Establishment and Verification of a Perioperative Blood Transfusion Model After Posterior Lumbar Interbody Fusion: A Retrospective Study Based on Data From a Local Hospital

Development and Validation of a Risk-Prediction Nomogram for Preoperative Blood Type and Antibody Testing in Spinal Fusion Surgery

OBJECTIVE

With advancements in minimally invasive techniques, the use of spinal fusion surgery is rapidly increasing and transfusion rates are decreasing. Routine preoperative ABO/Rh blood type and antibody screening (T&S) laboratory tests may not be appropriate for all spinal fusion patients. Herein, we constructed a nomogram to assess patient transfusion risk based on various risk factors in patients undergoing spinal fusion surgery, so that preoperative T&S testing can be selectively scheduled in appropriate patients to reduce healthcare and patient costs.

METHODS

Patients who underwent spinal fusion surgery between 01/2020 and 03/2023 were retrospectively examined and classified into the training (n = 3533, 70%) and validation (n = 1515, 30%) datasets. LASSO and multivariable logistic regression were used to analyze risk factors for blood transfusion. Nomogram predictive model was built according to the independent predictors and mode predictive power was validated using consistency index (C-index), Hosmer-Lemeshow (HL) test, calibration curve analysis and area under the curve (AUC) for receiver operating characteristic (ROC) curve. Bootstrap resampling was used for internal validation. Decision curve analysis (DCA) was applied to evaluate the model's performance in the clinic.

RESULTS

Being female, age, BMI, admission route, critical patient, operative time, heart failure, end-stage renal disease or chronic kidney disease (ESRD or CKD), anemia, and coagulation defect were predictors of blood transfusion for spinal fusion. A prediction nomogram was developed according to a multivariate model with good discriminatory power (C-index = 0.887); Bootstrap resampling internal validation C-index was 0.883. Calibration curves showed strong matching between the predicted and actual probabilities of the training and validation sets. HL tests for the training and validation sets had p-values of 0.327 and 0.179, respectively, indicating good calibration. When applied to the training set, the following parameters were found: AUC: 0.895, 95% CI: 0.871-0.919, sensitivity 78.2%, specificity 86.7%, positive predictive value 29.4% and negative predictive value 98.2%. If the model were applied in the training set, 2911 T&S tests (82.4%) would be eliminated, equaling a RMB349,320 cost reduction. The AUC in the internal validation was: 0.879, 95% CI: 0.839-0.927, sensitivity 75.2%, specificity 88.8%, positive predictive value 34.3%, negative predictive value 97.9%, would eliminate 1276 T&S tests (84.2%), saving RMB 153,120. The DCA curve indicated good clinical application value.

CONCLUSION

The nomogram based on 10 independent factors can help healthcare professionals predict the risk of transfusion for patients undergoing spinal fusion surgery to target preoperative T&S testing to appropriate patients and reduce healthcare costs.

Predictive modeling of perioperative blood transfusion in lumbar posterior interbody fusion using machine learning

Background: Accurate estimation of perioperative blood transfusion risk in lumbar posterior interbody fusion is essential to reduce the number, cost, and complications associated with blood transfusions. Machine learning algorithms have the potential to outperform traditional prediction methods in predicting perioperative blood transfusion. This study aimed to construct a machine learning-based perioperative transfusion risk prediction model for lumbar posterior interbody fusion in order to improve the efficacy of surgical decision-making. Methods: We retrospectively collected clinical data on 1905 patients who underwent lumbar posterior interbody fusion surgery at the Second Hospital of Shanxi Medical University between January 2021 and March 2023. All the data was randomly divided into a training set and a validation set, and the "feature_importances" method provided by eXtreme Gradient Boosting (XGBoost) algorithm was applied to select statistically significant features on the training set to establish five machine learning prediction models. The optimal model was identified by utilizing the area under the curve (AUC) and the probability calibration curve on the validation set. Shapley additive explanations (SHAP) and local interpretable model-agnostic explanations (LIME) were employed for interpretable analysis of the optimal model. Results: In the postoperative outcomes of patients, the number of hospital days in the transfusion group was longer than that in the non-transfusion group. Additionally, the transfusion group experienced higher total hospital costs, 90-day readmission rates, and complication rates within 90 days after surgery than the non-transfusion group. A total of 9 features were selected for the models. The XGBoost model performed best with an AUC value of 0.958. The SHAP values showed that intraoperative blood loss, intraoperative fluid infusion, and number of fused segments were the top 3 most important features affecting perioperative blood transfusion in lumbar posterior interbody fusion. The LIME algorithm was used to interpret the individualized prediction. Conclusion: Surgery, ASA class, levels fused, total intraoperative blood loss, operative time, and preoperative Hb are viable predictors of perioperative blood transfusion in lumbar posterior interbody fusion. The XGBoost model has demonstrated superior predictive efficacy compared to the traditional logistic regression model, making it a more effective decision-making tool for perioperative blood transfusion.

Application of machine learning model in predicting the likelihood of blood transfusion after hip fracture surgery

OBJECTIVE

Anemia is one of the common adverse reactions after hip fracture surgery. The traditional method to solve anemia is allogeneic transfusion. However, the transfusion may lead to some complications such as septicemia and fever. So far, few studies have reported roles of machine learning in predicting whether blood transfusion is needed or not after hip fracture surgery. Therefore, the purpose of this study is to develop machine learning models to predict the likelihood of postoperative blood transfusion in patients undergoing hip fracture surgery.

METHODS

This study enrolled 1355 patients who underwent hip fracture surgery at the Affiliated Hospital of Qingdao University from January 2016 to December 2021. Among all patients, 210 cases received postoperative blood transfusion. All patients were randomly divided into a training group and a testing group at a ratio of 7:3. In the training group, univariate and multivariate logistic regression analyses were used to determine independent risk factors for the postoperative transfusion. Then, based on these independent risk factors, tenfold cross-validation method was utilized to develop five machine learning models, including logistic, multilayer perceptron (MLP), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The receiver operating characteristic (ROC) curve, area under ROC curve (AUC), and Matthews correlation coefficient (MCC) were generated to evaluate the performance of the models. Calibration plot and decision curve analysis (DCA) were used to test the performance, stability, and clinical applicability of the models. The models were validated using the testing group; and the ROC curve, MCC, calibration plot, and DCA curves were also generated to validate the performance, stability, and clinical applicability of the models. To further verify the robustness of the model, we randomly grabbed 70% of the samples in the testing set, performed 1000 iterations, and calculated the AUC and confidence interval of the five models. Finally, we used SHapley Additive exPlanations (SHAP) to explain these models.

RESULTS

Multivariate logistic regression analysis showed that there were 8 independent risk factors, including age, blood transfusion history, albumin (ALB), globulin (GLO), total bilirubin (TBIL), indirect bilirubin (IBIL), hemoglobin (HB), and blood loss > 200 ml. We finally selected five independent risk factors including HB, GLO, age, IBIL, and blood loss > 200 ml. Based on these five independent risk factors, we generated six characteristic variables, namely HB, HB × HB, HB × blood loss, GLO × HB, age, age × IBIL, and established five machine learning models using a tenfold cross-validation method. In the training group, the AUC values of logistic, RF, MLP, SVM, and XGB were 0.9320, 0.8911, 0.9327, 0.9225, and 0.8825, respectively, and the average AUC was 0.9122 ± 0.0212. The MCC values were 0.65, 0.77, 0.65, 0.66, and 0.68, respectively, and the calibration plot and DCA performed well. In the testing group the AUC values of logistic, RF, MLP, SVM, and XGB were 0.8483, 0.7978, 0.8576, 0.8598, and 0.8216, respectively. The average AUC was 0.8370 ± 0.0238, and the MCC values were 0.41, 0.35, 0.40, 0.41, and 0.41, respectively. The calibration plot and DCA in the testing group also showed good performance. The AUC values and confidence intervals of the 1000-iteration model were: logistic (AUC, min confidence interval [CI]-max confidence interval [CI] 0.848, 0.804-0.903), RF (AUC, minCI-maxCI 0.797, 0.734-0.857), MLP (AUC, minCI-maxCI 0.858, 0.812-0.902), SVM (AUC, minCI-maxCI 0.859, 0.819-0.910), and XGB (AUC, minCI-maxCI 0.821, 0.764-0.894). The model performed well. Finally, according to SHAP, among all five models, HB played the most important role in model prediction and interpretation.

CONCLUSION

The five models we developed all performed well in predicting the likelihood of blood transfusion after hip fracture surgery. Therefore, we believed that the prediction model based on machine learning had great application prospects in clinical practice, which could help clinicians better predict the risk of blood transfusion after hip fracture surgery.

Risk Factors for Significant Intraoperative Blood Loss during Anterior Cervical Decompression and Fusion for Degenerative Cervical Diseases

OBJECTIVES

Anterior cervical decompression and fusion (ACF) has become a widely accepted surgical treatment for degenerative cervical diseases, but occasionally, significant intraoperative blood loss (SIBL), which is defined as IBL of 500 mL or more, will occur. We aimed to investigate the independent risk factors for SIBL during ACF for degenerative cervical diseases.

METHODS

We enrolled 1150 patients who underwent ACF for degenerative cervical diseases at our hospital between 2013 and 2019. The patients were divided into two groups: the SIBL group (n = 38) and the non-SIBL group (n = 1112). Demographic, surgical and radiographic data were recorded prospectively to investigate the independent risk factors for SIBL. For counting data, the chi-square test or Fisher's exact probability test was used. Student's t-test or the Mann-Whitney rank sum test was used for comparisons between groups of measurement data. Univariate analysis and multivariate logistic regression analysis were further used to analyze the significance of potential risk factors.

RESULTS

The incidence of SIBL during ACF was 3.3% (38/1150). A multivariate analysis revealed that female sex (odds ratio [OR], 6.285; 95% confidence interval [CI], 2.707-14.595; p < 0.001), corpectomy (OR, 3.872; 95% CI, 1.616-9.275; p = 0.002), duration of operation ≥150 min (OR, 8.899; 95% CI, 4.042-19.590; p < 0.001), C3 involvement (OR, 4.116; 95% CI, 1.808-9.369; p = 0.001) and ossification of posterior longitudinal ligament (OPLL) at the surgical level (OR, 6.007; 95% CI, 2.218-16.270; p < 0.001) were independent risk factors for SIBL. Patients with SIBL had more days of first-degree/intensive nursing (p = 0.003), longer length of stay (p = 0.003) and higher hospitalization costs (p = 0.023).

CONCLUSION

Female sex, corpectomy, duration of operation, C3 involvement and OPLL at the surgical level were independent risk factors for SIBL during ACF. SIBL in ACF was associated with more days of first-degree/intensive nursing, longer length of stay and higher hospitalization costs.

Predictors of Blood Transfusion in Patients Undergoing Lumbar Spinal Fusion

OBJECTIVE

To determine risk factors for perioperative blood transfusion after lumbar fusion surgery.

METHODS

After institutional review board approval, a retrospective cohort study of adult patients who underwent lumbar fusion at a single, urban tertiary academic center was retrospectively retrieved. Our primary outcome, blood transfusion, was collected via chart query. A receiver operating characteristic curve was used to evaluate the regression model. A P-value < 0.05 was considered statistically significant.

RESULTS

Of the 3,842 patients, 282 (7.3%) required a blood transfusion. For patients undergoing posterolateral decompression and fusion, predictors of transfusion included age (P < 0.001) and more levels fused (P < 0.001). A higher preoperative hemoglobin level (P < 0.001) and revision surgery (P = 0.005) were protective of blood transfusion. For patients undergoing transforaminal lumbar interbody fusion, greater Elixhauser comorbidity index (P < 0.001), longer operative time (P = 0.040), and more levels fused (P = 0.030) were independent predictors of the need for blood transfusion. Patients with a higher body mass index (P = 0.012) and preoperative hemoglobin level (P < 0.001) had a reduced likelihood of receiving a transfusion. For circumferential fusion, greater age (P = 0.006) and longer operative times (P = 0.015) were independent predictors of blood transfusion, while a higher preoperative hemoglobin level (P < 0.001) and male sex (P = 0.002) were protective.

CONCLUSIONS

Our analysis identified older age, lower body mass index, greater Elixhauser comorbidity index, longer operative duration, more levels fused, and lower preoperative hemoglobin levels as independent predictors of requiring a blood transfusion following lumbar spinal fusion. Different surgical approaches were not found to be associated with transfusion.

Clinical outcomes and prediction nomogram model for postoperative hemoglobin < 80 g/L in patients following primary lumbar interbody fusion surgery

OBJECTIVE

To analyze the association between different postoperative hemoglobin (Hb) levels and postoperative outcomes in patients who have undergone primary lumbar interbody fusion, and to investigate the risk factors and establish a predictive nomogram mode for postoperative Hb < 80 g/L.

METHODS

We retrospectively analyzed 726 cases who underwent primary lumbar interbody fusion surgery between January 2018 and December 2021in our hospital. All patients were divided into three groups according to the postoperative Hb levels (< 70 g/L, 70-79 g/L, ≥ 80 g/L). The postoperative outcomes among the three groups were compared, and the risk factors for postoperative Hb < 80 g/L were identified by univariate and multivariable logistic regression analysis. Based on these independent predictors, a nomogram model was developed. Predictive discriminative and accuracy ability of the predicting model was assessed using the concordance index (C-index) and calibration plot. Clinical application was validated using decision curve analysis. Internal validation was performed using the bootstrapping validation.

RESULTS

Patients with postoperative Hb < 80 g/L had higher rates of postoperative blood transfusion, a greater length of stay, higher rates of wound complications, and higher hospitalization costs than those with postoperative Hb ≥ 80 g/L. Preoperative Hb, preoperative platelets, fusion segments, body mass index, operation time, and intraoperative blood loss independently were associated with postoperative Hb < 80 g/L. Intraoperative blood salvage was found to be a negative predictor for postoperative Hb < 80 g/L (OR, 0.21 [95% CI 0.09-0.50]). The area under the curve of the nomogram model was 0.950. After internal validations, the C-index of the model was 0.939. The DCA and calibration curve suggested that the nomogram model had a good consistency and clinical utility.

CONCLUSIONS

Postoperative Hb < 80 g/L in patients following primary lumbar interbody fusion surgery increased blood transfusions requirement and was independently associated with poor outcomes. A novel nomogram model was established and could conveniently predict the risk of postoperative Hb < 80 g/L in patients after this type of surgery.

Blood transfusion risk prediction in spinal tuberculosis surgery: development and assessment of a novel predictive nomogram

Objective

The present study attempted to predict blood transfusion risk in spinal tuberculosis surgery by using a novel predictive nomogram.

Methods

The study was conducted on the clinical data of 495 patients (167 patients in the transfusion group and 328 patients in the non-transfusion group) who underwent spinal tuberculosis surgery in our hospital from June 2012 to June 2021. The least absolute shrinkage and selection operator (LASSO) and multivariable logistic regression analyses were used to screen out statistically significant parameters, which were included to establish a novel predictive nomogram model. The receiver operating characteristic (ROC) curve, calibration curves, C-index, and decision curve analysis (DCA) were used to evaluate the model. Finally, the nomogram was further assessed through internal validation.

Results

The C-index of the nomogram was 0.787 (95% confidence interval: 74.6%–.82.8%). The C-value calculated by internal validation was 0.763. The area under the curve (AUC) of the predictive nomogram was 0.785, and the DCA was 0.01–0.79.

Conclusion

A nomogram with high accuracy, clinical validity, and reliability was established to predict blood transfusion risk in spinal tuberculosis surgery. Surgeons must prepare preoperative surgical strategies and ensure adequate availability of blood before surgery.

The risk factors and predictive nomogram of human albumin infusion during the perioperative period of posterior lumbar interbody fusion: a study based on 2015-2020 data from a local hospital

BACKGROUND

Perioperative hypoalbuminemia of the posterior lumbar interbody fusion (PLIF) can increase the risk of infection of the incision site, and it is challenging to accurately predict perioperative hypoproteinemia. The objective of this study was to create a clinical predictive nomogram and validate its accuracy by finding the independent risk factors for perioperative hypoalbuminemia of PLIF.

METHODS

The patients who underwent PLIF at the Affiliated Hospital of Qingdao University between January 2015 and December 2020 were selected in this study. Besides, variables such as age, gender, BMI, current and past medical history, indications for surgery, surgery-related information, and results of preoperative blood routine tests were also collected from each patient. These patients were divided into injection group and non-injection group according to whether they were injected with human albumin. And they were also divided into training group and validation group, with the ratio of 4:1. Univariate and multivariate logistic regression analyses were performed in the training group to find the independent risk factors. The nomogram was developed based on these independent predictors. In addition, the area under the curve (AUC), the calibration curve and the decision curve analysis (DCA) were drawn in the training and validation groups to evaluate the prediction, calibration and clinical validity of the model. Finally, the nomograms in the training and validation groups and the receiver operating characteristic (ROC) curves of each independent risk factor were drawn to analyze the performance of this model.

RESULTS

A total of 2482 patients who met our criteria were recruited in this study and 256 (10.31%) patients were injected with human albumin perioperatively. There were 1985 people in the training group and 497 in the validation group. Multivariate logistic regression analysis revealed 5 independent risk factors, including old age, accompanying T2DM, level of preoperative albumin, amount of intraoperative blood loss and fusion stage. We drew nomograms. The AUC of the nomograms in the training group and the validation group were 0.807, 95% CI 0.774-0.840 and 0.859, 95% CI 0.797-0.920, respectively. The calibration curve shows consistency between the prediction and observation results. DCA showed a high net benefit from using nomograms to predict the risk of perioperative injection of human albumin. The AUCs of nomograms in the training and the validation groups were significantly higher than those of five independent risk factors mentioned above (P < 0.001), suggesting that the model is strongly predictive.

CONCLUSION

Preoperative low protein, operative stage ≥ 3, a relatively large amount of intraoperative blood loss, old age and history of diabetes were independent predictors of albumin infusion after PLIF. A predictive model for the risk of albumin injection during the perioperative period of PLIF was created using the above 5 predictors, and then validated. The model can be used to assess the risk of albumin injection in patients during the perioperative period of PLIF. The model is highly predictive, so it can be clinically applied to reduce the incidence of perioperative hypoalbuminemia.