A multicenter prospective study on postoperative pulmonary complications prediction in geriatric patients with deep neural network model

Abstract

AimPostoperative pulmonary complications (PPCs) can increase the risk of postoperative mortality, and the geriatric population has high incidence of PPCs. Early identification of high-risk geriatric patients is of great value for clinical decision making and prognosis improvement. Existing prediction models are based purely on structured data, and they lack predictive accuracy in geriatric patients. We aimed to develop and validate a deep neural network model based on combined natural language data and structured data for improving the prediction of PPCs in geriatric patients.MethodsWe consecutively enrolled patients aged ≥65 years who underwent surgery under general anesthesia at seven hospitals in China. Data from the West China Hospital of Sichuan University were used as the derivation dataset, and a deep neural network model was developed based on combined natural language data and structured data. Data from the six other hospitals were combined for external validation.ResultsThe derivation dataset included 12,240 geriatric patients, and 1949(15.9%) patients developed PPCs. Our deep neural network model outperformed other machine learning models with an area under the precision-recall curve (AUPRC) of 0.657(95% confidence interval [CI], 0.655–0.658) and an area under the receiver operating characteristic curve (AUROC) of 0.884(95% CI, 0.883–0.885). The external dataset included 7579 patients, and 776(10.2%) patients developed PPCs. In external validation, the AUPRC was 0.632(95%CI, 0.632–0.633) and the AUROC was 0.889(95%CI, 0.888–0.889).ConclusionsThis study indicated that the deep neural network model based on combined natural language data and structured data could improve the prediction of PPCs in geriatric patients.

External Validation of the American College of Surgeons Surgical Risk Calculator in Elderly Patients Undergoing General Surgery Operations

“…ACS-SRC is arguably the most widely used generic prognostic tool in surgery. Other novel prediction models, designed for geriatric surgical patients, have recently been mentioned in the literature [ 18 , 19 ]. Examples are the colorectal geriatric model (GerCRC), which used geriatric-specific predictors to estimate the risk of severe postoperative complications, and a deep neural network model from Chinese patients predicting postoperative pulmonary complications, but external validations are still lacking [ 18 , 19 ].…”

Development and performance assessment of novel machine learning models for predicting postoperative pneumonia in aneurysmal subarachnoid hemorrhage patients: external validation in MIMIC-IV

“…Jong Ho Kim et al developed an ML model to predict POP in patients undergoing surgery ( 28 ). Peng et al had successfully created and verified a deep-neural-network model based on combined natural language data and structured data to predict pulmonary complications in geriatric patients ( 29 ). However, there is no POP prediction ML model designed explicitly for aSAH patients.…”

Application of Machine Learning in Predicting Perioperative Outcomes in Patients with Cancer: A Narrative Review for Clinicians

“…By leveraging AI technologies like NN, anesthesia providers can gain valuable insights into how their patients will respond during and following surgery before a response even occurs (predictive analytics). Real-time predictive analytics has the potential to drastically improve the quality of care provided by surgeons and anesthesia providers today [55][56][57]. However, NNs are a growing and diverse set of algorithms that are beyond the scope of discussion in this paper.…”

“…Ensemble techniques, such as random forests and boosting, combine multiple models for improved prediction accuracy [41][42][43][44][45][46][47][48]. Neural network techniques are also being applied in anesthesiology and perioperative medicine to predict outcomes [51,53,56,57]. ML technology can help to allocate resources more efficiently across the perioperative continuum [58].…”