Try a new search

Format these results:

Searched for:

person:rj547

in-biosketch:true

Total Results:

12


Machine Learning for the Prediction of Surgical Morbidity in Placenta Accreta Spectrum

Futterman, Itamar D; Sher, Olivia; Saroff, Chaskin; Cohen, Alexa; Doulaveris, Georgios; Dar, Pe'er; Griffin, Myah M; Limaye, Meghana; Owens, Thomas; Brustman, Lois; Rosenberg, Henri; Jessel, Rebecca; Chudnoff, Scott; Haberman, Shoshana
OBJECTIVE: We sought to create a machine learning (ML) model to identify variables that would aid in the prediction of surgical morbidity in cases of placenta accreta spectrum (PAS). STUDY DESIGN/METHODS: A multicenter analysis including all cases of PAS identified by pathology specimen confirmation, across five tertiary care perinatal centers in New York City from 2013 to 2022. We developed models to predict operative morbidity using 213 variables including demographics, obstetrical information, and limited prenatal imaging findings detailing placental location. Our primary outcome was prediction of a surgical morbidity composite defined as including any of the following: blood loss (>1,500 mL), transfusion, intensive care unit admission, vasopressor use, mechanical ventilation/intubation, and organ injury. A nested, stratified, cross-validation approach was used to tune model hyperparameters and estimate generalizability. Gradient boosted tree classifier models incorporated preprocessing steps of standard scaling for numerical variables and one-hot encoding for categorical variables. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), positive and negative predictive values (PPV, NPV), and F1 score. Variable importance ranking was also determined. RESULTS: Among 401 PAS cases, 326 (81%) underwent hysterectomy. Of the 401 cases of PAS, 309 (77%) had at least one event defined as surgical morbidity. Our predictive model had an AUC of 0.79 (95% confidence interval: 0.69, 0.89), PPV 0.79, NPV 0.76, and F1 score of 0.88. The variables most predictive of surgical morbidity were completion of a hysterectomy, prepregnancy body mass index (BMI), absence of a second trimester ultrasound, socioeconomic status zip code, BMI at delivery, number of prenatal visits, and delivery time of day. CONCLUSION/CONCLUSIONS: By identifying social and obstetrical characteristics that increase patients' risk, ML models are useful in predicting PAS-related surgical morbidity. Utilizing ML could serve as a foundation for risk and complexity stratification in cases of PAS to optimize surgical planning. KEY POINTS/CONCLUSIONS:· ML models are useful models are useful in predicting PAS-related surgical morbidity.. · Optimal management for PAS remains unclear.. · Utilizing ML can serve as a foundation for risk and complexity stratification in cases of PAS..
PMID: 39288819
ISSN: 1098-8785
CID: 5720522

Machine Learning for the Prediction of Surgical Morbidity in Placenta Accreta Spectrum

Futterman, Itamar D; Sher, Olivia; Saroff, Chaskin; Cohen, Alexa; Doulaveris, Georgios; Dar, Pe'er; Griffin, Myah M; Limaye, Meghana; Owens, Thomas; Brustman, Lois; Rosenberg, Henri; Jessel, Rebecca; Chudnoff, Scott; Haberman, Shoshana
OBJECTIVE: We sought to create a machine learning (ML) model to identify variables that would aid in the prediction of surgical morbidity in cases of placenta accreta spectrum (PAS). STUDY DESIGN/METHODS: A multicenter analysis including all cases of PAS identified by pathology specimen confirmation, across five tertiary care perinatal centers in New York City from 2013 to 2022. We developed models to predict operative morbidity using 213 variables including demographics, obstetrical information, and limited prenatal imaging findings detailing placental location. Our primary outcome was prediction of a surgical morbidity composite defined as including any of the following: blood loss (>1,500 mL), transfusion, intensive care unit admission, vasopressor use, mechanical ventilation/intubation, and organ injury. A nested, stratified, cross-validation approach was used to tune model hyperparameters and estimate generalizability. Gradient boosted tree classifier models incorporated preprocessing steps of standard scaling for numerical variables and one-hot encoding for categorical variables. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), positive and negative predictive values (PPV, NPV), and F1 score. Variable importance ranking was also determined. RESULTS: Among 401 PAS cases, 326 (81%) underwent hysterectomy. Of the 401 cases of PAS, 309 (77%) had at least one event defined as surgical morbidity. Our predictive model had an AUC of 0.79 (95% confidence interval: 0.69, 0.89), PPV 0.79, NPV 0.76, and F1 score of 0.88. The variables most predictive of surgical morbidity were completion of a hysterectomy, prepregnancy body mass index (BMI), absence of a second trimester ultrasound, socioeconomic status zip code, BMI at delivery, number of prenatal visits, and delivery time of day. CONCLUSION/CONCLUSIONS: By identifying social and obstetrical characteristics that increase patients' risk, ML models are useful in predicting PAS-related surgical morbidity. Utilizing ML could serve as a foundation for risk and complexity stratification in cases of PAS to optimize surgical planning. KEY POINTS/CONCLUSIONS:· ML models are useful models are useful in predicting PAS-related surgical morbidity.. · Optimal management for PAS remains unclear.. · Utilizing ML can serve as a foundation for risk and complexity stratification in cases of PAS..
PMID: 39288819
ISSN: 1098-8785
CID: 5720512

Machine Learning for the Prediction of Surgical Morbidity in Placenta Accreta Spectrum

Futterman, Itamar D; Sher, Olivia; Saroff, Chaskin; Cohen, Alexa; Doulaveris, Georgios; Dar, Pe'er; Griffin, Myah M; Limaye, Meghana; Owens, Thomas; Brustman, Lois; Rosenberg, Henri; Jessel, Rebecca; Chudnoff, Scott; Haberman, Shoshana
OBJECTIVE: We sought to create a machine learning (ML) model to identify variables that would aid in the prediction of surgical morbidity in cases of placenta accreta spectrum (PAS). STUDY DESIGN/METHODS: A multicenter analysis including all cases of PAS identified by pathology specimen confirmation, across five tertiary care perinatal centers in New York City from 2013 to 2022. We developed models to predict operative morbidity using 213 variables including demographics, obstetrical information, and limited prenatal imaging findings detailing placental location. Our primary outcome was prediction of a surgical morbidity composite defined as including any of the following: blood loss (>1,500 mL), transfusion, intensive care unit admission, vasopressor use, mechanical ventilation/intubation, and organ injury. A nested, stratified, cross-validation approach was used to tune model hyperparameters and estimate generalizability. Gradient boosted tree classifier models incorporated preprocessing steps of standard scaling for numerical variables and one-hot encoding for categorical variables. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), positive and negative predictive values (PPV, NPV), and F1 score. Variable importance ranking was also determined. RESULTS: Among 401 PAS cases, 326 (81%) underwent hysterectomy. Of the 401 cases of PAS, 309 (77%) had at least one event defined as surgical morbidity. Our predictive model had an AUC of 0.79 (95% confidence interval: 0.69, 0.89), PPV 0.79, NPV 0.76, and F1 score of 0.88. The variables most predictive of surgical morbidity were completion of a hysterectomy, prepregnancy body mass index (BMI), absence of a second trimester ultrasound, socioeconomic status zip code, BMI at delivery, number of prenatal visits, and delivery time of day. CONCLUSION/CONCLUSIONS: By identifying social and obstetrical characteristics that increase patients' risk, ML models are useful in predicting PAS-related surgical morbidity. Utilizing ML could serve as a foundation for risk and complexity stratification in cases of PAS to optimize surgical planning. KEY POINTS/CONCLUSIONS:· ML models are useful models are useful in predicting PAS-related surgical morbidity.. · Optimal management for PAS remains unclear.. · Utilizing ML can serve as a foundation for risk and complexity stratification in cases of PAS..
PMID: 39288819
ISSN: 1098-8785
CID: 5720502

Implementing a Labor and Delivery Cell Salvage Protocol in Patients at Increased Risk of Hemorrhage: A Pilot Study

Cabrera, Camila; Tavella, Nicola F; Goldberger, Cody P; Iwelumo, Chioma; Mitchell, Eric; Lubell, David; Bianco, Angela T; Katz, Daniel; Jessel, Rebecca H
BACKGROUND:Postpartum hemorrhage (PPH) contributes significantly to maternal morbidity and mortality. The use of cell salvage has been implemented in operating rooms across the world, but only a limited number of institutions have protocols for use of cell salvage during vaginal hemorrhage at the time of vaginal delivery. Observations suggest that blood salvaged from vaginal delivery is comparable to blood salvaged during cesarean delivery. Using pre-validated protocols of cell salvage, we sought to assess the feasibility and potential benefit of implementing cell salvage in our Labor and Delivery unit in all patients at high risk of hemorrhage. METHODS:This was a prospective pilot study conducted from April 2022 to December 2022 on the Labor and Delivery floor at Mount Sinai Hospital in New York City. A total of 50 participants were identified for cell salvage after vaginal delivery during the study period. The mean age of participants was 34.4 years (SD 5.5). We utilized a cell salvage technique at the time of vaginal delivery in patients at high risk of PPH. We employed simple descriptive statistics and examined sums and percentages (and means and standard deviations, where appropriate). A simple equation was used to determine the average cell salvaged volume in each delivery and describe potential values. The HEMAsavR™ device (Ecomed Solutions, Mundelein, IL, USA) was used as a standby system to be used at the time of the vaginal delivery. RESULTS:Fifty participants were identified for the cell salvage protocol as described. Despite a diversity of clinical risk factors, the sample consisted of predominately non-Hispanic White patients. The mean quantitative blood loss of cell salvaged samples was 157.2 mL (SD 153.0). We identified that, on average, >33% of vaginally shed blood could be used for cell salvage and improve patient blood management. CONCLUSION/CONCLUSIONS:The implementation of cell salvage in our Labor and Delivery unit was feasible and easy to perform. We identified that a significant volume of blood would be available for cell salvage. Further studies should be done to evaluate the benefit of cell salvage to improve postpartum recovery.
PMCID:11549931
PMID: 39524169
ISSN: 2168-8184
CID: 5752522

Investigation of health inequities in maternal and neonatal outcomes of patients with placenta accreta spectrum: a multicenter study

Cohen, Alexa; Lambert, Calvin; Yanik, Megan; Nathan, Lisa; Rosenberg, Henri M; Tavella, Nicola; Bianco, Angela; Futterman, Itamar; Haberman, Shoshana; Griffin, Myah M; Limaye, Meghana; Owens, Thomas; Brustman, Lois; Wu, Haotian; Dar, Pe'er; Jessel, Rebecca H; Doulaveris, Georgios
BACKGROUND:Placenta accreta spectrum is associated with significant maternal and neonatal morbidity and mortality. There is limited established data on healthcare inequities in the outcomes of patients with placenta accreta spectrum. OBJECTIVE:This study aimed to investigate health inequities in maternal and neonatal outcomes of pregnancies with placenta accreta spectrum. STUDY DESIGN:This multicentered retrospective cohort study included patients with a histopathological diagnosis of placenta accreta spectrum at 4 regional perinatal centers between January 1, 2013, and June 30, 2022. Maternal race and ethnicity were categorized as either Hispanic, non-Hispanic Black, non-Hispanic White, or Asian or Pacific Islander. The primary outcome was a composite adverse maternal outcome: transfusion of ≥4 units of packed red blood cells, vasopressor use, mechanical ventilation, bowel or bladder injury, or mortality. The secondary outcomes were a composite adverse neonatal outcome (Apgar score of <7 at 1 minute, morbidity, or mortality), gestational age at placenta accreta spectrum diagnosis, and planned delivery by a multidisciplinary team. Multivariable logistic regression was used to estimate the associations of race and ethnicity with maternal and neonatal outcomes. RESULTS:A total of 408 pregnancies with placenta accreta spectrum were included. In 218 patients (53.0%), the diagnosis of placenta accreta spectrum was made antenatally. Patients predominantly self-identified as non-Hispanic White (31.6%) or non-Hispanic Black (24.5%). After adjusting for institution, age, body mass index, income, and parity, there was no difference in composite adverse maternal outcomes among the racial and ethnic groups. Similarly, adverse neonatal outcomes, gestational age at prenatal diagnosis, rate of planned delivery by a multidisciplinary team, and cesarean hysterectomy were similar among groups. CONCLUSION:In our multicentered placenta accreta spectrum cohort, race and ethnicity were not associated with inequities in composite maternal or neonatal morbidity, timing of diagnosis, or planned multidisciplinary care. This study hypothesized that a comparable incidence of individual risk factors for perinatal morbidity and geographic proximity reduces potential inequities that may exist in a larger population.
PMID: 38761887
ISSN: 2589-9333
CID: 5694952

Disparities in perinatal COVID-19 infection and vaccination

Dubois, Bethany; Mills, Alexandra N; Jessel, Rebecca H; Lieb, Whitney; Glazer, Kimberly B
The COVID-19 pandemic exposed and exacerbated persistent health inequities in perinatal populations, resulting in disparities of maternal and fetal complications. In this narrative review, we present an adapted conceptual framework of perinatal social determinants of health in the setting of the COVID-19 pandemic and use this framework to contextualize the literature regarding disparities in COVID-19 vaccination and infection. We synthesize how elements of the structural context, individual socioeconomic position, and concrete intermediary determinants influence each other and perinatal COVID-19 vaccination and infection, arguing that systemic inequities at each level contribute to observed disparities in perinatal health outcomes. From there, we identify gaps in the literature, propose mechanisms for observed disparities, and conclude with a discussion of strategies to mitigate them.
PMID: 38960750
ISSN: 1558-075x
CID: 5698382

SARS-CoV-2 infection, inflammation and birth outcomes in a prospective NYC pregnancy cohort

Gigase, Frederieke A J; Jessel, Rebecca H; Kaplowitz, Elianna; Boychuk, Natalie; Ohrn, Sophie; Ibroci, Erona; Castro, Juliana; Lynch, Jezelle; Tubassum, Rushna; Balbierz, Amy; Molenaar, Nina M; Graziani, Mara; Missall, Roy; Flores, Tammy; Stern, Toni; Carreno, Juan Manuel; ,; Krammer, Florian; Adler, Alan; Brody, Rachel I; Lesseur, Corina; Chen, Jia; Ellington, Sascha; Galang, Romeo R; Snead, Margaret C; Howell, Elizabeth; Stone, Joanne; Bergink, Veerle; Dolan, Siobhan; Lieb, Whitney; Rommel, Anna-Sophie; de Witte, Lotje D; Janevic, Teresa
Associations between antenatal SARS-CoV-2 infection and pregnancy outcomes have been conflicting and the role of the immune system is currently unclear. This prospective cohort study investigated the interaction of antenatal SARS-CoV-2 infection, changes in cytokine and HS-CRP levels, birthweight and gestational age at birth. 2352 pregnant participants from New York City (2020-2022) were included. Plasma levels of interleukin (IL)-1β, IL-6, IL-17A and high-sensitivity C-reactive protein (HS-CRP) were quantified in blood specimens obtained across pregnancy. Quantile and linear regression models were conducted to 1) assess the impact of antenatal SARS-CoV-2 infection, overall and by timing of detection of SARS-CoV-2 positivity (< 20 weeks versus ≥ 20 weeks), on birthweight and gestational age at delivery; 2) examine the relationship between SARS-CoV-2 infection and maternal immune changes during pregnancy. All models were adjusted for maternal demographic and obstetric factors and pandemic timing. Birthweight models were additionally adjusted for gestational age at delivery and fetal sex. Immune marker models were also adjusted for gestational age at specimen collection and multiplex assay batch. 371 (15.8%) participants were infected with SARS-CoV-2 during pregnancy, of which 98 (26.4%) were infected at < 20 weeks gestation. Neither SARS-CoV-2 infection in general nor in early or late pregnancy was associated with lower birthweight nor earlier gestational age at delivery. Further, we did not observe cytokine or HS-CRP changes in response to SARS-CoV-2 infection and thus found no evidence to support a potential association between immune dysregulation and the diversity in pregnancy outcomes following infection.
PMID: 38522364
ISSN: 1872-7603
CID: 5646762

Impact of maternal SARS-CoV-2 infection in the placenta

Chapter by: Moore, Kendall; Jessel, Rebecca H.; Chen, Jia; Lesseur, Corina
in: International and Life Course Aspects of COVID-19 by
[S.l.] : Elsevier, 2024
pp. 329-337
ISBN: 9780323956499
CID: 5717092

Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) Antibody Titer Levels in Pregnant Individuals After Infection, Vaccination, or Both

Marshall, Christina L; Kaplowitz, Elianna; Ibroci, Erona; Chung, Kyle; Gigase, Frederieke A J; Lieber, Molly; Graziani, Mara; Ohrn, Sophie; Lynch, Jezelle; Castro, Juliana; Tubassum, Rushna; Mutawakil, Farida; Jessel, Rebecca; Molenaar, Nina; Rommel, Anna-Sophie; Sperling, Rhoda S; Howell, Elizabeth A; Feldman, Hannah; Krammer, Florian; Stadlbauer, Daniel; de Witte, Lotje D; Bergink, Veerle; Stone, Joanne; Janevic, Teresa; Dolan, Siobhan M; Lieb, Whitney
We examined differences in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) antibody responses in pregnant individuals with natural, vaccine-induced, or combined immunity. Participants had live or nonlive births between 2020 and 2022, were seropositive (SARS-CoV-2 spike protein, anti-S), and had available mRNA vaccination and infection information (n=260). We compared titer levels among three immunity profiles: 1) natural immunity (n=191), 2) vaccine-induced immunity (n=37), and 3) combined immunity (ie, natural and vaccine-induced immunity; n=32). We applied linear regression to compare anti-S titers between the groups, controlling for age, race and ethnicity, and time between vaccination or infection (whichever came last) and sample collection. Anti-S titers were 57.3% and 94.4% lower among those with vaccine-induced and natural immunity, respectively, compared with those with combined immunity ( P <.001, P =.005).
PMID: 37141599
ISSN: 1873-233x
CID: 5646752

Impact of prenatal COVID-19 vaccination on delivery and neonatal outcomes: Results from a New York City cohort

Ibroci, Erona; Liu, Xiaoqin; Lieb, Whitney; Jessel, Rebecca; Gigase, Frederieke A J; Chung, Kyle; Graziani, Mara; Lieber, Molly; Ohrn, Sophie; Lynch, Jezelle; Castro, Juliana; Marshall, Christina; Tubassum, Rushna; Mutawakil, Farida; Kaplowitz, Elianna T; Ellington, Sascha; Molenaar, Nina; Sperling, Rhoda S; Howell, Elizabeth A; Janevic, Teresa; Dolan, Siobhan M; Stone, Joanne; De Witte, Lotje D; Bergink, Veerle; Rommel, Anna-Sophie
Research suggest prenatal vaccination against coronavirus disease-19 (COVID-19) is safe. However, previous studies utilized retrospectively collected data or examined late pregnancy vaccinations. We investigated the associations of COVID-19 vaccination throughout pregnancy with delivery and neonatal outcomes. We included 1,794 mother-neonate dyads enrolled in the Generation C Study with known prenatal COVID-19 vaccination status and complete covariate and outcome data. We used multivariable quantile regressions to estimate the effect of prenatal COVID-19 vaccination on birthweight, delivery gestational age, and blood loss at delivery; and Poisson generalized linear models for Caesarean delivery (CD) and Neonatal Intensive Care Unit (NICU) admission. Using the above methods, we estimated effects of trimester of vaccine initiation on these outcomes. In our sample, 13.7% (n = 250) received at least one prenatal dose of any COVID-19 vaccine. Vaccination was not associated with birthweight (β = 12.42 g [-90.5, 114.8]), gestational age (β = 0.2 days [-1.1, 1.5]), blood loss (β = -50.6 ml [-107.0, 5.8]), the risks of CD (RR = 0.8; [0.6, 1.1]) or NICU admission (RR = 0.9 [0.5, 1.7]). Trimester of vaccine initiation was also not associated with these outcomes. Our findings suggest that there is no associated risk between prenatal COVID-19 vaccination and adverse delivery and neonatal outcomes in a cohort sample from NYC.
PMCID:9749885
PMID: 36526507
ISSN: 1873-2518
CID: 5646742