Assessment of Breast Cancer Risk in an Iranian Female Population Using Bayesian Networks with Varying Node Number

Predictive factors of ergonomic behaviors based on social cognitive theory among women workers on assembly lines: application of Bayesian networks

BACKGROUND

This study focuses on identifying the key factors associated with ergonomic behaviors (ERBE) among women workers on assembly lines (WwAL) to prevent musculoskeletal disorders (MSDs) caused by repetitive motions and unfavorable body postures. To achieve this objective, this study employed Bayesian networks (BN) analysis based on social cognitive theory (SCT).

METHODS

A cross-sectional study was conducted to examine the predictive factors of ERBE among 250 WwAL from six different industries located in Neyshabur, a city in northeastern Iran. The study used a two-stage cluster sampling method for participant selection and self-report questionnaires to collect data on demographic characteristics, variables associated with SCT, ERBE, and the standard Nordic questionnaire. The collected data were analyzed using Netica and SPSS version 21, which involved statistical analyses such as independent t-tests, Pearson correlation, and ANOVA tests at a significance level of p < 0.05. BN analysis was conducted to identify the important factors that impact ERBE.

RESULTS

The majority of individuals reported experiencing chronic pain in their back, neck, and shoulder areas. Engaging in physical activity, consuming dairy products, and attaining a higher level of education were found to be significantly associated with the adoption of ERBE p < 0.05. Among the various SCT constructs, observational learning, intention, and social support demonstrated the highest levels of sensitivity towards ERBE, with scores of 4.08, 3.82, and 3.57, respectively. However, it is worth noting that all SCT constructs exhibited a certain degree of sensitivity towards ERBE.

CONCLUSIONS

The research findings demonstrate that all constructs within SCT are effective in identifying factors associated with ERBE among WwAL. The study also highlights the importance of considering education levels and variables related to healthy lifestyles when promoting ERBE in this specific population.

Assessing Breast Cancer Risk with an Artificial Neural Network

Objectives:

Radiologists face uncertainty in making decisions based on their judgment of breast cancer risk. Artificial intelligence and machine learning techniques have been widely applied in detection/recognition of cancer. This study aimed to establish a model to aid radiologists in breast cancer risk estimation. This incorporated imaging methods and fine needle aspiration biopsy (FNAB) for cyto-pathological diagnosis.

Methods:

An artificial neural network (ANN) technique was used on a retrospectively collected dataset including mammographic results, risk factors, and clinical findings to accurately predict the probability of breast cancer in individual patients. Area under the receiver-operating characteristic curve (AUC), accuracy, sensitivity, specificity, and positive and negative predictive values were used to evaluate discriminative performance.

Result:

The network incorporating the selected features performed best (AUC = 0.955). Sensitivity and specificity of the ANN were respectively calculated as 0.82 and 0.90. In addition, negative and positive predictive values were respectively computed as 0.90 and 0.80.

Conclusion:

ANN has potential applications as a decision-support tool to help underperforming practitioners to improve the positive predictive value of biopsy recommendations.