Current status and influencing factors of preoperative anxiety and information needs in patients undergoing daytime hysteroscopic surgery
Abstract
ObjectiveTo develop predictive models for preoperative anxiety and information needs in daytime hysteroscopic surgery patients using the eXtreme Gradient Boosting(XGBoost) machine learning algorithm,identify independent influencing factors,and quantify their importance weights.MethodsA retrospective cohort of 338 patients undergoing daytime hysteroscopic surgery at Huzhou Maternal and Child Health Hospital from March 2024 to February 2025 was selected as the training set.Logistic regression was used to analyze factors influencing preoperative anxiety and information needs.Another 145 patients from March to August 2025 were selected as the validation set.Independent influencing factors were used as feature variables to construct XGBoost prediction models.Model interpretation was performed using Shapley additive explanations(SHAP) bar plots and swarm plots.ResultsMultivariate analysis showed that age,education level,preoperative sleep quality,prior surgical experience,and prior anesthesia experience were independent influencing factors for preoperative anxiety(all P<0.05).Age,education level,preoperative sleep quality,prior surgery history,prior surgical experience,and prior anesthesia experience were independent influencing factors for information needs(all P<0.05).The XGBoost model achieved AUCs of 0.831 and 0.834 for preoperative anxiety in the training and validation sets,respectively,and 0.826 and 0.868 for information needs,respectively.SHAP bar plots showed that the importance ranking of factors for preoperative anxiety was:age>preoperative sleep quality>education level>prior surgical experience>prior anesthesia experience.For information needs,the ranking was:prior surgery history>age>preoperative sleep quality>education level>prior surgical experience>prior anesthesia experience.ConclusionsPreoperative anxiety and information needs are influenced by multiple factors.The XGBoost models demonstrated good predictive performance,with age exerting the greatest impact on preoperative anxiety and prior surgery history exerting the greatest impact on information needs.
Related
- Factors influencing preoperative outcome expectations in patients undergoing total knee arthroplasty: a cross-sectional observational study
- Latent profile analysis and influencing factors of dyadic coping levels in patients with hepatolithiasis undergoing percutaneous transhepatic biliary drainage and their spouses
- Effect of adding preoperative serratus anterior plane block to intercostal nerve block with liposomal bupivacaine on postoperative pain in patients undergoing video-assisted thoracoscopic lung resection: study protocol for a prospective randomized controlled trial
- The influencing factors of postoperative sleep disturbance in elderly patients undergoing transurethral prostate surgery and the construction and validation of a machine learning prediction model
- Perceived factors shaping preoperative self-preparation among older patients undergoing total knee arthroplasty: a qualitative study
BibTeX
@article{shuying2026current,
title = {{Current status and influencing factors of preoperative anxiety and information needs in patients undergoing daytime hysteroscopic surgery}},
author = {MA Shuying and LU Li},
journal = {Huli yanjiu},
year = {2026},
month = oct,
url = {http://hlyj.suo1.cn/thesisDetails#10.12102/j.issn.1009-6493.2026.21.024},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Current status and influencing factors of preoperative anxiety and information needs in patients undergoing daytime hysteroscopic surgery
AU - MA Shuying
AU - LU Li
PY - 2026
DA - 2026/10/30
JO - Huli yanjiu
UR - http://hlyj.suo1.cn/thesisDetails#10.12102/j.issn.1009-6493.2026.21.024
AB - ObjectiveTo develop predictive models for preoperative anxiety and information needs in daytime hysteroscopic surgery patients using the eXtreme Gradient Boosting(XGBoost) machine learning algorithm,identify independent influencing factors,and quantify their importance weights.MethodsA retrospective cohort of 338 patients undergoing daytime hysteroscopic surgery at Huzhou Maternal and Child Health Hospital from March 2024 to February 2025 was selected as the training set.Logistic regression was used to analyze factors influencing preoperative anxiety and information needs.Another 145 patients from March to August 2025 were selected as the validation set.Independent influencing factors were used as feature variables to construct XGBoost prediction models.Model interpretation was performed using Shapley additive explanations(SHAP) bar plots and swarm plots.ResultsMultivariate analysis showed that age,education level,preoperative sleep quality,prior surgical experience,and prior anesthesia experience were independent influencing factors for preoperative anxiety(all P<0.05).Age,education level,preoperative sleep quality,prior surgery history,prior surgical experience,and prior anesthesia experience were independent influencing factors for information needs(all P<0.05).The XGBoost model achieved AUCs of 0.831 and 0.834 for preoperative anxiety in the training and validation sets,respectively,and 0.826 and 0.868 for information needs,respectively.SHAP bar plots showed that the importance ranking of factors for preoperative anxiety was:age>preoperative sleep quality>education level>prior surgical experience>prior anesthesia experience.For information needs,the ranking was:prior surgery history>age>preoperative sleep quality>education level>prior surgical experience>prior anesthesia experience.ConclusionsPreoperative anxiety and information needs are influenced by multiple factors.The XGBoost models demonstrated good predictive performance,with age exerting the greatest impact on preoperative anxiety and prior surgery history exerting the greatest impact on information needs.
SN - 1009-6493
ER -