Lawrence D. Devoe
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lawrence D. Devoe has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- David W. Britt
Fetal Medicine Foundation of America, USA
3 shared publications - Mark I. Evans
Fetal Medicine Foundation of America, USA
3 shared publications - Christian Macedonia
University of Michigan, USA
2 shared publications - Claudia Szlek
Department of Obstetrics and Gynecology, Medical College of Georgia, Augusta, GA 30912, USA
2 shared publications - George M Mussallli
Department of Obstetrics, Gynecology, and Reproductive Sciences, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA
2 shared publications - James E. Maher
Department of Obstetrics and Gynecology (A.B., P.C.W., J.M., J.L.F.), Medical College of Georgia at Augusta University
2 shared publications
Latest Publications
- Open Access
- 26 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health
Early detection of intrapartum risks enables timely interventions to prevent or mitigate adverse labor outcomes such as cerebral palsy. However, accurate automated systems to support clinical decision-making during delivery are currently lacking. To address this gap, we propose Artificial Intelligence for Modeling and Explaining Neonatal Health (AIMEN), a deep learning framework that predicts adverse labor outcomes from maternal, fetal, obstetrical, and intrapartum factors while providing interpretable reasoning behind its predictions. AIMEN reveals how specific modifications to input variables could alter predicted outcomes, enhancing clinical insight. To address class imbalance and limited sample size, AIMEN employs Conditional Tabular GAN (CTGAN) for data augmentation. This process includes synthetic data generation, and we investigate in detail properties such as relaxing feature bounds for a subset of training points to explore slightly out-of-range physiological values, and applying silhouette-score-based filtering to increase the separability of synthetic samples. AIMEN uses an ensemble of fully connected neural networks for classification and outperforms state-of-the-art models such as XGBoost, TabNet, DANet, and LightGBM, achieving an average F1 score of 0.784 in predicting high-risk deliveries. Moreover, AIMEN generates counterfactual explanations that identify actionable changes involving only two to three attributes on average. Resources: https://github.com/ab9mamun/AIMEN.
- 26 May 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
Open AccessUse of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Health
Early detection of intrapartum risks enables timely interventions to prevent or mitigate adverse labor outcomes such as cerebral palsy. However, accurate automated systems to support clinical decision-making during delivery are currently lacking. To address this gap, we propose Artificial Intelligence for Modeling and Explaining Neonatal Health (AIMEN), a deep learning framework that predicts adverse labor outcomes from maternal, fetal, obstetrical, and intrapartum factors while providing interpretable reasoning behind its predictions. AIMEN reveals how specific modifications to input variables could alter predicted outcomes, enhancing clinical insight. To address class imbalance and limited sample size, AIMEN employs Conditional Tabular GAN (CTGAN) for data augmentation. This process includes synthetic data generation, and we investigate in detail properties such as relaxing feature bounds for a subset of training points to explore slightly out-of-range physiological values, and applying silhouette-score-based filtering to increase the separability of synthetic samples. AIMEN uses an ensemble of fully connected neural networks for classification and outperforms state-of-the-art models such as XGBoost, TabNet, DANet, and LightGBM, achieving an average F1 score of 0.784 in predicting high-risk deliveries. Moreover, AIMEN generates counterfactual explanations that identify actionable changes involving only two to three attributes on average. Resources: https://github.com/ab9mamun/AIMEN.
- Open Access
- 14 May 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (10) , 1490
Recurrent Hodgkin’s Lymphoma Detected Using Abnormal NIPT in Pregnancy: A Case Report and Literature Review
Background: Non-invasive prenatal testing (NIPT) examines cell-free DNA (cfDNA) in maternal serum, which includes both maternal DNA and apoptotic placental DNA. The presence of multiple aneuploidies or widespread abnormal patterns of gains and losses across chromosomes in a structurally normal fetus has been linked to maternal cancer. Case Presentation: The patient was a 22-year-old G1P0 with a history of classical Hodgkin’s lymphoma in remission. Her NIPT collected at 14 weeks and 3 days was reported as a “no call”. A second NIPT at a different laboratory showed multiple chromosomal aneuploidies (trisomy 18, 21, and monosomy X) with normal fetal anatomy on ultrasound. The patient was asymptomatic and was referred to hematology–oncology specifically to address the concern that these NIPT results could be related to cancer recurrence. Imaging was deferred as she was already on an established surveillance protocol for her Hodgkin’s lymphoma. At 26 weeks of gestation, the patient presented with a cough and dyspnea. Chest x-ray raised concern for disease recurrence, and biopsy confirmed recurrent Hodgkin’s lymphoma. She received two cycles of ICE chemotherapy. Cesarean delivery at 34 weeks and 2 days was performed for non-reassuring fetal heart tones. She continued chemotherapy, followed by BEAM conditioning and autologous stem cell transplantation. Genetic testing of the neonate revealed a normal karyotype; the placenta karyotype yielded no interpretable results. Discussion and Conclusions: Certain patterns of abnormal NIPT results may be associated with maternal malignancy and warrant further investigation. The absence of standardized protocols for reporting such NIPT results can complicate timely interdisciplinary evaluation and treatment. However, diagnostic testing should be offered with a positive NIPT result, a no-call or test failure, and abnormal ultrasound results, even with a “low-risk” NIPT result.
- 14 May 2026
- Published by MDPI AG in Diagnostics
- Vol. 16 (10) , 1490
Open AccessRecurrent Hodgkin’s Lymphoma Detected Using Abnormal NIPT in Pregnancy: A Case Report and Literature Review
Background: Non-invasive prenatal testing (NIPT) examines cell-free DNA (cfDNA) in maternal serum, which includes both maternal DNA and apoptotic placental DNA. The presence of multiple aneuploidies or widespread abnormal patterns of gains and losses across chromosomes in a structurally normal fetus has been linked to maternal cancer. Case Presentation: The patient was a 22-year-old G1P0 with a history of classical Hodgkin’s lymphoma in remission. Her NIPT collected at 14 weeks and 3 days was reported as a “no call”. A second NIPT at a different laboratory showed multiple chromosomal aneuploidies (trisomy 18, 21, and monosomy X) with normal fetal anatomy on ultrasound. The patient was asymptomatic and was referred to hematology–oncology specifically to address the concern that these NIPT results could be related to cancer recurrence. Imaging was deferred as she was already on an established surveillance protocol for her Hodgkin’s lymphoma. At 26 weeks of gestation, the patient presented with a cough and dyspnea. Chest x-ray raised concern for disease recurrence, and biopsy confirmed recurrent Hodgkin’s lymphoma. She received two cycles of ICE chemotherapy. Cesarean delivery at 34 weeks and 2 days was performed for non-reassuring fetal heart tones. She continued chemotherapy, followed by BEAM conditioning and autologous stem cell transplantation. Genetic testing of the neonate revealed a normal karyotype; the placenta karyotype yielded no interpretable results. Discussion and Conclusions: Certain patterns of abnormal NIPT results may be associated with maternal malignancy and warrant further investigation. The absence of standardized protocols for reporting such NIPT results can complicate timely interdisciplinary evaluation and treatment. However, diagnostic testing should be offered with a positive NIPT result, a no-call or test failure, and abnormal ultrasound results, even with a “low-risk” NIPT result.
- Open Access
- 20 March 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (6) , 2388
Hepatic Ectopic Pregnancy: A Diagnostic Challenge Highlighted by Multimodal Imaging
Background: Ectopic pregnancy occurs in about 1–2% of all pregnancies, with 95% implanting in the fallopian tubes. Hepatic implantation is one of the rarest and most dangerous forms of abdominal ectopic pregnancy. Its diagnosis is often delayed because of nonspecific symptoms, and it is also often difficult for routine ultrasound imaging to visualize ectopic pregnancy sites that are not in the pelvis. Since this type of pregnancy carries a risk of severe hemorrhage, early identification is crucial. Case: A 30-year-old woman, gravida 3 para 2, presented with a serum β-hCG of 66,408 mIU/mL, but no intrauterine pregnancy was detected on ultrasound imaging. At an outside facility, a laparoscopy was performed, which also failed to show a pelvic ectopic pregnancy. The patient then received her first dose of methotrexate and was subsequently transferred to a tertiary care center for further evaluation. MRI and liver ultrasound showed a 2.3 cm subcapsular lesion in segment 5 of the liver that was suspicious for a hepatic ectopic pregnancy. However, these imaging studies could not exclude a gestational trophoblastic disease or hepatic neoplasm. A dilation and curettage revealed no trophoblastic tissue. The patient next received two additional doses of methotrexate on hospital days 4 and 7 due to an inadequate decline in interval β-hCG; β-hCG levels declined gradually but steadily over several months until they became undetectable and indicated a successful medical treatment of her hepatic ectopic pregnancy. Conclusions: This case highlights the complex diagnostic and treatment challenges presented by a hepatic ectopic pregnancy. Multimodal imaging, serial monitoring of β-hCG levels, and the engagement of a multidisciplinary team were essential factors in achieving a safe, nonsurgical, and successful resolution of this condition. When a pregnancy of unknown location is suspected, extended imaging studies are critical tools for patient evaluation after initial imaging studies and laparoscopy are inconclusive.
- 20 March 2026
- Published by MDPI AG in Journal of Clinical Medicine
- Vol. 15 (6) , 2388
Open AccessHepatic Ectopic Pregnancy: A Diagnostic Challenge Highlighted by Multimodal Imaging
Background: Ectopic pregnancy occurs in about 1–2% of all pregnancies, with 95% implanting in the fallopian tubes. Hepatic implantation is one of the rarest and most dangerous forms of abdominal ectopic pregnancy. Its diagnosis is often delayed because of nonspecific symptoms, and it is also often difficult for routine ultrasound imaging to visualize ectopic pregnancy sites that are not in the pelvis. Since this type of pregnancy carries a risk of severe hemorrhage, early identification is crucial. Case: A 30-year-old woman, gravida 3 para 2, presented with a serum β-hCG of 66,408 mIU/mL, but no intrauterine pregnancy was detected on ultrasound imaging. At an outside facility, a laparoscopy was performed, which also failed to show a pelvic ectopic pregnancy. The patient then received her first dose of methotrexate and was subsequently transferred to a tertiary care center for further evaluation. MRI and liver ultrasound showed a 2.3 cm subcapsular lesion in segment 5 of the liver that was suspicious for a hepatic ectopic pregnancy. However, these imaging studies could not exclude a gestational trophoblastic disease or hepatic neoplasm. A dilation and curettage revealed no trophoblastic tissue. The patient next received two additional doses of methotrexate on hospital days 4 and 7 due to an inadequate decline in interval β-hCG; β-hCG levels declined gradually but steadily over several months until they became undetectable and indicated a successful medical treatment of her hepatic ectopic pregnancy. Conclusions: This case highlights the complex diagnostic and treatment challenges presented by a hepatic ectopic pregnancy. Multimodal imaging, serial monitoring of β-hCG levels, and the engagement of a multidisciplinary team were essential factors in achieving a safe, nonsurgical, and successful resolution of this condition. When a pregnancy of unknown location is suspected, extended imaging studies are critical tools for patient evaluation after initial imaging studies and laparoscopy are inconclusive.
- 14 January 2026
- Published by Wiley in BJOG: An International Journal of Obstetrics & Gynaecology
- Vol. 133 (6) , 1186-1187
Managing Impacted Fetal Head: Insights From a Simulation Study of Applied Forces
- 14 January 2026
- Published by Wiley in BJOG: An International Journal of Obstetrics & Gynaecology
- Vol. 133 (6) , 1186-1187
Managing Impacted Fetal Head: Insights From a Simulation Study of Applied Forces
- Open Access
- 28 September 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (19) , 2482
Generational Leaps in Intrapartum Fetal Surveillance
Background/Objectives: Electronic fetal monitoring (EFM) has been used for intrapartum fetal surveillance for over 50 years. Despite numerous trials comparing EFM with standard fetal heart rate (FHR) auscultation, it remains contentious whether continuous monitoring with standard interpretation has reliably improved perinatal outcomes, specifically lower rates of perinatal morbidity and mortality. This review examines previous attempts to improve fetal monitoring and presents future directions for novel intrapartum fetal surveillance systems. Methods: We conducted a chronological review of EFM developments, including ancillary methods such as fetal ECG analysis, automated systems for FHR analysis, and artificial intelligence applications. We analyzed the evolution from visual interpretation to intelligent systems and evaluated the performance of various automated monitoring platforms. Results: Various ancillary methods developed to improve EFM accuracy for predicting fetal compromise have shown limited success. Only a limited number of studies demonstrated that adding fetal ECG analysis to visual FHR pattern interpretation resulted in better fetal outcomes. Automated systems for FHR analysis have not consistently enhanced intrapartum fetal surveillance. However, novel approaches such as the Fetal Reserve Index (FRI) show promise by incorporating clinical risk factors with traditional FHR patterns to provide higher-level risk assessment and prognosis. Conclusions: The shortcomings of visual interpretation of FHR patterns persist despite technological advances. Future intelligent intrapartum surveillance systems must combine conventional fetal monitoring with comprehensive risk assessment that incorporates maternal, fetal, and obstetric factors. The integration of artificial intelligence with contextualized metrics like the FRI represents the most promising direction for improving intrapartum fetal surveillance and clinical outcomes.
- 28 September 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (19) , 2482
Open AccessGenerational Leaps in Intrapartum Fetal Surveillance
Background/Objectives: Electronic fetal monitoring (EFM) has been used for intrapartum fetal surveillance for over 50 years. Despite numerous trials comparing EFM with standard fetal heart rate (FHR) auscultation, it remains contentious whether continuous monitoring with standard interpretation has reliably improved perinatal outcomes, specifically lower rates of perinatal morbidity and mortality. This review examines previous attempts to improve fetal monitoring and presents future directions for novel intrapartum fetal surveillance systems. Methods: We conducted a chronological review of EFM developments, including ancillary methods such as fetal ECG analysis, automated systems for FHR analysis, and artificial intelligence applications. We analyzed the evolution from visual interpretation to intelligent systems and evaluated the performance of various automated monitoring platforms. Results: Various ancillary methods developed to improve EFM accuracy for predicting fetal compromise have shown limited success. Only a limited number of studies demonstrated that adding fetal ECG analysis to visual FHR pattern interpretation resulted in better fetal outcomes. Automated systems for FHR analysis have not consistently enhanced intrapartum fetal surveillance. However, novel approaches such as the Fetal Reserve Index (FRI) show promise by incorporating clinical risk factors with traditional FHR patterns to provide higher-level risk assessment and prognosis. Conclusions: The shortcomings of visual interpretation of FHR patterns persist despite technological advances. Future intelligent intrapartum surveillance systems must combine conventional fetal monitoring with comprehensive risk assessment that incorporates maternal, fetal, and obstetric factors. The integration of artificial intelligence with contextualized metrics like the FRI represents the most promising direction for improving intrapartum fetal surveillance and clinical outcomes.
- Open Access
- 23 January 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (3) , 255
Reconceptualizing Intrauterine Resuscitation and Its Short-Term Impact
Objective: Intrauterine resuscitation (IR) may be employed during labor to reduce emergency deliveries with concerns for fetal wellbeing emanating mostly from increased uterine contraction frequency and/or intensity. However, there is no standard definition of what constitutes IR, and how its impact is assessed. Here, we have created two measures of relative IR effectiveness, determined over a two-hour time frame after Pitocin was first initiated, and asked how fetal risk severity at the time of its initiation impacted IR effectiveness and the clinical decisions made. Methods: We analyzed 118 patients receiving Pitocin who underwent IR at least once during labor. Retrospectively, we assessed risk levels using our Fetal Reserve Index version 2 (FRI v2) scores that were calculated in 20 min timeframes. FRIv2 scores include various maternal, obstetric, and fetal risk factors, uterine contraction frequency, and FHR baseline rate, variability, accelerations, and decelerations. We define 3 IR scenarios to assess relative IR effectiveness. (1) No reduction in PIT infusion rates (PITSAME), (2) decreased PIT infusion rates (DPIT), or (3) PIT turned off (PIT OFF). Maternal repositioning and oxygen administration are nearly universal across all types and, therefore, are not considered in groupings. We then created two measures of IR effectiveness by classifying changes in FRI v2 scores over six 20 min windows coincident with and following IR use as (1) “Improvement” (improvement relative to the FRIv2 score at IR initiation) and (2) “Stabilization” (no further decrease in FRI score relative to the FRIv2 score in the sixth 20 min epoch after IR initiation). We evaluated the relative effectiveness of the three PIT options, and to test whether the level of fetal risk at the time of IR initiation affected its short-term effectiveness, FRI v2 risk scores were assigned to one of three groups (Green [1.00–0.625]; Yellow [0.50–0.25]; Red 0.25–0.0]). Higher scores indicate lower risk. Statistical analysis was performed with ANOVA and t- tests. Results: Overall, the first and/or the only initiation of IR resulted in improvement in 71% of cases and stabilization in 78% of cases. The remaining 22% were failures, meaning that the FRIv2 score in the 6th 20 min period was lower than the score at the time of initiation. There were modest, but not statistically significant, differences in effectiveness (improvement or stabilization) by type of IR. There was a trend toward lower IR effectiveness of PIT OFF during IR initiation when compared to PIT continuation or decreased groups. Conclusions: IR initiation or type did not vary significantly by retrospectively calculated levels of fetal risk, showing that wide variation in clinician practices, not necessarily correlated with what we believe actual risk was, determine how IR was used. The FRI provides contextualization of FHR elements by adding maternal, fetal, and obstetric risk factors, and increased uterine activity enables a more rigorous and reproducible approach to analysis of emerging fetal compromise and IR effectiveness. As practice has shifted from the over-aggressiveness of PIT use to now premature discontinuations with any tracing variation, we need better metrics. FRIv2 further improves its physiologic underpinnings. Thus, we propose a new approach to the overall assessment of IR practice.
- 23 January 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (3) , 255
Open AccessReconceptualizing Intrauterine Resuscitation and Its Short-Term Impact
Objective: Intrauterine resuscitation (IR) may be employed during labor to reduce emergency deliveries with concerns for fetal wellbeing emanating mostly from increased uterine contraction frequency and/or intensity. However, there is no standard definition of what constitutes IR, and how its impact is assessed. Here, we have created two measures of relative IR effectiveness, determined over a two-hour time frame after Pitocin was first initiated, and asked how fetal risk severity at the time of its initiation impacted IR effectiveness and the clinical decisions made. Methods: We analyzed 118 patients receiving Pitocin who underwent IR at least once during labor. Retrospectively, we assessed risk levels using our Fetal Reserve Index version 2 (FRI v2) scores that were calculated in 20 min timeframes. FRIv2 scores include various maternal, obstetric, and fetal risk factors, uterine contraction frequency, and FHR baseline rate, variability, accelerations, and decelerations. We define 3 IR scenarios to assess relative IR effectiveness. (1) No reduction in PIT infusion rates (PITSAME), (2) decreased PIT infusion rates (DPIT), or (3) PIT turned off (PIT OFF). Maternal repositioning and oxygen administration are nearly universal across all types and, therefore, are not considered in groupings. We then created two measures of IR effectiveness by classifying changes in FRI v2 scores over six 20 min windows coincident with and following IR use as (1) “Improvement” (improvement relative to the FRIv2 score at IR initiation) and (2) “Stabilization” (no further decrease in FRI score relative to the FRIv2 score in the sixth 20 min epoch after IR initiation). We evaluated the relative effectiveness of the three PIT options, and to test whether the level of fetal risk at the time of IR initiation affected its short-term effectiveness, FRI v2 risk scores were assigned to one of three groups (Green [1.00–0.625]; Yellow [0.50–0.25]; Red 0.25–0.0]). Higher scores indicate lower risk. Statistical analysis was performed with ANOVA and t- tests. Results: Overall, the first and/or the only initiation of IR resulted in improvement in 71% of cases and stabilization in 78% of cases. The remaining 22% were failures, meaning that the FRIv2 score in the 6th 20 min period was lower than the score at the time of initiation. There were modest, but not statistically significant, differences in effectiveness (improvement or stabilization) by type of IR. There was a trend toward lower IR effectiveness of PIT OFF during IR initiation when compared to PIT continuation or decreased groups. Conclusions: IR initiation or type did not vary significantly by retrospectively calculated levels of fetal risk, showing that wide variation in clinician practices, not necessarily correlated with what we believe actual risk was, determine how IR was used. The FRI provides contextualization of FHR elements by adding maternal, fetal, and obstetric risk factors, and increased uterine activity enables a more rigorous and reproducible approach to analysis of emerging fetal compromise and IR effectiveness. As practice has shifted from the over-aggressiveness of PIT use to now premature discontinuations with any tracing variation, we need better metrics. FRIv2 further improves its physiologic underpinnings. Thus, we propose a new approach to the overall assessment of IR practice.
- Open Access
- 26 December 2024
- Published by MDPI AG in Preprints.org
Reconceptualizing Intrauterine Resuscitation and Its Short-Term Impact
Objective: Intrauterine resuscitation (IR) may be employed during labor to reduce emergency deliveries with concerns for fetal wellbeing emanating mostly from increased uterine contraction frequency and/or intensity. However, there is no standard definition of what constitutes IR and how its impact is assessed. Here, we have created two measures of relative IR effectiveness, determined over a two-hour time frame after Pitocin (PIT) was first initiated, and ask how fetal risk severity at the time of its initiation impacted IR effectiveness. Study Design: We analyzed 118 patients receiving PIT who underwent IR at least once during labor. Retrospectively, we assessed risk levels using our Fetal Reserve Index version 2 (FRI v2) scores that were calculated in 20-minute timeframes. FRIv2 scores include various maternal, obstetric, and fetal risk factors, uterine contraction frequency and FHR baseline rate, variability, accelerations, and decelerations. We define 3 IR scenarios to assess relative IR effectiveness. [1] no reduction of PIT infusion rates (PIT), [2] decreased PIT infusion rates (DPIT), or [3] PIT turned off (PIT OFF). Maternal repositioning and oxygen administration are nearly universal across all types, and therefore are not considered in groupings. We then created three measures of IR effectiveness by classifying changes in FRI v2 scores over six 20-minute windows coincident with and following IR use as: (1) “Improvement” (FRI score improvement), (2) “Stabilization,” (no further decrease in FRI score) and (3) failure. We evaluated the relative effectiveness of the three PIT options, and to test whether the level of fetal risk at the time of IR initiation affected its short-term effectiveness, FRI v2 risk scores were assigned to one of three groups (Green [1.00-0.625]; Yellow [0.50-0.25]; Red 0.25-0.0]). Higher scores indicate lower risk. Statistical analysis was performed with ANOVA and t- tests. Results: Overall, the first and/or the only initiation of IR resulted in improvement in 71% of cases and stabilization in 78% of cases. The remaining 22% were failures, meaning that the FRIv2 score in the 7th 20-minute period was lower than the score at the time of initiation. There were modest, but not statistically significant, differences in effectiveness (improvement or stabilization) by type of IR. There was a trend toward lower IR effectiveness of PIT OFF during IR initiation when compared to PIT continuation or decreased groups. Conclusions: IR initiation or type did not vary significantly by retrospectively calculated levels of fetal risk showing that wide variation in clinician practices determine how IR was used. The FRI provides contextualization of FHR elements by adding maternal, fetal, and obstetric risk factors and increased uterine activity enables a more rigorous and reproducible approach to analysis of emerging fetal compromise and IR effectiveness. FRIv2 further improves its physiologic underpinnings. Thus, we propose a new approach to the overall assessment of IR practice.
- 26 December 2024
- Published by MDPI AG in Preprints.org
Open AccessReconceptualizing Intrauterine Resuscitation and Its Short-Term Impact
Objective: Intrauterine resuscitation (IR) may be employed during labor to reduce emergency deliveries with concerns for fetal wellbeing emanating mostly from increased uterine contraction frequency and/or intensity. However, there is no standard definition of what constitutes IR and how its impact is assessed. Here, we have created two measures of relative IR effectiveness, determined over a two-hour time frame after Pitocin (PIT) was first initiated, and ask how fetal risk severity at the time of its initiation impacted IR effectiveness. Study Design: We analyzed 118 patients receiving PIT who underwent IR at least once during labor. Retrospectively, we assessed risk levels using our Fetal Reserve Index version 2 (FRI v2) scores that were calculated in 20-minute timeframes. FRIv2 scores include various maternal, obstetric, and fetal risk factors, uterine contraction frequency and FHR baseline rate, variability, accelerations, and decelerations. We define 3 IR scenarios to assess relative IR effectiveness. [1] no reduction of PIT infusion rates (PIT), [2] decreased PIT infusion rates (DPIT), or [3] PIT turned off (PIT OFF). Maternal repositioning and oxygen administration are nearly universal across all types, and therefore are not considered in groupings. We then created three measures of IR effectiveness by classifying changes in FRI v2 scores over six 20-minute windows coincident with and following IR use as: (1) “Improvement” (FRI score improvement), (2) “Stabilization,” (no further decrease in FRI score) and (3) failure. We evaluated the relative effectiveness of the three PIT options, and to test whether the level of fetal risk at the time of IR initiation affected its short-term effectiveness, FRI v2 risk scores were assigned to one of three groups (Green [1.00-0.625]; Yellow [0.50-0.25]; Red 0.25-0.0]). Higher scores indicate lower risk. Statistical analysis was performed with ANOVA and t- tests. Results: Overall, the first and/or the only initiation of IR resulted in improvement in 71% of cases and stabilization in 78% of cases. The remaining 22% were failures, meaning that the FRIv2 score in the 7th 20-minute period was lower than the score at the time of initiation. There were modest, but not statistically significant, differences in effectiveness (improvement or stabilization) by type of IR. There was a trend toward lower IR effectiveness of PIT OFF during IR initiation when compared to PIT continuation or decreased groups. Conclusions: IR initiation or type did not vary significantly by retrospectively calculated levels of fetal risk showing that wide variation in clinician practices determine how IR was used. The FRI provides contextualization of FHR elements by adding maternal, fetal, and obstetric risk factors and increased uterine activity enables a more rigorous and reproducible approach to analysis of emerging fetal compromise and IR effectiveness. FRIv2 further improves its physiologic underpinnings. Thus, we propose a new approach to the overall assessment of IR practice.