Ovarian Cancer-Self Assessment: An Innovation for Early Detection and Risk Assessment of Ovarian Cancer

Salima, Siti; Rachmawati, Anita; Harsono, Ali Budi; Erfiandi, Febia; Fauzi, Hilman; Prasekti, Heti; Nurita, Rena

doi:10.31557/APJCP.2022.23.8.2643

Ovarian Cancer-Self Assessment: An Innovation for Early Detection and Risk Assessment of Ovarian Cancer

Document Type : Research Articles

Authors

¹ Department of Obstetrics and Gynecology, Faculty of Medicine, Universitas Padjajaran, Bandung, Indonesia.

² Biomedical Engineering, Faculty of Electrical Engineering, Telkom University, Bandung, Indonesia.

10.31557/APJCP.2022.23.8.2643

Abstract

Objective: The modality to detect ovarian cancer at an early stage is very limited. Early diagnosis determines the prognosis. This study aimed to develop a risk assessment tool for early detection of ovarian cancer using artificial intelligence. To accomplish this, the presence of ten signs and symptoms reported by patients with ovarian cancer was assessed. Methods: This study was carried out as a cohort study of patients diagnosed with suspected ovarian tumors undergoing cytoreduction operation at Hasan Sadikin Hospital, Bandung, from December 2019 to September 2020. Compared to ovarian cancer self-assessment through questionnaire, postoperative histopathology in patients with suspected ovarian tumors. The questionnaire proceeded by artificial intelligence is grouped into risk and no risk. Statistical analyses were done using Chi-Square and Exact Fisher Test. Result: In total, 115 patients included in this study. The differences were statistically significant in terms of the six variables (abdominal bloating, nausea/vomiting, decreased of appetite, fullness, menstrual disturbance, and weight loss) ovarian cancer self-assessment compared to postoperative histopathology with a tendency towards benign ovarian tumors (p<0.05), while there was no statistically significant difference in the four variables (abdominal enlargement, abdominal pain, urinating disturbance, and defecation disturbance) (p>0.05). According to the artificial intelligence grouping, fifty-five patients were at risk, and sixty patients were not at risk. The Fifty-five risk patients were related with postoperative histopathology diagnosis (with RR 0.682 and CI 95% 0.519-0.895). Conclusion: Risk assessments based on ovarian cancer self-assessment unfortunately were not comparable to postoperative histopathology as a single predictor. Ten variables in ovarian cancer artificial intelligence self-assessment for early detection needs improvement in adding another variable like tumor marker and ultrasonography assessment.

Keywords