PDF
Full
Outline
To construct a postpartum depression risk prediction model for multi-ethnic population in Yunnan Province of China, and identify predictive factors.
Women who were 42 days and within 1 year after childbirth were screened, and the Edinburgh Postnatal Depression Scale (EPDS≥9) was used for postpartum depression. 52 influencing factors from economics, social psychology, obstetrics, neonatology, spouse and family dynamics and other characteristics were included in the survey. A random forest algorithm was employed to construct a predictive model for postnatal depression risk in the multi-ethnic population of Yunnan Province. The model was evaluated on test sets with accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristic curve (Area Under Curve, AUC) to assess its performance.
A total of 459 women were analyzed, with a postpartum depression detection rate of 11.55%. Among them, the detection rates for Han, Zhuang and other ethnic minorities were 7.56%, 13.94% and 13.92%, respectively. The top 14 variables in terms of importance scores were: anxiety, history of previous negative emotions, marital relationship, family support level, physical and mental exhaustion in caring for newborns, pregnancy risk classification, mother-infant rooming-in, feeding mode, education level, spouse’s education level, frequency of nighttime newborn care, ethnicity, parity and age. The accuracy was 92.74%, specificity was 95.50%, sensitivity was 69.23%, positive predictive value was 64.29%, negative predictive value was 96.36%, and the AUC value was 0.925, using Han, Zhuang, and other ethnic minorities as validation sets respectively. The model also demonstrated good stability.
The random forest algorithm-based postpartum depression risk prediction model for the multi-ethnic population in Yunnan performed well, which can be utilized to predict risk factors for postpartum depression among women in minority ethnic areas, thereby facilitating targeted intervention measures.
PDF
43
19
| 科 Family | 属数 Number of genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) | 属 Genus | 种数 Number of species | 占总种数比例 Percentage of total species (%) |
|---|---|---|---|---|---|---|
| 鹅膏菌科Amanitaceae | 2 | 11 | 5.26 | 鹅膏菌属 Amanita | 10 | 4.78 |
| 小菇科 Mycenaceae | 2 | 12 | 5.74 | 丝盖伞属 Inocybe | 5 | 2.39 |
| 多孔菌科 Polyporaceae | 8 | 14 | 6.70 | 蜡蘑属 Laccaria | 5 | 2.39 |
| 红菇科 Russulaceae | 3 | 23 | 11.00 | 小皮伞属 Marasmius | 6 | 2.87 |
| 小菇属 Mycena | 11 | 5.26 | ||||
| 光柄菇属 Pluteus | 5 | 2.39 | ||||
| 红菇属 Russula | 17 | 8.13 | ||||
| 栓菌属 Trametes | 5 | 2.39 |
关闭全屏
No. 86 Xueyuan South Road, Haidian District, Beijing
010-62199257
qkjq@cast.org.cn
Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House
