Dataset of Indonesian women's reproductive, high-fat diet and body mass index risk factors for breast cancer

A dataset of breast cancer risk factors in Cuban women: Epidemiological evidence from Havana

This dataset compiles breast cancer risk factors from 1697 Cuban women who attended consultations at the Hospital Universitario Clínico-Quirúrgico Comandante Manuel Fajardo in Havana, Cuba. The data were collected to develop a breast cancer risk estimation model specifically tailored to the Cuban population. The dataset includes 23 variables encompassing internationally recognized risk factors such as family history of breast cancer, lifestyle habits, demographic characteristics, and clinical outcomes. The data were extracted from electronic records and anonymized to protect patient privacy, in compliance with the principles of the Declaration of Helsinki and with the approval of the hospital's scientific and ethics committees. This dataset can be employed in the development of predictive models and in comparative studies of risk factors across different populations. It is important to note that the data originate from a single hospital, which may limit their representativeness at the national level.

Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review

With the advances in artificial intelligence (AI), data-driven algorithms are becoming increasingly popular in the medical domain. However, due to the nonlinear and complex behavior of many of these algorithms, decision-making by such algorithms is not trustworthy for clinicians and is considered a black-box process. Hence, the scientific community has introduced explainable artificial intelligence (XAI) to remedy the problem. This systematic scoping review investigates the application of XAI in breast cancer detection and risk prediction. We conducted a comprehensive search on Scopus, IEEE Explore, PubMed, and Google Scholar (first 50 citations) using a systematic search strategy. The search spanned from January 2017 to July 2023, focusing on peer-reviewed studies implementing XAI methods in breast cancer datasets. Thirty studies met our inclusion criteria and were included in the analysis. The results revealed that SHapley Additive exPlanations (SHAP) is the top model-agnostic XAI technique in breast cancer research in terms of usage, explaining the model prediction results, diagnosis and classification of biomarkers, and prognosis and survival analysis. Additionally, the SHAP model primarily explained tree-based ensemble machine learning models. The most common reason is that SHAP is model agnostic, which makes it both popular and useful for explaining any model prediction. Additionally, it is relatively easy to implement effectively and completely suits performant models, such as tree-based models. Explainable AI improves the transparency, interpretability, fairness, and trustworthiness of AI-enabled health systems and medical devices and, ultimately, the quality of care and outcomes.

Breast cancer incidence in Yogyakarta, Indonesia from 2008-2019: A cross-sectional study using trend analysis and geographical information system

BACKGROUND

Breast cancer is a significant public health concern worldwide, including in Indonesia. Little is known about the spatial and temporal patterns of breast cancer incidence in Indonesia. This study aimed to analyze temporal and spatial variations of breast cancer incidence in Yogyakarta Province, Indonesia.

METHODS

The study used breast cancer case data from the Yogyakarta Population-Based Cancer Registry (PBCR) from 2008 to 2019. The catchment areas of the PBCR included the 48 subdistricts of 3 districts (Sleman, Yogyakarta City, and Bantul). Age-standardized incidence rates (ASR) were calculated for each subdistrict. Joinpoint regression was used to detect any significant changes in trends over time. Global Moran's and Local Indicators of Spatial Association (LISA) analyses were performed to identify any spatial clusters or outliers.

RESULTS

The subdistricts had a median ASR of 41.9, with a range of 15.3-70.4. The majority of cases were diagnosed at a late stage, with Yogyakarta City having the highest proportion of diagnoses at stage 4. The study observed a significant increasing trend in breast cancer incidence over the study period the fastest of which is in Yogyakarta City with an average annual percentage change of 18.77%, with Sleman having an 18.21% and Bantul having 8.94% average changes each year (p <0.05). We also found a significant positive spatial autocorrelation of breast cancer incidence rates in the province (I = 0.581, p <0.001). LISA analysis identified 11 subdistricts which were high-high clusters in the central area of Yogyakarta City and six low-low clusters in the southeast region of the catchment area in the Bantul and Sleman Districts. No spatial outliers were identified.

CONCLUSIONS

We found significant spatial clustering of BC ASR in the Yogyakarta Province, and there was a trend of increasing ASR across the region. These findings can inform resource allocation for public health efforts to high-risk areas and develop targeted prevention and early detection strategies. Further res is needed to understand the factors driving the observed temporal and spatial patterns of breast cancer incidence in Yogyakarta Province, Indonesia.

A Hybrid Algorithm of ML and XAI to Prevent Breast Cancer: A Strategy to Support Decision Making

Worldwide, the coronavirus has intensified the management problems of health services, significantly harming patients. Some of the most affected processes have been cancer patients' prevention, diagnosis, and treatment. Breast cancer is the most affected, with more than 20 million cases and at least 10 million deaths by 2020. Various studies have been carried out to support the management of this disease globally. This paper presents a decision support strategy for health teams based on machine learning (ML) tools and explainability algorithms (XAI). The main methodological contributions are: first, the evaluation of different ML algorithms that allow classifying patients with and without cancer from the available dataset; and second, an ML methodology mixed with an XAI algorithm, which makes it possible to predict the disease and interpret the variables and how they affect the health of patients. The results show that first, the XGBoost Algorithm has a better predictive capacity, with an accuracy of 0.813 for the train data and 0.81 for the test data; and second, with the SHAP algorithm, it is possible to know the relevant variables and their level of significance in the prediction, and to quantify the impact on the clinical condition of the patients, which will allow health teams to offer early and personalized alerts for each patient.

The risk factors and pregnant women's willingness toward the SARS-CoV-2 vaccination in various countries: A systematic review and meta-analysis

Introduction

Pregnant women will benefit from research on immunization during pregnancy because they will have more accurate information on the SARS-CoV-2 vaccine. The purpose of this study was to determine the risk factors and pregnant women's desire to get the SARS-CoV-2 vaccine in various countries.

Methods

A search of PubMed, ProQuest, and EBSCO for related publications published (January and December 2021) on risk factors and pregnant women's desire to get the SARS-CoV-2 vaccine in various countries. The Pooled Odds Ratio (POR) were calculated using fixed and random-effect analysis. The I-squared formula was used to calculate the heterogeneity. Egger's and Begg's tests were used to identify study bias. STATA 16.0 was used for data analysis.

Results

This study revealed good practice has the highest POR (8.99), followed by received influenza vaccine last year (2.72), high perception of SARS-CoV-2 vaccine (2.70), >35 years (2.01), sufficient information about the SARS-COV-2 vaccine (1.94), higher school education (1.84), and third trimester (1.35) with pregnant women's desire toward the SARS-CoV-2 vaccination. The heterogeneity analysis revealed homogenous among risk factors in >35 years, high perception of SARS-CoV-2 vaccine, good practice, and third trimester (I² ≤ 50%). In the articles combined in this study, there was no indication of study bias.

Conclusion

The insights of this study might help the authorities in determining the most effective strategy to deploy SARS-CoV-2 mass immunization campaigns for pregnant women.