Maternal Health Risk Detection: Advancing Midwifery with Artificial Intelligence
Abstract
:1. Introduction
Related Work
2. Materials and Methods
2.1. Dataset
- Age: measured in years;
- Systolic Blood Pressure: measured in mmHg;
- Diastolic Blood Pressure: measured in mmHg;
- Blood Sugar: measured in mmol/L;
- Body Temperature: measured in degrees Fahrenheit;
- Heart Rate: measured in beats per minute;
- Risk Level: a categorical target variable indicating high risk, mid risk, or low risk.
2.2. Preprocessing and Feature Extraction
2.2.1. Age
2.2.2. Systolic Blood Pressure (SystolicBP)
2.2.3. Diastolic Blood Pressure (DiastolicBP)
2.2.4. Blood Sugar (BS)
2.2.5. Body Temperature (BodyTemp)
2.2.6. Heart Rate
2.3. Classification
2.3.1. Naïve Bayes
2.3.2. Support Vector Machines (SVMs)
2.3.3. Multilayer Perceptron (MLP)
2.3.4. Fully Connected Neural Network (FCNN)
2.3.5. Decision Trees
2.3.6. Random Forests
- Random Forest: The number of trees was tuned within {50, 100, 200}, with the best result at 100 trees.
- SVM: Several different kernel functions were evaluated (linear, RBF, polynomial), with the RBF kernel showing the best performance.
- MLP (Neural Network): The learning rate was tuned within {0.001, 0.01, 0.1}, selecting 0.01 as optimal.
- Decision Tree and Naïve Bayes: Default hyperparameters were used, as preliminary tests showed competitive results without tuning.
3. Results
4. Discussion
5. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- UNICEF. Maternal Mortality Rates and Statistics. UNICEF Data. 2024. Available online: https://data.unicef.org/topic/maternal-health/maternal-mortality/ (accessed on 20 December 2024).
- Mapari, S.A.; Shrivastava, D.; Dave, A.; Bedi, G.N.; Gupta, A.; Sachani, P.; Pradeep, U. Revolutionizing Maternal Health: The Role of Artificial Intelligence in Enhancing Care and Accessibility. Cureus 2024, 16, e69555. [Google Scholar] [CrossRef]
- Bertini, A.; Salas, R.; Chabert, S.; Sobrevia, L.; Pardo, F. Using Machine Learning to Predict Complications in Pregnancy: A Systematic Review. Front. Bioeng. Biotechnol. 2022, 9, 780389. [Google Scholar] [CrossRef] [PubMed]
- Bruno, V.; D’Orazio, M.; Ticconi, C.; Abundo, P.; Riccio, S.; Martinelli, E.; Rosato, N.; Piccione, E.; Zupi, E.; Pietropolli, A. Machine Learning-Based Methods Applied in Recurrent Pregnancy Loss Diagnostic Work-Up: A Potential Innovation in Common Clinical Practice. Sci. Rep. 2020, 10, 7970. [Google Scholar] [CrossRef] [PubMed]
- Jhee, J.H.; Lee, S.; Park, Y.; Lee, S.E.; Kim, Y.A.; Kang, S.W.; Kwon, J.Y.; Park, J.T. Prediction Model Development of Late-Onset Preeclampsia Using Machine Learning-Based Methods. PLoS ONE 2019, 14, e0221202. [Google Scholar] [CrossRef]
- Zhao, Z.; Deng, Y.; Zhang, Y.; Zhang, Y.; Zhang, X.; Shao, L. DeepFHR: Intelligent Prediction of Fetal Acidemia Using Fetal Heart Rate Signals Based on Convolutional Neural Network. BMC Med. Inform. Decis. Mak. 2019, 19, 286. [Google Scholar] [CrossRef]
- Mennickent, D.; Rodríguez, A.; Opazo, M.C.; Riedel, C.A.; Castro, E.; Eriz-Salinas, A.; Appel-Rubio, J.; Aguayo, C.; Damiano, A.E.; Guzmán-Gutiérrez, E.; et al. Machine Learning Applied in Maternal and Fetal Health: A Narrative Review Focused on Pregnancy Diseases and Complications. Front. Endocrinol. 2023, 14, 1130139. [Google Scholar] [CrossRef]
- Islam, M.N.; Mustafina, S.N.; Mahmud, T.; Khan, N.I. Machine Learning to Predict Pregnancy Outcomes: A Systematic Review, Synthesizing Framework and Future Research Agenda. BMC Pregnancy Childbirth 2022, 22, 348. [Google Scholar] [CrossRef]
- Khadidos, A.O.; Saleem, F.; Selvarajan, S.; Ullah, Z.; Khadidos, A.O. Ensemble Machine Learning Framework for Predicting Maternal Health Risk During Pregnancy. Sci. Rep. 2024, 14, 21483. [Google Scholar] [CrossRef]
- Kopanitsa, G.; Metsker, O.; Kovalchuk, S. Machine Learning Methods for Pregnancy and Childbirth Risk Management. J. Pers. Med. 2023, 13, 975. [Google Scholar] [CrossRef]
- Moreira, M.W.L.; Rodrigues, J.J.P.C.; Marcondes, G.A.B.; Neto, A.J.V.; Kumar, N.; Diez, I.D.L.T. A Preterm Birth Risk Prediction System for Mobile Health Applications Based on the Support Vector Machine Algorithm. In Proceedings of the 2018 IEEE International Conference on Communications (ICC), Kansas City, MO, USA, 20–24 May 2018; pp. 1–5. [Google Scholar] [CrossRef]
- Wang, C.; Johansson, A.L.V.; Nyberg, C.; Pareek, A.; Almqvist, C.; Hernandez-Diaz, S.; Oberg, A.S. Prediction of Pregnancy-Related Complications in Women Undergoing Assisted Reproduction, Using Machine Learning Methods. Fertil. Steril. 2024, 122, 95–105. [Google Scholar] [CrossRef]
- Raza, A.; Siddiqui, H.U.R.; Munir, K.; Almutairi, M.; Rustam, F.; Ashraf, I. Ensemble Learning-Based Feature Engineering to Analyze Maternal Health During Pregnancy and Health Risk Prediction. PLoS ONE 2022, 17, e0276525. [Google Scholar] [CrossRef]
- Rahman, M.A.; Noor, R.M.; Mallik, S.; Santa, N.K.; Deb, S.; Pathak, A. Classification of Health Risk Levels for Pregnant Women Using Support Vector Machine (SVM) Algorithm. IOSR J. Comput. Eng. 2024, 26, 7–17. [Google Scholar]
- Tomar, K.; Sharma, C.M.; Prasad, T.; Chariar, V.M. A Machine Learning-Based Risk Prediction Model During Pregnancy in Low-Resource Settings. Med. Sci. Forum 2024, 25, 13. [Google Scholar] [CrossRef]
- Abhadiomhen, S.E.; Nzeakor, E.O.; Oyibo, K. Health Risk Assessment Using Machine Learning: Systematic Review. Electronics 2024, 13, 4405. [Google Scholar] [CrossRef]
- Aljameel, S.S.; Alzahrani, M.; Almusharraf, R.; Altukhais, M.; Alshaia, S.; Sahlouli, H.; Aslam, N.; Khan, I.U.; Alabbad, D.A.; Alsumayt, A. Prediction of Preeclampsia Using Machine Learning and Deep Learning Models: A Review. Big Data Cogn. Comput. 2023, 7, 32. [Google Scholar] [CrossRef]
- Sufian, M.A.; Hamzi, W.; Hamzi, B.; Sagar, A.S.; Rahman, M.; Varadarajan, J.; Hanumanthu, M.; Azad, M.A.K. Innovative Machine Learning Strategies for Early Detection and Prevention of Pregnancy Loss: The Vitamin D Connection and Gestational Health. Diagnostics 2024, 14, 920. [Google Scholar] [CrossRef]
- Ahmed, M.; Kashem, M.A.; Rahman, M.; Khatun, S. Review and Analysis of Risk Factor of Maternal Health in Remote Area Using the Internet of Things (IoT). Lect. Notes Electr. Eng. 2020, 599, 321–330. [Google Scholar]
- Duda, R.O.; Hart, P.E.; Stork, D.G. Pattern Classification, 2nd ed.; John Wiley and Sons, Inc.: New York, NY, USA, 2000. [Google Scholar]
- Alkema, L.; Chou, D.; Hogan, D.; Zhang, S.; Moller, A.B.; Gemmill, A.; Fat, D.M.; Boerma, T.; Temmerman, P.M.; Mathers, C.; et al. Global, regional, and national levels and trends in maternal mortality between 1990 and 2015, with scenario-based projections to 2030: A systematic analysis by the UN Maternal Mortality Estimation Inter-Agency Group. Lancet 2016, 387, 462–474. [Google Scholar] [CrossRef]
- Chersich, M.F.; Pham, M.D.; Areal, A.; Haghighi, M.M.; Manyuchi, A.; Swift, C.P.; Wernecke, B.; Robinson, M.; Hetem, R.; Hajat, S. Associations between high temperatures in pregnancy and risk of preterm birth, low birth weight, and stillbirths: Systematic review and meta-analysis. BMJ 2020, 371, m3811. [Google Scholar]
- Tzimourta, K.D.; Astrakas, L.G.; Gianni, A.M.; Tzallas, A.T.; Giannakeas, N.; Paliokas, I.; Tsalikakis, D.G.; Tsipouras, M.G. Evaluation of Window Size in Classification of Epileptic Short-Term EEG Signals Using a Brain-Computer Interface Software. Eng. Technol. Appl. Sci. Res. 2018, 8, 3093–3097. [Google Scholar] [CrossRef]
- Cortes, C.; Vapnik, V. Support-Vector Networks. Mach. Learn. 1995, 20, 273–297. [Google Scholar]
- Alghamdi, F.A.; Almanaseer, H.; Jaradat, G.; Jaradat, A.; Alsmadi, M.K.; Jawarneh, S.; Almurayh, A.S.; Alqurni, J.; Alfagham, H. Multilayer Perceptron Neural Network with Arithmetic Optimization Algorithm-Based Feature Selection for Cardiovascular Disease Prediction. Mach. Learn. Knowl. Extr. 2024, 6, 987–1008. [Google Scholar] [CrossRef]
- Feng, C.; Kang, K.; Xing, Y. Fully Connected Neural Network for Virtual Monochromatic Imaging in Spectral Computed Tomography. J. Med. Imaging 2019, 6, 011006. [Google Scholar] [CrossRef]
- Tzimourta, K.D.; Giannakeas, N.; Tzallas, A.T.; Astrakas, L.G.; Afrantou, T.; Ioannidis, P.; Grigoriadis, N.; Angelidis, P.; Tsalikakis, D.G.; Tsipouras, M.G. EEG Window Length Evaluation for the Detection of Alzheimer’s Disease over Different Brain Regions. Brain Sci. 2019, 9, 81. [Google Scholar] [CrossRef] [PubMed]
- Chawla, N.V.; Bowyer, K.W.; Hall, L.O.; Kegelmeyer, W.P. SMOTE: Synthetic Minority Oversampling Technique. J. Artif. Intell. Res. 2002, 16, 321–357. [Google Scholar] [CrossRef]
- Alamsyah, D.P.; Ramdhani, Y.; Susanti, L. Maternal Health Risk Classification: Random Forest and Evolutionary Algorithms. In Proceedings of the 10th International Conference on ICT for Smart Society (ICISS), Bandung, Indonesia, 27–28 September 2023. [Google Scholar]
- Noviandy, T.R.; Nainggolan, S.I.; Raihan, R.; Firmansyah, I.; Idroes, R. Maternal Health Risk Detection Using Light Gradient Boosting Machine Approach. Infolitika J. Data Sci. 2023, 1, 48–55. [Google Scholar]
- Raihen, M.N.; Akter, S. Comparative Assessment of Several Effective Machine Learning Classification Methods for Maternal Health Risk. Comput. J. Math. Stat. Sci. 2024, 3, 161–176. [Google Scholar]
- Togunwa, T.O.; Babatunde, A.O.; Abdullah, K.U.R. Deep Hybrid Model for Maternal Health Risk Classification in Pregnancy: Synergy of ANN and Random Forest. Front. Artif. Intell. 2023, 6, 1213436. [Google Scholar] [CrossRef]
- Kranz, A.; Abele, H. The Impact of Artificial Intelligence (AI) on Midwifery Education: A Scoping Review. Healthcare 2024, 12, 1082. [Google Scholar] [CrossRef]
- Saleh, S.N.; Elagamy, M.N.; Saleh, Y.N.M.; Osman, R.A. An Explainable Deep Learning-Enhanced IoMT Model for Effective Monitoring and Reduction of Maternal Mortality Risks. Future Internet 2024, 16, 411. [Google Scholar] [CrossRef]
- Vogiatzoglou, M.; Iliadou, M.; Antoniou, E.; Andersson, E.; Mrvoljak-Theodoropoulou, I.; Dagla, C.; Sotiropoulou, D.; Tsolaridou, E.; Orovou, E.; Tomara, E.; et al. Exploring the Relationship between Co-Sleeping, Maternal Mental Health and Expression of Complaints during Infancy, and Breastfeeding. Healthcare 2024, 12, 1278. [Google Scholar] [CrossRef] [PubMed]
- Tzoraki, M.; Karampas, G.; Sarantaki, A.; Lykeridou, A.; Kanaka-Gantenbein, C.; Metallinou, D. The Impact of Maternal Graves’ Disease on Neonatal Thyroid Function: A Systematic Review. Cureus 2024, 16, e75041. [Google Scholar] [CrossRef] [PubMed]
- Rajput, N.; Paldiya, D.; Verma, Y.S. Effects of advanced maternal age on pregnancy outcome. Int. J. Reprod. Contracept. Obstet. Gynecol. 2018, 7, 3941–3946. [Google Scholar] [CrossRef]
- Farhud, D.D.; Zokaei, S. Ethical Issues of Artificial Intelligence in Medicine and Healthcare. Iran J. Public Health 2021, 50, i–v. [Google Scholar] [CrossRef]
Low-Risk Class | Mid-Risk Class | High-Risk Class | |
---|---|---|---|
# instances | 406 | 336 | 272 |
Count | Min. | Max. | Mean | STD | 25% | 50% | 75% | Skewness | Kurtosis | |
---|---|---|---|---|---|---|---|---|---|---|
Age | 1014 | 10 | 70 | 29.87 | 13.47 | 19 | 26 | 39 | 0.783 | −0.391 |
Systolic BP | 1014 | 70 | 160 | 113.20 | 18.40 | 100 | 120 | 120 | −0.251 | −0.613 |
Diastolic BP | 1014 | 49 | 100 | 76.46 | 13.89 | 65 | 80 | 90 | −0.048 | −0.949 |
Blood Sugar (BS) | 1014 | 6 | 19 | 11.53 | 4.19 | 7 | 11 | 15 | 0.348 | −1.244 |
Body Temperature | 1014 | 98 | 103 | 98.67 | 1.37 | 98 | 98 | 98 | 1.747 | 1.436 |
Heart Rate | 1014 | 7 | 90 | 74.30 | 8.09 | 70 | 76 | 80 | −1.044 | 8.399 |
Metric | Naïve Bayes | Support Vector Machine | MLP | FCNN | Decision Tree | Random Forest |
---|---|---|---|---|---|---|
TP Rate | 59.10% | 75.70% | 61.01% | 68.91% | 78.60% | 84.52% |
Precision | 58.10% | 76.30% | 61.04% | 68.96% | 79.00% | 84.93% |
Accuracy | 59.07% | 75.74% | 69.03% | 68.93% | 78.60% | 84.52% |
Metric | Naïve Bayes | Support Vector Machine | MLP | FCNN | Decision Tree | Random Forest |
---|---|---|---|---|---|---|
TP Rate | 59.60% | 72.90% | 64.50% | 71.40% | 76.80% | 83.70% |
Precision | 57.40% | 73.80% | 64.60% | 71.40% | 76.20% | 83.60% |
Accuracy | 59.61% | 72.90% | 64.53% | 71.43% | 76.85% | 83.74% |
Predicted Values | ||||
---|---|---|---|---|
High Risk | Low Risk | Mid Risk | ||
Dataset | High risk | 90.07% | 3.31% | 6.62% |
Low risk | 2.22% | 81.03% | 16.75% | |
Mid risk | 5.65% | 10.12% | 84.23% |
Metric | TP Rate | Precision | Accuracy |
---|---|---|---|
Random Forests (SMOTE) | 88.00% | 88.10% | 88.03% |
Predicted Values | ||||
---|---|---|---|---|
High Risk | Low Risk | Mid Risk | ||
Dataset | High risk | 95.77% | 1.84% | 2.39% |
Low risk | 2.46% | 81.77% | 15.76% | |
Mid risk | 6.85% | 10.12% | 83.04% |
Metric | Naïve Bayes | Support Vector Machine | MLP | FCNN | Decision Tree | Random Forest |
---|---|---|---|---|---|---|
TP Rate (95 CI) | 58.44–60.07 | 67.81–75.34 | 61.33–70.81 | 67.31–72.49 | 77.00–82.18 | 83.62–87.76 |
Precision (95 CI) | 51.20–59.16 | 66.00–73.50 | 62.00–68.44 | 65.12–74.11 | 75.23–80.09 | 78.12–85.15 |
Accuracy (95 CI) | 58.44–60.07 | 67.81–75.32 | 61.33–70.80 | 67.32–72.48 | 77.01–82.19 | 83.62–87.76 |
TP Rate | Precision | Accuracy | ||||
---|---|---|---|---|---|---|
Model | Mean | p-Value | Mean | p-Value | Mean | p-Value |
Naïve Bayes | 26.113 | 0.000 | 26.046 | 0.000 | 26.118 | 0.000 |
Support Vector Machine | 14.620 | 0.000 | 9.246 | 0.000 | 14.622 | 0.001 |
MLP | 20.119 | 0.000 | 21.458 | 0.000 | 20.118 | 0.000 |
FCNN | 13.322 | 0.000 | 13.225 | 0.000 | 20.104 | 0.000 |
Decision Tree | 5.580 | 0.000 | 5.866 | 0.000 | 5.584 | 0.000 |
Study | Dataset | # of Cases | Evaluation Method | Classifier | Accuracy |
---|---|---|---|---|---|
Alamsyah et al. (2023) [27] | MHR dataset | 1013 | 10-fold cross-validation | Random Forests and Evolutionary Weighting | 82.18% |
Khadidos et al. (2024) [9] | MHR dataset | 1013 | 10-fold cross-validation | Gradient Boosted Trees | 86.00% |
Noviandy et al. (2023) [28] | MHR dataset | 1014 | 10-fold cross-validation | LightGBM | 84.73% |
Raihen and Akter (2024) [29] | MHR dataset | 1014 | 10-fold cross-validation | SVM (GridSearch) | 86.13% |
Rahman et al. (2023) [14] | MHR dataset | 1013 | 80% training 20% testing | SVM | 79.00% |
Togunwa et al. (2024) [30] | MHR dataset | 1014 | Stratified K-fold cross-validation | MaternalNET-RF | 95.00% |
This study | MHR dataset | 1013 | 10-fold cross-validation | Random Forests | 88.03% |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Tzimourta, K.D.; Tsipouras, M.G.; Angelidis, P.; Tsalikakis, D.G.; Orovou, E. Maternal Health Risk Detection: Advancing Midwifery with Artificial Intelligence. Healthcare 2025, 13, 833. https://doi.org/10.3390/healthcare13070833
Tzimourta KD, Tsipouras MG, Angelidis P, Tsalikakis DG, Orovou E. Maternal Health Risk Detection: Advancing Midwifery with Artificial Intelligence. Healthcare. 2025; 13(7):833. https://doi.org/10.3390/healthcare13070833
Chicago/Turabian StyleTzimourta, Katerina D., Markos G. Tsipouras, Pantelis Angelidis, Dimitrios G. Tsalikakis, and Eirini Orovou. 2025. "Maternal Health Risk Detection: Advancing Midwifery with Artificial Intelligence" Healthcare 13, no. 7: 833. https://doi.org/10.3390/healthcare13070833
APA StyleTzimourta, K. D., Tsipouras, M. G., Angelidis, P., Tsalikakis, D. G., & Orovou, E. (2025). Maternal Health Risk Detection: Advancing Midwifery with Artificial Intelligence. Healthcare, 13(7), 833. https://doi.org/10.3390/healthcare13070833