Clinicians' use of breast cancer risk assessment tools according to their perceived importance of breast cancer risk factors: an international survey

Prediction of Breast Cancer using Machine Learning Approaches

BACKGROUND

Breast cancer is considered one of the most common cancers in women caused by various clinical, lifestyle, social, and economic factors. Machine learning has the potential to predict breast cancer based on features hidden in data.

OBJECTIVE

This study aimed to predict breast cancer using different machine-learning approaches applying demographic, laboratory, and mammographic data.

MATERIAL AND METHODS

In this analytical study, the database, including 5,178 independent records, 25% of which belonged to breast cancer patients with 24 attributes in each record was obtained from Motamed cancer institute (ACECR), Tehran, Iran. The database contained 5,178 independent records, 25% of which belonged to breast cancer patients containing 24 attributes in each record. The random forest (RF), neural network (MLP), gradient boosting trees (GBT), and genetic algorithms (GA) were used in this study. Models were initially trained with demographic and laboratory features (20 features). The models were then trained with all demographic, laboratory, and mammographic features (24 features) to measure the effectiveness of mammography features in predicting breast cancer.

RESULTS

RF presented higher performance compared to other techniques (accuracy 80%, sensitivity 95%, specificity 80%, and the area under the curve (AUC) 0.56). Gradient boosting (AUC=0.59) showed a stronger performance compared to the neural network.

CONCLUSION

Combining multiple risk factors in modeling for breast cancer prediction could help the early diagnosis of the disease with necessary care plans. Collection, storage, and management of different data and intelligent systems based on multiple factors for predicting breast cancer are effective in disease management.

The emerging roles of NGS in clinical oncology and personalized medicine

Next-generation sequencing (NGS) has been increasingly popular in genomics studies over the last decade, as new sequencing technology has been created and improved. Recently, NGS started to be used in clinical oncology to improve cancer therapy through diverse modalities ranging from finding novel and rare cancer mutations, discovering cancer mutation carriers to reaching specific therapeutic approaches known as personalized medicine (PM). PM has the potential to minimize medical expenses by shifting the current traditional medical approach of treating cancer and other diseases to an individualized preventive and predictive approach. Currently, NGS can speed up in the early diagnosis of diseases and discover pharmacogenetic markers that help in personalizing therapies. Despite the tremendous growth in our understanding of genetics, NGS holds the added advantage of providing more comprehensive picture of cancer landscape and uncovering cancer development pathways. In this review, we provided a complete overview of potential NGS applications in scientific and clinical oncology, with a particular emphasis on pharmacogenomics in the direction of precision medicine treatment options.

Survey on Physicians' Knowledge and Training Needs in Genetic Counseling in Germany

Background

In recent years, germline testing of women with a risk of developing breast and ovarian cancer has increased rapidly. This is due to lower costs for new high-throughput sequencing technologies and the manifold preventive and therapeutic options for germline mutation carriers. The growing demand for genetic counseling meets a shortfall of counselors and illustrates the need to involve the treating clinicians in the genetic testing process. This survey was undertaken to assess their state of knowledge and training needs in the field of genetic counseling and testing.

Methods

A cross-sectional survey within the European Bridges Study (Breast Cancer Risk after Diagnostic Gene Sequencing) was conducted among physician members (n = 111) of the German Cancer Society who were primarily gynecologists. It was designed to examine their experience in genetic counseling and testing.

Results

Overall, the study revealed a need for training in risk communication and clinical recommendations for persons at risk. One-third of respondents communicated only relative disease risks (31.5%) instead of absolute disease risks in manageable time spans. Moreover, almost one-third of the respondents (31.2%) communicated bilateral and contralateral risk-reducing mastectomy as an option for healthy women and unilateral-diseased breast cancer patients without mutations in high-risk genes (e.g. BRCA1 or BRCA2). Most respondents expressed training needs in the field of risk assessment models, the clinical interpretation of genetic test results, and the decision-making process.

Conclusion

The survey demonstrates a gap of genetic and risk literacy in a relevant proportion of physicians and the need for appropriate training concepts.

Leveraging Health Information Technology to Collect Family Cancer History: A Systematic Review and Meta-Analysis

PURPOSE

Collection of family cancer histories (FCHs) can identify individuals at risk for familial cancer syndromes. The aim of this study is to evaluate the literature on existing strategies whereby providers use information technology to assemble FCH.

METHODS

A systematic search of online databases (Ovid MEDLINE, Cochrane, and Embase) between 1980 and 2020 was performed. Statistical heterogeneity was assessed through the chi-square test (ie, Cochrane Q test) and the inconsistency statistic (I2). A random-effects analysis was used to calculate the pooled proportions and means.

RESULTS

The comprehensive search produced 4,005 publications. Twenty-eight studies met inclusion criteria. Twenty-seven information technology tools were evaluated. Eighteen out of 28 studies were electronic surveys administered before visits (18, 64.3%). Five studies administered tablet surveys in offices (5, 17.8%). Four studies collected electronic survey via kiosk before visits (4, 14.3%), and one study used animated virtual counselor during visits (1, 3.6%). Among the studies that use an FCH tool, the pooled estimate of the overall completion rate was 86% (CI, 72% to 96%), 84% (CI, 65% to 97%) for electronic surveys before visits, 89% (CI, 0.74 to 0.98) for tablet surveys, and 85% (CI, 0.66 to 0.98) for surveys via kiosk. Mean time required for completion was 31.0 minutes (CI, 26.1 to 35.9), and the pooled estimate of proportions of participants referred to genetic testing was 12% (CI, 4% to 23%).

CONCLUSION

Our review found that electronic FCH collection can be completed successfully by patients in a time-efficient manner with high rates of satisfaction.

Patterns and Determinants of Attitudes towards Genetic Risk of Cancer: Case Study in a Malaysian Public University

Genetic risk to cancer is a knowledge largely confined to experts and the more educated sectors of the developed western countries. The perception of genetic susceptibility to cancer among the masses is fragmented, particularly in developing countries. As cancer diseases affect developing countries as much as developed nations, it is imperative to study perception and reception of genetic risk to cancer in Southeast Asia. Here, we report on a novel case study to gauge the awareness and attitudes towards genetic determination of cancer among the undergraduates of a Malaysian public university. A total of 272 university undergraduate students completed an online questionnaire. On causes of cancer, the respondents believed that cancer is caused by lifestyle and environmental factors, but those with science background were more likely to associate it with genetic factors. The results on awareness of genetic profiling of cancer risk showed that there are significant differences between those with science and nonscience background but there are no significant differences for gender and socioeconomic background. As for attitudes towards cancer risk, female respondents, those from middle socioeconomic status and science background, are more likely to believe in genetic determinism of cancer. The findings have implications on target population segmentation in strategic health communication on cancer.