Academic Journal
Προβολή σε EDS
Συνδεδεμένο Πλήρες Κείμενο

Fetal health classification: a deep learning model with enhanced interpretability and lightweight deployment.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: Fetal health classification: a deep learning model with enhanced interpretability and lightweight deployment.
Συγγραφείς: Hasan R; Department of Science and Engineering, Southampton Solent University, Southampton, SO14 0YN, UK. raza.hasan@solent.ac.uk., Dattana V; Department of Computer Science and Management Information System, College of Management & Technology, P.O. Box 680, Barka, 320, Oman., Mahmood S; Department of Computer Science, Nazeer Hussain University, ST-2, Near Karimabad, Karachi, 75950, Sindh, Pakistan., Abbas A; Department of Computing and Electronics Engineering, Middle East College, Muscat, Oman., Sojitra KK; School of Technology and Maritime Industries, Southampton Solent University, E Park Terrace, Southampton, Hampshire, SO14 0YN, UK., Hussain S; Department of Computer and Information Sciences, Northumbria University, Newcastle upon Tyne, NE1 8QH, UK.
Πηγή: Medical & biological engineering & computing [Med Biol Eng Comput] 2026 Jun; Vol. 64 (6), pp. 2057-2083. Date of Electronic Publication: 2026 Apr 06.
Τύπος έκδοσης: Journal Article
Γλώσσα: English
Στοιχεία περιοδικού: Publisher: Springer Country of Publication: United States NLM ID: 7704869 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1741-0444 (Electronic) Linking ISSN: 01400118 NLM ISO Abbreviation: Med Biol Eng Comput Subsets: MEDLINE
Imprint Name(s): Publication: New York, NY : Springer
Original Publication: Stevenage, Eng., Peregrinus.
Ιατρικοί όροι (MeSH): Fetus*/physiology , Classification Algorithms* , Deep Learning* , Predictive Learning Models*, Female ; Humans ; Pregnancy ; Bayes Theorem ; Boosting Machine Learning Algorithms ; Cardiotocography ; Feedforward Neural Networks ; Neural Networks, Computer
Περίληψη: Fetal health classification is crucial in the detection of potential pregnancy complications at an early level to enable timely medical intervention. Traditional diagnostic techniques rely on expert interpretation of cardiotocography (CTG) recordings, which is time-consuming and subjective in nature. To address this drawback, we suggest an optimized deep learning approach for fetal health classification based on a feedforward neural network (FNN) with hyperparameter optimization. Our methodology involves exhaustive data preprocessing, feature engineering, and hyperparameter optimization through Bayesian search, tuned with the best model consisting of 96 and 256 neurons in the first and second hidden layers, respectively, L2 regularization coefficients 0.000578 and 1.81e-05, dropout rates 0.213 and 0.458, and learning rate 0.001704. The suggested model is compared to traditional machine learning classifiers, i.e., Random Forest, XGBoost, LightGBM, and Gradient Boosting, using performance measures such as accuracy, precision, recall, F1-score, and AUC-ROC. Experimental findings demonstrate that the optimized FNN outperforms traditional models with better classification performance. Our findings reveal the potential of deep learning in fetal health assessment and its clinical usefulness in real-world environments.
Competing Interests: Declarations. Ethics approval and consent to participate: This study utilized a publicly available and fully anonymized dataset. In accordance with the ethical guidelines for biomedical research involving the secondary analysis of de-identified data, institutional ethics board approval was not required. The research was conducted in alignment with the principles of the Declaration of Helsinki. Consent for publication: Not applicable. Conflict of interest: The authors have no relevant financial or non-financial interests to disclose.
References: Peahl A.F., Turrentine M., Srinivas S., King T., Zahn C.M. (2023) Routine prenatal care. Obstet Gynecol Clin North Am 50:439–455. https://www.clinicalkey.es/playcontent/1-s2.0-S0889854523000499. (PMID: 10.1016/j.ogc.2023.03.00237500209)
Mendis L, Palaniswami M, Brownfoot F, Keenan E (2023) Computerised cardiotocography analysis for the automated detection of fetal compromise during labour: A review. Bioengineering 10:1007. https://www.ncbi.nlm.nih.gov/pubmed/37760109. (PMID: 10.3390/bioengineering100910073776010910525263)
Ben M’Barek I, Jauvion G, Ceccaldi P (2023) Computerized cardiotocography analysis during labor – a state-of‐the‐art review. Acta Obstet Gynecol Scand 102:130–137. (PMID: 10.1111/aogs.1449836541016)
Mennickent D, Rodríguez A, Opazo MC et al (2023) Machine learning applied in maternal and fetal health: a narrative review focused on pregnancy diseases and complications. Front Endocrinol 14:1130139. https://www.ncbi.nlm.nih.gov/pubmed/37274341. (PMID: 10.3389/fendo.2023.1130139)
Innab N, Alsubai S, Alabdulqader EA et al (2024) Automated approach for fetal and maternal health management using light gradient boosting model with SHAP explainable AI. Front Public Health 12:1462693. https://www.ncbi.nlm.nih.gov/pubmed/39758195. (PMID: 10.3389/fpubh.2024.14626933975819511695363)
Omar SM, Kimwele M, Olowolayemo A, Kaburu DM (2024) Enhancing EEG signals classification using LSTM-CNN architecture. Eng. Rep. 6, n/a https://onlinelibrary.wiley.com/doi/abs/10.1002%2Feng2.12827.
Mushtaq G, V K (2024) AI driven interpretable deep learning based fetal health classification. SLAS Technol 29:100206. https://doi.org/10.1016/j.slast.2024.100206. (PMID: 10.1016/j.slast.2024.10020639396731)
Ali S, Abuhmed T, El-Sappagh S et al (2023) Explainable artificial intelligence (XAI): what we know and what is left to attain trustworthy artificial intelligence. Inf Fusion 99:101805. https://doi.org/10.1016/j.inffus.2023.101805. (PMID: 10.1016/j.inffus.2023.101805)
Mahmood S, Hasan R, Hussain S, Adhikari R (2025) An interpretable and generalizable machine learning model for predicting asthma outcomes: integrating automl and explainable AI techniques. World 6:15. https://doi.org/10.3390/world6010015. (PMID: 10.3390/world6010015)
Sadeghi Z, Alizadehsani R, CIFCI MA et al (2024) A review of explainable artificial intelligence in healthcare. Comput Electr Eng 118:109370. https://doi.org/10.1016/j.compeleceng.2024.109370. (PMID: 10.1016/j.compeleceng.2024.109370)
Zhao Q, Nooner KB, Tapert SF et al (2025) The transition from homogeneous to heterogeneous machine learning in neuropsychiatric research. Biol Psychiatry Glob Open Sci 5:100397. (PMID: 10.1016/j.bpsgos.2024.10039739526023)
Maleki Varnosfaderani S, Forouzanfar M (2024) The role of AI in hospitals and clinics: transforming healthcare in the 21st century. Bioengineering 11:337. https://www.ncbi.nlm.nih.gov/pubmed/38671759. (PMID: 10.3390/bioengineering110403373867175911047988)
Suganthi SRL, Basilica M (2024) Deep learning approach for fetal health prediction. Int J Sci Res Comput Sci Eng Inf Technol 10:564–570. https://doi.org/10.32628/cseit241051041. (PMID: 10.32628/cseit241051041)
Harikumar A, Surendran S, Gargi S (2024) Explainable AI in deep learning based classification of fetal ultrasound image planes. Procedia Comput Sci 233:1023–1033. https://doi.org/10.1016/j.procs.2024.03.291. (PMID: 10.1016/j.procs.2024.03.291)
Venkatareddy D, Reddy KVN, Sowmya Y et al (2024) Explainable fetal ultrasound classification with CNN and MLP models. ICICEC, pp 1–7. https://ieeexplore.ieee.org/document/10808626.
Spairani E, Daniele B, Signorini MG, Magenes G (2022) A deep learning mixed-data type approach for the classification of FHR signals. Front Bioeng Biotechnol 10:887549. https://search.proquest.com/docview/2706718241. (PMID: 10.3389/fbioe.2022.887549360035389393210)
Hussain NM, Rehman AU, Othman MTB et al (2022) Accessing artificial intelligence for fetus health status using hybrid deep learning algorithm (AlexNet-SVM) on cardiotocographic data. Sensors 22:5103. https://www.proquest.com/docview/2694061379. (PMID: 10.3390/s22145103)
Gude V, Corns S (2022) Integrated deep learning and supervised machine learning model for predictive fetal monitoring. Diagnostics 12:2843. https://www.ncbi.nlm.nih.gov/pubmed/36428902. (PMID: 10.3390/diagnostics12112843364289029689398)
Petrozziello A, Redman CWG, Papageorghiou AT et al (2019) Multimodal convolutional neural networks to detect fetal compromise during labor and delivery. IEEE Access 7:112026–112036. https://ieeexplore.ieee.org/document/8788528. (PMID: 10.1109/ACCESS.2019.2933368)
Gaddam T, Maheswari BU, Chennupalle D (2023) Fetal abnormality detection: exploring trends using machine learning and explainable AI. C2I6:1–6 https://ieeexplore.ieee.org/document/10430676.
Zhang Y, Deng Y, Zhang X et al (2023) DT-CTNet: A clinically interpretable diagnosis model for fetal distress. Biomed Signal Process Control 86:105190. https://doi.org/10.1016/j.bspc.2023.105190. (PMID: 10.1016/j.bspc.2023.105190)
Alkhodari M, Widatalla N, Wahbah M et al (2022) Deep learning identifies cardiac coupling between mother and fetus during gestation. Front Cardiovasc Med 9:926965. https://search.proquest.com/docview/2702483475. (PMID: 10.3389/fcvm.2022.926965359665489372367)
Kim Y, Kim MK, Fu N et al (2025) Investigating the impact of data normalization methods on predicting electricity consumption in a Building using different artificial neural network models. Sustain Cities Soc 118:105570. https://doi.org/10.1016/j.scs.2024.105570. (PMID: 10.1016/j.scs.2024.105570)
Rondero-Guerrero C, González-Hernández I, Soto-Campos C (2022) An extended approach for the generalized powered uniform distribution. Comput Stat 1–24 https://www.ncbi.nlm.nih.gov/pubmed/36405879.
Wilcox R (2005) Trimming and winsorization. Encyclopedia Biostatistics 8:5531–5533. https://doi.org/10.1002/0470011815.b2a15165. (PMID: 10.1002/0470011815.b2a15165)
West RM (2022) Best practice in statistics: the use of log transformation. Ann Clin Biochem 59:162–165. https://journals.sagepub.com/doi/full/10.1177/00045632211050531. (PMID: 10.1177/0004563221105053134666549)
Neudecker H, Liu S (2001) Some statistical properties of Hadamard products of random matrices. Stat Pap 42:475–487. https://www.proquest.com/docview/237035566. (PMID: 10.1007/s003620100074)
Huo T, Glueck DH, Shenkman EA, Muller KE (2023) Stratified split sampling of electronic health records. BMC Med Res Methodol 23:128. https://www.ncbi.nlm.nih.gov/pubmed/37231360. (PMID: 10.1186/s12874-023-01938-03723136010210417)
Chen T, Guestrin C (2016) XGBoost: A Scalable Tree Boosting System. In: Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min., 785–794.
Menze BH, Kelm BM, Masuch R et al (2009) A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data. BMC Bioinform 10:213. (PMID: 10.1186/1471-2105-10-213)
Hajihosseinlou M, Maghsoudi A, Ghezelbash R (2023) A novel scheme for mapping of MVT-Type Pb–Zn prospectivity: LightGBM, a highly efficient gradient boosting decision tree machine learning algorithm. Nat Resour Res 32:2417–2438. https://link.springer.com/article/ https://doi.org/10.1007/s11053-023-10249-6. (PMID: 10.1007/s11053-023-10249-6)
Ayyadevara VK (2018) Gradient Boosting Machine. Pro Machine Learning Algorithms. pp 117–134.
Shen K, Guo J, Tan X et al (2023) A study on ReLU and softmax in Transformer. ArXiv Preprint ArXiv:2302.06461 https://arxiv.org/abs/2302.06461.
Dewage KAKW, Hasan R, Rehman B, Mahmood S (2024) Enhancing brain tumor detection through custom convolutional neural networks and Interpretability-Driven analysis. Information 15:653. https://www.proquest.com/docview/3120659451. (PMID: 10.3390/info15100653)
Molnar C, Freiesleben T, König G et al (1901) Relating the Partial Dependence Plot and Permutation Feature Importance to the Data Generating Process. Commun. Comput. Inf. Sci. 456–479 (2023). https://library.biblioboard.com/viewer/33ea692e-76c8-11ee-bb08-0a9b31268bf5.
Nirmalraj S, Antony ASM, Srideviponmalar P et al (2023) Permutation feature importance-based fusion techniques for diabetes prediction. Soft Comput.
Hasan R, Dattana V, Mahmood S, Hussain S (2025) Towards transparent diabetes prediction: combining automl and explainable AI for improved clinical insights. Information 16:7. https://www.proquest.com/docview/3159489321. (PMID: 10.3390/info16010007)
Goldstein A, Kapelner A, Bleich J, Pitkin E (2015) Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. J Comput Graph Stat 24:44–65. (PMID: 10.1080/10618600.2014.907095)
Smith MQRP, Ruxton GD (2020) Effective use of the McNemar test. Behav Ecol Sociobiol 74:133–139. https://www.jstor.org/stable/48727831. (PMID: 10.1007/s00265-020-02916-y)
Lee H, Lee N, Lee S (2022) A method of deep learning model optimization for image classification on edge device. Sensors 22:7344. https://www.proquest.com/docview/2724311487. (PMID: 10.3390/s22197344362364459571348)
Cheng H, Zhang M, Shi JQ (2024) A survey on deep neural network pruning: Taxonomy, Comparison, Analysis, and recommendations. IEEE Trans Pattern Anal Mach Intell 46:10558–10578. https://ieeexplore.ieee.org/document/10643325. (PMID: 10.1109/TPAMI.2024.344708539167504)
Contributed Indexing: Keywords: Deep learning; Feedforward neural network (FNN); Fetal health classification; Machine learning; Model interpretability
Entry Date(s): Date Created: 20260406 Date Completed: 20260627 Latest Revision: 20260628
Update Code: 20260629
DOI: 10.1007/s11517-026-03525-z
PMID: 41940912
Βάση Δεδομένων: MEDLINE
Περιγραφή
ISSN:1741-0444
DOI:10.1007/s11517-026-03525-z