Comparison of quality and interpretation of newborn ultrasound screening examinations for developmental dysplasia of the hip by basically trained nurses and junior physicians with no previous ultrasound experience.

BACKGROUND: We are obliged to give babies the chance to profit from a nationwide screening of developmental dysplasia of the hip in very rural areas of Mongolia, where trained physicians are scarce. This study aimed to compare the quality and interpretation of hip ultrasound screening examinations performed by nurses and junior physicians. METHODS: A group of 6 nurses and 6 junior physician volunteers with no previous ultrasound experience underwent Graf's standard training in hands-on practice. Newborns were examined before discharge from the hospital, according to the national guideline. Two standard documentation images of each hip were saved digitally. The groups were compared on the proportion of good quality of sonograms and correct interpretation. Two Swiss supervisors' agreed diagnosis according to Graf was considered the final reference for the study purposes. RESULTS: A total of 201 newborns (402 hips or 804 sonograms) were examined in the study, with a mean age of 1.3±0.8 days at examination. Junior physicians examined 100 newborns (200 hips or 400 sonograms), while nurses examined 101 newborns (202 hips or 404 sonograms). The study subjects of the two groups were well balanced for the distribution of baseline characteristics. The study observed no statistically significant difference in the quality of Graf's standard plane images between the providers. Eventually, 92.0% (92) of the physician group and 89.1% (90) of the nurse group were correctly diagnosed as "Group A" (Graf's Type 1 hip) or "Non-Group A" hips (p = 0.484). The most common errors among the groups were a missing lower limb, wrong measurement lines, and technical problems. CONCLUSION: Our study provides evidence that while there might be a trend of slightly more technical mistakes in the nurse group, the overall diagnosis accuracy is similar to junior physicians after receiving standard training in Graf's hip ultrasound method. However, after basic training, regular quality control is a must and all participants should receive refresher trainings. More specifically, nurses need training in the identification of anatomical structures.

Evaluation of an Artificial Intelligence System for Retinopathy of Prematurity Screening in Nepal and Mongolia.

Purpose: To evaluate the performance of a deep learning (DL) algorithm for retinopathy of prematurity (ROP) screening in Nepal and Mongolia. Design: Retrospective analysis of prospectively collected clinical data. Participants: Clinical information and fundus images were obtained from infants in 2 ROP screening programs in Nepal and Mongolia. Methods: Fundus images were obtained using the Forus 3nethra neo (Forus Health) in Nepal and the RetCam Portable (Natus Medical, Inc.) in Mongolia. The overall severity of ROP was determined from the medical record using the International Classification of ROP (ICROP). The presence of plus disease was determined independently in each image using a reference standard diagnosis. The Imaging and Informatics for ROP (i-ROP) DL algorithm was trained on images from the RetCam to classify plus disease and to assign a vascular severity score (VSS) from 1 through 9. Main Outcome Measures: Area under the receiver operating characteristic curve and area under the precision-recall curve for the presence of plus disease or type 1 ROP and association between VSS and ICROP disease category. Results: The prevalence of type 1 ROP was found to be higher in Mongolia (14.0%) than in Nepal (2.2%; P < 0.001) in these data sets. In Mongolia (RetCam images), the area under the receiver operating characteristic curve for examination-level plus disease detection was 0.968, and the area under the precision-recall curve was 0.823. In Nepal (Forus images), these values were 0.999 and 0.993, respectively. The ROP VSS was associated with ICROP classification in both datasets (P < 0.001). At the population level, the median VSS was found to be higher in Mongolia (2.7; interquartile range [IQR], 1.3-5.4]) as compared with Nepal (1.9; IQR, 1.2-3.4; P < 0.001). Conclusions: These data provide preliminary evidence of the effectiveness of the i-ROP DL algorithm for ROP screening in neonatal populations in Nepal and Mongolia using multiple camera systems and are useful for consideration in future clinical implementation of artificial intelligence-based ROP screening in low- and middle-income countries.

External Validation of a Retinopathy of Prematurity Screening Model Using Artificial Intelligence in 3 Low- and Middle-Income Populations.

Importance: Retinopathy of prematurity (ROP) is a leading cause of preventable blindness that disproportionately affects children born in low- and middle-income countries (LMICs). In-person and telemedical screening examinations can reduce this risk but are challenging to implement in LMICs owing to the multitude of at-risk infants and lack of trained ophthalmologists. Objective: To implement an ROP risk model using retinal images from a single baseline examination to identify infants who will develop treatment-requiring (TR)-ROP in LMIC telemedicine programs. Design, Setting, and Participants: In this diagnostic study conducted from February 1, 2019, to June 30, 2021, retinal fundus images were collected from infants as part of an Indian ROP telemedicine screening program. An artificial intelligence (AI)-derived vascular severity score (VSS) was obtained from images from the first examination after 30 weeks' postmenstrual age. Using 5-fold cross-validation, logistic regression models were trained on 2 variables (gestational age and VSS) for prediction of TR-ROP. The model was externally validated on test data sets from India, Nepal, and Mongolia. Data were analyzed from October 20, 2021, to April 20, 2022. Main Outcomes and Measures: Primary outcome measures included sensitivity, specificity, positive predictive value, and negative predictive value for predictions of future occurrences of TR-ROP; the number of weeks before clinical diagnosis when a prediction was made; and the potential reduction in number of examinations required. Results: A total of 3760 infants (median [IQR] postmenstrual age, 37 [5] weeks; 1950 male infants [51.9%]) were included in the study. The diagnostic model had a sensitivity and specificity, respectively, for each of the data sets as follows: India, 100.0% (95% CI, 87.2%-100.0%) and 63.3% (95% CI, 59.7%-66.8%); Nepal, 100.0% (95% CI, 54.1%-100.0%) and 77.8% (95% CI, 72.9%-82.2%); and Mongolia, 100.0% (95% CI, 93.3%-100.0%) and 45.8% (95% CI, 39.7%-52.1%). With the AI model, infants with TR-ROP were identified a median (IQR) of 2.0 (0-11) weeks before TR-ROP diagnosis in India, 0.5 (0-2.0) weeks before TR-ROP diagnosis in Nepal, and 0 (0-5.0) weeks before TR-ROP diagnosis in Mongolia. If low-risk infants were never screened again, the population could be effectively screened with 45.0% (India, 664/1476), 38.4% (Nepal, 151/393), and 51.3% (Mongolia, 266/519) fewer examinations required. Conclusions and Relevance: Results of this diagnostic study suggest that there were 2 advantages to implementation of this risk model: (1) the number of examinations for low-risk infants could be reduced without missing cases of TR-ROP, and (2) high-risk infants could be identified and closely monitored before development of TR-ROP.

Accuracy of Trained Physicians is Inferior to Deep Learning-Based Algorithm for Determining Angles in Ultrasound of the Newborn Hip.

PURPOSE: Sonographic diagnosis of developmental dysplasia of the hip allows treatment with a flexion-abduction orthosis preventing hip luxation. Accurate determination of alpha and beta angles according to Graf is crucial for correct diagnosis. It is unclear if algorithms could predict the angles. We aimed to compare the accuracy for users and automation reporting root mean squared errors (RMSE). MATERIALS AND METHODS: We used 303 306 ultrasound images of newborn hips collected between 2009 and 2016 in screening consultations. Trained physicians labelled every second image with alpha and beta angles during the consultations. A random subset of images was labeled with time and precision under lab conditions as ground truth. Automation predicted the two angles using a convolutional neural network (CNN). The analysis was focused on the alpha angle. RESULTS: Three methods were implemented, each with a different abstraction of the problem: (1) CNNs that directly learn the angles without any post-processing steps; (2) CNNs that return the relevant landmarks in the image to identify the angles; (3) CNNs that return the base line, bony roof line, and the cartilage roof line which are necessary to calculate the angles. The RMSE between physicians and ground truth were found to be 7.1° for alpha. The best CNN architecture was (2) landmark detection. The RMSE between landmark detection and ground truth was 3.9° for alpha. CONCLUSION: The accuracy of physicians in their daily routine is inferior to deep learning-based algorithms for determining angles in ultrasound of the newborn hip. Similar methods could be used to support physicians.

Traditional Mongolian swaddling and developmental dysplasia of the hip: a randomized controlled trial.

BACKGROUND: Mongolian traditional swaddling of infants, where arms and legs are extended with a tight wrapping and hips are in adduction position, may lead to abnormal maturation and formation of the hip joint; and is a contributing factor for developmental dysplasia of the hip (DDH). This hypothesis was tested in this randomized controlled trial. METHODS: Eighty newborns with one or two hips at risk of worsening to DDH (Graf Type 2a; physiologically immature hips) at birth were randomized into 2 groups at a tertiary hospital in Ulaanbaatar. The "swaddling" group (n = 40) was swaddled in the common traditional Mongolian method for a month while the "non-swaddling" group (n = 40) was instructed not to swaddle at all. All enrollees were followed up on monthly basis by hip ultrasound and treated with an abduction-flexion splint if necessary. The groups were compared on the rate of Graf's "non-Type 1" hips at follow-up controls as the primary outcome. Secondary outcomes were rate of DDH and time to discharge (Graf Type 1; healthy hips). In addition, correlation between the primary outcome and swaddling length in days and frequency of swaddling in hours per day were calculated. RESULTS: Recruitment continued from September 2019 to March 2020 and follow-up data were completed in June 2020. We collected final outcome data in all 80 enrollees. Percentages of cases with non-Type 1 hip at any follow-up examination were 7.5% (3/40) in the non-swaddling group and 40% (16/40) in the swaddling group (p = 0.001). There was no DDH case in the non-swaddling group while there were 8 cases of DDH in the swaddling group. The mean time to discharge was 5.1 ± 0.3 weeks in the non-swaddling group and 8.4 ± 0.89 weeks in the swaddling group (p = 0.001). There is a correlation between the primary outcome and the swaddling frequency in hours per day (r = 0.81) and swaddling length in days (r = 0.43). CONCLUSIONS: Mongolian traditional swaddling where legs are extended and hips are in extension and adduction position increases the risk for DDH. TRIAL REGISTRATION: Retrospectively registered, ISRCTN11228572 .

Implementation of a nationwide universal ultrasound screening programme for developmental dysplasia of the neonatal hip in Mongolia.

PURPOSE: Mongolia is the first Asian country to launch universal ultrasound screening for newborns with developmental dysplasia of the hip (DDH). The aims of this study were to determine the coverage and treatment rate of this programme. METHODS: Data from birth statistics and ultrasound hip screening from 29 hospitals were retrospectively reviewed (2010 to 2016, pre-nationwide phase; and 2017 to 2019, nationwide programme). DDH was diagnosed using the Graf-technique and treated according to 'ABCD', a modified Graf classification (Group A: Graf Type 1, mature; B: 2a, physiologically immature; C: 2c to 3, early DDH; D: 4, dislocated). Group B children were followed with monthly ultrasound. Group C and D children were treated with a flexion and abduction orthosis (Tübingen). Screeners used a web-based platform to upload images for quality surveillance. RESULTS: Between 2017 and 2019, 230 079 live births were registered and 176 388 newborns screened. The nationwide screening coverage rate in newborns increased from 73.6% in 2017 to 82.1% in 2019. Group A (148 510 children, 84.2%) was discharged, while Group B (25 820, 14.6%) was followed. Among children in Group B, 284 cases worsened to Group C and were, therefore, treated with a Tübingen orthosis. The remaining 2058 (1.2%) of newborns with DDH were treated with a Tübingen orthosis, including 1999 newborns in Group C and 59 in Group D. Since 2017, a total of 142 860 (81.0%) hip sonograms were uploaded to the platform. CONCLUSION: A simplified diagnostic and therapeutic framework for ultrasound DDH screening for newborns was successfully deployed in Mongolia, a developing country, providing high surveillance coverage and appropriate treatment.Level of evidence: IV.

Incidence and treatment of developmental hip dysplasia in Mongolia: a prospective cohort study.

BACKGROUND: In Mongolia, adequate early diagnosis and treatment of developmental hip dysplasia (DDH) have been unavailable and its incidence was unknown. We determined the incidence of ultrasonographic DDH in newborns and established adequate procedures for diagnosis and treatment of DDH at the largest maternity hospital in Ulaanbaatar, Mongolia. METHODOLOGY/PRINCIPAL FINDINGS: During one year (Sept 2010 - Aug 2011) we assessed the hips newborns using ultrasound and Graf's classification of DDH. 8,356 newborns were screened; median age at screening was 1 day. We identified 14,873 Type 1 (89.0%), 1715 Type 2a (10.3%), 36 Type 2c (0.2%), 70 Type D (0.4%), 14 Type 3 (0.08%), and 4 Type 4 hips (0.02%). Children with Type 1 hips (normal) were discharged. Children with Type 2a hips (physiologically immature) received follow-up ultrasounds at monthly intervals. Children with Type 2c to 4 (DDH; deformed or misaligned hip joint) hips were treated with a Tubingen hip flexion splint and also followed up. The hip abnormalities resolved to mature hips in all children who were followed up. There was no evidence for severe treatment related complications. CONCLUSION/SIGNIFICANCE: This study suggests that the incidence of DDH in Mongolian neonates is comparable to that in neonates in Europe. Early ultrasound-based assessment and splinting treatment of DDH led to mature hips in all children followed up. Procedures are feasible and will be continued.

Feasibility of one-stop antenatal syphilis screening in Ulaanbaatar, Mongolia: women and providers perspectives.

Congenital syphilis can be prevented by antenatal syphilis screening, however, the complexity of delivering prenatal service can result in low screening rates, and thus lower prevention and treatment rates. One-stop antenatal syphilis screening, which includes rapid testing and treatment, is the proposed method to overcome this problem. The feasibility of this type of screening needs to be tested to dertermine its effectiveness. In this study, the opinions and level of satisfaction of women undergoing antenatal care and their health care providers regarding a one-stop syphylis screening and treatment service at two antenatal clinics in Ulaanbaatar, Mongolia were assessed. The majority of the 246 women studied were satisfied with the service. The mean aggregate satisfaction score derived from 12 questions regarding specific aspects of satisfaction was 3.2. Most providers were also satisfied, not reporting any significant problems interfering with routine antenatal care. However, all providers felt the one-stop service is time consuming and leads to high staff workloads and needs good clinical management. The provider preferred instead to treat husbands presumptively to avoid the possibility of diagnosing couples with discordant syphilis, which could lead to possible violence. A one-stop syphilis diagnosis and treatment service during antenatal care is feasible in Ulaanbaatar, Mongolia from both the women's and providers' perspectives.

One-stop service for antenatal syphilis screening and prevention of congenital syphilis in Ulaanbaatar, Mongolia: a cluster randomized trial.

BACKGROUND: This cluster randomized trial was performed to test whether one-stop service could better prevent congenital syphilis than the conventional antenatal screening service in Mongolia. METHODS: Out of 14 antenatal clinics in 6 districts of Ulaanbaatar, 7 were randomly selected for the one-stop service and the remaining for the conventional service. Intervention clinics provided on-site rapid syphilis testing and immediate treatment for positive cases and their partners. In control clinics, syphilis screening services with routine off-site rapid plasma regain testing and case management were followed. Analysis was intention to treat. RESULTS: Of 3850 antenatal women recruited in each group, the proportion of syphilis testing at the first visit and third trimester was over 99% in the intervention group and 79.6% and 61.5% in the control group, respectively (P <0.001 for both periods). Correspondingly, syphilis cases detected in the intervention group were 73 (1.9%) and 20 (0.5%) for the first visit and third trimester, respectively, and 27 (0.9%) and 2 (0.08%) in the control group; and 98.9% (92/93) of the detected cases in the intervention group and 89.6% (26/29) in the control group were adequately treated (P = 0.02). The corresponding treatment rates for sexual partners were 94.6% and 55.2% (P <0.001). One congenital syphilis case out of 3632 deliveries in the intervention group, compared to 15 of 3552 in the control group, was diagnosed, a reduction of 93.5% (95% confidence interval, 66.0%-98.6%). CONCLUSIONS: One-stop services increased the detection rate of syphilis, treated more positive women and their partners, and effectively reduced the rate of congenital syphilis.

Coverage of antenatal syphilis screening and predictors for not being screened in Ulaanbaatar, Mongolia.

OBJECTIVES: To measure the coverage of antenatal syphilis screening and identify factors related to women not being screened. GOAL: To assess the syphilis control program in Mongolia. STUDY DESIGN: Antenatal care records of women in 16 antenatal care clinics of 6 districts were reviewed. Additionally, postpartum women were interviewed to identify potential factors for not being screened. RESULTS: Among 3,519 antenatal records, the coverage of syphilis screening was 77.7%. Of 2,735 screened women, 54 (2.0%) had reactive serological results and subsequently received treatment. Four late antenatal care comers delivered infants with congenital syphilis. Being unscreened was significantly associated with late antenatal care (odds ratio OR=2.6), lack of knowledge (OR=5.5), history of previous sexually transmitted infection (OR=3.7), and living far from screening services (OR=4.9). CONCLUSIONS: The coverage of antenatal syphilis screening is still low, with poor contact tracing. More efforts are needed to promote early antenatal care visit and improve syphilis screening systems.

Antenatal care providers' practices and opinions on the services of antenatal syphilis screening in Ulaanbaatar, Mongolia.

The objectives of this study were to review antenatal syphilis screening and to assess antenatal care providers' practices and opinions in Ulaanbaatar, Mongolia. A cross-sectional study on antenatal syphilis screening was conducted. The study settings were all 16 antenatal care clinics, and a random selection of 30 family units from six districts in Ulaanbaatar, Mongolia. Interviews were conducted with 150 antenatal care providers and 27 antenatal care heads/leaders. Antenatal syphilis screening in Ulaanbaatar was complex. Most pregnant women had antenatal care at family units or antenatal clinics, but syphilis blood testing could be performed only in some district general hospitals. Syphilis positive-screening cases were referred to the venereologists for confirmation of results, appropriate treatment, contact tracing, and follow-up. The providers agreed with the need for syphilis screening in pregnant women but identified as constraints the limited time for performing the screening due to late antenatal visit, women's lack of knowledge, poverty, and geographic barriers. The practice of providers varied, and the opinion on a one-stop service was positive. The main conclusions concerning the failure of universal antenatal syphilis screening were limited accessibility and feasibility of the service, and the ignorance of both women and providers on the importance of screening. It was agreed that decentralization of antenatal syphilis screening would improve the system.