بررسی روش‌های هوش مصنوعی برای پیش‌بینی و تشخیص پره‌اکلامپسی: یک مرور سیستماتیک
کد: G-1438
نویسندگان: محمدرضا مظاهری حبیبی *, Zahra Rezaei ℗, آیدا سیاوشی جامی, مهدیه ضمیری بیداری , اعظم خیردوست
زمان بندی: زمان بندی نشده!
برچسب: سیستم های تصمیم یار بالینی
دانلود: دانلود پوستر
خلاصه مقاله:
خلاصه مقاله
Introduction: Preeclampsia is a serious pregnancy disorder that threatens the health of the mother and fetus. Early diagnosis, especially in the early stages, plays an important role in reducing its complications. Advances in artificial intelligence and machine learning have provided new tools such as random forest (RF) and neural networks (ANN) that have high accuracy in predicting and diagnosing this disease by analyzing clinical and biological data. This study aimed to investigate artificial intelligence methods for predicting and diagnosing preeclampsia. Methods: This study was conducted as a systematic review in 2025 by searching for the keywords "artificial intelligence", "machine learning", "preeclampsia", "prediction" and "diagnosis" in PubMed and Science Direct databases and the Google Scholar search engine. Relevant English-language articles that examined AI methods for predicting or diagnosing preeclampsia and were published between 2020 and 2024 were included in the study. Articles related to other pregnancy diseases or non-AI methods were excluded. The extracted data included methods, results, and conclusions, which were used to analyze the effectiveness of AI in the management of this disease. Results: A total of 6785 articles were retrieved from the aforementioned databases, and after applying the inclusion and exclusion criteria, 48 articles were finally included in the study. The findings of these studies showed that artificial intelligence algorithms such as random forest (RF), support vector machine (SVM), and artificial neural networks (ANN) have high accuracy in predicting preeclampsia. These models have been able to provide acceptable prediction rates using clinical, para-clinical, and electrocardiogram (ECG) data. Also, artificial intelligence-based methods have been effective in reducing diagnostic errors and early identification of the disease. Conclusion: Artificial intelligence-based methods are effective tools for predicting and diagnosing preeclampsia. Models such as random forest and Neural Networks have been able to provide high accuracy by analyzing diverse data. By developing and expanding these technologies, we can help reduce the complications of this disease and improve the health of mothers and babies.
کلمات کلیدی
Artificial Intelligence, Preeclampsia, Prediction, Diagnosis
