Abstract
Hospital acquired thrombocytopenia (HAT) is a common hematological complication after surgery. This research aimed to develop and compare the performance of seven machine learning (ML) algorithms for predicting patients that are at risk of HAT after surgery. We conducted a retrospective cohort study which enrolled adult patients transferred to the intensive care unit (ICU) after surgery in West China Hospital of Sichuan University from January 2016 to December 2018. All subjects were randomly divided into a derivation set (70%) and test set (30%). ten-fold cross-validation was used to estimate the hyperparameters of ML algorithms during the training process in the derivation set. After ML models were developed, the sensitivity, specificity, area under the curve (AUC), and net benefit (decision analysis curve, DCA) were calculated to evaluate the performances of ML models in the test set. A total of 10,369 patients were included and in 1354 (13.1%) HAT occurred. The AUC of all seven ML models exceeded 0.7, the two highest were Gradient Boosting (GB) (0.834, 0.814–0.853, p < 0.001) and Random Forest (RF) (0.828, 0.807–0.848, p < 0.001). There was no difference between GB and RF (0.834 vs. 0.828, p = 0.293); however, these two were better than the remaining five models (p < 0.001). The DCA revealed that all ML models had high net benefits with a threshold probability approximately less than 0.6. In conclusion, we found that ML models constructed by multiple preoperative variables can predict HAT in patients transferred to ICU after surgery, which can improve risk stratification and guide management in clinical practice.
Highlights
Platelets are directly involved in thrombus formation and inflammatory regulation, and thrombocytopenia is a common complication in intensively ill patients [1]
We aimed to use machine learning (ML) algorithms with the clinical and laboratory test data before surgery to predict the occurrence of hospital acquired thrombocytopenia (HAT) in patients transferred to intensive care unit (ICU) after surgery
We found that all ML models performed well, as their area under the curve (AUC) of predicting HAT exceeded 0.7; the ROC analysis revealed that Gradient Boosting (GB) and Random Forest (RF) had higher AUC than other models
Summary
Platelets are directly involved in thrombus formation and inflammatory regulation, and thrombocytopenia is a common complication in intensively ill patients [1]. Because of tissue damage and blood loss, the platelet count usually drops to the lowest point between 1 and 4 days after surgery, rises back to preoperative levels between 5 and 7 days, and reaches the highest level around the 14th day [5]. It seems to be a short, transient, and reversible clinical process, which is not related to the patient’s postoperative recovery. Identifying patients at risk of developing HAT transferred to ICU after surgery is important for risk stratification, improving quality of care, and facilitating clinical decision-making
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.