Impact of a shift in nuchal translucency measurements on the detection rate of first-trimester Down syndrome screening: A population-based study

Application of intelligent algorithms in Down syndrome screening during second trimester pregnancy

BACKGROUND

Down syndrome (DS) is one of the most common chromosomal aneuploidy diseases. Prenatal screening and diagnostic tests can aid the early diagnosis, appropriate management of these fetuses, and give parents an informed choice about whether or not to terminate a pregnancy. In recent years, investigations have been conducted to achieve a high detection rate (DR) and reduce the false positive rate (FPR). Hospitals have accumulated large numbers of screened cases. However, artificial intelligence methods are rarely used in the risk assessment of prenatal screening for DS.

AIM

To use a support vector machine algorithm, classification and regression tree algorithm, and AdaBoost algorithm in machine learning for modeling and analysis of prenatal DS screening.

METHODS

The dataset was from the Center for Prenatal Diagnosis at the First Hospital of Jilin University. We designed and developed intelligent algorithms based on the synthetic minority over-sampling technique (SMOTE)-Tomek and adaptive synthetic sampling over-sampling techniques to preprocess the dataset of prenatal screening information. The machine learning model was then established. Finally, the feasibility of artificial intelligence algorithms in DS screening evaluation is discussed.

RESULTS

The database contained 31 DS diagnosed cases, accounting for 0.03% of all patients. The dataset showed a large difference between the numbers of DS affected and non-affected cases. A combination of over-sampling and under-sampling techniques can greatly increase the performance of the algorithm at processing non-balanced datasets. As the number of iterations increases, the combination of the classification and regression tree algorithm and the SMOTE-Tomek over-sampling technique can obtain a high DR while keeping the FPR to a minimum.

CONCLUSION

The support vector machine algorithm and the classification and regression tree algorithm achieved good results on the DS screening dataset. When the T21 risk cutoff value was set to 270, machine learning methods had a higher DR and a lower FPR than statistical methods.

[Skills assessment for the practice of fetal ultrasound biometry: Prospective validation of the OSAUS METHOD score]

OBJECTIVES

To develop and validate a customized variant for fetal biometry of the generic OSAUS score (Objective Structured Assessment of Ultrasound Skills) METHODS: The 5-points OSAUS METHOD grid was elaborated by defining five target skills specific to fetal biometry for each thematic item of the generic score. The level of skills of 43 trainees was prospectively assessed during an ultrasound examination by using this grid. The results of the "novice" level group (experience<10 ultrasounds) were compared to those of the "intermediate" level group (experience≥10 ultrasounds) (I). The reached/non-reached skills ratio within the different items composing the score allowed the identification of priority areas of improvement (II). Previously published distribution and actual distribution of ratings according to the generic pass/fail score were compared (III).

RESULTS

Median scores of "novices" (n=29) and "intermediates" (n=14) groups were statistically different, 1.87 (±0.75) and 3.31 (±0.83) (P=1.85-5), respectively and corresponded to the pre-existing experience (I). A lower ratio of reached skill allowed the identification of "documentation of the examination" item as a priority area of improvement for both groups (II). The relevance of the pass/fail score is consolidated, even if an overlap was observed between novices and intermediates groups (III).

CONCLUSIONS

The relevancy and feasibility of using OSAUS scoring method for fetal biometry are supported. In addition, the possibility of comparisons with generic OSAUS remains.

No. 375-Clinical Practice Guideline on the Use of First Trimester Ultrasound

OBJECTIVE

This guideline reviews the clinical indications for first trimester ultrasound.

OUTCOME

Proven clinical benefit has been reported from first trimester ultrasound.

EVIDENCE

A Medline search and bibliography reviews in relevant literature provided the evidence.

VALUES

Content and recommendations were reviewed by the principal authors and the Diagnostic Imaging Committee of the Society of Obstetricians and Gynaecologists of Canada. Levels of evidence were judged as outlined by the Canadian Task Force on Preventive Health Care.

RECOMMENDATIONS

[Training in fetal ultrasound biometry: Prospective assesment of Objective Structured Assessment of Ultrasound Skills (OSAUS) efficiency]

BACKGROUND

Fetal biometry quality directly influences obstetrical care relevance. However, obstetrician proficiencies are heterogeneous in particular during initial training.

OBJECTIVES

To assess the predictive value of OSAUS scale to identify operators with enough command to perform a valid estimation of fetal weight (EFW) (I). This study also assesses OSAUS intra-operator inter-exams variability (II) and pass/fail score relevancy (III).

METHODS

Lecturers in Nancy University Hospital assessed trainees' proficiency for EWF systematically and prospectively through OSAUS scale. The trainee assessment was performed right after the one of the senior operator (reference EFW) on three consecutive patients during standard care ultrasounds. To ensure variability in proficiency within the sample, previous practice was taken into account during enrollment ("novices" and "intermediates" for<20 and 20 past exams, respectively). Correlation between mean OSAUS and validity of EFW (a valid EFW was defined by a difference with the reference EWF<0.8 Z-score) and variability between consecutive assessments were assessed.

RESULTS

The study population was constituted of 8 "novice" and 8 "intermediate" trainees. Association between OSAUS and EFW validity was significant (P<0.03) (I). Intra-operator inter-exams variability was majored in the "novice" group (coefficients of variation were 25% vs. 10% in "novice" and "intermediate" group respectively) (II). Within the sample, specificity and positive predictive value of a pass/fail score OSAUS>3.5 to predict EFW validity were 77% and 71%, respectively (III).

CONCLUSION

A 3.5 OSAUS pass/fail score could provide a relevant threshold to estimate operator proficiency in assessing fetal biometry in an autonomous and secure way.

Sonologist's characteristics related to a higher quality in fetal nuchal translucency measured in primary antenatal care centers

OBJECTIVE

To assess the quality of nuchal translucency (NT) measurements in primary care and the sonologist's characteristics related with a higher quality.

METHODS

The median NT expressed in multiples of the median (MoM) was calculated for each sonologist of 14 participating antenatal primary care centers of the Catalan Institute of Health. A survey to the sonologists was used to establish variables related to higher-quality measurements.

RESULTS

The median NT MoM obtained in 16 448 NT measurements, performed by 102 sonologists, was 0.94 MoM. NT underestimation was observed in 46% of the sonologists. Underestimation were less frequent among professionals who performed more than 230 ultrasounds per year (26% vs 53%;p = .022), those who completed the online Fetal Medicine Foundation (FMF) course (22% vs 54%; p = .021), and those who were subject to periodic audits (24% vs 56%; p = .021). Underestimation rate decreased from 60%, to 33% and 14% with the increase of the years of experience from less than 5 years, to 6 to 15 years and more than 15 years of experience, respectively (p = .029).

CONCLUSIONS

Higher-quality measurements were demonstrated in sonologists who performed more ultrasounds per year, those with more years of scanning experience, those who completed the online FMF course, and those periodically audited.