View in EDS PDF Full Text

From Readiness to Response: AIDriven Antenatal Risk Assessment (mHealth application) and Machine Learning techniques for Midwives Predicting Maternal and Neonatal Outcomes in Low Resource Healthcare Settings.

Saved in:
Bibliographic Details
Title: From Readiness to Response: AIDriven Antenatal Risk Assessment (mHealth application) and Machine Learning techniques for Midwives Predicting Maternal and Neonatal Outcomes in Low Resource Healthcare Settings.
Alternate Title: De la preparación a la respuesta: evaluación de riesgos prenatales basada en la inteligencia artificial (mHealth) y técnicas de aprendizaje automático para que las enfermeiras matronas predigan los resultados maternos y neonatales en entornos sanitarios con escasos recursos.
Da prontidão à resposta: Avaliação de risco pré-natal baseada em ia (aplicativo mhealth) e técnicas de aprendizado de máquina para parteiras na predição de desfechos maternos e neonatais em ambientes de saúde com recursos limitados.
Authors: Devi, Seeta1 drseetadevi1981@gmail.com, Sayyed, Faheemuddin2 faheemuddinsayyed789@gmail.com, Awasthi, Sanidhya2 sanidhya.awasthi19@gmail.com, Sonchhatra, Raghav2 rsonchhatra49@gmail.com
Source: Investigación & Educación en Enfermería. May-Jul2026, Vol. 44 Issue 2, p94-114. 19p.
Subjects: Mobile apps, Risk assessment, Cross-sectional method, Random forest algorithms, Boosting algorithms, Prediction models, Infant mortality, Receiver operating characteristic curves, Artificial intelligence, Systems development, Statistical sampling, Primary health care, Logistic regression analysis, Pregnancy outcomes, Convolutional neural networks, Descriptive statistics, Prenatal care, Support vector machines, Deep learning, Resource-limited settings, Machine learning, Decision trees, Pregnancy complications, Data analysis software, Sensitivity & specificity (Statistics), Disease risk factors
Geographic Terms: India
Abstract (English): Objective. To assess high-risk pregnancies via AI based mHealth application and to develop innovative machine learning (ML) and deep learning (DL) models to predict maternal and neonatal outcomes. Methods. This study was conducted in two stages; in the first stage, we developed an AI-based mHealth application. In the second stage, data were collected using the mHealth application from an estimated sample of 1010 pregnant women who visited primary health centers in Pune, India, enabling seamless risk categorization into low-, moderate-, and high-risk pregnancy categories. The maternal and neonatal outcomes were predicted using ML and DL models. Evaluated with performance metrics such as AUC-ROC, precision, recall, and F1- Score, aligning with prediction models analysis. Results. The results showed that the prevalence of low, moderate, and highrisk pregnancies was 37.33%, 37.82%, and 24.85%, respectively. Support vector machine (SVM) produced an excellent AUCROC of 99.96, especially in predicting premature labor with 97.36% accuracy and an F1-score of 0.97. Random forest (RF) also performed well, detecting abnormal fetal heart rates with 95.75% accuracy. Bagging and RF excelled in predicting meconium in utero (AUC-ROC: 96.2% and 95.75%) and LSCS (AUC-ROC: 98.81% and 98.51%), respectively. Conclusions. The AI based mHealth application accurately predict the maternal and newborn outcomes, empowering midwives to make timely clinical decisions and reduce maternal and newborn mortality. [ABSTRACT FROM AUTHOR]
Abstract (Spanish): Objetivo. Evaluar los embarazos de alto riesgo mediante una aplicación de mHealth basada en IA y desarrollar modelos innovadores de aprendizaje automático (AA) y aprendizaje profundo (AP) para predecir los resultados maternos y neonatales. Métodos. Este estudio se llevó a cabo en dos fases; en la primera fase, desarrollo de una aplicación de mHealth basada en IA. En la segunda fase, se recopilaron datos mediante la aplicación mHealth de una muestra estimada de 1010 mujeres embarazadas que acudieron a centros de atención primaria en Pune (India), lo que permitió una categorización del riesgo del embarazo en bajo, moderado y alto. Los resultados maternos y neonatales se predijeron utilizando modelos de AA y AP. Se evaluaron con métricas de rendimiento como AUC-ROC, la precisión, y el F1-Score, en consonancia con el análisis de modelos de predicción. Resultados. Los resultados mostraron que la distribución de embarazos de riesgo bajo, moderado y alto fue del 37.33%, 37.82% y 24.85%, respectivamente. La máquina de vectores de soporte produjo un excelente AUC-ROC de 99.96%, especialmente en la predicción del parto prematuro, con una precisión del 97.36% y un F1-score de 0.97. El Random Forest también obtuvo buenos resultados, detectando frecuencias cardíacas fetales anormales con una precisión del 95.75 %. Los métodos de «bagging» y RF se destacaron en la predicción de la presencia de meconio intrauterino (AUC-ROC: 96.2% y 95.75%) y Cesárea (AUC-ROC: 98.81% and 98.51%). Conclusión. La aplicación de mHealth basada en inteligencia artificial predijo con precisión los resultados maternos y neonatales, lo que permite a las enfermeras madronas tomar decisiones clínicas oportunas que permitirían reducir la mortalidad materna y neonatal. [ABSTRACT FROM AUTHOR]
Abstract (Portuguese): Objetivo. Avaliar gestações de alto risco por meio de um aplicativo mHealth baseado em IA e desenvolver modelos inovadores de aprendizado de máquina (AM) e aprendizado profundo (AP) para predizer desfechos maternos e neonatais. Métodos. Este estudo foi conduzido em duas etapas; na primeira etapa, desenvolvemos um aplicativo mHealth baseado em IA. Na segunda etapa, os dados foram coletados por meio do aplicativo mHealth de uma amostra estimada de 1.010 gestantes que visitaram centros de saúde primários em Pune, Índia, possibilitando a categorização contínua em categorias de gestação de baixo, moderado e alto risco. Os desfechos maternos e neonatais foram preditos utilizando modelos de AM e AP. Avaliados com métricas de desempenho como AUC-ROC, precisão, revocação e F1-score, em consonância com a análise de modelos de predição médica. Resultados. Os resultados mostraram que a prevalência de gestações de baixo, moderado e alto risco foi de 37.33%, 37.82% e 24.85%, respectivamente. A máquina de vetores de suporte (MVS) produziu excelente AUC-ROC de 99.96, especialmente na predição de trabalho de parto prematuro, com acurácia de 97.36% e F1-score de 0.97. A floresta aleatória (FA) também apresentou bom desempenho, detectando frequências cardíacas fetais anormais com acurácia de 95.75%. Os métodos de «bagging» e RF se destacaram na previsão da presença de mecônio intrauterino (AUC-ROC: 96.2% e 95.75%) e da cesariana (AUC-ROC: 98.81% e 98.51%), respectivamente. Conclusões. O aplicativo mHealth baseado em IA prediz com precisão os desfechos maternos e neonatais, capacitando as parteiras a tomarem decisões clínicas oportunas e a reduzirem a mortalidade materna e neonatal. [ABSTRACT FROM AUTHOR]
Copyright of Investigación & Educación en Enfermería is the property of Universidad de Antioquia, Facultad de Enfermeria and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: MedicLatina
FullText Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: lth
DbLabel: MedicLatina
An: 194710375
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: From Readiness to Response: AIDriven Antenatal Risk Assessment (mHealth application) and Machine Learning techniques for Midwives Predicting Maternal and Neonatal Outcomes in Low Resource Healthcare Settings.
– Name: TitleAlt
  Label: Alternate Title
  Group: TiAlt
  Data: De la preparación a la respuesta: evaluación de riesgos prenatales basada en la inteligencia artificial (mHealth) y técnicas de aprendizaje automático para que las enfermeiras matronas predigan los resultados maternos y neonatales en entornos sanitarios con escasos recursos.<br />Da prontidão à resposta: Avaliação de risco pré-natal baseada em ia (aplicativo mhealth) e técnicas de aprendizado de máquina para parteiras na predição de desfechos maternos e neonatais em ambientes de saúde com recursos limitados.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Devi%2C+Seeta%22">Devi, Seeta</searchLink><relatesTo>1</relatesTo><i> drseetadevi1981@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Sayyed%2C+Faheemuddin%22">Sayyed, Faheemuddin</searchLink><relatesTo>2</relatesTo><i> faheemuddinsayyed789@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Awasthi%2C+Sanidhya%22">Awasthi, Sanidhya</searchLink><relatesTo>2</relatesTo><i> sanidhya.awasthi19@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Sonchhatra%2C+Raghav%22">Sonchhatra, Raghav</searchLink><relatesTo>2</relatesTo><i> rsonchhatra49@gmail.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Investigación+%26+Educación+en+Enfermería%22">Investigación & Educación en Enfermería</searchLink>. May-Jul2026, Vol. 44 Issue 2, p94-114. 19p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Mobile+apps%22">Mobile apps</searchLink><br /><searchLink fieldCode="DE" term="%22Risk+assessment%22">Risk assessment</searchLink><br /><searchLink fieldCode="DE" term="%22Cross-sectional+method%22">Cross-sectional method</searchLink><br /><searchLink fieldCode="DE" term="%22Random+forest+algorithms%22">Random forest algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Boosting+algorithms%22">Boosting algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Prediction+models%22">Prediction models</searchLink><br /><searchLink fieldCode="DE" term="%22Infant+mortality%22">Infant mortality</searchLink><br /><searchLink fieldCode="DE" term="%22Receiver+operating+characteristic+curves%22">Receiver operating characteristic curves</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Systems+development%22">Systems development</searchLink><br /><searchLink fieldCode="DE" term="%22Statistical+sampling%22">Statistical sampling</searchLink><br /><searchLink fieldCode="DE" term="%22Primary+health+care%22">Primary health care</searchLink><br /><searchLink fieldCode="DE" term="%22Logistic+regression+analysis%22">Logistic regression analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Pregnancy+outcomes%22">Pregnancy outcomes</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Descriptive+statistics%22">Descriptive statistics</searchLink><br /><searchLink fieldCode="DE" term="%22Prenatal+care%22">Prenatal care</searchLink><br /><searchLink fieldCode="DE" term="%22Support+vector+machines%22">Support vector machines</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Resource-limited+settings%22">Resource-limited settings</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Decision+trees%22">Decision trees</searchLink><br /><searchLink fieldCode="DE" term="%22Pregnancy+complications%22">Pregnancy complications</searchLink><br /><searchLink fieldCode="DE" term="%22Data+analysis+software%22">Data analysis software</searchLink><br /><searchLink fieldCode="DE" term="%22Sensitivity+%26+specificity+%28Statistics%29%22">Sensitivity & specificity (Statistics)</searchLink><br /><searchLink fieldCode="DE" term="%22Disease+risk+factors%22">Disease risk factors</searchLink>
– Name: SubjectGeographic
  Label: Geographic Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22India%22">India</searchLink>
– Name: Abstract
  Label: Abstract (English)
  Group: Ab
  Data: Objective. To assess high-risk pregnancies via AI based mHealth application and to develop innovative machine learning (ML) and deep learning (DL) models to predict maternal and neonatal outcomes. Methods. This study was conducted in two stages; in the first stage, we developed an AI-based mHealth application. In the second stage, data were collected using the mHealth application from an estimated sample of 1010 pregnant women who visited primary health centers in Pune, India, enabling seamless risk categorization into low-, moderate-, and high-risk pregnancy categories. The maternal and neonatal outcomes were predicted using ML and DL models. Evaluated with performance metrics such as AUC-ROC, precision, recall, and F1- Score, aligning with prediction models analysis. Results. The results showed that the prevalence of low, moderate, and highrisk pregnancies was 37.33%, 37.82%, and 24.85%, respectively. Support vector machine (SVM) produced an excellent AUCROC of 99.96, especially in predicting premature labor with 97.36% accuracy and an F1-score of 0.97. Random forest (RF) also performed well, detecting abnormal fetal heart rates with 95.75% accuracy. Bagging and RF excelled in predicting meconium in utero (AUC-ROC: 96.2% and 95.75%) and LSCS (AUC-ROC: 98.81% and 98.51%), respectively. Conclusions. The AI based mHealth application accurately predict the maternal and newborn outcomes, empowering midwives to make timely clinical decisions and reduce maternal and newborn mortality. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label: Abstract (Spanish)
  Group: Ab
  Data: Objetivo. Evaluar los embarazos de alto riesgo mediante una aplicación de mHealth basada en IA y desarrollar modelos innovadores de aprendizaje automático (AA) y aprendizaje profundo (AP) para predecir los resultados maternos y neonatales. Métodos. Este estudio se llevó a cabo en dos fases; en la primera fase, desarrollo de una aplicación de mHealth basada en IA. En la segunda fase, se recopilaron datos mediante la aplicación mHealth de una muestra estimada de 1010 mujeres embarazadas que acudieron a centros de atención primaria en Pune (India), lo que permitió una categorización del riesgo del embarazo en bajo, moderado y alto. Los resultados maternos y neonatales se predijeron utilizando modelos de AA y AP. Se evaluaron con métricas de rendimiento como AUC-ROC, la precisión, y el F1-Score, en consonancia con el análisis de modelos de predicción. Resultados. Los resultados mostraron que la distribución de embarazos de riesgo bajo, moderado y alto fue del 37.33%, 37.82% y 24.85%, respectivamente. La máquina de vectores de soporte produjo un excelente AUC-ROC de 99.96%, especialmente en la predicción del parto prematuro, con una precisión del 97.36% y un F1-score de 0.97. El Random Forest también obtuvo buenos resultados, detectando frecuencias cardíacas fetales anormales con una precisión del 95.75 %. Los métodos de «bagging» y RF se destacaron en la predicción de la presencia de meconio intrauterino (AUC-ROC: 96.2% y 95.75%) y Cesárea (AUC-ROC: 98.81% and 98.51%). Conclusión. La aplicación de mHealth basada en inteligencia artificial predijo con precisión los resultados maternos y neonatales, lo que permite a las enfermeras madronas tomar decisiones clínicas oportunas que permitirían reducir la mortalidad materna y neonatal. [ABSTRACT FROM AUTHOR]
– Name: Abstract
  Label: Abstract (Portuguese)
  Group: Ab
  Data: Objetivo. Avaliar gestações de alto risco por meio de um aplicativo mHealth baseado em IA e desenvolver modelos inovadores de aprendizado de máquina (AM) e aprendizado profundo (AP) para predizer desfechos maternos e neonatais. Métodos. Este estudo foi conduzido em duas etapas; na primeira etapa, desenvolvemos um aplicativo mHealth baseado em IA. Na segunda etapa, os dados foram coletados por meio do aplicativo mHealth de uma amostra estimada de 1.010 gestantes que visitaram centros de saúde primários em Pune, Índia, possibilitando a categorização contínua em categorias de gestação de baixo, moderado e alto risco. Os desfechos maternos e neonatais foram preditos utilizando modelos de AM e AP. Avaliados com métricas de desempenho como AUC-ROC, precisão, revocação e F1-score, em consonância com a análise de modelos de predição médica. Resultados. Os resultados mostraram que a prevalência de gestações de baixo, moderado e alto risco foi de 37.33%, 37.82% e 24.85%, respectivamente. A máquina de vetores de suporte (MVS) produziu excelente AUC-ROC de 99.96, especialmente na predição de trabalho de parto prematuro, com acurácia de 97.36% e F1-score de 0.97. A floresta aleatória (FA) também apresentou bom desempenho, detectando frequências cardíacas fetais anormais com acurácia de 95.75%. Os métodos de «bagging» e RF se destacaram na previsão da presença de mecônio intrauterino (AUC-ROC: 96.2% e 95.75%) e da cesariana (AUC-ROC: 98.81% e 98.51%), respectivamente. Conclusões. O aplicativo mHealth baseado em IA prediz com precisão os desfechos maternos e neonatais, capacitando as parteiras a tomarem decisões clínicas oportunas e a reduzirem a mortalidade materna e neonatal. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Investigación & Educación en Enfermería is the property of Universidad de Antioquia, Facultad de Enfermeria and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=lth&AN=194710375
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.17533/udea.iee.v44n2e08
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 19
        StartPage: 94
    Subjects:
      – SubjectFull: Mobile apps
        Type: general
      – SubjectFull: Risk assessment
        Type: general
      – SubjectFull: Cross-sectional method
        Type: general
      – SubjectFull: Random forest algorithms
        Type: general
      – SubjectFull: Boosting algorithms
        Type: general
      – SubjectFull: Prediction models
        Type: general
      – SubjectFull: Infant mortality
        Type: general
      – SubjectFull: Receiver operating characteristic curves
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Systems development
        Type: general
      – SubjectFull: Statistical sampling
        Type: general
      – SubjectFull: Primary health care
        Type: general
      – SubjectFull: Logistic regression analysis
        Type: general
      – SubjectFull: Pregnancy outcomes
        Type: general
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Descriptive statistics
        Type: general
      – SubjectFull: Prenatal care
        Type: general
      – SubjectFull: Support vector machines
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Resource-limited settings
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Decision trees
        Type: general
      – SubjectFull: Pregnancy complications
        Type: general
      – SubjectFull: Data analysis software
        Type: general
      – SubjectFull: Sensitivity & specificity (Statistics)
        Type: general
      – SubjectFull: Disease risk factors
        Type: general
      – SubjectFull: India
        Type: general
    Titles:
      – TitleFull: From Readiness to Response: AIDriven Antenatal Risk Assessment (mHealth application) and Machine Learning techniques for Midwives Predicting Maternal and Neonatal Outcomes in Low Resource Healthcare Settings.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Devi, Seeta
      – PersonEntity:
          Name:
            NameFull: Sayyed, Faheemuddin
      – PersonEntity:
          Name:
            NameFull: Awasthi, Sanidhya
      – PersonEntity:
          Name:
            NameFull: Sonchhatra, Raghav
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 05
              Text: May-Jul2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 01205307
          Numbering:
            – Type: volume
              Value: 44
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Investigación & Educación en Enfermería
              Type: main
ResultId 1