Implementation of a Smart Virtual Medical Assistant Using the XGBoost Method and NLP for Early Optimization of Preeclampsia Complications
DOI:
10.33395/sinkron.v10i4.16681Keywords:
Preeklamsia; Machine Learning; XGBoost; NLP; Smart Virtual Medical AssistantAbstract
Preeclampsia is one of the most significant complications occurring during pregnancy and remains a leading contributor to increased maternal and neonatal mortality rates worldwide. Early detection of this condition continues to pose considerable challenges, as most existing prediction systems rely solely on structured clinical data and have not yet incorporated unstructured patient-reported symptom information. This study aims to develop an Android-based Smart Virtual Medical Assistant that integrates Natural Language Processing (NLP) techniques with the Extreme Gradient Boosting (XGBoost) algorithm to support the early detection of preeclampsia risk. The research dataset comprised 100 records of pregnant women, encompassing a comprehensive set of clinical variables, including maternal age, gestational age, body mass index, blood pressure, urinary protein levels, history of hypertension, history of diabetes, previous obstetric history, and patient-reported complaints presented in textual form. The textual data underwent a series of natural language processing stages, namely text cleaning, tokenization, stop-word removal, stemming, and feature extraction using the Term Frequency–Inverse Document Frequency (TF-IDF) method. Subsequently, the features derived from the NLP process were integrated with the clinical dataset to construct a predictive model based on the XGBoost algorithm. The model was evaluated by splitting the dataset into training and testing sets at an 80:20 ratio, with hyperparameter optimization performed using GridSearchCV coupled with 5-fold cross-validation. The experimental results demonstrated that the proposed model achieved an accuracy of 95.00%, precision of 100.00%, recall of 75.00%, an F1-score of 85.71%, and an Area Under the Curve (AUC) value of 1.000. The developed model was successfully deployed within an Android-based application to predict preeclampsia risk and automatically generate follow-up recommendations. These findings indicate that the integration of NLP and XGBoost holds significant potential for enhancing the performance of early preeclampsia screening in primary healthcare settings, thereby contributing to improved maternal health outcomes.
Downloads
References
Aljameel, S. S., Alzahrani, M., Almusharraf, R., Altukhais, M., Alshaia, S., Sahlouli, H., Aslam, N., Khan, I. U., Alabbad, D. A., & Alsumayt, A. (2023). Prediction of Preeclampsia Using Machine Learning and Deep Learning Models : A Review. Big Data and Cognitive Computing. https://doi.org/https://doi.org/10.3390/bdcc7010032
Antika, A. P., Andriatha, Z., Istarini, A., & Kusdiyah, E. (2025). Karakteristik Komplikasi Luaran Janin dan Ibu Hamil yang Menderita Early Onset Preeclampsia (EOPE) dan Late Onset Preeclampsia (LOPE) yang Diterminasi di RSUD Raden Mattaher Jambi. Quantum Wellnes: Jurnal Ilmu Kesehatan, 2(2). https://doi.org/doi.org/10.62383/quwell.v2i2.2054
Bintarto, F., Seputro, P., & Koko, B. (2024). Predictive Modeling of Preeclampsia Risk Using Random Forest Algorithm within a Machine Learning Framework. Journal of Computer Networks, Architecture and High Performance Computing, 6(4), 1843–1850. https://doi.org/10.47709/cnahpc.v6i4.4779
Bulla, C., Parushetti, C., Teli, A., Aski, S., & Koppad, S. (2020). A Review of AI Based Medical Assistant Chatbot. Research and Applications of Web Development and Design, 3(2), 1–14.
Edvinsson, C., Bjornsson, O., Erlandsson, L., & Hansson, S. R. (2024). Predicting Intensive Care Need in Women with Preeclampsia Using Mashing Learning - A Pilot Study. Hypertension in Pregnancy, 43(1). https://doi.org/10.1080/10641955.2024.2312165
Fadila, D. A. N. (2023). Optimalisasi Gerakan Sayang Ibu Melalui Komunikasi Informasi Edukasi Terstruktur Sebagai Upaya Pencegahan Angka Kematian Ibu. Jurnal Keperawatan Muhammadiyah, 61–65.
Hasnah, H., Gani, N. F., & Nurhidayah, N. (2021). Optimalisasi Promosi Kesehatan terhadap Ibu Hamil Berisiko Preeklampsia di Desa Tangke Bajeng Kabupataen Gowa. Journal of Comunity Engagement in Health, 4(2), 400–405. https://doi.org/doi.org/10.30994/jceh.v4i1.259
Ilham, M., Adnyani, N. L. S. S., & Suryadi, K. (2024). Pembangunan Model Pendeteksi Risiko Preeklamsia pada Ibu Hamil dengan Menggunakan Metode Data Mining. Jurnal Teknik: Media Pengembangan Ilmu Dan Aplikasi Teknik, 23(01), 50–60.
Irawati, I., Ahmad, M., & Syarif, S. (2018). Optimasi Sistem Pakar Deteksi Dini Preeklamsia Berbasis Mobile. Jurnal Ners Dan Kebidanan, 5(2), 159–162. https://doi.org/10.26699/jnk.v5i2.ART.p159–162
Jhee, J. H., Lee, S., Park, Y., Lee, S. E., Kim, Y. A., Kang, W., Kwon, J., & Park, J. T. (2019). Prediction model development of late-onset preeclampsia using machine learning-based methods. PLoS ONE, 1–12. https://doi.org/doi.org/10.1371/journal. pone.0221202
Long, L., Zou, D., & Shi, W. (2026). NLP-Driven Psychological Contract Risk Detection in Cross-Cultural Teams : An XGBoost Approach with Cultural Adaptation. AIMLR, 43–53. https://doi.org/10.69987/AIMLR.2026.70203
Mudhawaroh, M., Ningtyas, S. F., Kolifah, K., & Bherty, C. P. (2025). Optimalisasi Pencegahan Pre Eklampsia Melalui Program Kelas Ibu Hamil di Desa Banjardowo Kabupaten Jombang. DEDIKASI SAINTEK: Jurnal Pengabdian Masyarakat, 4(2), 117–125. https://doi.org/10.58545/djpm.v4i2.545
Naraqi, A. E. (2024). Virtual Medical Assistant Model Using Natural Language Processing in Healthcare System. In Polytechnique Montreal. Université de Montréal.
Octaviani, D. A., Widiastuti, D., Amelia, R., & Salam, A. (2025). Implementasi Data Mining Untuk Memprediksi Dalam Kehamilan Menggunakan Algoritma C4.5. Jurnal Kesehatan Poltekkes Kemenkes Ternate, 18(1), 29–38. https://doi.org/10.32763/ps5qpj75
Rahagiyanto, A., Prakoso, B. H., Yunus, M., Vestine, V., Suyoso, G. E. J., & Deharja, A. (2025). Perbandingan Kinerja Algoritma KNN-DT-RF-SVM untuk Deteksi Dini Risiko Kematian Ibu. J-REMI: Jurnal Rekam Medik Dan Informasi Kesehatan, 6(2), 137–145. https://doi.org/10.25047/j-remi.v6i2.5658
Ranjbar, A., Montazeri, F., Ghamsari, S. R., Mehrnoush, V., Roozbeh, N., & Darsareh, F. (2024). Machine learning models for predicting preeclampsia : a systematic review. BMC Pregnancy and Childbirth, 1–6. https://doi.org/10.1186/s12884-023-06220-1
Rejeki, S. T., Fitriani, Y., Fatkhiyah, N., & Wahyuningsih, R. F. (2024). Deteksi dini Preeklamsia pada Ibu Hamil Sebagai Upaya Pencegahan Komplikasi Dalam Kehamilan. JABI: Jurnal Adimas Bhakti Indonesia, 5(1), 35–43.
Syaputra, R. D., Widya, S., & Harmanto, D. (2025). Sistem Aplikasi Deteksi Tingkat Risiko Kehamilan Pada AKI di Puskesmas Telaga Dewa. INFOKES : Jurnal Ilmiah Rekam Medis Dan Informatika Kesehatan, 15(2), 146–157.
Wesson, J. L., & Smith, N. (2024). A machine learning model to predict preeclampsia in pregnant women. Procedia Computer Science, 239(2023), 1645–1652. https://doi.org/10.1016/j.procs.2024.06.341
Wulan, W. R., Widianawati, E., & Pantiawati, I. (2024). Optimalisasi Deteksi Dini Pre Eklampsia Ibu Hamil Berbasis Telehealth oleh Kader Forum Kesehatan Kelurahan Tambakrejo. Jurnal Abdidas, 5(5), 450–459. https://doi.org/10.31004/abdidas.v5i5.971
Zhou, L., Zhu, Q., Chen, Q., Wang, P., & Huang, H. (2025). Predicting hospital outpatient volume using XGBoost : a machine learning approach. Scientific Reports, 1–13. https://doi.org/10.1038/s41598-025-01265-y 1
|
How to Cite
Issue
Section
License
Copyright (c) 2026 Abdi Rahim Damanik, Syawaluddin Kadafi Parinduri, Ela Roza Batubara
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Muhammad Khoiruddin harahap
Google Scholar 
Moraref
PKP Index
Garuda Kemdikbud
Indonesia OneSearch
OCLC Worldcat
Dimensions
Index Copernicus
Scilit
