DEVELOPMENT AND VALIDATION OF RISK SCORE PREDICTION MODEL FOR STILL BIRTH AT ASELLA TEACHING REFERRAL HOSPITAL, OROMIA, ETHIOPIA,2024

Abstract

Abstract Back ground: - stillbirth is defined as the death of the fetus after 28 weeks of gestation or weight more than 1000 g before extraction from the uterus. A grave public health concern, stillbirth was claiming the lives of over 1.9 million children; 83.6% of all stillbirths occurred in low-income countries in 2021. The silent tragedy of stillbirth devastates women's lives, families' lives, and even nations. Even though a number of studies have been done to predict the risk of stillbirth but the problem is still underestimated. In a limited resource country like Ethiopia, the development and validation of risk score prediction is quite substantial to take further meaningful action. Objective: - To develop and validate of risk score prediction model for stillbirth at Asella Teaching and Referral Hospital, Oromia, Ethiopia. 2024G.C Methodology: - A retrospective follow-up study was conducted at Asella Teaching and Referral Hospital from 1 October 2022 to 1 October 2024. Every expectant mother giving birth at Asella Teaching and Referral Hospital served as the source population. 1,008 participants were recruited in the study by a computer-generated random sampling technique. Data were collected using kobo tool box. The logistic regression analysis used to develop the model. To assess performance, the model discrimination and calibration of the model were done. Lastly, the model was validated by the bootstrapping method. Decision curve analysis was used to evaluate clinical implication model. Result: The study found incidence of stillbirth at Asella Teaching and Referral Hospital were 10.3% and those maternal characteristics like history of stillbirth, history of anemia, history of abortion, abruptio placenta, preeclampsia, and cord accident predictors of stillbirth, with a ROC of 0.767, and a well-calibrated model. It was internally validated and has optimism of 0.0007999. the model was found to have clinical benefit. Conclusion and Recommendation: - The developed risk-score has excellent discrimination performance and clinical benefit. It can be used in the clinical settings by healthcare providers for early detection, timely decision making, and improving care quality. Utilization of model is helpful to prevent incidence of stillbirth by 10.3%. The study reveals obstetric and gynecological issues predict stillbirth, recommending Hospital's maternal health team to consider these predictors and Key words:- development, validation, stillbirth, risk score prediction