Sildenafil for pulmonary hypertension in neonates: An updated systematic review and meta-analysis

OBJECTIVES

To provide an updated review and meta-analysis on the efficacy and safety of sildenafil for treating persistent pulmonary hypertension in neonates (PPHN).

METHODS

PubMed/Medline, SCOPUS, Cochrane Central Register of Controlled Trials, and Web of Science were searched from the inception of publication to January 2021. The principal outcomes include oxygenation parameters, hemodynamic metrics and echocardiographic measurements, as well as adverse outcomes.

RESULTS

A total of eight studies were included with 216 term and premature neonates with PPHN. Compelling evidence showed the use of sildenafil could improve the prognosis of PPHN neonates, compared with baseline or placebo in neonates with PPHN, and a time-dependent pattern of the improvements can be observed. After 24 h of treatment, the Oxygenation index suggested a steady decrease (SD: -1.80, 95% confidence interval [CI]: -2.92, -0.67) and sildenafil exerted peak effects after 72 h of treatment (SD: -4.02, 95% CI: -5.45, -2.59). No clinically significant side effects were identified. Egger's test and funnel plots of the major outcomes were performed, and the publication bias was not significant.

CONCLUSION

Improvements were shown in oxygenation index, pulmonary arterial pressure, and adverse outcomes after using sildenafil for PPHN in neonates. However, future research with robust longitudinal or randomized controlled design is still needed.

DNA polymerase β may be involved in protecting human bronchial epithelial cells from the toxic effects induced by methyl tert-butyl ether exposure

Methyl tert-butyl ether (MTBE), a widely used gasoline additive and a ubiquitous environmental pollutant in many countries and regions, can cause various kinds of toxic effects on human health. However, the molecular mechanism underlying its toxic effects remains elusive. The present study aimed to explore the cytotoxicity, DNA damage and oxidative damage effects of MTBE on human bronchial epithelial cells (16HBE) and the possible role of DNA polymerase β (pol-β) in this process. RNA interference (RNAi) was used to obtain pol-β gene knocked-down cells (pol-β^-). CCK-8 assay was adopted to analyze the cell viability. Alkaline single-cell gel electrophoresis (SCGE) was performed to detect the DNA damage effects of MTBE. The enzyme activity of GSH-Px, SOD, CAT and the level of MDA were assessed. The data indicated that when treated with MTBE at the concentration exceeding 50 μmol/L and for the time exceeding 24 h, the pol-β^- exhibited significantly decreased cell viability and increased DNA damage effects, as compared to the control (P < 0.05). Furthermore, there was significant difference in the levels of GSH-pX, SOD, CAT and MDA between the pol-β^- and the control (P < 0.05). Our investigation suggests that MTBE can cause obvious cytotoxicity, DNA damage and oxidative damage effects on 16HBE cells. DNA polymerase β may be involved in protecting 16HBE cells from the toxic effects induced by MTBE exposure. These findings provide a novel insight into the molecular mechanism underlying the toxic effects of MTBE on human cells.

A Comparison of Vaccine Hesitancy of COVID-19 Vaccination in China and the United States

OBJECTIVES

To investigate the differences in vaccine hesitancy and preference of the currently available COVID-19 vaccines between two countries, namely, China and the United States (U.S.).

METHOD

A cross-national survey was conducted in both China and the United States, and discrete choice experiments, as well as Likert scales, were utilized to assess vaccine preference and the underlying factors contributing to vaccination acceptance. Propensity score matching (PSM) was performed to enable a direct comparison between the two countries.

RESULTS

A total of 9077 (5375 and 3702 from China and the United States, respectively) respondents completed the survey. After propensity score matching, over 82.0% of respondents from China positively accepted the COVID-19 vaccination, while 72.2% of respondents from the United States positively accepted it. Specifically, only 31.9% of Chinese respondents were recommended by a doctor to have COVID-19 vaccination, while more than half of the U.S. respondents were recommended by a doctor (50.2%), local health board (59.4%), or friends and families (64.8%). The discrete choice experiments revealed that respondents from the United States attached the greatest importance to the efficacy of COVID-19 vaccines (44.41%), followed by the cost of vaccination (29.57%), whereas those from China held a different viewpoint, that the cost of vaccination covered the largest proportion in their trade-off (30.66%), and efficacy ranked as the second most important attribute (26.34%). Additionally, respondents from China tended to be much more concerned about the adverse effect of vaccination (19.68% vs. 6.12%) and have a lower perceived severity of being infected with COVID-19.

CONCLUSION

Although the overall acceptance and hesitancy of COVID-19 vaccination in both countries are high, underpinned distinctions between these countries were observed. Owing to the differences in COVID-19 incidence rates, cultural backgrounds, and the availability of specific COVID-19 vaccines in the two countries, vaccine rollout strategies should be nation-dependent.

Design and implementation of a portable diagnostic system for Thomson scattering and optical emission spectroscopy measurements

A diagnostic system, which has a design goal of high-portability, has been designed at Oak Ridge National Laboratory (ORNL). This project aims at providing measurements of key plasma parameters (n_e, T_e, n_i, T_i) for fusion-relevant devices, utilizing Thomson scattering (TS) and optical emission spectroscopy (OES). The innovative design employs mostly commercial off-the-shelf instrumentation and a traveling team of researchers to conduct measurements at various magnetic-confinement plasma devices. The TS diagnostic uses a Quantel Q-smart 1500 Nd:YAG laser with a 2ω harmonic generator to produce up to 850 mJ of 532 nm laser pulses at 10 Hz. Collection optics placed at the detection port consists of an 11 × 3 optical fiber bundle, where the TS diagnostic uses an 11 × 1 subset array of the fibers, the OES diagnostic uses another 11 fibers, and the remaining fibers are available to the host institution. The detection system is comprised of two separate IsoPlane-320 spectrometers with triple-grating turrets of various line spacing and two PI-MAX 4 intensified CCD detectors, used simultaneously to measure a broad range of ion, impurity, and electron parameters. The self-contained diagnostic package also includes a data processing and storage system. The design and initial implementation of the TS-OES diagnostic system are described. The experiments from the proof-of-principle operation of the portable package on a high density (∼2.5 × 10²² m^-3) and low-temperature (∼5 eV) electrothermal arc source at ORNL are also discussed.

Metagenomic analysis revealed the individualized shift in ileal microbiome of neonatal calves in response to delaying the first colostrum feeding

The aim of this study was to explore the effect of colostrum feeding time on the ileal microbiome of neonatal calves. In this study, 22 male Holstein calves were randomly assigned to different colostrum feeding time treatments: after birth (at 45 min, n = 7); at 6 h after birth (n = 8); and at 12 h after birth (TRT12h; n = 7). At 51 h after birth, calves were killed and ileum digesta was collected for microbiome analysis using shotgun metagenomic sequencing. Bacteria, archaea, eukaryotes, and viruses were identified from the ileum microbiome. For the bacteriome, Firmicutes and Proteobacteria were the predominant phyla, and Escherichia, Streptococcus, Lactobacillus were the 3 most abundant genera. For the archaeal community, Euryarchaeota and Crenarchaeota were the 2 major phyla, and Methanosarcina, Methanobrevibacter, and Methanocorpusculum were the 3 most abundant genera. In total, 116 Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways were identified from the ileal microbiome, with "biosynthesis of vancomycin group antibiotics," "biosynthesis of ansamycins," "valine, leucine, and isoleucine biosynthesis," "ribosome," and "d-alanine metabolism" as the top 5 functions. When the ileal microbiomes were compared among the 3 treatments, the relative abundance of Enterococcus was higher in TRT12h calves, suggesting that calves may have a higher abundance of opportunistic pathogens when the feeding of colostrum is delayed for 12 h. Moreover, among all KEGG pathways, the enriched "taurine and hypotaurine metabolism" (KO00430) pathway was identified in the ileal microbiome of TRT12h calves; however, future studies are needed to understand the effect on the host. Additionally, 2 distinct ileal microbial profiles were identified across all samples, indicating that that host factors may play a significant role in driving varied microbiome changes in response to colostrum feeding time. Whether such microbiome shifts affect long-term gut function and calf performance warrants future studies.

Indoor heat exposure in Baltimore: does outdoor temperature matter?

Heat exposure of a population is often estimated by applying temperatures from outdoor monitoring stations. However, this can lead to exposure misclassification if residents do not live close to the monitoring station and temperature varies over small spatial scales due to land use/built environment variability, or if residents generally spend more time indoors than outdoors. Here, we compare summertime temperatures measured inside 145 homes in low-income households in Baltimore city with temperatures from the National Weather Service weather station in Baltimore. There is a large variation in indoor temperatures, with daily-mean indoor temperatures varying from 10 °C lower to 10 °C higher than outdoor temperatures. Furthermore, there is only a weak association between the indoor and outdoor temperatures across all houses, indicating that the outdoor temperature is not a good predictor of the indoor temperature for the residences sampled. It is shown that much of the variation is due to differences in the availability of air conditioning (AC). Houses with central AC are generally cooler than outdoors (median difference of - 3.4 °C) while those with no AC are generally warmer (median difference of 1.4 °C). For the collection of houses with central or room AC, there is essentially no relationship between indoor and outdoor temperatures, but for the subset of houses with no AC, there is a weak relationship (correlation coefficient of 0.36). The results presented here suggest future epidemiological studies of indoor exposure to heat would benefit from information on the availability of AC within the population.

Absence of heterozygosity detected by single-nucleotide polymorphism array in prenatal diagnosis

OBJECTIVES

To investigate the general occurrence and clinical significance of absence of heterozygosity (AOH), detected by single-nucleotide polymorphism (SNP) array on prenatal diagnosis.

METHODS

We recruited pregnancies undergoing invasive prenatal diagnosis at our fetal medicine center over a 6-year period. All fetuses underwent SNP array using the Affymetrix CytoScan HD array platform. AOH was defined as a chromosomal homozygosity segment with neutral copy number. Cases with AOH over 10 Mb in size or with suspected pathogenicity were further analyzed, and the clinical features and outcome were reviewed.

RESULTS

Of 10 294 recruited fetuses, 100 (0.97%) with AOH were identified; in 81 (81.0%) of these, AOH occurred in a single chromosome, while 19 (19.0%) patients had multiple AOHs in different chromosomes. AOH was observed in all chromosomes, chromosomes X, 2 and 16 being the most frequently involved. The length of AOH ranged from partial chromosome (9.002-80.222 Mb) to the entire chromosome. Similar AOH regions displayed varied clinical manifestations. In total, 55 patients presented with concomitant ultrasound abnormalities, the most common being multiple abnormalities (14/55 (25.5%)), genitourinary malformations (8/55 (14.5%)), skeletal malformations (5/55 (9.1%)) and small-for-gestational age (5/55 (9.1%)). Notably, the rate of adverse perinatal outcome (including termination of pregnancy, neonatal death, fetal death, selective reduction and miscarriage) in fetuses with AOH and ultrasound abnormalities (30/48 (62.5%)) was higher than in those without ultrasound abnormalities (6/40 (15.0%)) (P < 0.001). Further non-invasive prenatal testing using cell-free fetal DNA from maternal blood indicated chromosomal copy number abnormalities in 11 patients; however, they were confirmed as AOH by SNP array of the amniotic fluid.

CONCLUSIONS

Genetic counseling regarding a prenatal diagnosis of AOH remains challenging. To evaluate comprehensively its significance, we propose a management strategy involving further serial ultrasound examinations, parental verification, whole-exome sequencing, placental study and effective follow-up. Copyright © 2019 ISUOG. Published by John Wiley & Sons Ltd.

The Influence of Average Temperature and Relative Humidity on New Cases of COVID-19: Time-Series Analysis

BACKGROUND

The influence of meteorological factors on the transmission and spread of COVID-19 is of interest and has not been investigated.

OBJECTIVE

This study aimed to investigate the associations between meteorological factors and the daily number of new cases of COVID-19 in 9 Asian cities.

METHODS

Pearson correlation and generalized additive modeling (GAM) were performed to assess the relationships between daily new COVID-19 cases and meteorological factors (daily average temperature and relative humidity) with the most updated data currently available.

RESULTS

The Pearson correlation showed that daily new confirmed cases of COVID-19 were more correlated with the average temperature than with relative humidity. Daily new confirmed cases were negatively correlated with the average temperature in Beijing (r=-0.565, P<.001), Shanghai (r=-0.47, P<.001), and Guangzhou (r=-0.53, P<.001). In Japan, however, a positive correlation was observed (r=0.416, P<.001). In most of the cities (Shanghai, Guangzhou, Hong Kong, Seoul, Tokyo, and Kuala Lumpur), GAM analysis showed the number of daily new confirmed cases to be positively associated with both average temperature and relative humidity, especially using lagged 3D modeling where the positive influence of temperature on daily new confirmed cases was discerned in 5 cities (exceptions: Beijing, Wuhan, Korea, and Malaysia). Moreover, the sensitivity analysis showed, by incorporating the city grade and public health measures into the model, that higher temperatures can increase daily new case numbers (beta=0.073, Z=11.594, P<.001) in the lagged 3-day model.

CONCLUSIONS

The findings suggest that increased temperature yield increases in daily new cases of COVID-19. Hence, large-scale public health measures and expanded regional research are still required until a vaccine becomes widely available and herd immunity is established.

The use of methylprednisolone in COVID-19 patients: A propensity score matched retrospective cohort study

PURPOSE

To evaluate the efficacy and safety of methylprednisolone in treating the coronavirus disease 2019 (COVID-19) patients.

METHODS

A retrospective cohort study was conducted, and all COVID-19 patients were recruited who were admitted to the Yichang Third People's Hospital from February 1st to March 31st, 2020. One-to-one propensity score matching (PSM) was used for minimizing confounding effects. The primary outcome was hospital mortality, with the secondary outcomes being the time needed for a positive SARS-CoV-2 nucleic acid test to turn negative and the length of hospital stay.

RESULTS

Totaling 367 patients with COVID-19 hospitalized at the Yichang Third People's Hospital were identified, of whom 276 were mild or stable COVID-19, and 67 were serious or critically ill. Among them, 255 patients were treated using methylprednisolone, and 188 did not receive any corticosteroid-related treatment. After PSM, no statistically significant difference was found in the baseline characteristics between the two groups. Regarding the outcomes, there also were no statistically significant difference between the two groups. Patients without the use of methylprednisolone were more quickly to obtain negative results of their nasopharyngeal swab tests of SARS-CoV-2 nucleic acid after treatment, compared to those receiving methylprednisolone.

CONCLUSION

Methylprednisolone could not improve the prognosis of patients with COVID-19, and the efficacy and safety of the use of methylprednisolone in patients with COVID-19 still remain uncertain, thus the use of corticosteroids clinically in patients with COVID-19 should be with cautions.

Where does fear originate in the brain? A coordinate-based meta-analysis of explicit and implicit fear processing

Processing of fear is of crucial importance for human survival and it can generally occur at explicit and implicit conditions. It is worth noting that explicit and implicit fear processing produces different behavioral and neurophysiological outcomes. The present study capitalizes on the Activation Likelihood Estimation (ALE) method of meta-analysis to identify: (a) the "core" network of fear processing in healthy individuals; (b) common and specific neural activations associated with explicit and implicit processing of fear. Following PRISMA guidelines, a total of 92 fMRI and PET studies were included in the meta-analysis. The overall analysis show that the core fear network comprises the amygdala, pulvinar, and fronto-occipital regions. Both implicit and explicit fear processing activated amygdala, declive, fusiform gyrus, and middle frontal gyrus, suggesting that these two types of fear processing share a common neural substrate. Explicit fear processing elicited more activations at the pulvinar and parahippocampal gyrus, suggesting visual attention/orientation and contextual association play important roles during explicit fear processing. In contrast, implicit fear processing elicited more activations at the cerebellum-amygdala-cortical pathway, indicating an 'alarm' system underlying implicit fear processing. These findings have shed light on the neural mechanism underlying fear processing at different levels of awareness.

Perceived Effectiveness, Safety, and Attitudes Toward the Use of Nucleic Tests of SARS-CoV-2 Among Clinicians and General Public in China

Objective: To assess whether there is a knowledge gap about the use of test kits for residents and to explore the knowledge, attitudes, and practices of using test kits in China during the coronavirus disease 2019 (COVID-19) epidemic. Method: An online-based, nationwide, and cross-sectional study was conducted. A total of 1,167 respondents were recruited from June 19 to July 2, 2020. All participants completed a validated questionnaire written in Chinese. Electronic consent was obtained from all participants upon their agreement to commence the questionnaire. Perceived efficacy, safety, and their attitudes toward the use of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) testing kits were measured. Result: The majority of the study respondents were female [749 (64.2%)], aged 31-40 years old [372 (31.9%)], and located in mainland China [1,137 (97.4%)]. The majority of the respondents held a positive view toward the introduction of the fast-track approval policy for novel coronavirus testing products (6.16 ± 1.30) as well as toward putting more investment in scientific research and biomedicine to improve the detection accuracy of detection kits (5.94 ± 1.55) in China. The respondents valued the detection accuracy more as opposed to the detection time of the testing kits (4.66 ± 2.00), whereas few participants agreed that in the research and development process, detection accuracy could be sacrificed to speed up production and coverage capacity (3.02 ± 2.04). Conclusion: The majority of the participants have a basic knowledge of the detection methods of the SARS-CoV-2 virus and the types of test kits, as well as great confidence in China's domestic production of test kits and decisions. However, how basic knowledge, high compliance, and positive attitudes play a role in easing the tension of the pandemic still remains unknown.

Psychobehavioral Responses, Post-Traumatic Stress and Depression in Pregnancy During the Early Phase of COVID-19 Outbreak

Objective

The novel coronavirus disease (COVID-19) outbreak has aroused a range of negative effects. Such considerable influence can be greater in vulnerable populations including pregnant women. This study aimed to assess the presence of prenatal depression (PND, as an important risk factor of postpartum depression) and post-traumatic stress disorder (PTSD) and to characterize infection-induced preventive behaviors and psychological responses in the early phase of COVID-19 outbreak.

Methods

Based on a population-based sample of pregnant women from all regions in China, presence of probable PND and suspected PTSD were assessed using the Edinburgh Postnatal Depression Scale (≥13) and the PTSD Checklist (≥14), respectively. A web-based questionnaire was used to assess psychological and behavioral responses to COVID-19.

Results

Among a total of 1908 questionnaires returned, 1901 women provided valid data (mean [SD] age, 28.9 [4.7] years). High prevalence of probable PND (34%) and suspected PTSD (40%) among pregnant women was observed. Those with suspected PTSD presented six times higher risk of probable PND than the non-suspected (OR=7.83, 95% CI: 6.29-9.75; p<0.001). Most women (91%-96%) reported anxiousness about infection of themselves and the members within their social network. Lack of security and loss of freedom were reported in approximately two-thirds of pregnant women. More frequent preventive behaviors, including handwashing, use of facemasks, and staying at home, were undertaken in more than 80% of the sample. Anxiousness of miscarriage and preterm birth were prevalent (>75%).

Conclusions

High prevalence of PND and PTSD and high levels of anxiety suggest profound impacts of the present outbreak on mental health. This calls for special attention and support for vulnerable populations. Mental health care should become part of public health measures during the present outbreak and should continue to be intensified to empower the health system for post-outbreak periods.

Abstract PR-010: Blinded and meta-analysis validation of an improved serological test for PDAC using the combination of CA19-9 and the sTRA glycan

Improvements in the clinical outcomes of pancreatic cancer patients may be achieved if physicians could identify the disease earlier. Recent studies demonstrated the promise of a biomarker panel is a simple combination between CA19-9 and another marker called sTRA, so named because it detects the sialylated version of the glycan bound by the TRA-1-60 (tumor-related antigen) antibody. The sTRA glycan is structurally related to the CA19-9 antigen and is produced by a different subtype of cancer cells than make CA19-9. We hypothesized that, among patients with PDAC, different patients have plasma elevations in CA19-9 than have plasma elevations in sTRA, and that as a result, a panel comprising the two markers detects more cancers at high specificity (low false-positive rate) than either marker alone. To test this hypothesis, we analyzed the relationships and biomarker performance of CA19-9 and sTRA across seven different datasets, encompassing 729 patient samples collected from four different clinical centers. We tested whether unique elevation occurred for each marker in each dataset, and whether the combination of markers performed better than then individual markers for distinguishing PDAC from healthy subjects and from benign pancreatic disease. We observed complementary elevations of sTRA or CA19-9 in the PDAC patients in each dataset. A two-marker panel composed of CA19-9 and sTRA and a three-marker panel composed of CA19-9 and two versions of the sTRA immunoassay gave statistically significant improvements over CA19-9 across the datasets for distinguishing PDAC from non-PDAC samples (healthy, chronic pancreatitis, pancreatic cyst, and biliary stricture/stones). At 95% specificity, sensitivity was improved from 36-55% across datasets for CA19-9 to 61-67% across datasets for the three-marker panel. The lead panel further showed 95% specificity and 61% sensitivity using blinded calls on another validation set (N = 340). This analysis serves as broad support for an improved serological test for PDAC using the combination of CA19-9 and sTRA. In light of this level of validation, the lead panel could be considered the most promising panel from the currently available information. If further validated using clinical assays, it may be good enough for surveillance among patients with increased risk for PDAC, in combination with follow-up modalities to establish diagnosis.

Citation Format: Ying Liu, Ben Staal, Daniel Barnett, Zonglin He, Chongfeng Gao, Mark Hurd, Pamela Bartlett, Aatur Singhi, J. Bradley Morrow, Gregory Cote, Anirban Maitra, Ying Huang, Randall Brand, Brian Haab. Blinded and meta-analysis validation of an improved serological test for PDAC using the combination of CA19-9 and the sTRA glycan [abstract]. In: Proceedings of the AACR Virtual Special Conference on Pancreatic Cancer; 2020 Sep 29-30. Philadelphia (PA): AACR; Cancer Res 2020;80(22 Suppl):Abstract nr PR-010.

The association between secondhand smoke and childhood asthma: A systematic review and meta-analysis

BACKGROUND

Secondhand smoke (SHS) exposure can trigger asthma exacerbations in children. Different studies have linked increased asthma symptoms and even deaths in children with SHS, but the risk has not been quantified uniformly across studies. We aimed to investigate the role of SHS exposure as a risk factor of asthma among children.

METHODS

We performed a systematic review in PubMed, Scopus, and Google Scholar from June 1975 to 10 March 2020. We included cohort, case-control, and cross-sectional studies reporting odds ratio (OR) or relative risk estimates and confidence intervals of all types of SHS exposure and childhood asthma.

RESULTS

Of the 26 970 studies identified, we included 93 eligible studies (42 cross-sectional, 41 cohort, and 10 case-control) in the meta-analysis. There were significantly positive associations between SHS exposure and doctor-diagnosed asthma (OR = 1.24; 95% confidence interval (CI) = 1.20-1.28), wheezing (OR = 1.27; 95% CI = 1.23-1.32) and asthma-like syndrome (OR = 1.34; 95% CI = 1.34-1.64). The funnel plots of all three outcomes skewed to the right, indicating that the studies generally favor a positive association of the disease with tobacco exposure. Subgroup analysis demonstrated that younger children tended to suffer more from developing doctor-diagnosed asthma, but older children (adolescents) suffered more from wheezing. There was no evidence of significant publication or small study bias using Egger's and Begg's tests.

CONCLUSION

The results show a positive association between prenatal and postnatal secondhand smoking exposure and the occurrence of childhood asthma, asthma-like syndrome, and wheezing. These results lend support to continued efforts to reduce childhood exposure to secondhand smoke.

A New Era of Epidemiology: Digital Epidemiology for Investigating the COVID-19 Outbreak in China

A novel pneumonia-like coronavirus disease (COVID-19) caused by a novel coronavirus named SARS-CoV-2 has swept across China and the world. Public health measures that were effective in previous infection outbreaks (eg, wearing a face mask, quarantining) were implemented in this outbreak. Available multidimensional social network data that take advantage of the recent rapid development of information and communication technologies allow for an exploration of disease spread and control via a modernized epidemiological approach. By using spatiotemporal data and real-time information, we can provide more accurate estimates of disease spread patterns related to human activities and enable more efficient responses to the outbreak. Two real cases during the COVID-19 outbreak demonstrated the application of emerging technologies and digital data in monitoring human movements related to disease spread. Although the ethical issues related to using digital epidemiology are still under debate, the cases reported in this article may enable the identification of more effective public health measures, as well as future applications of such digitally directed epidemiological approaches in controlling infectious disease outbreaks, which offer an alternative and modern outlook on addressing the long-standing challenges in population health.

An Innovative Artificial Intelligence-Based App for the Diagnosis of Gestational Diabetes Mellitus (GDM-AI): Development Study

Background

Gestational diabetes mellitus (GDM) can cause adverse consequences to both mothers and their newborns. However, pregnant women living in low- and middle-income areas or countries often fail to receive early clinical interventions at local medical facilities due to restricted availability of GDM diagnosis. The outstanding performance of artificial intelligence (AI) in disease diagnosis in previous studies demonstrates its promising applications in GDM diagnosis.

Objective

This study aims to investigate the implementation of a well-performing AI algorithm in GDM diagnosis in a setting, which requires fewer medical equipment and staff and to establish an app based on the AI algorithm. This study also explores possible progress if our app is widely used.

Methods

An AI model that included 9 algorithms was trained on 12,304 pregnant outpatients with their consent who received a test for GDM in the obstetrics and gynecology department of the First Affiliated Hospital of Jinan University, a local hospital in South China, between November 2010 and October 2017. GDM was diagnosed according to American Diabetes Association (ADA) 2011 diagnostic criteria. Age and fasting blood glucose were chosen as critical parameters. For validation, we performed k-fold cross-validation (k=5) for the internal dataset and an external validation dataset that included 1655 cases from the Prince of Wales Hospital, the affiliated teaching hospital of the Chinese University of Hong Kong, a non-local hospital. Accuracy, sensitivity, and other criteria were calculated for each algorithm.

Results

The areas under the receiver operating characteristic curve (AUROC) of external validation dataset for support vector machine (SVM), random forest, AdaBoost, k-nearest neighbors (kNN), naive Bayes (NB), decision tree, logistic regression (LR), eXtreme gradient boosting (XGBoost), and gradient boosting decision tree (GBDT) were 0.780, 0.657, 0.736, 0.669, 0.774, 0.614, 0.769, 0.742, and 0.757, respectively. SVM also retained high performance in other criteria. The specificity for SVM retained 100% in the external validation set with an accuracy of 88.7%.

Conclusions

Our prospective and multicenter study is the first clinical study that supports the GDM diagnosis for pregnant women in resource-limited areas, using only fasting blood glucose value, patients’ age, and a smartphone connected to the internet. Our study proved that SVM can achieve accurate diagnosis with less operation cost and higher efficacy. Our study (referred to as GDM-AI study, ie, the study of AI-based diagnosis of GDM) also shows our app has a promising future in improving the quality of maternal health for pregnant women, precision medicine, and long-distance medical care. We recommend future work should expand the dataset scope and replicate the process to validate the performance of the AI algorithms.