Article Data

  • Views 479
  • Dowloads 139

Original Research

Open Access

Effectiveness of artificial intelligence algorithms in identification of patients with high-grade histopathology after conisation

  • Marko Mlinarič1,*,†,
  • Maša Mlinarič2,†
  • Miljenko Križmarić3,†
  • Iztok Takač4,5,†
  • Alenka Repše Fokter6,†

1Outpatient clinic for gynaecology and obstetrics, 1410 Zagorje ob Savi, Slovenia

2General Hospital Trbovlje, 1420 Trbovlje, Slovenia

3University of Maribor Faculty of Medicine, 2000 Maribor, Slovenia

4University Clinic of Gynaecology and Perinatology, University Medical Centre Maribor, 2000 Maribor, Slovenia

5Department of Gynaecology and Perinatology, Faculty of Medicine, University of Maribor, 2000 Maribor, Slovenia

6Department of Pathology and Cytology, General Hospital Celje, 3000 Celje, Slovenia

DOI: 10.22514/ejgo.2023.050 Vol.44,Issue 4,August 2023 pp.66-75

Submitted: 26 October 2022 Accepted: 11 May 2023

Published: 15 August 2023

*Corresponding Author(s): Marko Mlinarič E-mail:

† These authors contributed equally.


The aim of this study was to compare effectiveness of various artificial intelligence classification algorithms in identifying patients with high-grade final histopathology of conisation based on last PAP smear result and risk factors for development of uterine cervical dysplasia and cancer. The data of 1475 patients who underwent conisation surgery at University Clinical Centre Maribor between 1993–2005 were analysed. Synthetic Minority Oversampling Technique (SMOTE) algorithm was employed for the imbalanced data correction. Various classification algorithms were tested with Weka open-source software. The 10-fold cross validation was used to define testing and hold-out set for analysis. Random Forest (RF) classification algorithm was better than the other tested algorithms and achieved 89.42% correct classifications (baseline ZeroR classification 63.4%, sensitivity 96.80%, specificity 76.60%, kappa 0.7632, Area under Receiver Operation Characteristic curve (AUC ROC) 0.911, Precision Recall curve (PRC) Area 0.916, and Matthews Correlation Coefficient (MCC) 0.771. Random Forest (RF) algorithm correctly identified majority of patients with final high-grade histopathology of conisation from patients dataset based on last PAP smear result and risk factors of developing high-grade dysplasia and carcinoma. Such algorithms can help clinicians to identify high-risk patients in future. An invitation could be sent to patients who did not participate in organized screening program, thus preventing the serious disease. Further studies are required in this regard.


Uterine cervical dysplasia; Uterine cervical cancer; Conisation; Artificial intelligence

Cite and Share

Marko Mlinarič,Maša Mlinarič,Miljenko Križmarić,Iztok Takač,Alenka Repše Fokter. Effectiveness of artificial intelligence algorithms in identification of patients with high-grade histopathology after conisation. European Journal of Gynaecological Oncology. 2023. 44(4);66-75.


[1] Cooper DB, McCathran CE. Cervical dysplasia. 1st edn. StatPearls Publishing: Treasure Island (FL). 2022.

[2] World Health Organization. WHO guideline for screening and treatment of cervical pre-cancer lesions for cervical cancer prevention. 2nd edn. World Health Organization: Geneva. 2021.

[3] Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA: A Cancer Journal for Clinicians. 2021; 71: 209–249.

[4] Zadnik V, Zagar T. SLORA: Slovenia and cancer. Epidemiology and cancer registry. Istitute of Oncology Ljubljana. Available at: (Accessed: 21 October 2022).

[5] Ivanuš U, Jerman T, Gašper Oblak U, Meglič L, Florjančič M, Strojan Fležar M, et al. The impact of the COVID-19 pandemic on organised cervical cancer screening: the first results of the Slovenian cervical screening programme and registry. The Lancet Regional Health—Europe. 2021; 5: 100101.

[6] Hecken JM, Rezniczek GA, Tempfer CB. Innovative diagnostic and therapeutic interventions in cervical dysplasia: a systematic review of controlled trials. Cancers. 2022; 14: 2670.

[7] Lasič A, Ivanuš U, Jerman T, Smrkolj Š, Cvjetičanin B, Lukanovič D, et al. Analysis of conizations in Slovenia 2009–2018: diagnosis, treatment and outcomes of cervical precancerous lesions in Slovenia. 2019. Available at: php?lang=slv&id=11590 (Accessed: 21 October 2022).

[8] Cervical Cancer Screening Program and Registry ZORA, Institute of Oncology Ljubljana. ZORA: Slovenian national cervical cancer screening programme and registry. 2022. Available at: (Accessed: 21 October 2022).

[9] Agarossi A, Delli Carpini G, Sopracordevole F, Serri M, Giannella L, Gardella B, et al. High-risk HPV positivity is a long-term risk factor for recurrence after cervical excision procedure in women living with HIV. International Journal of Gynecology & Obstetrics. 2021; 155: 442–449.

[10] Sulistyawati D, Faizah Z, Kurniawati EM. An association study of cervical cancer correlated with the age of coitarche in Dr. Soetomo hospital Surabaya. Indonesian Journal of Cancer. 2020; 14: 3–7.

[11] Nagelhout G, Ebisch RM, Van Der Hel O, Meerkerk G, Magnée T, De Bruijn T, et al. Is smoking an independent risk factor for developing cervical intra-epithelial neoplasia and cervical cancer? A systematic review and meta-analysis. Expert Review of Anticancer Therapy. 2021; 21: 781–794.

[12] Dahlman D, Li X, Magnusson H, Sundquist J, Sundquist K. Cervical cancer among Swedish women with drug use disorders: a nationwide epidemiological study. Gynecologic Oncology. 2021; 160: 742–747.

[13] Alimena S, Davis J, Fichorova RN, Feldman S. The vaginal microbiome: a complex milieu affecting risk of human papillomavirus persistence and cervical cancer. Current Problems in Cancer. 2022; 46: 100877.

[14] Xiao T, Ou CQ, Yang J, Wang C, Yang M, Yu T, et al. The risk factors for cervical cytological abnormalities among women infected with non-16/18 high-risk human papillomavirus: cross-sectional study. JMIR Public Health and Surveillance. 2022; 8: e38628.

[15] Wencel-Wawrzeńczyk A, Lewitowicz P, Lewandowska A, Saługa A. Sexual behavior and the awareness level of common risk factors for the development of cervical, anogenital and oropharyngeal cancer among women subjected to HR HPV DNA-testing. International Journal of Environmental Research and Public Health. 2022; 19: 9580.

[16] Kim JY, Lee DW, Kim MJ, Shin JE, Shin YJ, Lee HN. Secondhand smoke exposure, diabetes, and high BMI are risk factors for uterine cervical cancer: a cross-sectional study from the Korea national health and nutrition examination survey (2010–2018). BMC Cancer. 2021; 21: 880.

[17] Yang Z, Zhang Y, Stubbe-Espejel A, Zhao Y, Liu M, Li J, et al. Vaginal microbiota and personal risk factors associated with HPV status conversion—a new approach to reduce the risk of cervical cancer? PLOS ONE. 2022; 17: e0270521.

[18] Gajsek US, Dovnik A, Takac I, Ivanus U, Jerman T, Zatler SS, et al. Diagnostic performance of p16/Ki-67 dual immunostaining at different number of positive cells in cervical smears in women referred for colposcopy. Radiology and Oncology. 2021; 55: 426–432.

[19] Saraiya M, Cheung LC, Soman A, Mix J, Kenney K, Chen X, et al. Risk of cervical precancer and cancer among uninsured and underserved women from 2009 to 2017. American Journal of Obstetrics and Gynecology. 2021; 224: 366.e1–366.e32.

[20] zur Hausen H. Papillomaviruses and cancer: from basic studies to clinical application. Nature Reviews Cancer. 2002; 2: 342–350.

[21] Araldi RP, Sant’Ana TA, Módolo DG, de Melo TC, Spadacci-Morena DD, de Cassia Stocco R, et al. The human papillomavirus (HPV)-related cancer biology: an overview. Biomedicine & Pharmacotherapy. 2018; 106: 1537–1556.

[22] Bosch FX, Burchell AN, Schiffman M, Giuliano AR, de Sanjose S, Bruni L, et al. Epidemiology and natural history of human papillomavirus infections and type-specific implications in cervical neoplasia. Vaccine. 2008; 26: K1–K16.

[23] Zorzi M, Del Mistro A, Giorgi Rossi P, Laurino L, Battagello J, Lorio M, et al. Risk of CIN2 or more severe lesions after negative HPV-mRNA E6/E7 overexpression assay and after negative HPV-DNA test: concurrent cohorts with a 5-year follow-up. International Journal of Cancer. 2020; 146: 3114–3123.

[24] Kononenko I, Kukar M. Machine learning and data mining: introduction to principles and algorithms. 1st edn. Horwood Publishing: Chichester, UK. 2008.

[25] Kononenko I. Machine learning for medical diagnosis: history, state of the art and perspective. Artificial Intelligence in Medicine. 2001; 23: 89–109.

[26] Mlinaric M, Krizmaric M, Takac I, Repse Fokter A. Identification of women with high grade histopathology results after conisation by artificial neural networks. Radiology and Oncology. 2022; 56: 355–364.

[27] Mohammed R, Rawashdeh J, Abdullah M. Machine learning with oversampling and undersampling techniques: overview study and experimental results. 2020 11th International Conference on Information and Communication Systems (ICICS). Irbid, Jordan and 07–09 April 2020. IEEE. 2020.

[28] Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. SMOTE: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research. 2002; 16:321–357.

[29] Witten IH, Frank E, Hall MA. Data mining: practical machine learning tools and techniques. 3rd edn. Morgan Kaufmann: Burlington, MA. 2011.

[30] Airola A, Pahikkala T, Waegeman W, De Baets B, Salakoski T. An experimental comparison of cross-validation techniques for estimating the area under the ROC curve. Computational Statistics & Data Analysis. 2011; 55: 1828–1844.

[31] Maclin R, Opitz D. An empirical evaluation of bagging and boosting. American Association for Artificial Intelligence. 1997; 546–551.

[32] Dela Cruz CS, Tanoue LT, Matthay RA. Lung cancer: epidemiology, etiology, and prevention. Clinics in Chest Medicine. 2011; 32: 605–644.

[33] Mango LJ. Computer-assisted cervical cancer screening using neural networks. Cancer Letters. 1994; 77: 155–162.

[34] Sompawong N, Mopan J, Pooprasert P, Himakhun W, Suwannarurk K, Ngamvirojcharoen J, et al. Automated pap smear cervical cancer screen-ing using deep learning. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Berlin, Germany and 23–27 July 2019. IEEE. 2019.

[35] Holmström O, Linder N, Kaingu H, Mbuuko N, Mbete J, Kinyua F, et al. Point-of-care digital cytology with artificial intelligence for cervical cancer screening in a resource-limited setting. JAMA Network Open. 2021; 4: e211740.

[36] Bao H, Sun X, Zhang Y, Pang B, Li H, Zhou L, et al. The artificial intelligence-assisted cytology diagnostic system in large-scale cervical cancer screening: a population-based cohort study of 0.7 million women. Cancer Medicine. 2020; 9: 6896–6906.

[37] Turic B, Sun X, Wang J, Pang B. The role of AI in cervical cancer screening. 1st edn. IntechOpen: London. 2021.

[38] Karakitsos P, Chrelias C, Pouliakis A, Koliopoulos G, Spathis A, Kyrgiou M, et al. Identification of women for referral to colposcopy by neural networks: a preliminary study based on LBC and molecular biomarkers. Journal of Biomedicine and Biotechnology. 2012; 2012: 303192.

[39] Pouliakis A, Karakitsou E, Chrelias C, Pappas A, Panayiotides I, Valasoulis G, et al. The application of classification and regression trees for the triage of women for referral to colposcopy and the estimation of risk for cervical intraepithelial neoplasia: a study based on 1625 cases with incomplete data from molecular tests. BioMed Research International. 2015; 2015: 914740.

[40] Chandran V, Sumithra MG, Karthick A, George T, Deivakani M, Elakkiya B, et al. Diagnosis of cervical cancer based on ensemble deep learning network using colposcopy images. BioMed Research International. 2021; 2021: 5584004.

[41] Mendez MJG, Xue P, Quiao Y. Cervical cancer elimination in the era of COVID-19: the potential role of artificial intelligence (AI)-guided digital colposcope cloud platform. European Journal of Gynaecological Oncology. 2022; 43: 160–162.

[42] Weegar R, Sundström K. Using machine learning for predicting cervical cancer from Swedish electronic health records by mining hierarchical representations. PLOS ONE. 2020; 15: e0237911.

[43] Choudhury A, Al-Wesabi YMS, Won D. Classification of cervical cancer dataset. In: Proceedings of the 2018 IISE annual conference. Orlando. 2018; 1456–1461.

[44] World Health Organization. Turning the tide: Slovenia’s success story of fighting cervical cancer. 2020. Available at: https://www. (Accessed: 20 October 2022).

[45] Ferretti A, Ienca M, Velarde MR, Hurst S, Vayena E. The challenges of big data for research ethics committees: a qualitative Swiss study. Journal of Empirical Research on Human Research Ethics. 2022; 17: 129–143.

Abstracted / indexed in

Science Citation Index Expanded (SciSearch) Created as SCI in 1964, Science Citation Index Expanded now indexes over 9,500 of the world’s most impactful journals across 178 scientific disciplines. More than 53 million records and 1.18 billion cited references date back from 1900 to present.

Biological Abstracts Easily discover critical journal coverage of the life sciences with Biological Abstracts, produced by the Web of Science Group, with topics ranging from botany to microbiology to pharmacology. Including BIOSIS indexing and MeSH terms, specialized indexing in Biological Abstracts helps you to discover more accurate, context-sensitive results.

Google Scholar Google Scholar is a freely accessible web search engine that indexes the full text or metadata of scholarly literature across an array of publishing formats and disciplines.

JournalSeek Genamics JournalSeek is the largest completely categorized database of freely available journal information available on the internet. The database presently contains 39226 titles. Journal information includes the description (aims and scope), journal abbreviation, journal homepage link, subject category and ISSN.

Current Contents - Clinical Medicine Current Contents - Clinical Medicine provides easy access to complete tables of contents, abstracts, bibliographic information and all other significant items in recently published issues from over 1,000 leading journals in clinical medicine.

BIOSIS Previews BIOSIS Previews is an English-language, bibliographic database service, with abstracts and citation indexing. It is part of Clarivate Analytics Web of Science suite. BIOSIS Previews indexes data from 1926 to the present.

Journal Citation Reports/Science Edition Journal Citation Reports/Science Edition aims to evaluate a journal’s value from multiple perspectives including the journal impact factor, descriptive data about a journal’s open access content as well as contributing authors, and provide readers a transparent and publisher-neutral data & statistics information about the journal.

Submission Turnaround Time