โก Quick Summary
This study investigates intrahepatic cholestasis of pregnancy (ICP), a liver disorder affecting pregnant women, and employs machine learning techniques to predict its occurrence and severity. The top-performing model, CatBoost, achieved an impressive AUC of 0.9614, demonstrating the potential of AI in enhancing clinical diagnosis and intervention.
๐ Key Details
- ๐ Dataset: 798 participants (300 normal, 312 mild, 186 severe cases)
- ๐งฉ Features used: 11 critical risk factors identified through regression analysis
- โ๏ธ Technology: Thirteen machine learning techniques, with CatBoost as the top performer
- ๐ Performance: CatBoost: AUC 0.9614, Accuracy 90.85%, Precision 89.30%
๐ Key Takeaways
- ๐ ICP is a significant liver disorder that can lead to severe fetal complications.
- ๐ก Identified risk factors include total bile acid, gamma-glutamyl transferase, and multiple pregnancies.
- ๐ค Machine learning models can effectively predict ICP and its severity.
- ๐ CatBoost outperformed other models with an AUC of 0.9614.
- ๐ Study conducted at Jiaxing Maternity and Child Health Care Hospital in China.
- ๐ Importance of timely diagnosis to prevent fetal complications.
- ๐ Models can assist healthcare professionals in making informed decisions regarding patient care.
๐ Background
Intrahepatic cholestasis of pregnancy (ICP) is a liver disorder that typically arises during the second and third trimesters. It is characterized by pruritus and elevated serum bile acids, which can lead to serious fetal complications such as premature birth and even fetal death. Traditional diagnostic methods may overlook or delay the identification of ICP, highlighting the need for improved predictive tools.
๐๏ธ Study
This study was conducted at Jiaxing Maternity and Child Health Care Hospital between July 2020 and October 2023. Researchers collected clinical data from both ICP patients and healthy pregnant women, employing univariable and lasso regression analyses to identify the top 11 risk factors associated with ICP. The dataset was then divided into training and testing cohorts to evaluate various machine learning models.
๐ Results
The analysis revealed that the identified risk factors significantly correlated with ICP. The top five machine learning models demonstrated excellent performance, with the CatBoost model achieving an AUC of 0.9614, an accuracy of 90.85%, and a precision of 89.30%. These results indicate a high level of reliability in predicting ICP and its severity.
๐ Impact and Implications
The findings from this study have the potential to transform the management of ICP in pregnant women. By utilizing machine learning algorithms, healthcare providers can achieve more accurate and timely diagnoses, ultimately improving patient outcomes and reducing the risk of fetal complications. This research paves the way for further exploration of AI applications in obstetric care.
๐ฎ Conclusion
This study highlights the significant role of machine learning in predicting intrahepatic cholestasis of pregnancy. The successful identification of risk factors and the development of predictive models can enhance clinical decision-making, ensuring better care for expectant mothers. Continued research in this area is essential for advancing maternal-fetal health.
๐ฌ Your comments
What are your thoughts on the use of machine learning in predicting pregnancy-related complications? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
Risk factors and machine learning prediction models for intrahepatic cholestasis of pregnancy.
Abstract
BACKGROUND: Intrahepatic cholestasis of pregnancy (ICP) is a liver disorder that occurs in the second and third trimesters of pregnancy and is associated with a significant risk of fetal complications, including premature birth and fetal death. In clinical practice, the diagnosis of ICP is predominantly based on the presence of pruritus in pregnant women and elevated serum total bile acid. However, this approach may result in missed or delayed diagnoses. Therefore, it is essential to explore the risk factors associated with ICP and to accurately identify affected individuals to enable timely prophylactic interventions. The existing literature exhibits a paucity of studies employing artificial intelligence to predict ICP. Therefore, developing machine learning-based diagnostic and severity classification models for ICP holds significant importance.
METHODS: This study included ICP patients and some healthy pregnant women from Jiaxing Maternity and Child Health Care Hospital in China between July 2020 and October 2023. We collected clinical data during their pregnancies and selected the top 11 critical risk factors through univariable and lasso regression analysis. The dataset was randomly divided into training and testing cohorts. Thirteen machine learning techniques, including Random Forest, Support Vector Machine, and Artificial Neural Network, were employed. Based on their various classification performances on the training set, the top five models were selected for internal validation.
RESULTS: The dataset included 798 participants (300 normal, 312 mild, and 186 severe cases). Through univariable and lasso regression analysis, total bile acid, gamma-glutamyl transferase, multiple pregnancy, lymphocyte percentage, hematocrit, neutrophil percentage, prothrombin time, Aspartate aminotransferase, red blood cell count, lymphocyte count and platelet count were identified as risk factors of ICP. The AUCs of the selected top five models ranged from 0.9509 to 0.9614. The CatBoost model achieved the best performance, with an AUC of 0.9614 (95% confidence interval, 0.9377-0.9813), an accuracy of 0.9085, a precision of 0.8930, a recall of 0.9059, and a F1-score of 0.8981.
CONCLUSIONS: We identified risk factors for ICP and developed machine learning models based on these factors. These models demonstrated good performance and can be used to help predict whether pregnant women have ICP and the degree of ICP (mild or severe).
Author: [‘Ren Y’, ‘Shan X’, ‘Ding G’, ‘Ai L’, ‘Zhu W’, ‘Ding Y’, ‘Yu F’, ‘Chen Y’, ‘Wu B’]
Journal: BMC Pregnancy Childbirth
Citation: Ren Y, et al. Risk factors and machine learning prediction models for intrahepatic cholestasis of pregnancy. Risk factors and machine learning prediction models for intrahepatic cholestasis of pregnancy. 2025; 25:89. doi: 10.1186/s12884-025-07180-4