HARNESSING MACHINE LEARNING IN HPV DIAGNOSTICS: MODEL PERFORMANCE, EXPLAINABILITY, AND CLINICAL INTEGRATION

Abstract

: Human Papillomavirus (HPV) remains a significant global health concern, contributing to cervical and oropharyngeal cancers. While traditional diagnostic methods such as PCR-based assays and cytological screenings are widely used, they present limitations in sensitivity, specificity, and scalability. Recent advances in machine learning (ML) have enabled more precise and automated HPV detection and genotyping. This review aims to evaluate the current ML methodologies in HPV diagnostics, compare their performance metrics, and discuss future directions for improving artificial intelligence (AI) -driven HPV screening. CNN-based models exhibited superior performance in cytology and histopathology-based HPV detection, achieving high accuracy in lesion classification. Hybrid models integrating ML with molecular diagnostics improved HPV genotyping precision. Support vector machine (SVM) and random forest (RF) demonstrated efficacy in genomic classification, whereas transformer-based models enhanced feature extraction and risk stratification. Despite these advancements, data heterogeneity, explainability, and clinical validation remain substantial barriers to widespread adoption. ML-driven HPV diagnostics offer unprecedented improvements in efficiency, accuracy, and accessibility. However, critical issues related to data standardization, bias mitigation, and regulatory frameworks must be addressed to ensure clinical reliability. Future research should prioritize explainable AI (XAI), federated learning, and robust validation studies to enhance model generalizability and real-world applicability. The seamless integration of AI-powered tools into HPV screening programs holds transformative potential for early detection, personalized risk assessment, and improved patient outcomes, ultimately contributing to the global reduction of HPV-related malignancies.

Keywords

• Human Papillomavirus
• machine learning
• HPV genotyping
• artificial intelligence
• cervical cancer detection

Ethical Statement

This review article does not require ethics committee approval or any special permission, as it does not involve human or animal subjects, experiments, or hazardous procedures.

References

1. Arney, A., Bennett, K. M., “Molecular diagnostics of human papillomavirus,” Lab Med., vol. 41, no. 9, pp. 523–530, Sep. 2010, doi: 10.1309/LM75WGJSVMI7VVEF.
2. Williams, J., Kostiuk, M., Biron, V. L., “Molecular detection methods in HPV-related cancers,” Front. Oncol., vol. 12, Apr. 2022, doi: 10.3389/fonc.2022.864820.
3. Abreu, A. L., Souza, R. P., Gimenes, F., Consolaro, M. E., “A review of methods for detecting human papillomavirus infection,” Virol. J., vol. 9, Nov. 2012, doi: 10.1186/1743-422X-9-262.
4. Bosch, F. X., Broker, T. R., Forman, D., et al., “Comprehensive control of human papillomavirus infections and related diseases,” Vaccine, vol. 31, Suppl. 6, pp. G1–G31, 2013, doi: 10.1016/j.vaccine.2013.10.003.
5. Alacam, S., Bakir, A., “Human papillomavirus prevalence and genotype distribution in cervical swab samples in Istanbul, Turkey,” J. Infect. Dev. Ctries., vol. 15, no. 8, pp. 1190–1196, Aug. 2021, doi: 10.3855/jidc.14663.
6. Gecer, M., “High-risk human papillomavirus (hrHPV) prevalence and genotype distribution among Turkish women,” J. Cytol., vol. 40, no. 1, pp. 42–48, Jan.–Mar. 2023, doi: 10.4103/joc.joc_129_22.
7. Daponte, N., Valasoulis, G., Michail, G., et al., “HPV-based self-sampling in cervical cancer screening: an updated review of the current evidence in the literature,” Cancers (Basel)., vol. 15, no. 6, Mar. 2023, doi: 10.3390/cancers15061669.
8. Drysdale, H., Marlow, L. A. V., Lim, A., Waller, J., “Experiences of self-sampling and future screening preferences in non-attenders who returned an HPV vaginal self-sample in the YouScreen study: findings from a cross-sectional questionnaire,” Health Expect., vol. 27, 2024, doi: 10.1111/hex.14118.

9. Yao, H., Zhang, X., “A comprehensive review for machine learning-based human papillomavirus detection in forensic identification with multiple medical samples,” Front. Microbiol., vol. 14, Jul. 2023, doi: 10.3389/fmicb.2023.1232295.
10. Bartosik, M., Moranova, L., Izadi, N., et al., “Advanced technologies towards improved HPV diagnostics,” J. Med. Virol., vol. 96, 2024, doi: 10.1002/jmv.29409.
11. Vanderveren, E., Debeer, E., Craeynest, M., Hermans, D., Raes, F., “Psychometric properties of the Dutch Cognitive Avoidance Questionnaire,” Psychol. Belg., vol. 60, no. 1, pp. 184–197, Jul. 2020, doi: 10.5334/pb.522.
12. He, S., Xiao, B., Wei, H., Huang, S., Chen, T., “SVM classifier of cervical histopathology images based on texture and morphological features,” Technol. Health Care., vol. 31, no. 1, pp. 69–80, 2023, doi: 10.3233/THC-220031.
13. Ramakrishnan, G., Nori, A., Murfet, H., Cameron, P., “Towards compliant data management systems for healthcare ML,” arXiv [Preprint]., 2020. [Online]. Available: https://arxiv.org/abs/2011.07555
14. Varricchio, S., Ilardi, G., Crispino, A., et al., “A machine learning approach to predict HPV positivity of oropharyngeal squamous cell carcinoma,” Pathologica., vol. 116, no. 6, 2024, doi: 10.32074/1591-951X-1027.
15. Chen, X., Aljrees, T., Umer, M., et al., “Cervical cancer detection using K nearest neighbor imputer and stacked ensemble learning model,” Digit. Health., vol. 9, Oct. 2023, doi: 10.1177/20552076231203802.
16. Zammataro, L., “CINNAMON-GUI: Revolutionizing Pap Smear Analysis with CNN-Based Digital Pathology Image Classification,” F1000Res., vol. 13, Aug. 2024, doi: 10.12688/f1000research.154455.1.
17. Santa, S., Kwofie, S. K., Agyenkwa-Mawuli, K., et al.,“Prediction of human papillomavirus-host oncoprotein interactions using deep learning,” Bioinform. Biol. Insights., vol. 18, 2024, doi: 10.1177/11779322241304666.
18. Jia, F., Li, S., Zhang, T., “Detection of cervical cancer cells based on strong feature CNN-SVM network,” Neurocomputing., vol. 411, 2020, doi: 10.1016/j.neucom.2020.06.006.
19. Darwish, M., Altabel, M. Z., Abiyev, R. H., “Enhancing cervical pre-cancerous classification using advanced vision transformer,” Diagnostics (Basel)., vol. 13, no. 18, 2023, doi: 10.3390/diagnostics13182884.
20. Yilmaz, A., Demircali, A. A., Kocaman, S., Uvet, H., “Comparison of deep learning and traditional machine learning techniques for classification of Pap smear images,” arXiv [Preprint]., 2020. [Online]. Available: https://arxiv.org/abs/2009.06366
21. Lang, D. M., Peeken, J. C., Combs, S. E., Wilkens, J. J., Bartzsch, S., “Deep learning-based HPV status prediction for oropharyngeal cancer patients,” arXiv [Preprint]., 2020. [Online]. Available: https://arxiv.org/abs/2011.08555
22. Ma, Y., Xu, T., Huang, X., et al., “Computer-aided diagnosis of label-free 3-D optical coherence microscopy images of human cervical tissue,” IEEE Trans. Biomed. Eng., vol. 66, no. 9, pp. 2447–2456, 2019, doi: 10.1109/TBME.2018.2890167.
23. Liu, W., Li, C., Xu, N., et al., “CVM-Cervix: A hybrid cervical Pap-smear image classification framework using CNN, visual transformer, and multilayer perceptron,” arXiv [Preprint]., 2022. [Online]. Available: https://arxiv.org/abs/2206.00971
24. Ince, O., Uysal, E., Durak, G., et al., “Prediction of carcinogenic human papillomavirus types in cervical cancer from multiparametric magnetic resonance images with machine learning-based radiomics models,” Diagn. Interv. Radiol., vol. 29, no. 3, pp. 460–468, May 2023, doi: 10.4274/dir.2022.221335.
25. Sornapudi, S., Brown, G. T., Xue, Z., et al., “Comparing deep learning models for multi-cell classification in liquid-based cervical cytology images,” arXiv [Preprint]., 2019. [Online]. Available: https://arxiv.org/abs/1910.00722
26. Kularathne, Y., Janitha, P., Ambepitiya, S., et al., “SynthVision – Harnessing minimal input for maximal output in computer vision models using synthetic image data,” arXiv [Preprint]., 2024. [Online]. Available: https://arxiv.org/abs/2402.02826
27. Zhang, L., Lu, L., Nogues, I., et al., “DeepPap: Deep convolutional networks for cervical cell classification,” IEEE J. Biomed. Health Inform., vol. 21, no. 6, pp. 1633–1643, 2017, doi: 10.1109/JBHI.2017.2705583.
28. Rahaman, M. M., Li, C., Yao, Y., et al., “DeepCervix: A deep learning-based framework for the classification of cervical cells using hybrid deep feature fusion techniques,” Comput. Biol. Med., vol. 136, 2021, doi: 10.1016/j.compbiomed.2021.104649.
29. Uehara, S., Kobayashi, M., Kimura, K., Suzuki, J., Sadamasu, K., “Rapid identification of histamine-producing bacteria isolated from fish using MALDI-TOF MS,” J. Food Sci. Technol., vol. 58, no. 10, pp. 4055–4061, Oct. 2021, doi: 10.1007/s13197-021-05092-7.
30. Lomsadze, A., Li, T., Rajeevan, M. S., Unger, E. R., Borodovsky, M., “Bioinformatics pipeline for human papillomavirus short read genomic sequences classification using support vector machine,” Viruses., vol. 12, no. 7, p. 710, Jun. 2020, doi: 10.3390/v12070710.
31. Asensio-Puig, L., Alemany, L., Pavón, M., “A straightforward HPV16 lineage classification based on machine learning,” Front. Artif. Intell., vol. 5, p. 851841, Jun. 2022, doi: 10.3389/frai.2022.851841.
32. Tanchotsrinon, W., Lursinsap, C., Poovorawan, Y., “A high performance prediction of HPV genotypes by Chaos game representation and singular value decomposition,” BMC Bioinformatics, vol. 16, p. 71, Mar. 2015, doi: 10.1186/s12859-015-0493-4.
33. Senthilkumar, R., Al Musleh, M., “Smart temperature-controlled infant car seat using thermoelectric devices,” in Proc. IEEE Int. IEMTRONICS Conf., Vancouver, BC, Canada, Sep. 2020, pp. 1–7, doi: 10.1109/IEMTRONICS51293.2020.9216387.
34. Klein, S., Wuerdemann, N., Demers, I., et al., “Predicting HPV association using deep learning and regular H&E stains allows granular stratification of oropharyngeal cancer patients,” NPJ Digit. Med., vol. 6, p. 152, 2023, doi: 10.1038/s41746-023-00901-z.
35. Geeitha, S., Renuka, P., Thilagavathi, C., et al., “LSTM - Recurrent neural network model to forecast the risk factors in recurrent cervical carcinoma,” in Proc. Int. Conf. Self Sustain. Artif. Intell. Syst. (ICSSAS), Erode, India, Jan. 2024, pp. 132–137, doi: 10.1109/ICSSAS64001.2024.10760386.
36. Li, P., Wang, X., Liu, P., et al., “Cervical lesion classification method based on cross-validation decision fusion method of vision transformer and DenseNet,” J. Healthc. Eng., vol. 2022, p. 3241422, May 2022, doi: 10.1155/2022/3241422.
37. Cheng, S., Liu, S., Yu, J., et al., “Robust whole slide image analysis for cervical cancer screening using deep learning,” Nat. Commun., vol. 12, no. 1, p. 5639, 2021, doi: 10.1038/s41467-021-25296-x.
38. Shakil, R., Islam, S., Akter, B., “A precise machine learning model: Detecting cervical cancer using feature selection and explainable AI,” J. Pathol. Inform., vol. 15, p. 100398, Sep. 2024, doi: 10.1016/j.jpi.2024.100398.
39. Zhai, F., Mu, S., Song, Y., et al., “Machine learning prediction of residual and recurrent high-grade CIN post-LEEP,” Cancer Manag. Res., vol. 16, pp. 1175–1187, 2024, doi: 10.2147/CMAR.S484057.
40. Wong, O. G. W., Ng, I. F. Y., Tsun, O. K. L., et al., “Machine learning interpretation of extended human papillomavirus genotyping by Onclarity in an Asian cervical cancer screening population,” J. Clin. Microbiol., vol. 57, no. 12, p. e00997-19, Nov. 2019, doi: 10.1128/JCM.00997-19.
41. Remita, M. A., Halioui, A., Diouara, A. A. M., et al., “A machine learning approach for viral genome classification,” BMC Bioinformatics, vol. 18, no. 1, p. 208, Apr. 2017, doi: 10.1186/s12859-017-1602-3.
42. Hou, X., Shen, G., Zhou, L., Li, Y., Wang, T., Ma, X., “Artificial intelligence in cervical cancer screening and diagnosis,” Front. Oncol., vol. 12, p. 851367, Mar. 2022, doi: 10.3389/fonc.2022.851367.
43. Crowson, M. G., Moukheiber, D., Arévalo, A. R., et al., “A systematic review of federated learning applications for biomedical data,” PLOS Digit. Health, vol. 1, no. 5, p. e0000033, May 2022, doi: 10.1371/journal.pdig.0000033.
44. Doshi-Velez, F., Kim, B., “Towards a rigorous science of interpretable machine learning,” arXiv preprint, 2017. Available: https://arxiv.org/abs/1702.08608.
45. Dellino, M., Cerbone, M., d’Amati, A., et al., “Artificial intelligence in cervical cancer screening: Opportunities and challenges,” AI, vol. 5, no. 4, pp. 2984–3000, 2024, doi: 10.3390/ai5040144.
46. Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., Galstyan, A., “A survey on bias and fairness in machine learning,” ACM Comput. Surv., vol. 54, no. 6, Article 115, 2021, doi: 10.1145/3457607.
47. Gichoya, J. W., Banerjee, I., Bhimireddy, A. R., et al., “AI recognition of patient race in medical imaging: A modelling study,” Lancet Digit. Health, vol. 4, no. 6, pp. e406–e414, Jun. 2022, doi: 10.1016/S2589-7500(22)00063-2.
48. Arora, A., Alderman, J. E., Palmer, J., et al., “The value of standards for health datasets in artificial intelligence-based applications,” Nat. Med., vol. 29, no. 11, pp. 2929–2938, Nov. 2023, doi: 10.1038/s41591-023-02608-w.
49. Rieke, N., Hancox, J., Li, W., et al., “The future of digital health with federated learning,” NPJ Digit. Med., vol. 3, p. 119, Sep. 2020, doi: 10.1038/s41746-020-00323-1.
50. Kaissis, G., Ziller, A., Passerat-Palmbach, J., et al., “End-to-end privacy preserving deep learning on multi-institutional medical imaging,” Nat. Mach. Intell., vol. 3, no. 6, pp. 473–484, 2021, doi: 10.1038/s41563-021-00838-z.
51. Chandra Sekar, P. K., Thomas, S. M., Veerabathiran, R., “The future of cervical cancer prevention: Advances in research and technology,” Explor. Med., vol. 5, pp. 384–400, 2024. doi: 10.37349/emed.2024.00226
52. Wu, E., Wu, K., Daneshjou, R., et al., “How medical AI devices are evaluated: Limitations and recommendations from an analysis of FDA approvals,” Nat. Med., vol. 27, no. 4, pp. 582–584, 2021. doi: 10.1038/s41591-021-01312-x
53. Ahmed, M. I., Spooner, B., Isherwood, J., et al., “A systematic review of the barriers to the implementation of artificial intelligence in healthcare,” Cureus, vol. 15, no. 10, p. e46454, 2023. doi: 10.7759/cureus.46454
54. Wang, R., Gunesli, G. N., Skingen, V. E., et al., “Deep learning for predicting prognostic consensus molecular subtypes in cervical cancer from histology images,” NPJ Precis. Oncol., vol. 9, no. 1, p. 11, 2025. doi: 10.1038/s41571-024-00955-3
55. Egemen, D., Perkins, R. B., Cheung, L. C., et al., “Artificial intelligence–based image analysis in clinical testing: lessons from cervical cancer screening,” J. Natl. Cancer Inst., vol. 116, no. 1, pp. 26–33, 2024. doi: 10.1093/jnci/djad202
56. Wu T., Lucas E., Zhao F., Basu P., and Qiao Y., "Artificial intelligence strengthens cervical cancer screening – present and future," Cancer Biol. Med., 2024. doi: 10.20892/j.issn.2095-3941.2024.0198
57. Xiao, T., Wang, C., Yang, M., et al., “Use of virus genotypes in machine learning diagnostic prediction models for cervical cancer in women with high-risk human papillomavirus infection,” JAMA Netw. Open, vol. 6, no. 8, p. e2326890, 2023. doi: 10.1001/jamanetworkopen.2023.26890
58. Ma, C. H., Li, L., Cai, S., et al., “Development of an HPV genotype detection platform based on aggregation-induced emission (AIE) and flow-through hybridization technologies,” Molecules, vol. 27, no. 20, p. 7036, 2022. doi: 10.3390/molecules27207036
59. Stegmüller, T., Abbet, C., Bozorgtabar, B., et al., “Self-supervised learning-based cervical cytology for the triage of HPV-positive women in resource-limited settings and low-data regime,” arXiv preprint, 2023. [Online]. Available: https://arxiv.org/abs/2302.05195
60. Wang R., Khurram S. A., Asif A., Young L., Rajpoot N., "Rank the triplets: a ranking-based multiple instance learning framework for detecting HPV infection in head and neck cancers using routine H&E images," *arXiv*, 2022. [Online]. Available: https://arxiv.org/abs/2206.08275
61. Chen, K., Wang, Q., & Ma, Y., “Cervical optical coherence tomography image classification based on contrastive self-supervised texture learning,” Med. Phys., vol. 49, no. 6, pp. 3638–3653, 2022. doi: 10.1002/mp.15630
62. Murdoch, B., “Privacy and artificial intelligence: challenges for protecting health information in a new era,” BMC Med. Ethics, vol. 22, p. 122, 2021. doi: 10.1186/s12910-021-00687-3
63. de Filippis, R., Al Foysal, A., Rocco, V., et al., “The risk perspective of AI in healthcare: GDPR and GELSI framework (Governance, Ethical, Legal and Social Implications) and the new European AI Act,” Ital. J. Psychiatry, vol. 10, no. 1, 2024. doi: 10.36180/2421-4469-2024-4
64. Wang C., Zhang J., Lassi N., Zhang X., "Privacy protection in using artificial intelligence for healthcare: Chinese regulation in comparative perspective," *Healthcare (Basel)*, vol. 10, no. 10, p. 1878, 2022. doi: 10.3390/healthcare10101878.
65. Mittermaier M., Raza M. M., and Kvedar J. C., "Bias in AI-based models for medical applications: challenges and mitigation strategies," NPJ Digit. Med., vol. 6, p. 113, 2023. doi: 10.1038/s41746-023-00858-z.
66. Colón-Rodríguez C. J., "Shedding light on healthcare algorithmic and artificial intelligence bias," Office of Minority Health, U.S. Department of Health and Human Services, 2023. [Online]. Available: https://minorityhealth.hhs.gov/news/shedding-light-healthcare-algorithmic-and-artificial-intelligence-bias. [Accessed: Feb. 26, 2025].
67. Abràmoff, M. D., Tarver, M. E., Loyo-Berrios, N., et al., “Considerations for addressing bias in artificial intelligence for health equity,” NPJ Digit. Med., vol. 6, no. 1, p. 170, 2023. doi: 10.1038/s41746-023-00869-7
68. Abgrall, G., Holder, A. L., Chelly Dagdia, Z., Zeitouni, K., & Monnet, X., “Should AI models be explainable to clinicians?,” Crit. Care, vol. 28, no. 1, p. 301, 2024. doi: 10.1186/s13054-024-05005-y
69. Amann, J., Vetter, D., Blomberg, S. N., et al., “To explain or not to explain?—Artificial intelligence explainability in clinical decision support systems,” PLOS Digit. Health, vol. 1, no. 2, p. e0000016, 2022. doi: 10.1371/journal.pdig.0000016
70. Amann J., Blasimme A., Vayena E., Frey D., Madai V.I., "Explainability for artificial intelligence in healthcare: a multidisciplinary perspective," BMC Med. Inform. Decis. Mak., vol. 20, no. 1, p. 310, 2020. doi: 10.1186/s12911-020-01332-6
71. Hill, D. L. G., “AI in imaging: the regulatory landscape,” Br. J. Radiol., vol. 97, no. 1155, pp. 483–491, 2024. doi: 10.1093/bjr/tqae002
72. Palaniappan K., Lin E.Y.T., Vogel S., "Global regulatory frameworks for the use of artificial intelligence (AI) in the healthcare services sector," Healthcare (Basel), vol. 12, no. 5, p. 562, 2024. doi: 10.3390/healthcare12050562
73. Sidharthan C., Cheriyedath S., "FDA strengthens AI regulation to ensure patient safety and innovation in healthcare," News Med., Oct. 16, 2024. [Online]. Available: https://www.news-medical.net/news/20241016/FDA-strengthens-AI-regulation-to-ensure-patient-safety-and-innovation-in-healthcare.aspx [Accessed: Feb. 26, 2025].
74. Cestonaro C., Delicati A., Marcante B., Caenazzo L., Tozzo P., "Defining medical liability when artificial intelligence is applied on diagnostic algorithms: a systematic review," Front. Med. (Lausanne), vol. 10, p. 1305756, 2023, doi: 10.3389/fmed.2023.1305756.
75. Lawton, T., Morgan, P., Porter, et al., “Clinicians risk becoming 'liability sinks' for artificial intelligence,” Future Healthc. J., vol. 11, no. 1, p. 100007, 2024. doi: 10.1016/j.fhj.2024.100007
76. Egan D., Ji J., "AI in healthcare: legal and ethical considerations in this new frontier," [Online]. Available: https://www.ibanet.org/ai-healthcare-legal-ethical [Accessed: Feb. 26, 2025].