Explainable Artificial Intelligence in Quantifying Breast Cancer Factors: Saudi Arabia Context.

Breast cancer represents a significant health concern, particularly in Saudi Arabia, where it ranks as the most prevalent cancer type among women. This study focuses on leveraging eXplainable Artificial Intelligence (XAI) techniques to predict benign and malignant breast cancer cases using various clinical and pathological features specific to Saudi Arabian patients. Six distinct models were trained and evaluated based on common performance metrics such as accuracy, precision, recall, F1 score, and AUC-ROC score. To enhance interpretability, Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) were applied. The analysis identified the Random Forest model as the top performer, achieving an accuracy of 0.72, along with robust precision, recall, F1 score, and AUC-ROC score values. Conversely, the Support Vector Machine model exhibited the poorest performance metrics, indicating its limited predictive capability. Notably, the XAI approaches unveiled variations in the feature importance rankings across models, underscoring the need for further investigation. These findings offer valuable insights into breast cancer diagnosis and machine learning interpretation, aiding healthcare providers in understanding and potentially integrating such technologies into clinical practices.

Evaluation of the Mawid mobile healthcare application in delivering services during the COVID-19 pandemic in Saudi Arabia.

PURPOSE: The purpose of this study is to evaluate MAWID mobile application developed by the Ministry of Health, Saudi Arabia, which is used for primary care hospitals appointments management and for tracking and tracing COVID-19. PARTICIPANTS AND METHODS: An online questionnaire-based survey was used for collecting data related to three major factors including Ease of Use, Satisfaction, and Benefits of MAWID application among its users. Out of total 2542 participants, 345 participants completed only a part of the survey, and 204 participants did not use the application. After removing, 549 invalid responses, a final sample of 1993 was included for the data analysis. RESULTS: 82.1% of the participants referred MAWID as easy to use application, 79.8% were highly satisfied with the application, and majority of the participants reflected potential benefits of using the application. T-test results have revealed that significant differences existed between males and females, and young and older participants in relation to the Ease of Use and Satisfaction levels associated with MAWID application. CONCLUSION: Mobile applications can be very effective in delivering the healthcare services during pandemics. However, there is a need for regular evaluation and assessment to trach the change in users' needs and update the app according to the changing requirements.

A comparative study of strategies for containing the COVID-19 pandemic in Gulf Cooperation Council countries and the European Union.

BACKGROUND: The COVID-19 pandemic has impacted every aspect of human lives including health, businesses, and lifestyles. In spite of governments implementing various strategies across the globe, the pandemic is still expanding with increasing numbers of positive cases. In addition, countries are reopening and easing lockdown restrictions in order to get their economies back on track, and this has led to an increase in the transmission of novel coronavirus. Therefore, it is essential to regularly review the containment strategies employed in different regions in order to understand the characteristics of COVID-19 transmission and to formulate a future course of actions. OBJECTIVE: The objective of this study is to review the COVID-19 transmission statistics in Gulf Cooperation Council (GCC) and European Union (EU) countries, and to compare these data with the various containment strategies implemented for containing the spread of the virus. METHODS: A review method was adopted along with different statistical methods for comparing and analyzing COVID-19 data and containment strategies. Transmission types and the Case Fatality Rate (CFR) in the countries in both regions are used to present the current state of the pandemic. In addition, changes in the number of COVID-19 cases are compared with the mitigation and suppression strategies implemented in both regions and their impact is analyzed. RESULTS: Countries in the EU were slow in reacting to the pandemic, as delays are observed in the implementation of mitigation strategies. However, suppression strategies were implemented soon after mitigation strategies. GCC countries, on the other hand, were quick to react, and they implemented both mitigation and suppression strategies simultaneously, as soon as the pandemic emerged. The CFR was found to be low among GCC countries compared to EU countries. In addition, a second wave of transmission was observed in the EU, whereas in GCC countries there has been no second wave, although a gradual increase in the number of cases is observed. Community transmission was observed among the majority of countries in both GCC and EU countries. CONCLUSIONS: With the reopening of markets, the focus of governments should be on developing integrated user-centric preventive strategies, with a blend of awareness creation, motivation, and support.

Mammography Image-Based Diagnosis of Breast Cancer Using Machine Learning: A Pilot Study.

A tumor is an abnormal tissue classified as either benign or malignant. A breast tumor is one of the most common tumors in women. Radiologists use mammograms to identify a breast tumor and classify it, which is a time-consuming process and prone to error due to the complexity of the tumor. In this study, we applied machine learning-based techniques to assist the radiologist in reading mammogram images and classifying the tumor in a very reasonable time interval. We extracted several features from the region of interest in the mammogram, which the radiologist manually annotated. These features are incorporated into a classification engine to train and build the proposed structure classification models. We used a dataset that was not previously seen in the model to evaluate the accuracy of the proposed system following the standard model evaluation schemes. Accordingly, this study found that various factors could affect the performance, which we avoided after experimenting all the possible ways. This study finally recommends using the optimized Support Vector Machine or Naïve Bayes, which produced 100% accuracy after integrating the feature selection and hyper-parameter optimization schemes.