{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T21:50:17Z","timestamp":1793829017369,"version":"4.6.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Vellore Institute of Technology, Vellore"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Cervical cancer, predominantly caused by Human Papillomavirus (HPV) infection, remains a significant global health burden for women, contributing to elevated morbidity and mortality rates. Early and accurate prediction is critical in improving patient outcomes and optimizing healthcare resource allocation. While machine learning (ML) and deep learning (DL) methods\u2013such as support vector machines, random forests, and convolutional neural networks\u2013have demonstrated promise in disease prediction, model interpretability, computational efficiency, and rely on large, labeled datasets. Additionally, conventional diagnostic methods like piezoresistive, piezoelectric, and optical lever techniques are often cost-prohibitive and complex, limiting widespread use. This study proposes a hybrid ML framework that integrates H2O AutoML with an autoencoder-based feature extraction and Fisher Score-based feature selection. To enhance model transparency and clinical trust, Local Interpretable Model-Agnostic Explanations (LIME) and SHAP (SHapley Additive exPlanations) are employed. The workflow initiates with exploratory data analysis (EDA) and dimensionality reduction using a stacked autoencoder, followed by selection of the top predictive features via Fisher Score. The refined feature set is used to train multiple models via H2O AutoML, with the best-performing deep learning model selected. On the training dataset, the selected model achieved 95.24% accuracy, an AUC of 98.10, and a log loss of 0.1747. Cross-validation confirms the model\u2019s robustness with consistent AUC and log loss values. At the optimal F1 threshold of 0.517, the confusion matrix indicates an error rate of 5.75% for actual negatives and 2.59% for actual positives, leading to an overall error rate of 4.14%. LIME and SHAP are used to interpret predictions at the instance level, providing actionable insights for clinicians. These results demonstrate the effectiveness of combining AutoML with explainable AI and advanced feature engineering to enhance the predictive power and interpretability of cervical cancer risk models, offering a scalable solution for clinical decision support.<\/jats:p>","DOI":"10.1038\/s41598-025-23593-9","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T13:23:25Z","timestamp":1763472205000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Explainable AI based cervical cancer prediction using FSAE feature engineering and H2O AutoML"],"prefix":"10.1038","volume":"15","author":[{"given":"Panneerselvam","family":"Karthikeyan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"I.","family":"Malaserene","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"E.","family":"Deepakraj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"23593_CR1","doi-asserted-by":"crossref","unstructured":"Bhatla, N., Aoki, D., Sharma, D. N., & Sankaranarayanan, R. (2025). Cancer of the cervix uteri: 2025 update. International Journal of Gynecology & Obstetrics, 171, 87-108.","DOI":"10.1002\/ijgo.70277"},{"key":"23593_CR2","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1007\/s12011-022-03226-2","volume":"201","author":"AB Sravani","year":"2023","unstructured":"Sravani, A. B., Ghate, V. & Lewis, S. Human papillomavirus infection, cervical cancer and the less explored role of trace elements. Biol. Trace Elem. Res. 201, 1026\u20131050 (2023).","journal-title":"Biol. Trace Elem. Res."},{"key":"23593_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.health.2024.100324","volume":"5","author":"MS Ali","year":"2024","unstructured":"Ali, M. S., Hossain, M. M., Kona, M. A., Nowrin, K. R. & Islam, M. K. An ensemble classification approach for cervical cancer prediction using behavioral risk factors. Healthc. Anal. 5, 100324 (2024).","journal-title":"Healthc. Anal."},{"key":"23593_CR4","doi-asserted-by":"crossref","unstructured":"Chandana, B.\u00a0S. et al. Explainable screening and classification of cervical cancer cells with enhanced resnet-50 and lime. In 2024 3rd International Conference for Innovation in Technology (INOCON), 1\u20137 (IEEE, 2024).","DOI":"10.1109\/INOCON60754.2024.10512322"},{"key":"23593_CR5","doi-asserted-by":"crossref","unstructured":"Civit-Masot, J., Luna-Perejon, F., Mu\u00f5oz-Saavedra, L., Dom\u00ednguez-Morales, M. & Civit, A. A lightweight xai approach to cervical cancer classification. Med. Biol. Eng. Comput. 62, 2281-2304 (2024).","DOI":"10.1007\/s11517-024-03063-6"},{"key":"23593_CR6","doi-asserted-by":"publisher","first-page":"2809","DOI":"10.3390\/s20102809","volume":"20","author":"MF Ijaz","year":"2020","unstructured":"Ijaz, M. F., Attique, M. & Son, Y. Data-driven cervical cancer prediction model with outlier detection and over-sampling methods. Sensors 20, 2809 (2020).","journal-title":"Sensors"},{"key":"23593_CR7","doi-asserted-by":"publisher","first-page":"11947","DOI":"10.3390\/su141911947","volume":"14","author":"K Kaushik","year":"2022","unstructured":"Kaushik, K. et al. A machine learning-based framework for the prediction of cervical cancer risk in women. Sustainability 14, 11947 (2022).","journal-title":"Sustainability"},{"key":"23593_CR8","doi-asserted-by":"crossref","unstructured":"Mohanty, A. & Mishra, S. A comprehensive study of explainable artificial intelligence in healthcare. In Augmented intelligence in healthcare: A pragmatic and integrated analysis, 475\u2013502 (Springer Nature Singapore, 2022).","DOI":"10.1007\/978-981-19-1076-0_25"},{"key":"23593_CR9","unstructured":"Pawar, U., O\u2019Shea, D., Rea, S. & O\u2019Reilly, R. Incorporating explainable artificial intelligence (xai) to aid the understanding of machine learning in the healthcare domain. In AICS, 169\u2013180 (2020)."},{"key":"23593_CR10","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1916","volume":"10","author":"S Prusty","year":"2024","unstructured":"Prusty, S. et al. Predicting cervical cancer risk probabilities using advanced h2o automl and local interpretable model-agnostic explanation techniques. PeerJ Comput. Sci. 10, e1916 (2024).","journal-title":"PeerJ Comput. Sci."},{"key":"23593_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2019.112951","volume":"141","author":"Z Alyafeai","year":"2020","unstructured":"Alyafeai, Z. & Ghouti, L. A fully-automated deep learning pipeline for cervical cancer classification. Expert Syst. Appl. 141, 112951 (2020).","journal-title":"Expert Syst. Appl."},{"key":"23593_CR12","doi-asserted-by":"crossref","unstructured":"Habtemariam, L. W., Zewde, E. T. & Simegn, G. L. Cervix type and cervical cancer classification system using deep learning techniques. Med. Devices: Evid. Res. 15, 163\u2013176 (2022).","DOI":"10.2147\/MDER.S366303"},{"key":"23593_CR13","doi-asserted-by":"publisher","first-page":"18813","DOI":"10.1007\/s00521-023-08757-w","volume":"35","author":"I Pacal","year":"2023","unstructured":"Pacal, I. & K\u0131l\u0131carslan, S. Deep learning-based approaches for robust classification of cervical cancer. Neural Comput. Appl. 35, 18813\u201318828 (2023).","journal-title":"Neural Comput. Appl."},{"key":"23593_CR14","doi-asserted-by":"publisher","first-page":"123579","DOI":"10.1016\/j.eswa.2024.123579","volume":"249","author":"E Hussain","year":"2024","unstructured":"Hussain, E. et al. Exploring explainable artificial intelligence techniques for evaluating cervical intraepithelial neoplasia (cin) diagnosis using colposcopy images. Expert Syst. Appl. 249, 123579 (2024).","journal-title":"Expert Syst. Appl."},{"key":"23593_CR15","doi-asserted-by":"crossref","unstructured":"Di Giammarco, M. et al. A robust and explainable deep learning method for cervical cancer screening. In International Conference on Applied Intelligence and Informatics, 111\u2013125 (Springer Nature Switzerland, 2023).","DOI":"10.1007\/978-3-031-68639-9_8"},{"key":"23593_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101822","volume":"104","author":"J Waring","year":"2020","unstructured":"Waring, J., Lindvall, C. & Umeton, R. Automated machine learning: Review of the state-of-the-art and opportunities for healthcare. Artif. Intell. Med. 104, 101822. https:\/\/doi.org\/10.1016\/j.artmed.2020.101822 (2020).","journal-title":"Artif. Intell. Med."},{"key":"23593_CR17","unstructured":"Ooms, R. L.\u00a0J. Self-Service Data Science in Healthcare: Using AutoML in the Knowledge Discovery Process. Master\u2019s thesis, University of Groningen (2019)."},{"key":"23593_CR18","doi-asserted-by":"publisher","unstructured":"Reddy, M. S. R.\u00a0L. et al. Automated machine learning for healthcare. In Cybernetics, Human Cognition, and Machine Learning in Communicative Applications, 25\u201337, https:\/\/doi.org\/10.1007\/978-981-15-8165-2_3 (Springer Nature Singapore, 2025).","DOI":"10.1007\/978-981-15-8165-2_3"},{"key":"23593_CR19","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1111\/ijlh.13244","volume":"43","author":"HH Rashidi","year":"2021","unstructured":"Rashidi, H. H., Tran, N., Albahra, S. & Dang, L. T. Machine learning in health care and laboratory medicine: General overview of supervised learning and auto-ml. Int. J. Lab. Hematol. 43, 15\u201322. https:\/\/doi.org\/10.1111\/ijlh.13244 (2021).","journal-title":"Int. J. Lab. Hematol."},{"key":"23593_CR20","doi-asserted-by":"publisher","first-page":"3977","DOI":"10.1007\/s11831-024-09994-5","volume":"31","author":"J Gupta","year":"2024","unstructured":"Gupta, J. & Seeja, K. R. A comparative study of xai models and their applications in healthcare. Arch. Comput. Methods Eng. 31, 3977\u20134002. https:\/\/doi.org\/10.1007\/s11831-024-09994-5 (2024).","journal-title":"Arch. Comput. Methods Eng."},{"key":"23593_CR21","doi-asserted-by":"publisher","first-page":"4793","DOI":"10.1109\/TNNLS.2020.2978365","volume":"32","author":"E Tjoa","year":"2020","unstructured":"Tjoa, E. & Guan, C. A survey on explainable artificial intelligence (xai): Toward medical xai. IEEE Trans. Neural Netw. Learn. Syst. 32, 4793\u20134813. https:\/\/doi.org\/10.1109\/TNNLS.2020.2978365 (2020).","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"23593_CR22","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1536\/ihj.21-00301","volume":"62","author":"H Taniguchi","year":"2021","unstructured":"Taniguchi, H. et al. Explainable artificial intelligence model for diagnosis of atrial fibrillation using holter electrocardiogram waveforms. Int. Heart J. 62, 534\u2013539. https:\/\/doi.org\/10.1536\/ihj.21-00301 (2021).","journal-title":"Int. Heart J."},{"key":"23593_CR23","doi-asserted-by":"publisher","first-page":"3140","DOI":"10.3390\/diagnostics13193140","volume":"13","author":"SS Sandhu","year":"2023","unstructured":"Sandhu, S. S., Gorji, H. T., Tavakolian, P., Tavakolian, K. & Akhbardeh, A. Medical imaging applications of federated learning. Diagnostics 13, 3140. https:\/\/doi.org\/10.3390\/diagnostics13193140 (2023).","journal-title":"Diagnostics"},{"key":"23593_CR24","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s13040-022-00300-2","volume":"15","author":"A Romero","year":"2022","unstructured":"Romero, A. et al. Benchmarking automl frameworks for disease prediction using medical claims. BioData Min. 15, 15 (2022).","journal-title":"BioData Min."},{"key":"23593_CR25","doi-asserted-by":"crossref","unstructured":"Chitara, D., Dutta, P.\u00a0K., Kumar, P. & Kumar, K. Automl frameworks for disease prediction using medical claims. In IET Conference Proceedings CP859, 183\u2013189 (The Institution of Engineering and Technology, Stevenage, UK, 2023).","DOI":"10.1049\/icp.2024.0922"},{"key":"23593_CR26","doi-asserted-by":"publisher","first-page":"13484","DOI":"10.3390\/su151813484","volume":"15","author":"LP Zhuhadar","year":"2023","unstructured":"Zhuhadar, L. P. & Lytras, M. D. The application of automl techniques in diabetes diagnosis: Current approaches, performance, and future directions. Sustainability 15, 13484. https:\/\/doi.org\/10.3390\/su151813484 (2023).","journal-title":"Sustainability"},{"key":"23593_CR27","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1186\/s40537-022-00496-5","volume":"9","author":"T Siriborvornratanakul","year":"2022","unstructured":"Siriborvornratanakul, T. Human behavior in image-based road health inspection systems despite the emerging automl. J. Big Data 9, 96. https:\/\/doi.org\/10.1186\/s40537-022-00496-5 (2022).","journal-title":"J. Big Data"},{"key":"23593_CR28","doi-asserted-by":"crossref","unstructured":"Tirumanadham, N. K. M. K. & Thaiyalnayaki, S. Enhancing student performance prediction in e-learning environments: Advanced ensemble techniques and robust feature selection. Int. J. Mod. Educ. Comput. Sci. 17, 67-86 (2025).","DOI":"10.5815\/ijmecs.2025.02.03"},{"key":"23593_CR29","unstructured":"Ranzeet013. Cervical cancer dataset. https:\/\/www.kaggle.com\/datasets\/ranzeet013\/cervical-cancer-dataset?resource=download. Accessed: 2024-11-30."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-23593-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-23593-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-23593-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,23]],"date-time":"2025-11-23T02:02:35Z","timestamp":1763863355000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-23593-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["23593"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-23593-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"29 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"40439"}}