The Application of Gail Model to Predict the Risk of Developing Breast Cancer among Jordanian Women

The Gail Model and Its Use in Preventive Screening: A Comparison of the Corbelli Study

Background This study aims to determine the usage of the Gail model in screening for breast cancer during physical examinations of women by sampling primary care physicians in two regions of Texas - Hidalgo County and Johnson County. A Gail score of 1.66% or higher indicates increased breast cancer risk. Three specialties are surveyed: internal medicine (IM), family medicine (FM), and gynecology (GYN). The null hypothesis for this study is that primary care physicians do not use the Gail model in screening for breast cancer during physical examinations of women. Methods A survey was distributed to 100 physicians with specialties in IM, FM, and GYN from May 2022 to July 2022. The survey assessed the physician's frequency of use of the Gail model and chemoprevention. Data were collected by distributing survey questionnaires to physicians in person. Descriptive statistics were used for response distributions. Fisher's exact probability test was used for comparisons across specialties. Results The response rate was 34% (34/100). Thirty-eight percent of the physicians surveyed reported using the Gail model in their practice (IM 46%, FM 23%, and GYN 31%). All 13 of the physicians using the Gail model were open to using chemoprevention. Conclusions Only 38% of the physicians surveyed responded that they use the Gail model in their practice. The study concluded that a minority of primary care physicians used the Gail model to decrease breast cancer risk. Further research would help to define better the Gail model and its use in preventing breast cancer in women. The Gail model appears to be beneficial to breast cancer risk reduction; however, risk reduction medication side effects need to be minimized.

An Assessment of the Predictive Performance of Current Machine Learning-Based Breast Cancer Risk Prediction Models: Systematic Review

BACKGROUND

Several studies have explored the predictive performance of machine learning-based breast cancer risk prediction models and have shown controversial conclusions. Thus, the performance of the current machine learning-based breast cancer risk prediction models and their benefits and weakness need to be evaluated for the future development of feasible and efficient risk prediction models.

OBJECTIVE

The aim of this review was to assess the performance and the clinical feasibility of the currently available machine learning-based breast cancer risk prediction models.

METHODS

We searched for papers published until June 9, 2021, on machine learning-based breast cancer risk prediction models in PubMed, Embase, and Web of Science. Studies describing the development or validation models for predicting future breast cancer risk were included. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was used to assess the risk of bias and the clinical applicability of the included studies. The pooled area under the curve (AUC) was calculated using the DerSimonian and Laird random-effects model.

RESULTS

A total of 8 studies with 10 data sets were included. Neural network was the most common machine learning method for the development of breast cancer risk prediction models. The pooled AUC of the machine learning-based optimal risk prediction model reported in each study was 0.73 (95% CI 0.66-0.80; approximate 95% prediction interval 0.56-0.96), with a high level of heterogeneity between studies (Q=576.07, I²=98.44%; P<.001). The results of head-to-head comparison of the performance difference between the 2 types of models trained by the same data set showed that machine learning models had a slightly higher advantage than traditional risk factor-based models in predicting future breast cancer risk. The pooled AUC of the neural network-based risk prediction model was higher than that of the nonneural network-based optimal risk prediction model (0.71 vs 0.68, respectively). Subgroup analysis showed that the incorporation of imaging features in risk models resulted in a higher pooled AUC than the nonincorporation of imaging features in risk models (0.73 vs 0.61; P_{heterogeneity}=.001, respectively). The PROBAST analysis indicated that many machine learning models had high risk of bias and poorly reported calibration analysis.

CONCLUSIONS

Our review shows that the current machine learning-based breast cancer risk prediction models have some technical pitfalls and that their clinical feasibility and reliability are unsatisfactory.

Gail model utilization in predicting breast cancer risk in Egyptian women: a cross-sectional study

PURPOSE

Herein, our purpose was to calculate the 5-year and lifetime risk of breast cancer and to assess new breast cancer potential contributors among Egyptian women utilizing the modified Gail model, while presenting a global comparison of risk assessment.

METHODS

This study included 7009 women from both urban and rural areas scattered across 40% of the Egyptian provinces. The 5-year risk categories were defined as low risk (≤ 1.66%) or high risk (> 1.66%), whereas the lifetime risk categories were defined as low risk (≤ 20%) or high risk (> 20%). Pearson's Chi-squared test was performed to determine the association between participants' characteristics and distinct risk categories. Binary logistic regression was carried out for correlation analysis.

RESULTS

The mean estimated risk for developing invasive breast cancer over 5 years was 0.86 (± 0.67), whereas the mean lifetime breast cancer risk score was 11.26 (± 5.7). Accordingly, only 614 (8.75%) and 470 (6.7%) women were categorized as individuals with high risk of breast cancer incidence in 5-year and lifetime, respectively. Only 192 participants (2.7%) conferred both high 5-year and high lifetime risk scores. Marital status, method of feeding, physical activity behavior, contraceptive use, menopause and number of children were found to have a statistically significant association with both 5-year and lifetime breast cancer risk categories.

CONCLUSION

We revealed that modified Gail model had a well-fitting and discrimination accuracy in Egyptian women when compared with other countries.