scholarly journals Toward Using Twitter Data to Monitor Covid-19 Vaccine Safety in Pregnancy

2021 ◽  
Author(s):  
Ari Z Klein ◽  
Karen O'Connor ◽  
Graciela Gonzalez-Hernandez
Keyword(s):  
Language Processing ◽  
Pregnancy Outcomes ◽  
Safety Data ◽  
Vaccine Safety ◽  
Machine Learning Algorithms ◽  
Increased Risk ◽  
Complementary Resource ◽  
Future Work ◽  
To Receive ◽  
In Pregnancy

Background: Coronavirus Disease 2019 (Covid-19) during pregnancy is associated with an increased risk of maternal death, intensive care unit (ICU) admission, and preterm birth; however, many people who are pregnant refuse to receive Covid-19 vaccination because of a lack of safety data. Objective: The objective of this preliminary study was to assess whether we could identify (1) users who have reported on Twitter that they received Covid-19 vaccination during pregnancy or the periconception period, and (2) reports of their pregnancy outcomes. Methods: We searched for reports of Covid-19 vaccination in a large collection of tweets posted by users who have announced their pregnancy on Twitter. To help determine if users were vaccinated during pregnancy, we drew upon a natural language processing (NLP) tool that estimates the timeframe of the prenatal period. For users who posted tweets with a timestamp indicating they were vaccinated during pregnancy, we drew upon additional NLP tools to help identify tweets that report their pregnancy outcomes. Results: Upon manually verifying the content of tweets detected automatically, we identified 150 users who reported on Twitter that they received at least one dose of Covid-19 vaccination during pregnancy or the periconception period. Among the 60 completed pregnancies, we manually verified at least one reported outcome for 45 (75%) of them. Conclusions: Given the limited availability of data on Covid-19 vaccine safety in pregnancy, Twitter can be a complementary resource for potentially increasing the acceptance of Covid-19 vaccination in pregnant populations. Directions for future work include developing machine learning algorithms to detect a larger number of users for observational studies.

scholarly journals Toward Using Twitter Data to Monitor COVID-19 Vaccine Safety in Pregnancy: Proof-of-Concept Study of Cohort Identification (Preprint)

2021 ◽  
Author(s):  
Ari Z Klein ◽  
Karen O'Connor ◽  
Graciela Gonzalez-Hernandez
Keyword(s):  
Language Processing ◽  
Pregnancy Outcomes ◽  
Safety Data ◽  
Vaccine Safety ◽  
Epidemiologic Studies ◽  
Twitter Data ◽  
Increased Risk ◽  
Complementary Resource ◽  
Preliminary Study ◽  
In Pregnancy

BACKGROUND COVID-19 during pregnancy is associated with an increased risk of maternal death, intensive care unit admission, and preterm birth; however, many people who are pregnant refuse to receive COVID-19 vaccination because of a lack of safety data. OBJECTIVE The objective of this preliminary study was to assess whether Twitter data could be used to identify a cohort for epidemiologic studies of COVID-19 vaccination in pregnancy. Specifically, we examined whether it is possible to identify users who have reported (1) that they received COVID-19 vaccination during pregnancy or the periconception period, and (2) their pregnancy outcomes. METHODS We developed regular expressions to search for reports of COVID-19 vaccination in a large collection of tweets posted through the beginning of July 2021 by users who have announced their pregnancy on Twitter. To help determine if users were vaccinated during pregnancy, we drew upon a natural language processing (NLP) tool that estimates the timeframe of the prenatal period. For users who posted tweets with a timestamp indicating they were vaccinated during pregnancy, we drew upon additional NLP tools to help identify tweets that reported their pregnancy outcomes. RESULTS We manually verified the content of tweets detected automatically, identifying 150 users who reported on Twitter that they received at least one dose of COVID-19 vaccination during pregnancy or the periconception period. We manually verified at least one reported outcome for 45 of the 60 (75%) completed pregnancies. CONCLUSIONS Given the limited availability of data on COVID-19 vaccine safety in pregnancy, Twitter can be a complementary resource for potentially increasing the acceptance of COVID-19 vaccination in pregnant populations. The results of this preliminary study justify the development of scalable methods to identify a larger cohort for epidemiologic studies.

Understanding Language Features in Loneliness Forum Posts that Elicit Comments (Preprint)

2021 ◽  
Author(s):  
Anietie Andy
Keyword(s):  
Language Processing ◽  
Latent Dirichlet Allocation ◽  
Well Being ◽  
Time Of Day ◽  
Online Forums ◽  
Cohen’S D ◽  
Increased Risk ◽  
Social Media Platforms ◽  
Cohen's D ◽  
To Receive

BACKGROUND Loneliness is a threat to the well-being of individuals and in older adults is associated with increased risk of early mortality. Studies have shown that some individuals seek support around loneliness on online forums/social media platforms. A common challenge in online forums is that some posts do not receive comments. In some non-health related forums, posts not receiving comments may not be a serious concern, however, in an online health forum such as those focused on discussions around loneliness, posts not receiving comments could translate to individuals seeking support around loneliness not receiving adequate support. OBJECTIVE The aim of this work is to analyze posts published on an active online forum focused on discussions around loneliness (loneliness forum) to determine the language features associated with posts that elicit comments from members of the forum. METHODS For the analysis in this work, 15,012 posts published on an online loneliness forum by 9,956 users were analyzed. Of these posts, 6,450 received five or more comments, 13,221 received one or more comments, and 1,791 received no comments. Using the natural language processing method, latent dirichlet allocation (LDA) and a psycholinguistic dictionary, Linguistics Inquiry and Word Count (LIWC), the language features expressed in posts that elicit comments from members of the forum were determined. RESULTS The findings from this work show that posts related to topics themes on relationships (Cohen’s D = 0.319) and the use of negation words (Cohen’s D = 0.149) tend to receive one or more comments. Also, posts associated with LIWC categories on first person singular pronouns (Cohen’s D = 0.264) tend to elicit one or more comments. Posts on topic themes related to spending time around holidays/birthdays/year/time of day or week (Cohen’s D = 0.79) and affection relative to relationships (Cohen’s D = 0.102) tend to receive five or more comments. CONCLUSIONS This work identifies language features expressed in loneliness forum posts that elicit comments. The findings from this work can provide members of online loneliness forums tips on how to write posts that potentially elicit comments from members of the forum.

The Spectrum of Adverse Pregnancy Outcomes Based on Kidney Disease Diagnoses: A 20-Year Population Study

2019 ◽  
Vol 49 (5) ◽  
pp. 400-409 ◽  
Author(s):  
Alyssa Fitzpatrick ◽  
Kamalesh Venugopal ◽  
Wendy Scheil ◽  
Stephen P. McDonald ◽  
Shilpanjali Jesudason
Keyword(s):  
Preterm Birth ◽  
Caesarean Section ◽  
Pregnancy Outcomes ◽  
Clinical Care ◽  
Vesicoureteric Reflux ◽  
Population Level ◽  
Diagnostic Code ◽  
Benign Condition ◽  
Increased Risk ◽  
In Pregnancy

Background and Objectives: Kidney disorders in pregnancy may be under-recognized and have variable impact on outcomes depending on diagnosis. Population-level data are limited, particularly for Australia, and comparison of impact of different kidney disorders on pregnancy has rarely been assessed. This study examined the prevalence and outcomes of varied kidney disorders using population-level perinatal data from a large cohort. Methods: Women with singleton pregnancies > 20 weeks’ gestation from the South Australian Pregnancy Outcomes Unit (1990–2012). Women with a kidney disorders diagnostic code were grouped into categories (immunological, cystic/genetic, urological, vesicoureteral reflux (VUR), pyelonephritis and “other”). Key pregnancy outcomes were assessed, with adjustment for demographic variables. Results: Kidney disorders were reported in 1,392 (0.3%) of 407,580 births. These pregnancies had increased risk of pregnancy-induced hypertension (OR 2.16, 95% CI 1.82–2.56), induction of labor (RRR vs. spontaneous birth 2.10, 95% CI 1.87–2.36), all Caesarean section (OR 1.31, 95% CI 1.17–1.47) as well as Caesarean section without labor (RRR 1.82, 95% CI 1.57–2.10), preterm birth (< 37 weeks; 2.76, 95% CI 2.40–3.18), low birth weight (< 2,500 g) infants (OR 2.43, 95% CI 2.07–2.84), and neonatal intensive care admission (OR 2.64, 95% CI 2.12–3.29). Diagnostic subgroups demonstrated differing patterns of adverse outcomes, enabling the development of a matrix of risk. Women with immunological renal conditions and VUR had greatest risk overall, and only women with immunological diseases had increased risk of small-for-gestational age < 10th centile (OR 2.36, 95% CI 1.26–4.42). Women with nonchronic urological conditions and pyelonephritis had increased risk of preterm birth, but not other adverse events. VUR conferred particularly increased risk of Caesarean section and induced labor. Conclusions: In a cohort of > 1,300 women with varied kidney disorders, increased adverse obstetric and perinatal events were observed, and the nature and magnitude of risk differed according to diagnosis. In particular, vesicoureteric reflux is not a benign condition in pregnancy. Women with nonchronic conditions still had increased risk of preterm birth. We confirm that women with kidney disorders warrant vigilant and tailored prepregnancy care and clinical care in pregnancy.

scholarly journals Insulin Glulisine in Pregnancy – Experience from Clinical Trials and Post-marketing Surveillance

2015 ◽  
Vol 11 (1) ◽  
pp. 17 ◽  
Author(s):  
Zoran Doder ◽  
Demi Vanechanos ◽  
Manfred Oster ◽  
Wolfgang Landgraf ◽  
Stephen Lin ◽  
...  
Keyword(s):  
Diabetes Mellitus ◽  
Clinical Trials ◽  
Congenital Malformations ◽  
Safety Data ◽  
Live Births ◽  
Post Marketing Surveillance ◽  
Increased Risk ◽  
Post Marketing ◽  
Insulin Glulisine ◽  
In Pregnancy

Pregnancies complicated by gestational diabetes or pre-existing type 1 or type 2 diabetes mellitus are associated with a higher rate of adverse outcomes compared with pregnancies in the background population. These outcomes include miscarriage, pre-term delivery, pre-eclampsia, perinatal mortality and congenital malformations. Insulin glulisine (ApidraR, Sanofi) is a rapid-acting insulin analogue indicated for the treatment of adults, adolescents and children 6 years or older with diabetes mellitus where treatment with insulin is required. Here, all post-marketing and clinical trials safety data with insulin glulisine in pregnancy available to Sanofi up to June 2014 are summarised together with the findings of a comprehensive literature search. Cumulatively, a total of 303 pregnancy exposures to insulin glulisine were received. Of these 303 pregnancy exposures, there were 116 live births, 12 spontaneous abortions, two late foetal intra-uterine deaths (>28 weeks), three elective abortions and 170 cases without a known pregnancy outcome. There were six cases of congenital malformations; of these, there were five live births; in the other case a live birth was not confirmed. The congenital malformations reported to date do not reveal a pattern of defects. In conclusion, the evidence to date does not suggest a causal association between insulin glulisine and an increased risk of pregnancy complications or congenital malformations.

scholarly journals Prevalence of asymptomatic Plasmodium falciparuminfection, anaemia and use of ITNs among pregnant women yet to receive IPTp in parts of southern Ghana

2020 ◽  
pp. 36-42
Author(s):  
Leslie L Afutu ◽  
Johnson N Boampong ◽  
Neils B Quashie
Keyword(s):  
Pregnant Women ◽  
Parasite Density ◽  
Intermittent Preventive Treatment ◽  
Malaria In Pregnancy ◽  
Asymptomatic Malaria ◽  
Nested Polymerase Chain Reaction ◽  
Increased Risk ◽  
The Mean ◽  
To Receive ◽  
In Pregnancy

Background: Asymptomatic malaria in pregnancy evades most fever-based surveillance systems yet causes significant morbidities such as anaemia in the pregnant woman and low birth weight in the neonate. Objective:This study determined the prevalence of asymptomatic malaria and its association with anaemia among pregnant women who are yet to receive their first dose of Sulphadoxine-Pyrimethamine (SP) as intermittent preventive treatment of malaria in pregnancy (IPTp). Information on the use of insecticide treated nets(ITNs)as vector control by the pregnant women was also sought. Methods: This is a cross-sectional hospital-based study conducted in the Western Region of Ghana. Pregnant women at gestational ages, 16-26 wkwere included. A structured questionnaire was used to collect vital information from the participants. Plasmodiumparasitaemia was determined by rapid diagnostic test (MRDT), microscopy and species-specific nested polymerase chain reaction (PCR). Anaemia was classified using the level of haemoglobin. Results: A total of 413 antenatal clinic attendants were recruited. Prevalence of asymptomatic Plasmodium falciparuminfection was 13.1% by MRDT, 10.1% by microscopy and 13.8% by PCR. The mean haemoglobin was 10.73g/dL. Prevalence of anaemia was 40.49% and the mean parasite density was 149.6 parasite/μL. Pregnant women with asymptomatic malaria were 4 times more at risk of being anaemic (adjusted odds ratio with 95% confidence interval: 4.42, 1.82 -10.70)than those who did not have malaria. There was statistically significant negative correlation between parasite density and anaemia (r=0.0028, p=0.02). Conclusion: Asymptomatic P. falciparuminfection was found among some of the pregnant women and the presence of the parasites make them 4 times at increased risk of developing anaemia. Anaemia when occurring amongst such women was significantly worsened by increasing parasitaemia.

scholarly journals ISIDOG Consensus Guidelines on COVID-19 Vaccination for Women before, during and after Pregnancy

2021 ◽  
Vol 10 (13) ◽  
pp. 2902
Author(s):  
Gilbert Donders ◽  
Svitrigaile Grinceviciene ◽  
Kai Haldre ◽  
Risa Lonnee-Hoffmann ◽  
Francesca Donders ◽  
...  
Keyword(s):  
Pregnant Women ◽  
Safety Information ◽  
Safety Data ◽  
Scientific Data ◽  
Policy Makers ◽  
Additional Risk ◽  
Based Medicine ◽  
To Receive ◽  
Diabetes And Obesity ◽  
In Pregnancy

Introduction. Sars-CoV-2 infection poses particular problems in pregnancy, as the infection more frequently causes severe complications than in unaffected pregnant women or nonpregnant women with SARS-CoV-2 infection. Now that vaccination is available and rapidly being implemented worldwide, the question arises whether pregnant women should be vaccinated, and if so, whether they should receive priority. Methods. Available scientific data and available guidelines about vaccination against SARS-CoV-2 were collected by the Guideline Committee of the International Society of Infectious Diseases in Obstetrics and Gynecology (ISIDOG) and were analyzed, discussed and summarized as guidelines for healthcare workers caring for pregnant women. Concluding statements were graded according to the Oxford evidence-based medicine grading system. Results. There is evidence to consider pregnancy as a risk factor for serious complications of COVID-19 infection, even in the absence of additional risk factors, such as hypertension, diabetes and obesity which increase these risks even more in pregnancy. Currently available data slightly favor mRNA-based vaccines above vector-based vaccines during pregnancy and breastfeeding, until more safety data become available. Conclusion. ISIDOG advises policy makers and societies to prioritize pregnant women to receive vaccination against SARS-CoV-2 and favor the mRNA vaccines until further safety information becomes available.

scholarly journals Ondansetron and pregnancy: Understanding the data

2015 ◽  
Vol 9 (1) ◽  
pp. 28-33 ◽  
Author(s):  
Debra Kennedy
Keyword(s):  
Birth Defects ◽  
Pregnancy Outcomes ◽  
Safety Data ◽  
First Trimester ◽  
Common Condition ◽  
Off Label ◽  
Increased Risk ◽  
Practical Guidelines ◽  
Potential Risks ◽  
Adverse Pregnancy

Nausea and vomiting of pregnancy (NVP) is a common condition affecting 75% of pregnant women. NVP generally commences early in the first trimester, peaking in severity between 7 and 12 weeks and in over 90% symptoms will have abated by week 20. Thus, the time when women are most likely to have NVP and require treatment coincides with the embryonic period when there is maximum susceptibility to any teratogenic risk. Following the thalidomide tragedy of 55 years ago there is a particular awareness and sensitivity about these potential risks, especially in relation to any medication used to treat NVP. Despite several studies showing no clear benefits of ondansetron over other NVP treatments such as doxylamine, and the paucity of safety data, the off-label prescribing and use of ondansetron to treat NVP has increased significantly worldwide. Albeit based on limited human pregnancy data, ondansetron has not been associated with a significantly increased risk of birth defects or other adverse pregnancy outcomes. This review attempts to highlight some of the difficulties in interpreting the available data and the need to follow practical guidelines regarding treatment of NVP.

Pregnancy outcomes in DMARD-exposed patients with juvenile idiopathic arthritis—results from a JIA biologic registry

Rheumatology ◽  
2019 ◽  
Author(s):  
Paula Drechsel ◽  
Katrin Stüdemann ◽  
Martina Niewerth ◽  
Gerd Horneff ◽  
Rebecca Fischer-Betz ◽  
...  
Keyword(s):  
Pregnancy Outcomes ◽  
Observation Study ◽  
Patient Interviews ◽  
Increased Risk ◽  
Patient Reported ◽  
Male Patients ◽  
Adverse Pregnancy ◽  
Reported Data ◽  
Long Term Observation ◽  
In Pregnancy

Abstract Objectives To investigate the courses and outcomes of pregnancies involving JIA patients who were exposed to DMARDs. Methods In the Juvenile arthritis MTX/Biologics long-term Observation study, pregnant patients or male patients with pregnant partners were identified. Standardized patient interviews were conducted, and the course and outcome of pregnancy were assessed. Prospectively collected physician- and patient-reported data were also considered in the analysis. Results The study sample included 152 pregnancies in 98 women with JIA and 39 pregnancies involving 21 male patients as partners. The majority of patients had polyarticular-onset/-course JIA (61%). The average age of patients at first pregnancy was 24.1 (4.5) years, and their mean disease duration was 13.8 (5.9) years. Patients had been exposed to DMARDs for 9.5 (5.6) years, and 90% of these patients had received biologics before. Half of the pregnancies occurred during DMARD exposure, mostly with etanercept. Significant differences in pregnancy outcomes between DMARD-exposed and -unexposed pregnancies were not observed. Spontaneous abortion (13.1%) and congenital anomaly (3.6%) rates were not suggestive of increased risk compared with expected background rates. However, the rates of premature birth (12.3%) and caesarean section (37.7%) were slightly above those in the German birthing population. The disease activity of female patients remained relatively stable in pregnancy, with mean cJADAS-10 scores of 5.3, 7.1 and 5.6 in each trimester, respectively. Conclusion Young adults with JIA often become pregnant or become fathers of children while still being treated with DMARDs. Data suggest no increased risk of major adverse pregnancy outcomes.

scholarly journals ISIDOG Consensus Guidelines on Covid-19 Vaccination for Women before, during and after Pregnancy

2021 ◽  
Author(s):  
Gilbert Gerard Ghislain Donders ◽  
Svitrigaile Grinceviciene ◽  
Kai Haldre ◽  
Risa Lonnee-Hofmann ◽  
Francesca Donders ◽  
...  
Keyword(s):  
Pregnant Women ◽  
Safety Information ◽  
Safety Data ◽  
Scientific Data ◽  
Policy Makers ◽  
Care Workers ◽  
Based Medicine ◽  
To Receive ◽  
Diabetes And Obesity ◽  
In Pregnancy

Introduction.Sars-CoV-2 infection poses particular problems in pregnancy, as the infection more frequently causes severe complications than in unaffected pregnant women, or non-pregnant women with SARS-CoV-2 infection. Now that vaccination is available and rapidly getting implemented worldwide, the question arises whether pregnant women should be vaccinated, and if so, whether they should get priority. Methods. Available scientific data and available guidelines about vaccination against SARS-CoV-2 were collected by the Guideline Committee of the International Society of Infectious Diseases in Obstetrics and Gynecology (ISIDOG), and were analyzed, discussed and summarized as guidelines for health care workers caring for pregnant women. Concluding statements were graded according to the Oxford Evidence Based Medicine Grading System. Results. There is evidence to consider pregnancy as a risk factor for serious complications of COVID-19 infection, even in the absence of additional risk factors, such as hypertension, diabetes and obesity which increase these risks even more in pregnancy. Currently available data slightly favor mRNA-based vaccines above vector-based vaccines during pregnancy and breastfeeding, until more safety data become available. Conclusion. ISIDOG advices policy makers and societies to prioritize pregnant women to receive vaccination against SARS-CoV-2, and favor the mRNA vaccines until further safety information becomes available.

scholarly journals Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis (Preprint)

2019 ◽  
Author(s):  
Herdiantri Sufriyana ◽  
Atina Husnayain ◽  
Ya-Lin Chen ◽  
Chao-Yang Kuo ◽  
Onkar Singh ◽  
...  
Keyword(s):  
Machine Learning ◽  
Systematic Review ◽  
Pregnancy Outcomes ◽  
Prediction Models ◽  
Meta Analysis ◽  
Machine Learning Algorithms ◽  
Gradient Boosting ◽  
Pregnancy Care ◽  
Prognostic Prediction ◽  
In Pregnancy

BACKGROUND Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method. OBJECTIVE This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians’ decision making. METHODS Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians’ decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using <i>τ<sup>2</sup></i> and <i>I<sup>2</sup></i>. RESULTS Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; <i>I<sup>2</sup></i>=86%; <i>τ<sup>2</sup></i>=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; <i>I<sup>2</sup></i>=75%; <i>τ<sup>2</sup></i>=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; <i>I<sup>2</sup></i>=75%; <i>τ<sup>2</sup></i>=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; <i>I<sup>2</sup></i>=83%; <i>τ<sup>2</sup></i>=0.07). CONCLUSIONS Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines. CLINICALTRIAL PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106

Sign in / Sign up

Export Citation Format

Share Document