METHODS: A large hospital-based breast cancer dataset retrieved from the University Malaya Medical Centre, Kuala Lumpur, Malaysia (n = 8066) with diagnosis information between 1993 and 2016 was used in this study. The dataset contained 23 predictor variables and one dependent variable, which referred to the survival status of the patients (alive or dead). In determining the significant prognostic factors of breast cancer survival rate, prediction models were built using decision tree, random forest, neural networks, extreme boost, logistic regression, and support vector machine. Next, the dataset was clustered based on the receptor status of breast cancer patients identified via immunohistochemistry to perform advanced modelling using random forest. Subsequently, the important variables were ranked via variable selection methods in random forest. Finally, decision trees were built and validation was performed using survival analysis.
RESULTS: In terms of both model accuracy and calibration measure, all algorithms produced close outcomes, with the lowest obtained from decision tree (accuracy = 79.8%) and the highest from random forest (accuracy = 82.7%). The important variables identified in this study were cancer stage classification, tumour size, number of total axillary lymph nodes removed, number of positive lymph nodes, types of primary treatment, and methods of diagnosis.
CONCLUSION: Interestingly the various machine learning algorithms used in this study yielded close accuracy hence these methods could be used as alternative predictive tools in the breast cancer survival studies, particularly in the Asian region. The important prognostic factors influencing survival rate of breast cancer identified in this study, which were validated by survival curves, are useful and could be translated into decision support tools in the medical domain.
EDUCATIONAL ACTIVITY AND SETTING: Pharmacy students developed a "hands-on" health campaign for delivery to university students. A health promotion topic was chosen and delivered each year for 2015-2017; sexual health, diabetes, and antimicrobial resistance, respectively. All health campaign participants were screened for cardiovascular risk factors. University students who participated in the health campaign in 2017 also completed a questionnaire assessing their understanding and knowledge of antimicrobial resistance.
FINDINGS: In the three health campaigns conducted from 2015 to 2017, 1010 university students and adults were screened. Pharmacy students expressed a high level of professional achievement and satisfaction and felt that the activities provided a meaningful learning experience. Similarly, supervising pharmacists reported satisfaction with students' competency.
SUMMARY: The use of a health education campaign is an alternative model to educate pharmacy students on communication and critical thinking skills, as well as provide an opportunity for service learning.
RECENT FINDINGS: Over the years, immunological therapy has become the center of attraction to treat T1D. Immunomodulatory approaches on non-antigens involving agents such as cyclosporine A, mycophenolate mofetil, anti-CD20, cytotoxic T cells, anti-TNF, anti-CD3, and anti-thymocyte globulin as well as immunomodulative approaches on antigens such as insulin, glutamic acid decarboxylase, and heat shock protein 60 have been studied. Aside from these two approaches, studies and trials have also been conducted on regulatory T cells, dendritic cells, interleukin 2, interleukin 4, M2 macrophages, and rapamycin/interleukin 2 combination therapy to test their effects on patients with T1D. Many of these agents have successfully suppressed T1D in non-obese diabetic (NOD) mice and in human trials. However, some have shown negative results. To date, the insights into the management of the immune system have been increasing rapidly to search for potential therapies and treatments for T1D. Nevertheless, some of the challenges are still inevitable. A lot of work and effort need to be put into the investigation on T1D through immunological therapy, particularly to reduce complications to improve and enhance clinical outcomes.
METHODS: Data were retrieved for major SGC patients diagnosed between 1988 and 2011 from Surveillance, Epidemiology, and End Results program.
RESULTS: We have included 5446 patients with major SGC. Most patients had parotid gland cancer (84.61%). Patients having >18 ELNs, >4 PLNs, and >33.33% LNR were associated with a worse survival. Moreover, older age, male patients, grade IV, distant stage, unmarried patients, submandibular gland cancer, and received chemotherapy but not received surgery were significantly associated with a worse survival.
CONCLUSIONS: We demonstrated that patients with >18 ELNs and >4 PLNs counts, and >33.33% LNR were high-risk group patients. We strongly suggest adding the ELNs and PLNs counts and/or LNR into the current staging system.