriction (IUGR) of one twin before 24 weeks with continuous or intermittent absent or reversed end-diastolic flow (AREDF) in the umbilical artery, with or without twin-to-twin transfusion syndrome (TTTS). METHOD: This study is a retrospective comparison of 45 consecutive cases of severe selective IUGR (s-IUGR) defined as an estimated fetal weight at or below the fifth centile with a >25% weight discordance and AREDF in the umbilical artery before 24 weeks and 166 consecutive cases of TTTS stage III, with AREDF in the donor (TTTS3D) and also with s-IUGR. These were treated by either selective laser photocoagulation of chorionic vessels (SLPCV) or cord coagulation (CC). RESULTS: The 166 cases of TTTS3D were treated by SLPCV, whereas 23 and 22 cases of s-IUGR were treated by SLPCV and CC, respectively. Overall survival was 52.17% or 45.45% in s-IUGR treated by SLPCV or CC, respectively, and 48.49% in TTTS3D. The survival of appropriately grown for gestational age (AGA) twins following CC (90.9%) was higher than that following SLPCV in s-IUGR (74%) or in recipient twins of TTTS3D (55.42%) (p = 0.001). Survival of the IUGR twin was 30% and 41.56% with SLPCV in s-IUGR and TTTS3D, respectively. CONCLUSIONS: Active management of severe IUGR with AREDF in the umbilical artery seems beneficial. Survival rates with SLPCV were similar in s-IUGR and TTTS3D. However, there was a trend for higher survival rates in the AGA twin for CC. The choice of the technique should be driven by objective counseling on survival of both IUGR and AGA twins and therefore by the utility-based ethical values expressed by the pregnant woman.

A nomogram for perioperative prognostic risk-assessment in twin-twin transfusion syndrome.

OBJECTIVE: Prognostic assessment in twin-to-twin transfusion syndrome (TTTS) is ill-defined. The objective of this study is to define a perioperative prognostic score for TTTS treated by percutaneous laser coagulation. METHODS: Consecutive cases of TTTS treated by percutaneous fetoscopic laser coagulation over a 6-year period were reviewed. Twin survival at 28 days was considered using a 3-level polytomous variable defined by 0, 1, or 2 fatal events. A multivariate prognostic analysis with internal validation was conducted using gestational age at diagnosis, weight discordance, umbilical artery, and ductus venosus abnormalities in the donor and the recipient respectively, cervical length, selectivity of surgery, and transplacental approach. RESULTS: On the basis of 507 cases, the perinatal survival rate of 2 and 1 twin was 46.2% and 31.5%, respectively. Statistically significant factors included umbilical artery abnormalities in the donor, gestational age, and transplacental approach, but with different effects regarding survival of 0, 1, or 2 twins. A scoring chart was subsequently constructed together with a nomogram for both a preoperative and immediate post-operative prognostic assessment. CONCLUSION: Part of the prognosis can be anticipated by perioperative findings. Although further validation is required, the presented nomogram should help unify the prognostic assessment in TTTS.

Density estimation of a biomedical variable subject to measurement error using an auxiliary set of replicate observations.

Correcting for measurement error when estimating the density of a routinely collected biomedical variable is an important issue when describing reference values for both healthy and pathological states. The present work addresses the problem of estimating the density of a biomedical variable observed with measurement error without any a priori knowledge on the error density. Assuming the availability of a sample of replicate observations, either internal or external, which is generally easily obtained in clinical settings, we propose an estimator based on the non-parametric deconvolution theory with an adaptive procedure for cutoff selection, the replicates being used for an estimation of the error density. We illustrate this approach in two applicative examples: (i) the systolic blood pressure distribution density, using the Framingham Study data set, and (ii) the distribution of the timing of onset of pregnancy within the female cycle, using ultrasound measurements in the first trimester of pregnancy.

Individual predictions based on nonlinear mixed modeling: application to prenatal twin growth.

The assessment of growth during fetal life and childhood commonly relies upon cross'sectional reference ranges or centiles. However, individual sequential predictions may help the timewise assessment of a growth process. In twin pregnancies for example, which are at risk of growth restriction, such predictions may improve the detection of abnormal trajectories. In this article, we present a simple forecasting method, assuming that a given normal individual behaves in the same way as a reference population. We consider, as a prediction in a given individual, the forecast of a future observation conditional to any previous observation and a set of population parameters obtained by nonlinear mixed modeling in a reference population. We suggest an estimator for this prediction without resorting to linear approximation and show that it enjoys interesting asymptotics when the amount of observations increases over time. We use two independent real datasets of twin pregnancies with normal growth and outcome to illustrate the application of such predictions in prenatal growth. We consider the first dataset as a reference dataset and model it using a two'level nonlinear model. We perform illustration and validation of predictions on the second dataset.

Likelihood ratio-based quality control for nuchal translucency measurements at 11-14 weeks of gestation.

OBJECTIVE: To develop a quantitative quality control process of nuchal translucency (NT) measurement at 11-14 weeks of gestation based on the mixture model, characterized by analysis of the corresponding distribution of the likelihood ratio (LR). METHODS: Based on the published mixture model for NT measurement in the first trimester, we simulated the expected distribution of NT and the corresponding LR. This approach was then tested for the quality control of 15 048 NT measurements performed by four operators trained and certified by The Fetal Medicine Foundation. The new quality control approach based on LR was compared with existing processes based on NT plots, multiples of the median (MoMs) and analysis of the 95(th) centile. RESULTS: Each operator contributed 2176-4730 examinations. Median, 5(th) and 95(th) centile of NT values ranged from 1.4 to 1.6, 1.0 to 1.0 and 2.2 to 2.6 mm, respectively. Median of NT-MoM values ranged from 0.83 to 0.95. Analysis of the distribution of NT measurements confirmed departure from the assumptions of the delta-NT and NT-MoM models. Analysis of LR distributions demonstrated a significant difference between observed and expected distributions for all operators (P < 10(-4) ). CONCLUSION: An LR-based quality control process is feasible at 11-14 weeks of gestation. Because it is more sensitive to measurement bias around the critical area of the 95(th) centile, its use should be encouraged.

Specific complications of monochorionic twin pregnancies: twin-twin transfusion syndrome and twin reversed arterial perfusion sequence.

Monochorionic twins are subjected to specific complications which originate in either imbalance or abnormality of the single placenta serving two twins. This unequal placental sharing can cause complications including twin-twin transfusion syndrome (TTTS), twin anemia-polycythemia sequence (TAPS), selective intrauterine growth restriction or twin reversed arterial perfusion sequence (TRAP). Monochorionicity also makes the management of these specific complications as well as that of a severe malformation in one twin hazardous since the spontaneous death of one twin exposes the co-twin to a risk of exsanguination into the dead twin and its placenta. The latter is responsible for the death of the co-twin in up to 20% of the cases and in ischemic sequelae in about the same proportions in the survivors. Although the symptoms of all these complications are very different, the keystone of their management comes down to either surgical destruction of the inter-twin anastomoses on the chorionic plate when aiming at dual survival or selective and permanent occlusion of the cord of a severely affected twin aiming at protecting the normal co-twin. This can be best achieved by fetoscopic selective laser coagulation and bipolar forceps cord coagulation respectively.

Evaluation of the CHOP cardiovascular score as a prognostic predictor of outcome in twin-twin transfusion syndrome after laser coagulation of placental vessels in a prospective cohort.

OBJECTIVE: To investigate the prognostic value of cardiac function assessment by the previously reported CHOP (Children's Hospital of Philadelphia) cardiovascular score in twin-twin transfusion syndrome (TTTS). METHODS: All consecutive monochorionic pregnancies presenting with TTTS over a 24-month period were evaluated by preoperative echocardiography before percutaneous laser coagulation of chorionic vessels. Each of the 12 items of the CHOP score was evaluated prospectively and the cardiovascular score was categorized into stages using previously published cut-offs. The outcome considered for this study was neonatal survival of neither, one or both twins. RESULTS: In total, 215 pregnancies were enrolled. Due to technical issues, CHOP evaluation was incomplete in 16% of cases and follow-up was unavailable in 12%. Overall, there was a significant relationship between the CHOP score and the Quintero staging system, although this relationship was significantly reduced when parameters used in the Quintero system were removed from the CHOP score. Based upon neonatal survival, the CHOP score did not show any prognostic value regarding overall pregnancy outcome or individual recipient survival. CONCLUSION: Cardiac function assessment using the CHOP score is not of clinical use as a prognostic marker in TTTS. This suggests that cardiac function may not be of interest for preoperative staging when laser coagulation is the first-line treatment, other than to confirm the diagnosis of TTTS requiring surgery.

Profiling fetal cardiac function in twin-twin transfusion syndrome.

OBJECTIVES: Cardiomyopathy in the recipient twin is a marker of severity in twin-twin transfusion syndrome (TTTS), making it a potentially valuable tool for staging the disease. This study aimed to provide a quantitative description of cardiac function in the recipient twin. METHODS: Consecutive monochorionic pregnancies complicated with TTTS and treated by percutaneous laser coagulation underwent fetal echocardiography before surgery. An unsupervised classification analysis was conducted to identify groups of twins with similar cardiac profiles. The predictive value of the recipient twin's preoperative cardiac function based on these profiles was assessed, using perinatal death of at least one twin as the main outcome. The cardiac function profiles that we identified were compared with the current Quintero staging. RESULTS: A total of 107 pregnancies were included, with six of these lost to follow-up; 63/107 complete cases were available for multivariate description of the recipient's cardiac function. Three different preoperative cardiac profiles were identified with increasing right and left myocardial performance index, decreasing right and left shortening fraction, and increasing ductus venosus pulsatility index. Although the three groups represented progressive stages of the syndrome-related cardiomyopathy, no correlation was found with pregnancy outcome. Of Quintero Stage 1 cases, 55% showed significant alterations of cardiac function in the recipient twin. CONCLUSIONS: Progressive cardiomyopathy can be assessed quantitatively in the recipient twin and does not influence pregnancy outcome when fetoscopic laser coagulation is the first-line treatment. Compared with the current staging, cardiac profiling allows discrimination of cases with significant myocardial dysfunction.