Fetal imaging and diagnosis services in developing countries – A call to action

Akinmoladun, J A; Anumba, Dilly

doi:10.4103/tjog.tjog_59_18

Cited by 13 publications

(12 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address this need, we aimed to develop a screening technology based on deep neural networks and facial statistical shape models (SSM) to evaluate a child's risk of presenting with a genetic syndrome for use at the point of care-eg in maternity wards, paediatricians' offices, and general practitioner clinics. We built this technology based on our experience quantifying facial phenotypes from photographs, interpreting facial dysmorphology in paediatric populations of diverse race or ethnicity, [7][8][9][10][11] and working with health authorities in countries with different systems of access to health care.…”

Section: Implications Of All the Available Evidencementioning

confidence: 99%

“…The situation is worse in LMICs, where screening and testing services are less common, and often only available through private institutions. 6,7 Consequently, children with genetic syndromes at risk of lifethreatening conditions are often identified after birth, based on physical examination. Since dysmorphology can be mild and vary largely with age and race or ethnicity, [8][9][10][11][12] many children are not identified in time for preventive care.…”

Section: Introductionmentioning

confidence: 99%

“…17 Since the performance of neural net works is dependent on the availability of large training datasets representing the observed variability in the population, 18 and some syndromes are rare, we believe that this approach will likely succeed only in the identification of common genetic conditions. Earlier studies using traditional machine learning approaches for facial analysis have shown high performance on either binary classification problems [7][8][9][10][11] or classification problems with a reduced number of syndromes. 19,20 Threedimensional (3D) facial phenotyping models have also been studied, 21 but 3D photogrammetry is rarely available, particularly in LMICs.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Development and evaluation of a machine learning-based point-of-care screening tool for genetic syndromes in children: a multinational retrospective study

Porras

Rosenbaum

Tor-Díez

et al. 2021

The Lancet Digital Health

View full text Add to dashboard Cite

Background Delays in the diagnosis of genetic syndromes are common, particularly in low and middle-income countries with limited access to genetic screening services. We, therefore, aimed to develop and evaluate a machine learning-based screening technology using facial photographs to evaluate a child's risk of presenting with a genetic syndrome for use at the point of care. MethodsIn this retrospective study, we developed a facial deep phenotyping technology based on deep neural networks and facial statistical shape models to screen children for genetic syndromes. We trained the machine learning models on facial photographs from children (aged <21 years) with a clinical or molecular diagnosis of a genetic syndrome and controls without a genetic syndrome matched for age, sex, and race or ethnicity. Images were obtained from three publicly available databases (the Atlas of Human Malformations in Diverse Populations of the National Human Genome Research Institute, Face2Gene, and the dataset available from Ferry and colleagues) and the archives of the Children's National Hospital (Washington, DC, USA), in addition to photographs taken on a standard smartphone at the Children's National Hospital. We designed a deep learning architecture structured into three neural networks, which performed image standardisation (Network A), facial morphology detection (Network B), and genetic syndrome risk estimation, accounting for phenotypic variations due to age, sex, and race or ethnicity (Network C). Data were divided randomly into 40 groups for cross validation, and the performance of the model was evaluated in terms of accuracy, sensitivity, and specificity in both the total population and stratified by race or ethnicity, age, and sex. Findings Our dataset included 2800 facial photographs of children (1318 [47%] female and 1482 [53%] male; 1576 [56%] White, 432 [15%] African, 430 [15%] Hispanic, and 362 [13%] Asian). 1400 children with 128 genetic conditions were included (the most prevalent being Williams-Beuren syndrome [19%], Cornelia de Lange syndrome [17%], Down syndrome [16%], 22q11.2 deletion [13%], and Noonan syndrome [12%] syndrome) in addition to 1400 photographs of matched controls. In the total population, our deep learning-based model had an accuracy of 88% (95% CI 87-89) for the detection of a genetic syndrome, with 90% sensitivity (95% CI 88-92) and 86% specificity (95% CI 84-88). Accuracy was greater in White (90%, 89-91) and Hispanic populations (91%, 88-94) than in African (84%, 81-87) and Asian populations (82%, 78-86). Accuracy was also similar in male (89%, 87-91) and female children (87%, 85-89), and similar in children younger than 2 years (86%, 84-88) and children aged 2 years or older (eg, 89% [87-91] for those aged 2 years to <5 years). Interpretation This genetic screening technology could support early risk stratification at the point of care in global populations, which has the potential accelerate diagnosis and reduce mortality and morbidity through preventive care.

show abstract

Section: Implications Of All the Available Evidencementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Development and evaluation of a machine learning-based point-of-care screening tool for genetic syndromes in children: a multinational retrospective study

Porras

Rosenbaum

Tor-Díez

et al. 2021

The Lancet Digital Health

View full text Add to dashboard Cite

show abstract

“…[2,8] A significant majority of women who attend antenatal ultrasound clinic find it interesting and reassuring, especially as it offers improved mother-to-child bonding. [4,9] The World Health Organization (WHO) has recommended that routine obstetric ultrasound investigation be performed for proper pregnancy dating and identification of high-risk pregnancies [4] and this has since triggered a rise in routine antenatal ultrasound screening in sub-Saharan Africa. [10,11] The alarming rates of pregnancy-related complications including child and maternal mortality in resource-poor and remote communities in Africa [12] emphasize the need to ensure optimal utilization of ultrasound in routine obstetric workups to improve positive perinatal outcome and reduce complications in these regions.…”

Section: Introductionmentioning

confidence: 99%

Utilization of obstetric ultrasonography and findings in a cottage hospital in Nigeria

Inah

Ngaji

Erim

et al. 2021

CJHS

View full text Add to dashboard Cite

Objectives: The integration of ultrasound into routine obstetric workup has transformed antenatal care in resource-poor and remote communities in Africa. The present study aims to investigate the utilization of obstetric ultrasound at a cottage hospital in suburban Nigeria. Material and Methods: This retrospective study was conducted at Obio Cottage Hospital, Port Harcourt, Rivers State, South-South Nigeria. Ethical approval was obtained before commencement of the study from the Health Research Ethics Committee of University of Calabar Teaching Hospital with reference number UCTH/HREC/33/533. Reports were retrieved from the records of the radiology unit of the study facility, and data including biometric data and radiological diagnosis were transferred to Microsoft Excel spreadsheet for data analysis. Simple proportions and percentages were used to analyze the data. All statistical analyses were conducted using Statistical Package for the Social Science version 21.0, IBM Inc., Chicago, Illinois, USA. Statistical significance was set at P ≤ 0.05. Results: The total ANC visits at Obio Cottage Hospital was 28,072, with 27% (7689) utilization of ultrasound scan. The mean age and range of parity of attendees were 32 ± 2.3 and 1–5, respectively. Of the total scans performed, 99.93% was routine, while 0.07% (5) was clinical-based (targeted). Normal findings were 7520 (97.8%) of antenatal scans recorded, while abnormal cases, multiple gestation, and uncertain diagnosis accounted for 121 (1.57%), 44 (0.57%), and 4 (0.06%), respectively. Conclusion: The present study has shown a considerable volume of obstetric ultrasound scan in this cottage hospital, albeit, with low utilization compared to the number of antenatal registration. Findings were mainly normal with minimal need for referral for advance care.

show abstract

“…About 34% of all global maternal deaths occur in Nigeria and India, making this topic a public health priority. [ 1 ] Access to AU services is limited in rural areas because of its nonavailability, the need to travel to urban areas, poor road networks, and high cost. [ 1 ] The cost of antenatal care, ultrasound services, and childbirth in rural Nigeria is put at $10–100/pregnancy, and the woman bears over 70% of this cost.…”

mentioning

confidence: 99%

Determinants of access to low-cost ultrasound services among pregnant women in rural areas of Keffi, Nigeria

Yakubu¹,

Banerjee

Letam

2021

Indian J Community Med

View full text Add to dashboard Cite

Fetal imaging and diagnosis services in developing countries – A call to action

Cited by 13 publications

References 2 publications

Development and evaluation of a machine learning-based point-of-care screening tool for genetic syndromes in children: a multinational retrospective study

Development and evaluation of a machine learning-based point-of-care screening tool for genetic syndromes in children: a multinational retrospective study

Utilization of obstetric ultrasonography and findings in a cottage hospital in Nigeria

Determinants of access to low-cost ultrasound services among pregnant women in rural areas of Keffi, Nigeria

Contact Info

Product

Resources

About