Artificial Intelligence in Ovarian Cancer Diagnosis

Abstract

Background/Aim: This study aimed to use artificial intelligence (AI) to predict the pathological diagnosis of ovarian tumors using patient information and data from preoperative examinations. Patients and Methods: A total of 202 patients with ovarian tumors were enrolled, including 53 with ovarian cancer, 23 with borderline malignant tumors, and 126 with benign ovarian tumors. Using 5 machine learning classifiers, including support vector machine, random forest, naive Bayes, logistic regression, and XGBoost, we derived diagnostic results from 16 features, commonly available from blood tests, patient background, and imaging tests. We also analyzed the importance of 16 features on the prediction of disease. Results: The highest accuracy was 0.80 in the machine learning algorithm of XGBoost. The evaluation of importance of the features showed different results among the correlation coefficient of the features, the regression coefficient, and the features importance of random forest. Conclusion: AI could play a role in the prediction of pathological diagnosis of ovarian cancer from preoperative examinations.

Utility of a Machine-Guided Tool for Assessing Risk Behavior Associated With Contracting HIV in Three Sites in South Africa: Protocol for an In-Field Evaluation

“…Machine guidance and artificial intelligence have proven useful in the health sector and are being used in many branches of medicine, including gastroenterology and hepatology [ 18 ], oncology [ 19 , 20 ], and infectious diseases [ 21 , 22 ]. For HIV, the potential benefits of engaging in machine-guided identification include immediate and private HIV test results, which may encourage frequent testing of individuals in high-risk groups who would otherwise refrain from testing due to the unknown risk factors associated with susceptibility to acquiring HIV.…”

Application of artificial intelligence in gynecologic malignancies: A review

“…The results showed an accuracy of 66% and a negative predictive value of approximately 90% 42 . Akazawa et al 43 analyzed clinical information (age, menopause, endometriosis, BMI, white blood cell count, hemoglobin, C‐reactive protein, CA 125, CA 19‐9, etc.) and CT image information (tumor size, presence, or absence of ascites) from 202 patients with ovarian tumors (cancer 53, borderline malignancy 23, benign tumor 126) using five machine learning methods to develop a predictive model for benign or malignant potential.…”

“…and CT image information (tumor size, presence, or absence of ascites) from 202 patients with ovarian tumors (cancer 53, borderline malignancy 23, benign tumor 126) using five machine learning methods to develop a predictive model for benign or malignant potential. Among the five approaches, the proper diagnosis rate was highest at 0.80 for the machine learning method called XGBoost 43 . Kawakami et al 44 studied blood sampling data (albumin, C‐reactive protein, CA 125, leukocytes, hemoglobin, lactate dehydrogenase, etc.)…”

The Use of Artificial Intelligence in Automation in the Fields of Gynaecology and Obstetrics – an Assessment of the State of Play

“…In a recent study on the validity of two AI models to determine the character (benign/malignant) of adnexal lesions (trained on grey-scale and power doppler images), Christiansen et al demonstrated a sensitivity of 96% and 97.1%, respectively, and a specificity of 86.7% and 93.7%, respectively, with no significant differences to expert assessments 33 . The additional benefit of various ML classifiers, alone or in combination, has been investigated in several other approaches, which have likewise found that, in the future, AI approaches will be able to identify more ovarian neoplasms and be increasingly employed in their (early) detection 34 , 35 , 36 , 37 , 38 . In a recently published study, Al-Karawi et al used ML algorithms (support vector machine classification) to investigate seven differing familiar image texture parameters in ultrasound still images, which, according to the authors, can provide information about altered cellular composition in the process of carcinogenesis.…”

“…93,7% erreichen – ohne signifikante Unterschiede im Vergleich zur Experteneinschätzung 33 . Der Mehrwert verschiedener ML-Klassifikatoren allein oder in Kombination wurde in verschiedenen anderen Ansätzen untersucht, mit dem ähnlichen Ergebnis, dass KI-Ansätze zukünftig mehr und mehr Einsatz in der (Früh-)Entdeckung ovarieller Neoplasien finden werden 34 , 35 , 36 , 37 , 38 . Al-Karawi et al untersuchten im Rahmen einer aktuellen Arbeit mittels ML-Algorithmen (Support Vector Machine Classifier) 7 unterschiedliche bekannte Bildtexturparameter in US-Standbildern, die nach Vorstellung der Autoren Auskunft über die veränderte zelluläre Zusammensetzung i. R. d. Karzinogenese geben können.…”