Maria Kyrgiou1, Abraham Pouliakis2, John G Panayiotides3, Niki Margari2, Panagiotis Bountris4, George Valasoulis5, Maria Paraskevaidi6, Evripidis Bilirakis7, Maria Nasioutziki8, Aristotelis Loufopoulos8, Maria Haritou9, Dimitrios D Koutsouris4, Petros Karakitsos2, Evangelos Paraskevaidis5. 1. Institute of Reproductive and Developmental Biology, Department of Surgery and Cancer, Imperial College London, UK; West London Gynaecological Cancer Centre, Queen Charlotte's and Chelsea - Hammersmith Hospital, Imperial Healthcare NHS Trust, London, UK. Electronic address: m.kyrgiou@imperial.ac.uk. 2. Cytopathology, National and Kapodistrian University of Athens, Athens, Greece. 3. 2nd Department of Pathology, National and Kapodistrian University of Athens, Athens, Greece. 4. Biomedical Engineering Laboratory, National Technical University of Athens, Greece. 5. Obstetrics & Gynaecology, University of Ioannina, Ioannina, Greece. 6. Institute of Reproductive and Developmental Biology, Department of Surgery and Cancer, Imperial College London, UK. 7. Elena Venizelou Hospital, Athens, Greece. 8. 2nd Department of Obstetrics & Gynecology and Molecular Clinical Cytology Laboratory, Hippokration Hospital, Aristotle University of Thessaloniki, Greece. 9. Institute of Communication and Computer Systems, Athens, Greece.
Abstract
OBJECTIVES: To develop a clinical decision support scoring system (DSSS) based on artificial neural networks (ANN) for personalised management of women with cervical abnormalities. METHODS: We recruited women with cervical abnormalities and healthy controls that attended for opportunistic screening between 2006 and 2014 in 3 University Hospitals. We prospectively collected detailed patient characteristics, the colposcopic impression and performed a series of biomarkers using a liquid-based cytology sample. These included HPV DNA typing, E6&E7 mRNA by NASBA or flow cytometry and p16INK4a immunostaining. We used ANNs to combine the cytology and biomarker results and develop a clinical DSSS with the aim to improve the diagnostic accuracy of tests and quantify the individual's risk for different histological diagnoses. We used histology as the gold standard. RESULTS: We analysed data from 2267 women that had complete or partial dataset of clinical and molecular data during their initial or followup visits (N=3565). Accuracy parameters (sensitivity, specificity, positive and negative predictive values) were assessed for the cytological result and/or HPV status and for the DSSS. The ANN predicted with higher accuracy the chances of high-grade (CIN2+), low grade (HPV/CIN1) and normal histology than cytology with or without HPV test. The sensitivity for prediction of CIN2 or worse was 93.0%, specificity 99.2% with high positive (93.3%) and negative (99.2%) predictive values. CONCLUSIONS: The DSSS based on an ANN of multilayer perceptron (MLP) type, can predict with the highest accuracy the histological diagnosis in women with abnormalities at cytology when compared with the use of tests alone. A user-friendly software based on this technology could be used to guide clinician decision making towards a more personalised care.
OBJECTIVES: To develop a clinical decision support scoring system (DSSS) based on artificial neural networks (ANN) for personalised management of women with cervical abnormalities. METHODS: We recruited women with cervical abnormalities and healthy controls that attended for opportunistic screening between 2006 and 2014 in 3 University Hospitals. We prospectively collected detailed patient characteristics, the colposcopic impression and performed a series of biomarkers using a liquid-based cytology sample. These included HPV DNA typing, E6&E7 mRNA by NASBA or flow cytometry and p16INK4a immunostaining. We used ANNs to combine the cytology and biomarker results and develop a clinical DSSS with the aim to improve the diagnostic accuracy of tests and quantify the individual's risk for different histological diagnoses. We used histology as the gold standard. RESULTS: We analysed data from 2267 women that had complete or partial dataset of clinical and molecular data during their initial or followup visits (N=3565). Accuracy parameters (sensitivity, specificity, positive and negative predictive values) were assessed for the cytological result and/or HPV status and for the DSSS. The ANN predicted with higher accuracy the chances of high-grade (CIN2+), low grade (HPV/CIN1) and normal histology than cytology with or without HPV test. The sensitivity for prediction of CIN2 or worse was 93.0%, specificity 99.2% with high positive (93.3%) and negative (99.2%) predictive values. CONCLUSIONS: The DSSS based on an ANN of multilayer perceptron (MLP) type, can predict with the highest accuracy the histological diagnosis in women with abnormalities at cytology when compared with the use of tests alone. A user-friendly software based on this technology could be used to guide clinician decision making towards a more personalised care.
Authors: Maria Kyrgiou; Ilkka E J Kalliala; Anita Mitra; Christina Fotopoulou; Sadaf Ghaem-Maghami; Pierre Pl Martin-Hirsch; Margaret Cruickshank; Marc Arbyn; Evangelos Paraskevaidis Journal: Cochrane Database Syst Rev Date: 2017-01-26
Authors: Seán Walsh; Evelyn E C de Jong; Janna E van Timmeren; Abdalla Ibrahim; Inge Compter; Jurgen Peerlings; Sebastian Sanduleanu; Turkey Refaee; Simon Keek; Ruben T H M Larue; Yvonka van Wijk; Aniek J G Even; Arthur Jochems; Mohamed S Barakat; Ralph T H Leijenaar; Philippe Lambin Journal: JCO Clin Cancer Inform Date: 2019-02
Authors: Wolf Ramackers; Julia Victoria Stupak; Indra Louisa Marcheel; Annette Tuffs; Harald Schrem; Volkhard Fischer; Jan Beneke Journal: BMC Med Educ Date: 2020-10-16 Impact factor: 2.463