Skip to content
Conference Open access

An Adaptive Data Quality and Standardization Strategy for Female Infertility Analysis using Machine Learning

Oct 2026 · International Conference on Innovative Mechanisms for Industry Applications · pp. 1524-1530 · 0 citations · 16 references

Abstract

Female infertility has become a significant public health concern, affecting reproductive health, family planning, and maternal healthcare worldwide. Factors such as lifestyle changes, environmental influences, hormonal imbalances, metabolic disorders, and reproductive abnormalities have contributed to the growing prevalence of infertility. Modern healthcare systems generate large volumes of fertility-related data from fertility clinics, diagnostic laboratories, electronic health records, wearable devices, and telemedicine platforms. However, these datasets often contain missing values, inconsistencies, duplicate records, and variations in clinical standards, which can reduce the reliability of predictive models. To address these challenges, this study proposes an Adaptive Data Quality and Standardization Strategy for Female Infertility Analysis using Machine Learning. The framework integrates intelligent data profiling, adaptive quality assessment, reproductive health data standardization, feature harmonization, and explainable machine learning techniques. It employs Data Reliability Assessment Networks (DRAN), Adaptive Feature Harmonization (AFH), and Explainable Gradient Boosting Infertility Analysis (EGBIA) to improve data integrity and prediction accuracy. A dynamic quality evaluation mechanism continuously assesses data completeness, consistency, validity, and reliability. Experimental results demonstrate strong predictive performance, achieving an accuracy of 98.12%, precision of 97.84%, recall of 97.63%, and F1-score of 97.73%. The proposed framework enhances data quality, reduces analytical uncertainty, and improves clinical interpretability. By enabling accurate infertility prediction and reliable reproductive health analytics, the system supports early risk identification, personalized fertility care, and more effective women’s healthcare management.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.