Risk Prediction Model for Early Pregnancy Loss in Uncertain Viability Cases

446 women with pregnancies of uncertain viability were prospectively studied at a Singapore hospital from 2017 to 2023. The research developed a four-factor model predicting spontaneous miscarriage by 16 weeks with an AUROC of 0.88. The dataset likely contains predictor variables like maternal age, serum progesterone, and gestational age.

Use Cases

• Training a binary classifier for miscarriage risk based on clinical variables like serum progesterone and nausea.
• Validating a risk stratification tool using the low, medium, and high risk groups defined in the study.
• Analyzing the independent predictive power of factors such as maternal age and gestational age for early pregnancy loss.

Strengths

• Prospective cohort design with 446 eligible participants recruited over nearly 6 years.
• Model achieved a high predictive accuracy with an AUROC of 0.88 and specificity of 0.88.
• Clear outcome definition (spontaneous miscarriage by 16 weeks) and risk score categorization.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is from a single hospital in Singapore, which may limit geographic generalizability.

Provenance

Source

KK Women’s and Children’s Hospital, Singapore.

Collection Method

Prospective cohort study.

Time Range

October 2017 to May 2023.

Freshness

Last updated 2026-05 05:48:06; freshness should be verified.

Geography

Singapore.