MEDPSeg: Hierarchical polymorphic multitask learning for the segmentation of ground-glass opacities, consolidation, and pulmonary structures on computed tomography (preprint)

The COVID-19 pandemic response highlighted the potential of deep learning methods in facilitating the diagnosis, prognosis and understanding of lung diseases through automated segmentation of pulmonary structures and lesions in chest computed tomography (CT). Automated separation of lung lesion into ground-glass opacity (GGO) and consolidation is hindered due to the labor-intensive and subjective nature of this task, resulting in scarce availability of ground truth for supervised learning. To tackle this problem, we propose MEDPSeg. MEDPSeg learns from heterogeneous chest CT targets through hierarchical polymorphic multitask learning (HPML). HPML explores the hierarchical nature of GGO and consolidation, lung lesions, and the lungs, with further benefits achieved through multitasking airway and pulmonary artery segmentation. Over 6000 volumetric CT scans from different partially labeled sources were used for training and testing. Experiments show PML enabling new state-of-the-art performance for GGO and consolidation segmentation tasks. In addition, MEDPSeg simultaneously performs segmentation of the lung parenchyma, airways, pulmonary artery, and lung lesions, all in a single forward prediction, with performance comparable to state-of-the-art methods specialized in each of those targets. Finally, we provide an open-source implementation with a graphical user interface at https://github.com/MICLab-Unicamp/medpseg.

Assessment of the effectiveness of required weekly COVID-19 surveillance antigen testing at a university (preprint)

ObjectivesTo mitigate the COVID-19 pandemic, many institutions implemented a regimen of periodic required testing, irrespective of symptoms. The effectiveness of this"surveillance testing" requires assessment. MethodsI fit a zero-inflated negative binomial model to COVID-19 testing and case investigation data between 1 November 2020 and 15 May 2021, from young adult subjects in one community. I compared the duration of symptoms at time of specimen collection in those diagnosed via (1) surveillance testing at a university, (2) the same universitys student health services, and (3) all other testing venues. ResultsThe data comprised 2926 records: 393 from surveillance testing, 493 from student health service, and 2040 from other venues. About 65% of people with COVID-19 detected via surveillance testing were already symptomatic at time of specimen collection. Predicted mean duration of pre-testing symptoms was 1.7 days (95% CI 1.59 to 1.84) for the community, 1.81 days (95% CI 1.62 to 1.99) for surveillance, and 2 days (95% CI 1.83 to 2.16) for student health service. The modelled "inflated" proportions of asymptomatic subjects from the surveillance stream and the other/community stream were comparable (odds ratio 0.95, p = 0.7709). Comparing surveillance testing with the student health service, the proportion of "excess" zero symptom durations was signficantly higher in the former (Chi-square = 12.08, p = 0.0005) ConclusionsSurveillance testing at a university detected 393 people with COVID-19, but no earlier in their trajectory than similar-aged people detected in the broader community. This casts some doubt on the public health value of such programs, which tend to be labor-intensive and expensive. 2 Three-question summary boxO_ST_ABSWhat is the current understanding of this subject?C_ST_ABSAssessments of long-term operational effectiveness of COVID-19 "surveillance testing" have not been published. What does this report add to the literature?During the 2020-2021 academic year at one university, people with COVID-19 detected via compulsory weekly surveillance antigen testing were equally likely to be symptomatic at time of detection, and for just as long, as similar-aged people detected via testing venues in the community. What are the implications for public health practice?Surveillance testing programs during the pandemic consumed a large amount of time, money, and effort. In future respiratory pandemics, resources might be better devoted to other mitigation measures.

Copper and zinc deficiency to the risk of preterm labor in pregnant women: a case-control study.

OBJECTIVE: The present study explored the relationship between maternal copper and zinc levels and preterm labor. DESIGN: The design of the present study was a case-control. Two groups were matched in terms of early-pregnancy body mass index (BMI), pregnancy and childbirth rating, education level, income, and employment status. Blood samples were taken from mothers after meeting the inclusion criteria when admitted to the maternity ward to check copper and zinc serum levels. Demographic and midwifery data were also collected using a questionnaire and patient records. The data were analyzed in SPSS26 using independent-samples T-test, chi-square, Fisher exact test, and regression analysis, and the p < 0.05 was considered statistically significant. SETTING: Bohloul Hospital in Gonabad, Iran. PARTICIPANTS: The subjects were 86 pregnant women visiting the hospital in two cases (preterm delivery) and control (term delivery) groups. RESULTS: The mean serum level of zinc in the case group (preterm delivery) (44.97 ± 13.06 µg/dl) was significantly lower than the control group (term) (52.63 ± 21.51 µg/dl), and the mean serum level of copper in the case group (149.82 ± 53.13 µg/dl) was significantly lower than the control group (183.97 ± 71.40 µg/dl). CONCLUSION: As the findings showed, copper and zinc serum levels in mothers with preterm delivery were significantly lower than mothers with term delivery, which shows the biological role of these elements in the pathogenesis of preterm delivery.

Maternal SARS-COV-2 infection and prematurity: the Southern Michigan COVID-19 collaborative.

OBJECTIVE: COVID-19 has been reported to increase the risk of prematurity, however, due to the frequent absence of unaffected controls as well as inadequate accounting for confounders in many studies, the question requires further investigation. We sought to determine the impact of COVID-19 disease on preterm birth (PTB) overall, as well as related subcategories such as early prematurity, spontaneous, medically indicated preterm birth, and preterm labor (PTL). We assessed the impact of confounders such as COVID-19 risk factors, a-priori risk factors for PTB, symptomatology, and disease severity on rates of prematurity. METHODS: This was a retrospective cohort study of pregnant women from March 2020 till October 1st, 2020. The study included patients from 14 obstetric centers in Michigan, USA. Cases were defined as women diagnosed with COVID-19 at any point during their pregnancy. Cases were matched with uninfected women who delivered in the same unit, within 30 d of the delivery of the index case. Outcomes of interest were frequencies of prematurity overall and subcategories of preterm birth (early, spontaneous/medically indicated, preterm labor, and premature preterm rupture of membranes) in cases compared to controls. The impact of modifiers of these outcomes was documented with extensive control for potential confounders. A p value <.05 was used to infer significance. RESULTS: The rate of prematurity was 8.9% in controls, 9.4% in asymptomatic cases, 26.5% in symptomatic COVID-19 cases, and 58.8% among cases admitted to the ICU. Gestational age at delivery was noted to decrease with disease severity. Cases were at an increased risk of prematurity overall [adjusted relative risk (aRR) = 1.62 (1.2-2.18)] and of early prematurity (<34 weeks) [aRR = 1.8 (1.02-3.16)] when compared to controls. Medically indicated prematurity related to preeclampsia [aRR = 2.46 (1.47-4.12)] or other indications [aRR = 2.32 (1.12-4.79)], were the primary drivers of overall prematurity risk. Symptomatic cases were at an increased risk of preterm labor [aRR = 1.74 (1.04-2.8)] and spontaneous preterm birth due to premature preterm rupture of membranes [aRR = 2.2(1.05-4.55)] when compared to controls and asymptomatic cases combined. The gestational age at delivery followed a dose-response relation with disease severity, as more severe cases tended to deliver earlier (Wilcoxon p < .05). CONCLUSIONS: COVID-19 is an independent risk factor for preterm birth. The increased preterm birth rate in COVID-19 was primarily driven by medically indicated delivery, with preeclampsia as the principal risk factor. Symptomatic status and disease severity were significant drivers of preterm birth.

SARS-CoV-2 in Pregnancy-The First Wave.

Background and Objectives: COVID-19, a disease caused by SARS-CoV-2, is a public health emergency. Data on the effect of the virus on pregnancy are limited. Materials and Methods: We carried out a retrospective descriptive study, in order to evaluate the obstetric results on pregnant women in which SARS-CoV-2 was detected through RT-PCR of the nasopharyngeal swab, at admission to the maternity hospital. Results: From 16 March to 31 July 2020, 12 SARS-CoV-2 positive pregnant women have been hospitalized. Eleven were hospitalized for initiation or induction of labor, corresponding to 0.64% of deliveries in the maternity hospital. One pregnant woman was hospitalized for threatened abortion, culminating in a stillbirth at 20 weeks of gestation. Regarding the severity of the disease, nine women were asymptomatic and three had mild illness (two had associated cough and one headache). Three had relevant environmental exposure and a history of contact with infected persons. None had severe or critical illness due to SARS-CoV-2. There were no maternal deaths. The following gestational complications were observed: one stillbirth, one preterm labor, one preterm prelabor rupture of membranes, and one fetal growth restriction. Four deliveries were eutocic, two vacuum-assisted deliveries and five were cesarean sections. The indications for cesarean section were obstetric. Conclusions: SARS-CoV-2 infection was found in a minority of hospitalized pregnant women in this sample. Most are asymptomatic or have mild illness, from gestational complications to highlight stillbirth and preterm birth. There were no cases of vertical transmission by coronavirus.

Declaration of emergency state due to COVID-19 spread in Japan reduced maternal transports without reduction in preterm delivery.

INTRODUCTION: To clarify whether the declaration of an emergency state due to the spread of COVID-19 in Japan affected the number of maternal transports and premature births. METHODS: A questionnaire-based descriptive study was conducted in perinatal centers throughout Japan in 2020. The incidence of maternal transport and preterm delivery rates every month after the COVID-19 spread in 2020 were compared with those in 2019. RESULTS: Participants were recruited from 52 perinatal centres. The maternal transport rate (maternal transports per number of deliveries) was 10.6% in April and 11.0% in June 2020, compared with 12.5% in 2019 (P < 0.05). The maternal transport rate due to preterm labor was 4.8% in April 2020 and 5.8% in 2019 (P < 0.05). The maternal transport rate during the declaration of emergency state decreased by 21% in April 2020 in non-emergency-declared prefectures, and decreased by 17% in May 2020 in emergency-declared prefectures. However, there was no significant difference in the preterm delivery rate between 2020 and 2019, regardless of the prefecture and gestational period. CONCLUSION: Declaration of the emergency status due to COVID-19 spread in Japan reduced maternal transport due to preterm labor, but did not reduce preterm delivery itself.

Childbirth and puerperium during the COVID-19 pandemic: patient experience and frequency of prematurity / Parto y puerperio durante la pandemia por COVID-19: experiencia de las pacientes y frecuencia de prematuridad

Objetivo: Evaluar la percepción de las madres que tuvieron su parto durante la pandemia COVID en relación a la obligación de no recibir visitas en su puerperio, y cuantificar la frecuencia de prematuridad que otros centros del mundo mostraron que se redujo durante la pandemia. Método: Estudio observacional retrospectivo con encuestas realizadas entre el 1 de septiembre y el 31 diciembre 2020, y análisis de estadísticas locales de la Unidad de Maternidad y Neonatología. Resultados: Sobre el 90% de las madres que contestaron la encuesta afirmó haber descansado mejor y preferir un retorno a las visitas con horarios reducidos. La frecuencia de prematuridad se redujo significativamente en nuestra institución (8,08% entre 2014 y 2019 vs. 1,6% en 2020). Conclusiones: La mayoría de las puérperas prefiere un horario reducido para visitas en el posparto. Este hallazgo y la caída en la frecuencia de prematuridad obligan a reflexionar sobre nuestro cuidado prenatal actual.

Objective: To evaluate the perception of mothers who gave birth during the COVID pandemic in relation to the obligation not to receive visits during the puerperium, and to quantify the frequency of prematurity that other centers in the world showed decreased during the pandemic. Method: Retrospective observational study with surveys conducted between September 1st and December 31, 2020, and analysis of local statistics from the Maternity and Neonatal Unit. Results: Over 90% of the mothers who answered the survey stated that they had rested better and preferred a return to visits with reduced hours. The frequency of prematurity was signficantly reduced in our institution ((8.08% between 2014 and 2019 vs 1.6% in 2020). Conclusions: Most postpartum women prefer a reduced schedule for pospartum visits. This finding and the drop in the frequency of prematurity force us to reflect on our current prenatal care.

Maternal sepsis caused by Listeria monocytogenes with a fatal fetal outcome.

Improving maternal and child health is a global priority. Although infection with Listeria monocytogenes (LM), a small facultative anaerobic, gram-positive motile bacillus is rare, when it infects the maternal-fetoplacental unit, it can result in adverse fetal sequelae such as chorioamnionitis, preterm labour, neonatal sepsis, meningitis and neonatal death. Pregnancy-associated listeriosis may present with a plethora of diverse, non-specific symptoms such as fever, influenza-like or gastrointestinal symptoms, premature contractions and preterm labour. It has a predilection for the second and third trimester of pregnancy, occurring sporadically or as part of an outbreak, most of which have involved unpasteurised dairy products, long shelf life products, contaminated ready-to-eat food, deli meats and soft cheeses. Strains belonging to the clonal complexes 1, 4 and 6 are hypervigilant and are commonly associated with maternal-neonatal infections. Maternal listeriosis occurs as a direct consequence of LM-specific placental tropism, which is mediated by the conjugated action of internalin A and internalin B at the placental barrier. The diagnosis is established from placental culture. Penicillin, ampicillin and amoxicillin are the antimicrobials of choice. It has a high fetal morbidity of up to 30%. The authors present the case of a multiparous woman in her early 20s presenting with sepsis and preterm premature rupture of her membranes at 21 weeks gestation. A live baby was delivered spontaneously and died shortly after birth. Placental cultures and postmortem examination were consistent with the diagnosis of disseminated Listeria infection. Due to the increased susceptibility of pregnant women for LM, a high index of clinical suspicion is required to establish the diagnosis and initiate appropriate antimicrobial therapy to reduce adverse fetal outcomes.

Amelioration of prevalence of threatened preterm labor during the COVID-19 pandemic: nationwide database analysis in Japan.

We aimed to evaluate the changes in maternal and neonatal complications such as threatened preterm labor (TPL) and preterm birth before and during the coronavirus disease 2019 (COVID-19) pandemic using large-scale real-world data in Japan. We obtained data from the Japan Medical Data Center claims database and evaluated differences in maternal and neonatal complications, such as the prevalence of TPL and preterm birth before the COVID-19 pandemic (in the year 2018 or 2019) and during the COVID-19 pandemic (in 2020). We included 5533, 6257, and 5956 deliveries in the years 2018, 2019, and 2020, respectively. TPL prevalence and preterm birth had significantly decreased in 2020 (41.3%, 2.6%, respectively) compared with those reported in 2018 (45.3%, 3.9%, respectively) and 2019 (44.5%, 3.8%, respectively). Neonatal outcomes such as low-birth-weight infants and retinopathy of prematurity were also improved during the pandemic. There were no clear trends in the prevalence of maternal complications such as hypertensive disorders of pregnancy; hemolysis, elevated liver enzymes, and low platelets (HELLP) syndrome; and preeclampsia. Oral ritodrine hydrochloride usage in all participants had significantly decreased during the COVID-19 pandemic. In conclusion, our results suggest that the COVID-19 pandemic has ameliorated TPL and consequently reduced the number of preterm births.

Threatened abortion, threatened premature labor, and preterm birth during the first state of emergency for COVID-19 in 2020 in Japan.

AIM: This study examined the maternal experience of threatened abortion, threatened premature labor, or preterm birth before, during, and after the first state of emergency for COVID-19 in 2020 in Japan. METHODS: This was a cross-sectional, internet-based questionnaire survey. We recruited 600 postpartum women and divided them into three groups by date of delivery: before (October 2019-March 2020), during (April-May 2020), and after (June-October 2020) the first state of emergency. The outcome was the presence of at least one of the following complications: threatened abortion, threatened premature labor, and/or preterm birth. The prevalence ratios (PRs) of the outcome were calculated and compared among the three groups using a multivariable Poisson regression model with adjustment for potential confounders. RESULTS: Of the 553 women eligible for analysis, those who delivered during (PR 0.69, 95% confidence interval [CI] 0.47-0.99) and after (PR 0.62, 95% CI 0.42-0.90) the state of emergency were less likely to have experienced either threatened abortion, threatened premature labor, or preterm birth than those who delivered before the state of emergency. Among the adjustment variables, smoking at the time of survey (PR 1.68, 95% CI 1.01-2.80) and living in the prefectures with a population of >5 million (PR 0.71, 95% CI 0.51-0.97) were associated with the study outcome. CONCLUSION: Threatened abortion, threatened premature labor, or preterm birth appeared to decrease during and after the first state of emergency in 2020. The longitudinal effects of coronavirus disease on maternal and newborn health should be monitored continuously.

Assessment of an intervention to optimise antenatal management of women admitted with preterm labour and intact membranes using amniocentesis-based predictive risk models: study protocol for a randomised controlled trial (OPTIM-PTL Study).

INTRODUCTION: The majority of women admitted with threatened preterm labour (PTL) do not delivery prematurely. While those with microbial invasion of the amniotic cavity (MIAC) represent the highest risk group, this is a condition that is not routinely ruled out since it requires amniocentesis. Identification of low-risk or high-risk cases might allow individualisation of care, that is, reducing overtreatment with corticosteroids and shorten hospital stay in low-risk women, while allowing early antibiotic therapy in those with MIAC. Benefits versus risks of amniocentesis-based predictor models of spontaneous delivery within 7 days and/or MIAC have not been evaluated. METHODS AND ANALYSIS: This will be a Spanish randomised, multicentre clinical trial in singleton pregnancies (23.0-34.6 weeks) with PTL, conducted in 13 tertiary centres. The intervention arm will consist in the use of amniocentesis-based predictor models: if low risk, hospital discharge within 24 hours of results with no further medication will be recommended. If high risk, antibiotics will be added to standard management. The control group will be managed according to standard institutional protocols, without performing amniocentesis for this indication. The primary outcome will be total antenatal doses of corticosteroids, and secondary outcomes will be days of maternal stay and the occurrence of clinical chorioamnionitis. A cost analysis will be undertaken. To observe a reduction from 90% to 70% in corticosteroid doses, a reduction in 1 day of hospital stay (SD of 2) and a reduction from 24% to 12% of clinical chorioamnionitis, a total of 340 eligible patients randomised 1 to 1 to each study arm is required (power of 80%, with type I error α=0.05 and two-sided test, considering a dropout rate of 20%). Randomisation will be stratified by gestational age and centre. ETHICS AND DISSEMINATION: Prior to receiving approval from the Ethics Committee (HCB/2020/1356) and the Spanish Agency of Medicines and Medical Devices (AEMPS) (identification number: 2020-005-202-26), the trial was registered in the European Union Drug Regulating Authorities Clinical Trials database (2020-005202-26). AEMPS approved the trial as a low-intervention trial. All participants will be required to provide written informed consent. Findings will be disseminated through workshops, peer-reviewed publications and national/international conferences. PROTOCOL VERSION: V.4 10 May 2021. TRIAL REGISTRATION NUMBERS: NCT04831086 and Eudract number 2020-005202-26.

Availability and use of fetal fibronectin testing and transvaginal ultrasound for preterm labor evaluation in the United States.

OBJECTIVE: Measure availability and use of fetal fibronectin (fFN) testing and transvaginal ultrasound to measure cervical length (TVCL) for symptomatic preterm labor (PTL) patients. Additionally, assess the presence and impact of PTL triage protocols. STUDY DESIGN: Cross-sectional online survey among clinicians from 255 unique hospitals regarding prior 12-month practices (pre-COVID-19). RESULTS: fFN testing was always available in 87% (221) of hospitals, while TVCL was always available in 69% (175) of hospitals. Utilization was lower: fFN specimens were often/always collected in 61% (156) of hospitals and TVCL was often/always performed in 43% (110) of hospitals. fFN testing was significantly more likely than TVCL to be available and used (p < .05). Written PTL protocols were available in 47% (121) of hospitals but not consistently followed. CONCLUSION: The most accurate risk assessment approach for imminent spontaneous preterm birth is the implementation of a universal screening program for symptomatic patients, including fFN testing and TVCL.

Drug development research in pregnant and lactating women.

Pregnant and lactating women are considered "therapeutic orphans" because they generally have been excluded from clinical drug research and the drug development process owing to legal, ethical, and safety concerns. Most medications prescribed for pregnant and lactating women are used "off-label" because most of the clinical approved medications do not have appropriate drug labeling information for pregnant and lactating women. Medications that lack human safety data on use during pregnancy and lactation may pose potential risks for adverse effects in pregnant and lactating women as well as risks of teratogenic effects to their unborn and newborn babies. Federal policy requiring the inclusion of women in clinical research and trials led to considerable changes in research design and practice. Despite more women being included in clinical research and trials, the inclusion of pregnant and lactating women in drug research and clinical trials remains limited. A recent revision to the "Common Rule" that removed pregnant women from the classification as a "vulnerable" population may change the culture of drug research and drug development in pregnant and lactating women. This review article provides an overview of medications studied by the Obstetric-Fetal Pharmacology Research Units Network and Centers and describes the challenges in current obstetrical pharmacology research and alternative strategies for future research in precision therapeutics in pregnant and lactating women. Implementation of the recommendations of the Task Force on Research Specific to Pregnant Women and Lactating Women can provide legislative requirements and opportunities for research focused on pregnant and lactating women.

Real-time RT-PCR Allelic Discrimination Assay for Detection of N501Y Mutation in the Spike Protein of SARS-CoV-2 Associated with Variants of Concern (preprint)

The N501Y amino acid mutation caused by a single point substitution A23063T in the spike gene of SARS-CoV2 is possessed by the three most common variants of concern - B.1.1.7, B.1.351, and P.1. A rapid screening tool using this mutation is important for surveillance during the COVID-19 pandemic. We developed and validated a single nucleotide polymorphism real-time reverse transcription polymerase chain reaction assay using allelic discrimination of the spike gene N501Ymutation to screen for potential variants of concern and differentiate them from wild-type SARS-CoV-2. A total of 160 clinical specimens positive for SARS-CoV-2 were characterized as mutant (N501Y) or wild-type by Sanger sequencing and were subsequently tested with the N501Y single nucleotide polymorphism real time reverse transcriptase polymerase chain reaction assay. Our assay compared to sequencing, the gold standard for SNP detection and lineage identification, demonstrated clinical sensitivity of 100% for all 57 specimens displaying N501Y mutant, which were confirmed by Sanger sequencing to be typed as A23063T, including one specimen with mixed signal for wildtype and mutant. Clinical specificity was 100% in all 103 specimens typed as wild-type, with A23063 identified as wild-type by Sanger sequencing. The identification of circulating SARS-CoV-2 lineages carrying an N501Y mutation is critical for surveillance purposes. Current identification methods rely primarily on Sanger sequencing or whole genome sequencing which are time-consuming, labor-intensive and costly. The assay described herein is an efficient tool for high-volume specimen screening for SARS-CoV-2 VOCs and for selecting specimens for confirmatory Sanger or whole genome sequencing.

Development and rapid rollout of The QUiPP App Toolkit for women who arrive in threatened preterm labour.

BACKGROUND: Often the first opportunity for clinicians to assess risk of preterm birth is when women present with threatened preterm labour symptoms (such as period-like pain, tightening's or back ache). However, threatened preterm labour symptoms are not a strong predictor of imminent birth. Clinicians are then faced with a complex clinical dilemma, the need to ameliorate the consequences of preterm birth requires consideration with the side-effects and costs. The QUiPP app is a validated app which can aid clinicians when they triage a women who is in threatened preterm labour. AIM: Our aim was to produce a toolkit to promote a best practice pathway for women who arrive in threatened preterm labour. METHODS: We worked with two hospitals in South London. This included the aid of a toolkit midwife at each hospital. We also undertook stakeholder focus groups and worked with two Maternity Voice Partnership groups to ensure a diverse range of voices was heard in the toolkit development. While we aimed to produce the toolkit in September 2020, we rapidly rolled out and produced the first version of the toolkit in April 2020 due to COVID-19. As the QUiPP app can reduce admissions and hospital transfers, there was a need to enable all hospitals in England to have access to the toolkit as soon as possible. RESULTS: While the rapid rollout of The QUiPP App Toolkit due to COVID-19 was not planned, it has demonstrated that toolkits to improve clinical practice can be produced promptly. Through actively welcoming continued feedback meant the initial version of the toolkit could be continually and iteratively refined. The toolkit has been recommended nationally, with National Health Service England recommending the app and toolkit in their COVID-19 update to the Saving Babies Lives Care Bundle and in the British Association of Perinatal Medicine Antenatal Optimisation Toolkit.

Severity Quantification and Lesion Localization of COVID-19 on CXR using Vision Transformer (preprint)

Under the global pandemic of COVID-19, building an automated framework that quantifies the severity of COVID-19 and localizes the relevant lesion on chest X-ray images has become increasingly important. Although pixel-level lesion severity labels, e.g. lesion segmentation, can be the most excellent target to build a robust model, collecting enough data with such labels is difficult due to time and labor-intensive annotation tasks. Instead, array-based severity labeling that assigns integer scores on six subdivisions of lungs can be an alternative choice enabling the quick labeling. Several groups proposed deep learning algorithms that quantify the severity of COVID-19 using the array-based COVID-19 labels and localize the lesions with explainability maps. To further improve the accuracy and interpretability, here we propose a novel Vision Transformer tailored for both quantification of the severity and clinically applicable localization of the COVID-19 related lesions. Our model is trained in a weakly-supervised manner to generate the full probability maps from weak array-based labels. Furthermore, a novel progressive self-training method enables us to build a model with a small labeled dataset. The quantitative and qualitative analysis on the external testset demonstrates that our method shows comparable performance with radiologists for both tasks with stability in a real-world application.

Maternal and neonatal outcomes of pregnant patients with COVID-19: A prospective cohort study.

OBJECTIVE: To determine the maternal and neonatal outcomes of pregnant women with COVID-19 infection. METHODS: A cohort study was conducted on 56 pregnant women with COVID-19 and 94 healthy pregnant women during the COVID-19 epidemic in Iran. Two groups were followed until childbirth. Demographic and obstetric information, clinical symptoms, laboratory and radiographic findings of the patients, and maternal and neonatal outcomes of the two groups were gathered by a checklist. Data were analyzed using SPSS version 16. A P value < 0.05 was considered significant. RESULTS: The two groups were similar in terms of maternal age, gravida, parity, and co-morbidities (P > 0.05). The rate of cesarean delivery in the exposed group was higher than that in the control group (P = 0.027; relative risk [RR] =2.23). Pre-eclampsia was seen in 19.8% of the exposed group and 7.4% of the control group (P = 0.037; RR = 2.68). The rate of preterm labor in the exposed group was higher than that in the control group (P = 0.003; RR = 2.70). Fetal distress was seen in 16.1% of the exposed group and 4.3% of the control group (P = 0.016; RR = 3.84). CONCLUSION: Pregnant women with COVID-19 had an increased risk of pre-eclampsia, preterm labor, and cesarean delivery. Their fetal and neonatal outcomes were fetal distress, newborn prematurity, and low Apgar score.

Coronavirus disease 2019 infection among asymptomatic and symptomatic pregnant women: two weeks of confirmed presentations to an affiliated pair of New York City hospitals.

Novel coronavirus disease 2019 is rapidly spreading throughout the New York metropolitan area since its first reported case on March 1, 2020. The state is now the epicenter of coronavirus disease 2019 outbreak in the United States, with 84,735 cases reported as of April 2, 2020. We previously presented an early case series with 7 coronavirus disease 2019-positive pregnant patients, 2 of whom were diagnosed with coronavirus disease 2019 after an initial asymptomatic presentation. We now describe a series of 43 test-positive cases of coronavirus disease 2019 presenting to an affiliated pair of New York City hospitals for more than 2 weeks, from March 13, 2020, to March 27, 2020. A total of 14 patients (32.6%) presented without any coronavirus disease 2019-associated viral symptoms and were identified after they developed symptoms during admission or after the implementation of universal testing for all obstetric admissions on March 22. Among them, 10 patients (71.4%) developed symptoms of coronavirus disease 2019 over the course of their delivery admission or early after postpartum discharge. Of the other 29 patients (67.4%) who presented with symptomatic coronavirus disease 2019, 3 women ultimately required antenatal admission for viral symptoms, and another patient re-presented with worsening respiratory status requiring oxygen supplementation 6 days postpartum after a successful labor induction. There were no confirmed cases of coronavirus disease 2019 detected in neonates upon initial testing on the first day of life. Based on coronavirus disease 2019 disease severity characteristics by Wu and McGoogan, 37 women (86%) exhibited mild disease, 4 (9.3%) severe disease, and 2 (4.7%) critical disease; these percentages are similar to those described in nonpregnant adults with coronavirus disease 2019 (about 80% mild, 15% severe, and 5% critical disease).

Inpatient obstetric management of COVID-19.

OBJECTIVE: To describe inpatient management strategies and considerations for pregnant patients with severe acute respiratory syndrome coronavirus 2 infection. FINDINGS: The novel coronavirus has posed challenges to both obstetric patients and the staff caring for them, due to its variable presentation and current limited knowledge about the disease. Inpatient antepartum, intrapartum and postpartum management can be informed by risk stratification, severity of disease, and gestational age. Careful planning and anticipation of emergent situations can prevent unnecessary exposures to patients and clinical staff. CONCLUSION: As new data arises, management recommendations will evolve, thus practitioners must maintain a low threshold for adaptation of their clinical practice during obstetric care for patients with severe acute respiratory syndrome coronavirus 2 infection.