Estimation of Prediction Intervals for Performance Assessment of Building Using Machine Learning.

This study utilizes artificial neural networks (ANN) to estimate prediction intervals (PI) for seismic performance assessment of buildings subjected to long-term ground motion. To address the uncertainty quantification in structural health monitoring (SHM), the quality-driven lower upper bound estimation (QD-LUBE) has been opted for global probabilistic assessment of damage at local and global levels, unlike traditional methods. A distribution-free machine learning model has been adopted for enhanced reliability in quantifying uncertainty and ensuring robustness in post-earthquake probabilistic assessments and early warning systems. The distribution-free machine learning model is capable of quantifying uncertainty with high accuracy as compared to previous methods such as the bootstrap method, etc. This research demonstrates the efficacy of the QD-LUBE method in complex seismic risk assessment scenarios, thereby contributing significant enhancement in building resilience and disaster management strategies. This study also validates the findings through fragility curve analysis, offering comprehensive insights into structural damage assessment and mitigation strategies.

FRAX calculation with and without bone mineral density for assessment of osteoporotic fracture risk in patients of rheumatic disease: a cross-sectional study.

To compare fracture risk assessment (FRAX) calculation with and without bone mineral density (BMD) in predicting 10-year probability of hip and major osteoporotic fracture in patients of rheumatic diseases. Methodology: A cross-sectional was conducted at outpatient Department of Rheumatology. Eighty-one Patients of more than 40 years of age having either sex. Diagnosed case of Rheumatic diseases were according to American College of Rheumatology (ACR) /European Alliance of Associations for Rheumatology (EULAR) criteria were included in our study. FRAX score without BMD was calculated and information was recorded in proforma. These patients were advised dual energy X-ray absorptiometry Scan and after that FRAX with BMD was calculated, after which comparison between result of two scores was made. The data were analyzed by SPSS software version 24. Effect modifiers were controlled by stratification. Post-stratification χ2 test were applied. P value less than 0.05 was considered as significant. Results: This study consisted of 63 participants, who were assessed for osteoporotic risk fracture, with and without BMD. Data analysis revealed a significant association between the type of fracture and age (p value=0.009), previous fracture (p value=0.25), parent fractured hip (p values) and treatment with bone mineral dismissal. There was no statistically significant association seen of fractures with bone deterioration with sex, weight, height, or current smoking. Conclusion: FRAX may be crucial in rural areas where dual energy X-ray absorptiometry scanning is not available since it is a readily available instrument. FRAX is a useful substitute for estimating osteoporosis risk when funds are scarce. Given the possible effect it will have on healthcare costs, this is extremely pertinent.