Accurate breast cancer risk prediction is essential for early detection and personalized prevention strategies. While traditional models, such as Gail and Tyrer–Cuzick, are widely utilized, machine learning-based approaches may offer enhanced predictive performance. This systematic review and meta-analysis compare the accuracy of traditional statistical models and machine learning models in breast cancer risk prediction. A total of 144 studies from 27 countries were systematically reviewed, incorporating genetic, clinical, and imaging data. Pooled C-statistics were calculated to assess model discrimination, while observed-to-expected (O/E) ratios were used to evaluate calibration. Subgroup and sensitivity analyses were conducted to examine heterogeneity and assess the influence of study bias across various populations. Machine learning-based models demonstrated superior performance, with a pooled C-statistic of 0.74, compared to 0.67 for traditional models. Models that integrated genetic and imaging data showed the highest levels of accuracy, although performance varied by population. Sensitivity analyses excluding high-bias studies showed improved discrimination in models incorporating genetic factors, with the pooled C-statistic increasing to 0.72. Traditional models, such as Gail, exhibited notably poor predictive accuracy in non-Western populations, as evidenced by a C-statistic of 0.543 in Chinese cohorts. Machine learning models provide significantly greater predictive accuracy for breast cancer risk, particularly when incorporating multidimensional data. However, issues related to model generalizability and interpretability remain, particularly in diverse populations. Future research should focus on developing more interpretable models and expanding global validation efforts to improve model applicability across different demographic groups.

Accurate breast cancer risk prediction is essential for early detection and personalized prevention strategies. While traditional models, such as Gail and Tyrer–Cuzick, are widely utilized, machine learning-based approaches may offer enhanced predictive performance. This systematic review and meta-analysis compare the accuracy of traditional statistical models and machine learning models in breast cancer risk prediction. A total of 144 studies from 27 countries were systematically reviewed, incorporating genetic, clinical, and imaging data. Pooled C-statistics were calculated to assess model discrimination, while observed-to-expected (O/E) ratios were used to evaluate calibration. Subgroup and sensitivity analyses were conducted to examine heterogeneity and assess the influence of study bias across various populations. Machine learning-based models demonstrated superior performance, with a pooled C-statistic of 0.74, compared to 0.67 for traditional models. Models that integrated genetic and imaging data showed the highest levels of accuracy, although performance varied by population. Sensitivity analyses excluding high-bias studies showed improved discrimination in models incorporating genetic factors, with the pooled C-statistic increasing to 0.72. Traditional models, such as Gail, exhibited notably poor predictive accuracy in non-Western populations, as evidenced by a C-statistic of 0.543 in Chinese cohorts. Machine learning models provide significantly greater predictive accuracy for breast cancer risk, particularly when incorporating multidimensional data. However, issues related to model generalizability and interpretability remain, particularly in diverse populations. Future research should focus on developing more interpretable models and expanding global validation efforts to improve model applicability across different demographic groups.

We collected three sediment cores in the Northwest Pacific Plain in 2021 and 2022. Using with these cores, we measured radionuclides (210Pb and 226Ra). This dataset contains sampling site locations, 210Pb ,226Ra and excess 210Pb activities of these cores. These data are used for preparing figures, tables and the discussions in Zhu et al. (2024).

We collected three sediment cores in the Northwest Pacific plain in 2021 and 2022. Using with these cores, we measured radionuclides (210Pb and 226Ra). This dataset contains sampling site locations, 210Pb ,226Ra and excess 210Pb activities of these cores. These data are used for preparing figures, tables and the discussions in Zhu et al. (2024).

We collected three sediment cores in the Northwest Pacific plain in 2021 and 2022. Using with these cores, we measured radionuclides (210Pb and 226Ra). This dataset contains sampling site locations, 210Pb ,226Ra and excess 210Pb activities of these cores. These data are used for preparing figures, tables and the discussions in Zhu et al. (2024).

Original data for Figure 1, Figure 2, Figure 3a, Figure 4a, Figure S1, Figure S2 and Figure S3.

Original data for Figure 1, Figure 2, Figure 3a, Figure 4a, Figure S1, Figure S2 and Figure S3.

Supporting Information Table S1-S5 for Closing the global marine 226Ra budget reveals the biological pump as a dominant removal flux in the upper ocean
Table S1. River water and 226Ra fluxes, dissolved 226Ra concentration, and sediment desorption efficiency for rivers around the world. Table S2. Diffusive flux of 226Ra from coastal and shelf sediment. Table S3: Summary of 226Ra activity for all oceans. Table S4: Upwelling-downwelling velocity between the upper and lower ocean. Table S5. Estimates and values of the particle scavenging rate coefficient (k) in the ocean.

Supporting Information Table S1-S5 for Closing the global marine 226Ra budget reveals the biological pump as a dominant removal flux in the upper ocean
Table S1. River water and 226Ra fluxes, dissolved 226Ra concentration, and sediment desorption efficiency for rivers around the world. Table S2. Diffusive flux of 226Ra from coastal and shelf sediment. Table S3: Summary of 226Ra activity for all oceans. Table S4: Upwelling-downwelling velocity between the upper and lower ocean. Table S5. Estimates and values of the particle scavenging rate coefficient (k) in the ocean.

The diazotrophic cyanobacterium Trichodesmium is thought to be a major contributor to the new N in the parts of the oligotrophic, subtropical and tropical oceans. In this study physiological and biochemical methods and transcriptome sequencing were used to investigate the influences of ocean acidification (OA) on Trichodesmium erythraeum (T. erythraeum). We presented evidence that OA caused by CO2 slowed the growth rate and physiological activity of T. erythraeum. OA led to reduced development of proportion of the vegetative cells into diazocytes which included up‐regulated genes of nitrogen fixation. Reactive oxygen species (ROS) accumulation was increased due to the disruption of photosynthetic electron transport and decrease in antioxidant enzyme activities under acidified conditions. This study showed that OA increased the amounts of (exopolysaccharides) EPS in T. erythraeum, and the key genes of ribose‐5‐phosphate (R5P) and glycosyltransferases (Tery_3818) were up‐regulated. These results provide new insight into how ROS and EPS of T. erythraeum increase in an acidified future ocean to cope with OA‐imposed stress.