โก Quick Summary
A recent study explored the use of multimodal machine learning to predict perioperative safety indicators in spinal surgery by integrating structured electronic health record (EHR) data with unstructured free-text inputs. The findings revealed that the combined model significantly outperformed traditional models, achieving an AUC of up to 0.903 and demonstrating the potential for improved patient outcomes.
๐ Key Details
- ๐ Dataset: 1,898 patients from four urban academic spine centers
- ๐งฉ Features used: Structured EHR data and unstructured free-text inputs
- โ๏ธ Technology: Extreme Gradient Boosting (XGBoost) for model training
- ๐ Performance: Combined model AUC ranging from 0.827 to 0.903
๐ Key Takeaways
- ๐ Multimodal machine learning integrates structured and unstructured data for enhanced predictions.
- ๐ก Natural language processing (NLP) was utilized to process free-text EHR inputs.
- ๐ฉโ๐ฌ Study population included 1,898 patients with a median age of 60 years.
- ๐ฅ Extended length of stay (LOS) was observed in 10.1% of patients, with a median LOS of 4 days.
- ๐ ICU admission rate was recorded at 7.74%, while the 90-day reoperation rate was 10.54%.
- ๐ The combined model showed superior performance metrics compared to baseline models.
- ๐ Important predictors included patient demographics and specific medical conditions.
- ๐ฎ Future research aims to incorporate additional clinical data for further model refinement.
๐ Background
The integration of machine learning (ML) in healthcare has opened new avenues for predicting patient outcomes, particularly in surgical settings. By leveraging the vast amounts of data available in electronic health records (EHRs), researchers aim to enhance the accuracy of predictions related to perioperative safety. This study specifically focuses on spinal surgery, where predicting complications can significantly impact patient care and resource allocation.
๐๏ธ Study
Conducted over a five-year period from 2018 to 2023, this retrospective cohort study analyzed data from 1,898 patients undergoing elective or emergency spine surgery. The researchers developed a multi-modal machine learning architecture that combined structured EHR dataโsuch as demographics and clinical covariatesโwith unstructured free-text inputs, processed through natural language processing (NLP) techniques.
๐ Results
The study found that the multi-modal models achieved an impressive AUC ranging from 0.827 to 0.903, indicating a strong ability to predict perioperative safety indicators. The baseline models, which relied solely on structured data, had AUC values between 0.770 and 0.779. Additionally, the multi-modal models demonstrated improved precision and recall, with F1-scores ranging from 0.943 to 0.962, showcasing their effectiveness in clinical predictions.
๐ Impact and Implications
The implications of this research are profound. By integrating machine learning with both structured and unstructured data, healthcare providers can achieve a more comprehensive understanding of patient risks, leading to better pre-operative planning and patient management. This approach not only enhances predictive accuracy but also paves the way for future innovations in surgical care and patient safety.
๐ฎ Conclusion
This study highlights the transformative potential of multimodal machine learning in predicting perioperative outcomes in spinal surgery. The integration of NLP with EHR data represents a significant advancement in the field, promising to improve patient safety and surgical success rates. Continued research and development in this area could lead to even more refined models and better clinical practices in the future.
๐ฌ Your comments
What are your thoughts on the integration of machine learning in predicting surgical outcomes? We would love to hear your insights! ๐ฌ Leave your comments below or connect with us on social media:
Multimodal Machine Learning for Predicting Perioperative Safety Indicators in Spinal Surgery.
Abstract
BACKGROUND CONTEXT: Machine learning (ML) algorithms can utilize the large amount of tabular data in electronic health records (EHRs) to predict peri-operative safety indicators. Integrating unstructured free-text inputs via natural language processing (NLP) may further enhance predictive accuracy.
PURPOSE: To design and validate a pre-operative multi-modal machine learning architecture that integrates structured EHR data (patient demographics, comorbidities, and clinical covariates) with unstructured free-text inputs (past medical and surgical history, medications, and problem lists) via natural language processing (NLP). The multi-modal models aim to improve the prediction of peri-operative safety indicators compared to baseline ML models that only use structured tabular EHR data.
STUDY DESIGN: Retrospective cohort study PATIENT SAMPLE: 1,898 patients admitted for elective or emergency spine surgery at four separate large urban academic spine centers during a five-year period from 2018-2023.
OUTCOME MEASURES: Numerical outputs between 0 to 1 corresponding to the likelihood of (I) extended length of stay (LOS), (II) 90-day reoperation, and (III) peri-operative intensive care unit (ICU) admission.
METHODS: We predicted the following safety indicators (I) extended length of stay (LOS), II (90-day reoperation, and (III) peri-operative intensive care unit (ICU) admission. The quanteda package for NLP within the R environment was utilized to preprocess free-text EHR inputs. The refined text was tokenized and transformed into numerical vectors using a bag-of-words approach and integrated with the tabular EHR data to create a document-feature matrix. Two extreme gradient boosted (XGBoost) ML models were trained: a base model utilizing only structured tabular EHR data and a combined multi-modal model that leveraged both combined structured tabular EHR data with numerical vectors derived from free-text NLP inputs. Hyperparameter tuning was performed via grid search, and the models were validated using 10-fold cross validation with an 80:20 training/testing split. Word clouds were generated for the free-text data and explainable artificial intelligence (XAI) techniques were employed for feature importance. Metrics calculated for model performance included Area Under the Receiving-Operating Characteristic Curve (AUC-ROC), Brier score, Calibration slope, Calibration Intercept, Precision, Recall and F1-Score.
RESULTS: 1,898 patients (60.7% female) were extracted from January 2018 to September 2023, with a median age of 60.0 (IQR: 52.0 – 68.0) and median body mass index (BMI) of 30.3 kgm2 (IQR: 26.3 – 34.6). Extended LOS was defined as โฅ 14.4 days, constituting 10.1% of all individuals. The median LOS for the entire cohort was 4.0 days (IQR: 2.0 – 7.0), while the 90-day reoperation rate was 10.54%, and the ICU admission rate was 7.74%. The pre-operative tabular EHR models predicted peri-operative safety indicators with AUC ranging from 0.770 to 0.779, Brier scores ranging from 0.074 to 0.099, and calibration slopes ranging from 2.279 to 2.418. Precision and recall for this model ranged from 0.918 to 0.973 and 0.988 to 0.994, respectively, resulting in F1-scores between 0.954 and 0.973. The combined multi-modal models predicted peri-operative safety indicators with AUC ranging from 0.827 to 0.903, Brier scores ranging from 0.056 to 0.083, and calibration slopes ranging from 0.755 to 1.217. The multi-modal models achieved precision ranging from 0.909 to 0.933 and recall ranging from 0.979 to 0.994, leading to F1-scores between 0.943 and 0.962. Important tabular predictors included patient age, BMI, hemoglobin level, white blood cell count, platelet count, and a combined anterior/posterior spinal fusion approach. Important free-text inputs included vertebral osteomyelitis, radiculopathy, myelopathy, and spinal metastasis.
CONCLUSIONS: The multi-modal NLP model exhibited superior performance in all outcome measures when compared to the baseline tabular model. Future work includes incorporating additional model dimensions, such as the history of present illness, physical exam, and spinal imaging, and clinically implementing the models into our informed consent and pre-operative optimization pathway.
Author: [‘Mani K’, ‘Scharfenberger T’, ‘Goldman SN’, ‘Kleinbart E’, ‘Mostafa E’, ‘Ramos RG’, ‘Fourman MS’, ‘Eleswarapu A’]
Journal: Spine J
Citation: Mani K, et al. Multimodal Machine Learning for Predicting Perioperative Safety Indicators in Spinal Surgery. Multimodal Machine Learning for Predicting Perioperative Safety Indicators in Spinal Surgery. 2025; (unknown volume):(unknown pages). doi: 10.1016/j.spinee.2025.03.021