Development and Evaluation of a Mobile Health Application for Ovarian Cancer Diagnosis Using Bioinformatics and Deep Learning Methods

Background and Aims: Ovarian cancer is one of the most lethal types of cancer among women, and early diagnosis plays a crucial role in improving patient outcomes. In this study, a mobile health application has been developed to assist in the diagnosis of ovarian cancer by utilizing bioinformatics methods and deep learning to evaluate the likelihood of the disease. The goal of this research is to design and evaluate a mobile health app that helps with early detection of ovarian cancer using biological data processing techniques and deep learning models. Methods: The application consists of four main modules. The first is data collection, in which data is gathered from reputable bioinformatics databases and patient medical records. The second is data preprocessing and analysis, where the data is normalized and key features are extracted to improve model accuracy. The third module includes several deep learning models, such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), which are used to analyze bioinformatics data and identify patterns related to ovarian cancer. The fourth module is the developed application itself, which features a simple and user-friendly interface allowing users to input basic information and receive a risk assessment for ovarian cancer. The application also supports communication with physicians and the sending of analytical reports. Results: To evaluate the performance of the application, the developed deep learning models were tested on validated datasets. Evaluation metrics included accuracy, sensitivity, specificity, false positive rate, and false negative rate. The system achieved an accuracy of over ۸۷% in detecting ovarian cancer, indicating the high potential of this method for early diagnosis. Additionally, the application was reviewed by medical professionals, who confirmed its high usability. Conclusion and Future Recommendations: This study demonstrated that using advanced mobile health applications can be an effective tool for the early detection of ovarian cancer and can support physicians in decision-making alongside traditional diagnostic methods. It is recommended that in the future, larger datasets and more