Measurement of breast cancer burden and identification of its influencing factors help in the development of public health policy and strategy against the disease. This study aimed to examine the variability of the excess mortality of female breast cancer patients in the North East Region of Peninsular Malaysia. This retrospective cohort study was conducted using breast cancer data from the Kelantan Cancer Registry between 2007 and 2011, and Kelantan general population mortality data. The breast cancer cases were followed up for five years until 2016. Out of 598 cases, 549 cases met the study criteria and were included in the analysis. Modelling of excess mortality was conducted using Poisson regression. Excess mortality of breast cancer varied according to age group (50 years old and below vs above 50 years old, Adj. EHR: 1.47; 95% CI: 1.31, 4.09; P=0.004), ethnicity (Malay vs non-Malay, Adj. EHR: 2.31; 95% CI: 1.11, 1.96; P=0.008), and stage (stage III and IV vs. stage I and II, Adj. EHR: 5.75; 95% CI: 4.24, 7.81; P<0.001). In conclusion, public health policy and strategy aim to improve cancer survival should focus more on patients presented at age below 50 years old, Malay ethnicity, and at a later stage.

This study utilised an ensemble of pre-trained networks and digital mammograms to develop a supplementary diagnostic tool for radiologists. Digital mammograms and their associated information were collected from the department of radiology and pathology, Hospital Universiti Sains Malaysia. Thirteen pre-trained networks were selected and explored in this study. ResNet101V2 and ResNet152 had the highest mean PR-AUC, MobileNetV3Small and ResNet152 had the highest mean precision, ResNet101 had the highest mean F1 score, and ResNet152 and ResNet152V2 had the highest mean Youden J index. Subsequently, three ensemble models were developed using the top three pre-trained networks based on PR-AUC, precision, and F1 score. The final ensemble model had a mean precision, F1 score, and Youden J index of 0.82, 0.68, and 0.12, respectively. Additionally, the final model demonstrated a balanced performance across mammographic density. In conclusion, this study exhibited the good performance of the ensemble transfer learning on digital mammograms for the purpose of breast cancer risk estimation. This model can be utilised as a supplementary diagnostic tool for radiologists, thus, reducing their workloads.

This study aimed to determine the feasibility of the development of an over-the-counter (OTC) screening model using machine learning for breast cancer screening in the Asian women population. Data were retrospectively collected from women who came to the Hospital Universiti Sains Malaysia, Malaysia. Five screening models were developed based on machine learning methods; random forest, artificial neural network (ANN), support vector machine (SVM), elastic-net logistic regression and extreme gradient boosting (XGBoost). Features used for the development of the screening models were limited to information from the patients’ registration form. The model performance was assessed across the dense and non-dense groups. SVM had the best sensitivity while elastic-net logistic regression had the best specificity. In terms of precision, both random forest elastic-net logistic regression had the best performance, while, in terms of PR-AUC, XGBoost had the best performance. Additionally, SVM had a more balanced performance in terms of sensitivity and specificity across the mammographic density groups. The three most important features were age at examination, weight and number of children. In conclusion, OTC models developed from machine learning methods can improve the prognostic process of breast cancer in Asian women.

To quantify the time-varying reproduction number (Rt) for Malaysia using the COVID-19 incidence data., we used data the from the Johns Hopkins University Center for Systems Science and Engineering (JHU CCSE) Coronavirus repository. Day 1 was taken from the first assumed local transmission of COVID-19. Data was split into four intervals: a) Interval 1: from Day 1 to Day 10 MCO 1, b) Interval 2: from Day 1 to Day 10 MCO 2, c) Interval 3: from Day 1 to Day 10 MCO 3 and d) Interval 4: from Day 1 to Day 10 MCO 4. We estimated the Rt using the EpiEstim package. The means for Rt at Day 1, Day 5 and Day 10 for all MCOs ranged between 0.665 to 1.147. The average Rt gradually decreased in MCO 1 and MCO 2. However, Rt increased in MCO 3 before stabilized around 0.8 in MCO 4. MCO 1 and MCO 2 which were stricter coincide with the gradual reduction of Rt. However, the more relaxed MCO 3 and MCO 4 correspond to a slight increase in the Rt before it stabilized.