Breast cancer prediction using different machine learning methods applying multi factors

OBJECTIVE

Breast cancer (BC) is a multifactorial disease and is one of the most common cancers globally. This study aimed to compare different machine learning (ML) techniques to develop a comprehensive breast cancer risk prediction model based on features of various factors.

METHODS

The population sample contained 810 records (115 cancer patients and 695 healthy individuals). 45 attributes out of 85 were selected based on the opinion of experts. These selected attributes are in genetic, biochemical, biomarker, gender, demographic and pathological factors. 13 Machine learning models were trained with proposed attributes and coefficient of attributes and internal relationships were calculated.

RESULT

Compared to other methods random forest (RF) has higher performance (accuracy 99.26%, precision 99%, and area under the curve (AUC) 99%). The results of assessing the impact and correlation of variables using the RF method based on PCA indicated that pathology, biomarker, biochemistry, gene, and demographic factors with a coefficient of 0.35, 0.23, 0.15, 0.14, and 0.13 respectively, affected the risk of BC (r2 = 0.54).

CONCLUSION

Breast cancer has several risk factors. Medical experts use these risk factors for early diagnosis. Therefore, identifying related risk factors and their effect can increase the accuracy of diagnosis. Considering the broad features for predicting breast cancer leads to the development of a comprehensive prediction model. In this study, using RF technique a breast cancer prediction model with 99.3% accuracy was developed based on multifactorial features.

Human T lymphotropic virus type 1 and risk of cardiovascular disease: High-density lipoprotein dysfunction versus serum HDL-C concentrations

High-density lipoprotein (HDL) is thought to be protective against cardiovascular disease (CVD), and HDL dysfunction is considered to be a risk factor for CVD. It is unclear whether there is an association between Human T lymphotropic virus type 1 (HTLV1) infection and CVD risk. We have assessed HDL lipid peroxidation (HDLox) as a marker of HDL dysfunction and CVD risk in a subgroup of the MASHAD cohort study. One hundred and sixty two individuals including 50 subjects positive for HTLV1 infection and 112 individuals negative for HTLV1 infection were recruited. Anthropometric and biochemical parameters including serum hs-CRP, fasted lipid profile (HDL-C, LDL, triglycerides, and cholesterol), and fasting blood glucose were determined. Serum HDLox was also measured in the study participants. Multivariate analyses were used to evaluate the association between serum HDLox and HTLV1 infection. None of the traditional CVD risk factors were associated with HTLV1 infection, including serum HDL-C. However, serum HDLox was independently associated with the presence of HTLV1 infection. Logistic regression analysis showed that subjects who were positive for HTLV1 infection were also significantly more likely than uninfected individuals to have higher HDLox (odds ratio 9.35, 95%CI: 3.5-24.7; P < 0.001). HDLox was increased approximately 20% (P < 0.001) in infected subjects compared to the uninfected group. Serum HDLox is a marker of CVD risk factor and increased in individuals affected by HTLV1 infection compared to healthy subjects. © 2019 BioFactors, 45(3):374-380, 2019.

High-density lipoprotein functionality and breast cancer: A potential therapeutic target

Breast cancer is a major cause of death globally, and particularly in developed countries. Breast cancer is influenced by cholesterol membrane content, by affecting the signaling pathways modulating cell growth, adherence, and migration. Furthermore, steroid hormones are derived from cholesterol and these play a key role in the pathogenesis of breast cancer. Although most findings have reported an inverse association between serum high-density lipoprotein (HDL)-cholesterol level and the risk of breast cancer, there have been some reports of the opposite, and the association therefore remains unclear. HDL is principally known for participating in reverse cholesterol transport and has an inverse relationship with the cardiovascular risk. HDL is heterogeneous, with particles varying in composition, size, and structure, which can be altered under different circumstances, such as inflammation, aging, and certain diseases. It has also been proposed that HDL functionality might have a bearing on the breast cancer. Owing to the potential role of cholesterol in cancer, its reduction using statins, and particularly as an adjuvant during chemotherapy may be useful in the anticancer treatment, and may also be related to the decline in cancer mortality. Reconstituted HDLs have the ability to release chemotherapeutic drugs inside the cell. As a consequence, this may be a novel way to improve therapeutic targeting for the breast cancer on the basis of detrimental impacts of oxidized HDL on cancer development.