Uterine disorders classification based on symptomic and behaviorial data

The Uterine Disorder Diagnostic Dataset (UDD-2025) consists of 223 anonymized patient records collected through hand-on interviews and clinical ultrasound reports from the Department of Gynecology, R.S. Unit, Shaheed Tajuddin Ahmad Medical College Hospital, Bangladesh. The data collection took place between May 5 – August 7, 2025, spanning a total of 95 days.

Each participant record includes validated diagnostic parameters extracted directly from ultrasound and medical reports, along with corresponding symptomatic and behavioral indicators gathered via structured in-person interviews. Each participant gave consent to interview willingly and shared their experience without any external influence. The dataset is stored in a single .xlsx file (which can be converted to a csv file), with each row representing one participant and each column corresponding to a clinical or behavioral variable.

The ethical clearance for this dataset was obtained from the Institutional Ethics Committee of Daffodil International University, and official permission for clinical data collection was granted by the Assistant Director of Shaheed Tajuddin Ahmad Medical College Hospital.

All diagnostic fields were verified and approved by experts at the same department before inclusion. The ultrasound-based diagnostic summaries were then manually entered and validated for consistency by the research team. All diagnosis summaries were input manually from the reports, maintaining the sequence of other data of each participant. No personally identifiable information is present in the final .xlsx file.

The ultrasound report summaries for each patient were collected immediately following their consultation with the attending physician. As approval had been obtained from the relevant institutional authorities, the procedure ensured the validity and reliability of the diagnostic information.

This dataset serves as a reliable resource for research in:
-Predictive modeling of uterine disorders
-Statistical correlation between menstrual behavior and clinical diagnosis
-Machine learning applications in reproductive health diagnostics
-Multimodal health data integration and analysis

By combining expert-validated ultrasound diagnostics with real-world behavioral data, the UDD-2025 dataset provides an authentic foundation for advancing AI-based women’s health research, reproductive disease prediction, and evidence-driven gynecological analytics.

子宫疾病诊断数据集（Uterine Disorder Diagnostic Dataset, UDD-2025）包含223条匿名化患者记录，数据采集自孟加拉国沙希德·塔吉丁·艾哈迈德医学院附属医院妇科R.S.单元，通过实地访谈与临床超声报告收集。数据采集时间为2025年5月5日至8月7日，共计95天。

每份受试者记录包含直接从超声及医疗报告中提取的经验证的诊断参数，以及通过结构化面对面访谈收集的对应症状与行为指标。所有受试者均自愿签署访谈知情同意书，且在无外界干扰的情况下分享自身情况。该数据集存储为单个.xlsx文件（可转换为CSV格式），每行代表一名受试者，每列对应一项临床或行为变量。

本数据集已获得达芙妮国际大学（Daffodil International University）机构伦理委员会的伦理审批，且沙希德·塔吉丁·艾哈迈德医学院附属医院助理主任批准了临床数据采集的官方许可。

所有诊断字段在纳入数据集前均经该科室专家审核确认。基于超声的诊断总结由研究团队手动录入并进行一致性校验。所有诊断总结均从报告中手动录入，保留了每位受试者其他数据的原始顺序。最终的.xlsx文件中未包含任何可识别个人身份的信息。

每位患者的超声报告总结均在其接诊医师会诊后立即收集。由于已获得相关机构的审批，该流程确保了诊断信息的有效性与可靠性。

本数据集可作为以下研究方向的可靠资源：
- 子宫疾病预测建模
- 月经行为与临床诊断间的统计相关性分析
- 生殖健康诊断领域的机器学习应用
- 多模态健康数据集成与分析

该数据集将经专家验证的超声诊断结果与真实世界行为数据相结合，为基于人工智能的女性健康研究、生殖疾病预测以及循证妇科分析提供了真实可信的研究基础。