Melissa Spring Wong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Melissa Spring Wong has a total of 62 co-authors. Here are the top co-authors by number of shared publications:
Kimberly D. Gregory
Department of Obstetrics and Gynecology, Cedars-Sinai Medical Center, Los Angeles, CA, United States
3 shared publications- Sarah Madhu Temkin
Patient Support American Cancer Society Atlanta Georgia USA
3 shared publications Barry E Hurwitz
Department of Psychology, University of Miami, FL (B.E.H.).
2 shared publications- Brian Lee Claggett
Cardiovascular Division, Brigham and Women's Hospital, Harvard Medical School , 75 Francis Street, Boston, MA 02115
2 shared publications Catherine J. Vladutiu
Department of Obstetrics and Gynecology, University of North Carolina, Chapel Hill (C.J.V.).
2 shared publications- Cecilia B. Leggett
Department of Obstetrics and Gynecology, Cedars-Sinai Medical Center, Los Angeles, CA
2 shared publications
Latest Publications
- Open Access
- 14 August 2026
- Published by Springer Nature in Current Obstetrics and Gynecology Reports
- Vol. 15 (1) , 28
Correction: Artificial Intelligence Use in Menopause Care
- 14 August 2026
- Published by Springer Nature in Current Obstetrics and Gynecology Reports
- Vol. 15 (1) , 28
Open AccessCorrection: Artificial Intelligence Use in Menopause Care
- Open Access
- 30 July 2026
- Published by Springer Nature in Current Obstetrics and Gynecology Reports
- Vol. 15 (1) , 27
Current Obstetrics and Gynecology Reports
Purpose of Review: This report describes an overview of current applications of artificial intelligence in healthcare with specific focus on uses within women’s health and menopause care. We aim to identify which tools and methods have been applied to menopause diagnosis, symptom management, and treatment personalization, while also reflecting upon the structural and data barriers that prevent equitable use of AI in this domain. Recent Findings: As AI has continued to advanced rapidly within healthcare, mature applications such as in drug discovery and diagnostic imaging have shown promise to improve care. Despite this, advancements in menopuase care remain a significant gap: as of 2025, none of the 1,257 FDA-approved AI algorithms focus on menopause diagnosis or treatment. Existing maching learning approaches are limited by data issues such as sparse, inconsistently captured clinical data as well as underrepresentation of large groups of women, partricularly women of color, in research databases. Data missingness disproportionately affects already-underserved populations, meaning application of these AI tools risks amplifying these disparities further. Summary: While menopause represents a potential space for development of artificial intelligence solutions, meaningful structural changes to data acquisition and interpretation are required to ensure accurate, impactful, and equitable care.
- 30 July 2026
- Published by Springer Nature in Current Obstetrics and Gynecology Reports
- Vol. 15 (1) , 27
Open AccessCurrent Obstetrics and Gynecology Reports
Purpose of Review: This report describes an overview of current applications of artificial intelligence in healthcare with specific focus on uses within women’s health and menopause care. We aim to identify which tools and methods have been applied to menopause diagnosis, symptom management, and treatment personalization, while also reflecting upon the structural and data barriers that prevent equitable use of AI in this domain. Recent Findings: As AI has continued to advanced rapidly within healthcare, mature applications such as in drug discovery and diagnostic imaging have shown promise to improve care. Despite this, advancements in menopuase care remain a significant gap: as of 2025, none of the 1,257 FDA-approved AI algorithms focus on menopause diagnosis or treatment. Existing maching learning approaches are limited by data issues such as sparse, inconsistently captured clinical data as well as underrepresentation of large groups of women, partricularly women of color, in research databases. Data missingness disproportionately affects already-underserved populations, meaning application of these AI tools risks amplifying these disparities further. Summary: While menopause represents a potential space for development of artificial intelligence solutions, meaningful structural changes to data acquisition and interpretation are required to ensure accurate, impactful, and equitable care.
- Open Access
- 31 May 2024
- Published by Elsevier in Social Science & Medicine
- Vol. 351, 116556
“Women's work”: Gender and the physician workforce
- 31 May 2024
- Published by Elsevier in Social Science & Medicine
- Vol. 351, 116556
Open Access“Women's work”: Gender and the physician workforce
- Open Access
- 1 February 2024
- Published by Wolters Kluwer Health in Hypertension
- Vol. 81 (2) , 255-263
Cardiac Abnormalities in Hispanic/Latina Women With Prior De Novo Hypertensive Disorders of Pregnancy
BACKGROUND: Hypertensive disorders of pregnancy (HDP) are associated with long-term maternal risks for cardiovascular disease for reasons that remain incompletely understood. METHODS: The HCHS/SOL (Hispanic Community Health Study/Study of Latinos), a multi-center community-based cohort of Hispanic/Latino adults recruited 2008 to 2011, was used to evaluate the associations of history of de novo HDP (gestational hypertension, preeclampsia, eclampsia) with echocardiographic measures of cardiac structure and function in Hispanic/Latina women with ≥1 prior pregnancy and the proportion of association mediated by current hypertension (>140/90 mm Hg or antihypertensive therapy). RESULTS.: The study cohort included 5168 Hispanic/Latina women with an average age (SD) of 58.7 (9.7) years at time of echocardiogram. Prior de novo HDP was reported by 724 (14%) of the women studied and was associated with lower left ventricle (LV) ejection fraction −0.66 (95% confidence interval [CI], −1.21 to −0.11), higher LV relative wall thickness 0.09 (95% CI, 0–0.18), and 1.39 (95% CI, 1.02–1.89) higher risk of abnormal LV geometry after adjusting for blood pressure and other confounders. The proportion of the association mediated by current hypertension between HDP and LV ejection fraction was 0.09 (95% CI, 0.03–0.45), LV relative wall thickness was 0.28 (95% CI, 0.16–0.51), abnormal LV geometry was 0.14 (95% CI, 0.12–0.48), concentric left ventricular hypertrophy was 0.31 (95% CI, 0.19–0.86), and abnormal LV diastolic dysfunction was 0.58 (95% CI, 0.26–0.79). CONCLUSIONS.: In a large cohort of Hispanic/Latina women those with history of de novo HDP had detectable and measurable subclinical alterations in cardiac structure and both systolic and diastolic dysfunction that were only partially mediated by current hypertension.
- 1 February 2024
- Published by Wolters Kluwer Health in Hypertension
- Vol. 81 (2) , 255-263
Open AccessCardiac Abnormalities in Hispanic/Latina Women With Prior De Novo Hypertensive Disorders of Pregnancy
BACKGROUND: Hypertensive disorders of pregnancy (HDP) are associated with long-term maternal risks for cardiovascular disease for reasons that remain incompletely understood. METHODS: The HCHS/SOL (Hispanic Community Health Study/Study of Latinos), a multi-center community-based cohort of Hispanic/Latino adults recruited 2008 to 2011, was used to evaluate the associations of history of de novo HDP (gestational hypertension, preeclampsia, eclampsia) with echocardiographic measures of cardiac structure and function in Hispanic/Latina women with ≥1 prior pregnancy and the proportion of association mediated by current hypertension (>140/90 mm Hg or antihypertensive therapy). RESULTS.: The study cohort included 5168 Hispanic/Latina women with an average age (SD) of 58.7 (9.7) years at time of echocardiogram. Prior de novo HDP was reported by 724 (14%) of the women studied and was associated with lower left ventricle (LV) ejection fraction −0.66 (95% confidence interval [CI], −1.21 to −0.11), higher LV relative wall thickness 0.09 (95% CI, 0–0.18), and 1.39 (95% CI, 1.02–1.89) higher risk of abnormal LV geometry after adjusting for blood pressure and other confounders. The proportion of the association mediated by current hypertension between HDP and LV ejection fraction was 0.09 (95% CI, 0.03–0.45), LV relative wall thickness was 0.28 (95% CI, 0.16–0.51), abnormal LV geometry was 0.14 (95% CI, 0.12–0.48), concentric left ventricular hypertrophy was 0.31 (95% CI, 0.19–0.86), and abnormal LV diastolic dysfunction was 0.58 (95% CI, 0.26–0.79). CONCLUSIONS.: In a large cohort of Hispanic/Latina women those with history of de novo HDP had detectable and measurable subclinical alterations in cardiac structure and both systolic and diastolic dysfunction that were only partially mediated by current hypertension.
- Open Access
Cardiac Abnormalities in Hispanic Women with Prior De Novo Hypertensive Disorders of Pregnancy
Background: Hypertensive disorders of pregnancy (HDP) are associated with longer-term maternal risks for cardiovascular disease for reasons that remain incompletely understood. Methods: The Hispanic Community Health Study/Study of Latinos (HCHS/SOL), a multi-center community-based cohort of Hispanic/Latino adults recruited 2008 to 2011 was used to evaluate the associations of history of de novo HDP (gestational hypertension, preeclampsia, eclampsia) with echocardiographic measures of left ventricular (LV) structure and function in Hispanic/Latina women with ≥1 prior pregnancy and the proportion of association mediated by current hypertension. Results: The study cohort included 5,168 Hispanic/Latina women. Prior de novo HDP was reported by 724 (14%) of the women studied with an average age of 58.7 ± 9.7 years at time of echocardiogram and was associated with lower ejection fraction −0.66 (−1.21, −0.11), greater relative wall thickness (RWT) 0.09 (0, 0.18), and 1.39 (1.02, 1.89) greater odds of abnormal LV geometry after adjusting for blood pressure and other risk factors. The proportion of association mediated by current hypertension between HDP and LV ejection fraction was 0.09 (95% CI 0.03, 0.45), any abnormal LV geometry was 0.14 (0.12, 0.48), LV RWT 0.28 (0.16, 0.51), concentric LVH was 0.31 (0.19, 0.86), and abnormal LV diastolic dysfunction was 0.58 (0.26, 1.79). Conclusions: In a large cohort of Hispanic/Latina women those with de novo HDP had detectable and measurable subclinical alterations in cardiac structure and both systolic and diastolic dysfunction that were only partially mediated by current hypertension.
Open AccessCardiac Abnormalities in Hispanic Women with Prior De Novo Hypertensive Disorders of Pregnancy
Background: Hypertensive disorders of pregnancy (HDP) are associated with longer-term maternal risks for cardiovascular disease for reasons that remain incompletely understood. Methods: The Hispanic Community Health Study/Study of Latinos (HCHS/SOL), a multi-center community-based cohort of Hispanic/Latino adults recruited 2008 to 2011 was used to evaluate the associations of history of de novo HDP (gestational hypertension, preeclampsia, eclampsia) with echocardiographic measures of left ventricular (LV) structure and function in Hispanic/Latina women with ≥1 prior pregnancy and the proportion of association mediated by current hypertension. Results: The study cohort included 5,168 Hispanic/Latina women. Prior de novo HDP was reported by 724 (14%) of the women studied with an average age of 58.7 ± 9.7 years at time of echocardiogram and was associated with lower ejection fraction −0.66 (−1.21, −0.11), greater relative wall thickness (RWT) 0.09 (0, 0.18), and 1.39 (1.02, 1.89) greater odds of abnormal LV geometry after adjusting for blood pressure and other risk factors. The proportion of association mediated by current hypertension between HDP and LV ejection fraction was 0.09 (95% CI 0.03, 0.45), any abnormal LV geometry was 0.14 (0.12, 0.48), LV RWT 0.28 (0.16, 0.51), concentric LVH was 0.31 (0.19, 0.86), and abnormal LV diastolic dysfunction was 0.58 (0.26, 1.79). Conclusions: In a large cohort of Hispanic/Latina women those with de novo HDP had detectable and measurable subclinical alterations in cardiac structure and both systolic and diastolic dysfunction that were only partially mediated by current hypertension.
- Open Access
- 13 December 2022
- Published by Frontiers Media SA in Frontiers in Pain Research
- Vol. 3, 1063751
Patient perceptions of virtual reality for pain relief in labor: A qualitative study
Introduction: Labor represents the most common reason for hospitalization, and most patients will use some form of pain management during their labor. While some studies have suggested that virtual reality (VR) may be an effective option for managing pain, more study is necessary to understand the patient experience of VR. The aim of this study is to characterize the effect of VR on patient perceptions of coping in labor and their descriptions of the VR experience.Methodology: A nested prospective, descriptive study within a randomized controlled trial of VR in laboring patients. We included nulliparous, term patients, having contractions at least every 5 min, a pain score on the Wong-Baker pain scale of 4–7, and who had been randomized to receive the 30 min virtual reality intervention in the trial. Subjects completed a childbirth self-efficacy inventory prior to the intervention. After the intervention, they completed a modified childbirth self-efficacy inventory related to VR and underwent a structured interview. Self-efficacy scores were compared using t-tests and qualitative, thematic analysis was performed using Dedoose.Results: Twenty-one subjects received the VR intervention. Twenty subjects completed the post-intervention survey and structured interview; one declined due to discomfort. Subjects noted a significant increase in perceived degree to which VR could improve their self-efficacy in managing pain during labor. Thematic analysis revealed that subjects described the VR experience as allowing them to connect with their breathing, feeling more relaxed, and being distracted from pain. In total, 70% believed VR reduced their pain, 60% felt it reduced their anxiety, and 100% would recommend VR availability for laboring patients.Conclusion: VR can improve patient self-efficacy for managing pain in labor. Future studies should focus on the content of the visualizations, optimized user experience and design, and effectiveness with ongoing exposure to VR content in labor.
- 13 December 2022
- Published by Frontiers Media SA in Frontiers in Pain Research
- Vol. 3, 1063751
Open AccessPatient perceptions of virtual reality for pain relief in labor: A qualitative study
Introduction: Labor represents the most common reason for hospitalization, and most patients will use some form of pain management during their labor. While some studies have suggested that virtual reality (VR) may be an effective option for managing pain, more study is necessary to understand the patient experience of VR. The aim of this study is to characterize the effect of VR on patient perceptions of coping in labor and their descriptions of the VR experience.Methodology: A nested prospective, descriptive study within a randomized controlled trial of VR in laboring patients. We included nulliparous, term patients, having contractions at least every 5 min, a pain score on the Wong-Baker pain scale of 4–7, and who had been randomized to receive the 30 min virtual reality intervention in the trial. Subjects completed a childbirth self-efficacy inventory prior to the intervention. After the intervention, they completed a modified childbirth self-efficacy inventory related to VR and underwent a structured interview. Self-efficacy scores were compared using t-tests and qualitative, thematic analysis was performed using Dedoose.Results: Twenty-one subjects received the VR intervention. Twenty subjects completed the post-intervention survey and structured interview; one declined due to discomfort. Subjects noted a significant increase in perceived degree to which VR could improve their self-efficacy in managing pain during labor. Thematic analysis revealed that subjects described the VR experience as allowing them to connect with their breathing, feeling more relaxed, and being distracted from pain. In total, 70% believed VR reduced their pain, 60% felt it reduced their anxiety, and 100% would recommend VR availability for laboring patients.Conclusion: VR can improve patient self-efficacy for managing pain in labor. Future studies should focus on the content of the visualizations, optimized user experience and design, and effectiveness with ongoing exposure to VR content in labor.
- 25 June 2022
- Published by Georg Thieme Verlag KG in American Journal of Perinatology
- Vol. 41 (S 01) , e412-e419
Applying Automated Machine Learning to Predict Mode of Delivery Using Ongoing Intrapartum Data in Laboring Patients
Objective This study aimed to develop and validate a machine learning (ML) model to predict the probability of a vaginal delivery (Partometer) using data iteratively obtained during labor from the electronic health record. Study Design A retrospective cohort study of deliveries at an academic, tertiary care hospital was conducted from 2013 to 2019 who had at least two cervical examinations. The population was divided into those delivered by physicians with nulliparous term singleton vertex (NTSV) cesarean delivery rates <23.9% (Partometer cohort) and the remainder (control cohort). The cesarean rate among this population of lower risk patients is a standard metric by which to compare provider rates; <23.9% was the Healthy People 2020 goal. A supervised automated ML approach was applied to generate a model for each population. The primary outcome was accuracy of the model developed on the Partometer cohort at 4 hours from admission to labor and delivery. Secondary outcomes included discrimination ability (receiver operating characteristics–area under the curve [ROC-AUC]), precision-recall AUC, and calibration of the Partometer. To assess generalizability, we compared the performance and clinical predictors identified by the Partometer to the control model. Results There were 37,932 deliveries during the study period; after exclusions, 9,385 deliveries were included in the Partometer cohort and 19,683 in the control cohort. Accuracy of predicting vaginal delivery at 4 hours was 87.1% for the Partometer (ROC-AUC: 0.82). Clinical predictors of greatest importance in the stacked Intrapartum Partometer Model included the Admission Model prediction and ongoing measures of dilatation and station which mirrored those found in the control population. Conclusion Using automated ML and intrapartum factors improved the accuracy of prediction of probability of a vaginal delivery over both previously published models based on logistic regression. Harnessing real-time data and ML could represent the bridge to generating a truly prescriptive tool to augment clinical decision-making, predict labor outcomes, and reduce maternal and neonatal morbidity. Key Points
- 25 June 2022
- Published by Georg Thieme Verlag KG in American Journal of Perinatology
- Vol. 41 (S 01) , e412-e419
Applying Automated Machine Learning to Predict Mode of Delivery Using Ongoing Intrapartum Data in Laboring Patients
Objective This study aimed to develop and validate a machine learning (ML) model to predict the probability of a vaginal delivery (Partometer) using data iteratively obtained during labor from the electronic health record. Study Design A retrospective cohort study of deliveries at an academic, tertiary care hospital was conducted from 2013 to 2019 who had at least two cervical examinations. The population was divided into those delivered by physicians with nulliparous term singleton vertex (NTSV) cesarean delivery rates <23.9% (Partometer cohort) and the remainder (control cohort). The cesarean rate among this population of lower risk patients is a standard metric by which to compare provider rates; <23.9% was the Healthy People 2020 goal. A supervised automated ML approach was applied to generate a model for each population. The primary outcome was accuracy of the model developed on the Partometer cohort at 4 hours from admission to labor and delivery. Secondary outcomes included discrimination ability (receiver operating characteristics–area under the curve [ROC-AUC]), precision-recall AUC, and calibration of the Partometer. To assess generalizability, we compared the performance and clinical predictors identified by the Partometer to the control model. Results There were 37,932 deliveries during the study period; after exclusions, 9,385 deliveries were included in the Partometer cohort and 19,683 in the control cohort. Accuracy of predicting vaginal delivery at 4 hours was 87.1% for the Partometer (ROC-AUC: 0.82). Clinical predictors of greatest importance in the stacked Intrapartum Partometer Model included the Admission Model prediction and ongoing measures of dilatation and station which mirrored those found in the control population. Conclusion Using automated ML and intrapartum factors improved the accuracy of prediction of probability of a vaginal delivery over both previously published models based on logistic regression. Harnessing real-time data and ML could represent the bridge to generating a truly prescriptive tool to augment clinical decision-making, predict labor outcomes, and reduce maternal and neonatal morbidity. Key Points
- 16 June 2022
- Published by Elsevier in Gastroenterology
- Vol. 162 (7)
EP1299: BIOLOGIC USE AND PREGNANCY AND NEONATAL OUTCOMES IN PREGNANT PEOPLE WITH INFLAMMATORY BOWEL DISEASE
- 16 June 2022
- Published by Elsevier in Gastroenterology
- Vol. 162 (7)
EP1299: BIOLOGIC USE AND PREGNANCY AND NEONATAL OUTCOMES IN PREGNANT PEOPLE WITH INFLAMMATORY BOWEL DISEASE
- 1 April 2022
- Published by Elsevier in American Journal of Obstetrics and Gynecology
- Vol. 226 (4) , 552.e1-552.e6
Incorporating personal-device-based point-of-care ultrasound into obstetric care: a validation study
- 1 April 2022
- Published by Elsevier in American Journal of Obstetrics and Gynecology
- Vol. 226 (4) , 552.e1-552.e6
Incorporating personal-device-based point-of-care ultrasound into obstetric care: a validation study
- Open Access
- 1 January 2022
- Published by Elsevier in American Journal of Obstetrics and Gynecology
- Vol. 226 (1) , S736
Identification of criteria missed by clinicians among patients not prescribed aspirin prophylaxis for preeclampsia
- 1 January 2022
- Published by Elsevier in American Journal of Obstetrics and Gynecology
- Vol. 226 (1) , S736
Open AccessIdentification of criteria missed by clinicians among patients not prescribed aspirin prophylaxis for preeclampsia