No abstract

The prevalence of thalassemia among the Vietnamese population was studied, and clinical decision support systems (CDSSs) for prenatal screening of thalassemia were created. A cross-sectional study was conducted on pregnant women and their husbands visiting from October 2020 to December 2021. A total of 10,112 medical records of first-time pregnant women and their husbands were collected. CDSS including two different types of systems for prenatal screening for thalassemia (expert system [ES] and four artificial intelligence [AI]-based CDSS) was built. 1,992 cases were used to train and test machine learning (ML) models while 1,555 cases were used for specialized ES evaluation. There were 10 key variables for AI-based CDSS for ML. The four most important features in thalassemia screening were identified. Accuracy of ES and AI-based CDSS was compared. The rate of patients with alpha thalassemia is 10.73% (1,085 patients), the rate of patients with beta-thalassemia is 2.24% (227 patients), and 0.29% (29 patients) of patients carry both alpha-thalassemia and beta-thalassemia gene mutations. ES showed an accuracy of 98.45%. Among AI-based CDSS developed, multilayer perceptron model was the most stable regardless of the training database (accuracy of 98.50% using all features and 97.00% using only the four most important features). AI-based CDSS showed satisfactory results. Further development of such systems is promising with a view to their introduction into clinical practice.

Background and objectives. Investigating the prevalence of thalassemia in the Vietnamese population, building a clinical decision support system for prenatal screening for thalassemia. Methods. A cross-sectional study was conducted on pregnant women and their husbands visiting Vietnam National Hospital of Obstetrics and Gynecology from October 2020 to December 2021. Results. The clinical decision support system including 2 different types of systems for prenatal screening for thalassemia (expert system and 4 AI-based CDSS) was built. Accuracy of expert system and AI-based CDSS was compared. The rate of patients with Alpha thalassemia is 10.73%, the rate of patients with beta-thalassemia is 2.24%, and 0.29% of patients carry both alpha-thalassemia and beta-thalassemia gene mutations. The expert system showed an accuracy of 98.45%. Among the AI-based CDSS developed, the MLP model was the most stable regardless of the training database. Conclusions. When comparing the expert system with the AI-based CDSS, the accuracy of the expert system and AI-based models was found to be comparable. The developed expert system for prenatal thalassemia screening showed high accuracy. AI-based CDSS showed satisfactory results and can be applied in clinical practice.

No abstract