Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Leveraging machine learning for fetal health classification

IAES International Journal of Artificial Intelligence · Vol. 15 No. 5 (2026) · hlm. 4315–4324

DOI
10.11591/ijai.v15.i5.pp4315-4324
ISSN
2252-8938, 2089-4872
Terbit
2026-10-01
Penerbit
Institute of Advanced Engineering and Science
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Early diagnosis of fetal health complications is crucial to ensure maternal and infant safety. However, conventional tabular machine learning approaches often suffer from severe majority-class bias and a lack of clinical interpretability. In this research, an optimized Python-based framework was developed using a 2,126-record dataset containing 21 predictive features to classify fetal health status. To resolve structural class imbalance without data leakage, the synthetic minority over-sampling technique (SMOTE) was dynamically applied strictly within stratified 5-fold cross-validation loops. Six configurations—naive Bayes, logistic regression, support vector machines, a multi-tiered deep multi-layer perceptron (deep MLP), random forest, and extreme gradient boosting (XGBoost)—were systematically tuned using randomized grid searches. Among the benchmarked models, the upgraded XGBoost ensemble demonstrated the highest performance, leading with a diagnostic accuracy of 94.87%, a macro F1-score of 91.37%, and an area under the curve (AUC) of 98.77%. While the deep MLP required a high training latency of 13.8179 seconds, the optimal XGBoost layout achieved superior power with a training runtime of only 1.8325 seconds and an inference speed of 0.0046 seconds. Game-theoretic Shapley additive explanations (SHAP) values confirmed abnormal short-term variability as the primary risk driver, ensuring a transparent, high-throughput decision-support tool.

Kata kunci

Jaringan kolaborasi para penulis

26 penulis · 74 tautan kepenulisan bersama · 24 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Tun Hussein Onn University of Malaysia
  • Universiti Teknikal Malaysia Melaka
  • Maharishi Markandeshwar University, Mullana
  • Chitkara University
  • Chandigarh University
  • INTI International University
  • Northwestern Polytechnical University
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Rosli OmarTun Hussein Onn University of Malaysia3
Khalil Azha Mohd AnnuarUniversiti Teknikal Malaysia Melaka3
Mohd Razali Mohamad SapieeUniversiti Teknikal Malaysia Melaka3
Susama BagchiTun Hussein Onn University of Malaysia2
Elia Nadira SabudinTun Hussein Onn University of Malaysia2
Nor Badariyah Abdul LatipTun Hussein Onn University of Malaysia1
Kim Gaik TayTun Hussein Onn University of Malaysia1
Audrey HuongAfiliasi tidak diketahui1
Muhammad Suhaimi SulongTun Hussein Onn University of Malaysia1
B.S.S.K. IbrahimTun Hussein Onn University of Malaysia1
Faisal AminTun Hussein Onn University of Malaysia1
Bashir Bala MuhammadNorthwestern Polytechnical University1
Muhammad Aiman Mohd AzamAfiliasi tidak diketahui1
Khajan SegaranUniversiti Teknikal Malaysia Melaka1
Jawad AliTun Hussein Onn University of Malaysia1
Samsul Haimi DahlanTun Hussein Onn University of Malaysia1
Jiwa AbdullahTun Hussein Onn University of Malaysia1
Rozlan AliasTun Hussein Onn University of Malaysia1
Abdul Rashid O. MuminTun Hussein Onn University of Malaysia1
Md Azim Affzani Md RozaniUniversiti Teknikal Malaysia Melaka1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) http://ijai.iaescore.com/index.php/IJAI/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 16 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Leveraging machine learning for fetal health classification</dc:title>
	<dc:creator>Sachdeva, Ravi Kumar</dc:creator>
	<dc:creator>Bathla, Priyanka</dc:creator>
	<dc:creator>Lamba, Rohit</dc:creator>
	<dc:creator>Rani, Pooja</dc:creator>
	<dc:creator>Debnath, Sanjoy Kumar</dc:creator>
	<dc:creator>Yie Leong, Wai</dc:creator>
	<dc:subject xml:lang="en-US"></dc:subject>
	<dc:subject xml:lang="en-US">Classifying fetal health; Clinical decision making; Cross validation; Predictive modeling; Public health</dc:subject>
	<dc:description xml:lang="en-US">Early diagnosis of fetal health complications is crucial to ensure maternal and infant safety. However, conventional tabular machine learning approaches often suffer from severe majority-class bias and a lack of clinical interpretability. In this research, an optimized Python-based framework was developed using a 2,126-record dataset containing 21 predictive features to classify fetal health status. To resolve structural class imbalance without data leakage, the synthetic minority over-sampling technique (SMOTE) was dynamically applied strictly within stratified 5-fold cross-validation loops. Six configurations—naive Bayes, logistic regression, support vector machines, a multi-tiered deep multi-layer perceptron (deep MLP), random forest, and extreme gradient boosting (XGBoost)—were systematically tuned using randomized grid searches. Among the benchmarked models, the upgraded XGBoost ensemble demonstrated the highest performance, leading with a diagnostic accuracy of 94.87%, a macro F1-score of 91.37%, and an area under the curve (AUC) of 98.77%. While the deep MLP required a high training latency of 13.8179 seconds, the optimal XGBoost layout achieved superior power with a training runtime of only 1.8325 seconds and an inference speed of 0.0046 seconds. Game-theoretic Shapley additive explanations (SHAP) values confirmed abnormal short-term variability as the primary risk driver, ensuring a transparent, high-throughput decision-support tool.</dc:description>
	<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
	<dc:contributor xml:lang="en-US">INTI International University research incentive fund (2025/12)</dc:contributor>
	<dc:date>2026-10-01</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijai.iaescore.com/index.php/IJAI/article/view/31128</dc:identifier>
	<dc:identifier>10.11591/ijai.v15.i5.pp4315-4324</dc:identifier>
	<dc:source xml:lang="en-US">IAES International Journal of Artificial Intelligence (IJ-AI); Vol 15, No 5: October 2026; 4315-4324</dc:source>
	<dc:source>2252-8938</dc:source>
	<dc:source>2089-4872</dc:source>
	<dc:source>10.11591/ijai.v15.i5</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijai.iaescore.com/index.php/IJAI/article/view/31128/15397</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2026 Ravi Kumar Sachdeva, Priyanka Bathla, Rohit Lamba, Pooja Rani, Sanjoy Kumar Debnath, Wai Yie Leong</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>