Related Experiment Video
Updated: May 12, 2025
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024
Identification of Major Bleeding Events in Postoperative Patients With Malignant Tumors in Chinese Electronic Medical
Hui Li1, Haiyang Yao2, Yuxiang Gao2
1Department of Thoracic Surgery, Beijing Chao-Yang Hospital, Capital Medical University, No.8 South Road of Workers' Stadium, Chaoyang District, Beijing, 100020, China, 86 13701158350.
Insights
Machine learning models effectively identify postoperative bleeding in abdominal tumor surgery patients using electronic medical records. Logistic Regression (LR) and Convolutional Neural Network (CNN) show promise for improving diagnosis and research.
Area of Science:
- Utilizes machine learning and natural language processing for medical data analysis.
- Focuses on clinical informatics and computational medicine applications.
Background:
- Postoperative bleeding after abdominal tumor surgery is a significant clinical challenge in China.
- Manual review of medical records for bleeding is inefficient and hinders large-scale data analysis.
- The efficacy of machine learning in identifying postoperative bleeding from medical texts is unexplored.
Purpose of the Study:
- To develop and evaluate machine learning models for identifying major postoperative bleeding.
- To leverage electronic medical record (EMR) data for automated detection of bleeding events.
Main Methods:
- Retrospective analysis of 2,000 EMRs from tumor resection patients (2018-2021).
- Manual physician classification of major bleeding events.
- Development and comparison of Logistic Regression (LR), K-nearest neighbor (KNN), and Convolutional Neural Network (CNN) models using 270 engineered features.
Main Results:
- The LR model achieved 82.75% accuracy and 89.47% sensitivity in the test set.
- The CNN model demonstrated 89.00% accuracy and 89.24% specificity in the test set.
- KNN showed high specificity (99.48%) but low sensitivity (21.05%).
Conclusions:
- Both LR and CNN models show strong performance in identifying major postoperative bleeding from EMRs.
- The LR model offers higher sensitivity, while the CNN model provides higher specificity.
- These models offer potential for practical clinical application based on prioritized outcomes.
Background:
Postoperative bleeding is a serious complication following abdominal tumor surgery, but it is often not clearly diagnosed and documented in clinical practice in China. Previous studies have relied on manual interpretation of medical records to determine the presence of postoperative bleeding in patients, which is time-consuming and laborious. More critically, this manual approach severely hinders the efficient analysis of large volumes of medical data, impeding in-depth research into the incidence patterns and risk factors of postoperative bleeding. It remains unclear whether machine learning can play a role in processing large volumes of medical text to identify postoperative bleeding effectively.
Objective:
This study aimed to develop a machine learning model tool for identifying postoperative patients with major bleeding based on the electronic medical record system.
Methods:
This study used data from the available information in the National Health and Medical Big Data (Eastern) Center in Jiangsu Province of China. We randomly selected the medical records of 2,000 patients who underwent in-hospital tumor resection surgery between January 2018 and December 2021 from the database. Physicians manually classified each note as present or absent for a major bleeding event during the postoperative hospital stay. Feature engineering involved bleeding expressions, high-frequency related expressions, and quantitative logical judgment, resulting in 270 features. Logistic regression (LR), K-nearest neighbor (KNN), and convolutional neural network (CNN) models were developed and trained using the 1600-note training set. The main outcomes were accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) for each model.
Results:
Major bleeding was present in 4.31% (69/1600) of the training set and 4.75% (19/400) of the test set. In the test set, the LR method achieved an accuracy of 0.8275, a sensitivity of 0.8947, a specificity of 0.8241, a PPV of 0.2024, an NPV of 0.9937, and an F1-score of 0.3301. The CNN method demonstrated an accuracy of 0.8900, sensitivity of 0.8421, specificity of 0.8924, PPV of 0.2807, NPV of 0.9913, and an F1-score of 0.4211. While the KNN method showed a high specificity of 0.9948 and an accuracy of 0.9575 in the test set, its sensitivity was notably low at 0.2105. The C-statistic for the LR method was 0.9018 and for the CNN method was 0.8830.
Conclusions:
Both the LR and CNN methods demonstrate good performance in identifying major bleeding in patients with postoperative malignant tumors from electronic medical records, exhibiting high sensitivity and specificity. Given the higher sensitivity of the LR method (89.47%) and the higher specificity of the CNN method (89.24%) in the test set, both models hold promise for practical application, depending on specific clinical priorities.
