Establishment and assessment of a nomogram for predicting blood transfusion risk in posterior lumbar spinal fusion

Clinical prediction model for red cell blood transfusion in elective primary posterior lumbar spine fusion

Overestimated the cross-match of preoperative PRC preparation for elective primary lumbar spinal fusion needs revision for cost-effectiveness. We aimed to develop a novel preoperative predictive model for appropriate PRC preparation. This clinical prediction model in a retrospective cohort was studied between January 2015 and September 2022. Multivariate logistic regression models were used to assess predictive variables. The logistic coefficient of each predictor generated scores to establish a predictive model. The area under the receiver operating characteristic curve (AuROC) was used to evaluate the model. The predictive performance was validated using bootstrapping techniques and externally validated in 102 independent cases. Among 416 patients, 178 (43%) required transfusion. Four final predictors: preoperative hematocrit level, laminectomy level, transforaminal lumbar interbody fusion level, and sacral fusion. When categorized into two risk groups, the positive predictive values for the low-risk score (≤ 4) were 18.4 (95% Cl 13.9, 23.6) and 83.9 (95% CI 77.1, 89.3) for the high-risk score (> 4). AuROC was 0.90. Internal validation (bootstrap shrinkage = 0.993) and external validation (AuROC: 0.91). A new model demonstrated exemplary performance and discrimination in predicting the appropriate preparation for PRC. This study should be corroborated by rigorous external validation in other hospitals and by prospective assessments.

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.

The severity of preoperative anemia escalates risk of poor short-term outcomes after lumbar spine fusion

OBJECTIVE

To evaluate how preoperative anemia severity affects 90-day outcomes of spinal fusion surgery.

METHODS

A retrospective cohort study was conducted on adult lumbar fusion patients at a tertiary medical center. Patients were classified by World Health Organization anemia severity definitions for comparisons. Multivariate regression models were created to control for confounding variables, for all primary outcomes of transfusion requirements, non-home discharge, readmissions, complications, and length of stay.

RESULTS

A total of 2582 patients were included: 2.7% with moderate-severe anemia, 11.0% with mild anemia, and 86.3% without anemia. Moderate-severe patients had the longest hospital stay (5.03 days vs 4.14 and 3.59 days, p < 0.001) and highest risk of transfusion (52.2% vs 13.0% vs 2.69%, p < 0.001), non-home discharge (39.1% vs 27.8% vs 15.4%, p < 0.001), readmission (7.25% vs 5.99% vs 3.36%, p = 0.023), and complications (13.0% vs 9.51% vs 6.20%, p = 0.012). On multivariable logistic regression, both patients with mild and moderate-severe anemia had an increased risk of transfusion (OR: 37.3, p < 0.001; OR: 5.25, p < 0.001, respectively) and non-home discharge (OR: 2.00, p = 0.021; OR: 1.71, p = 0.001, respectively) compared to patients without anemia. Anemia severity was not independently associated with complications or 90-day readmission. On multivariable linear regression, mild anemia (β: 0.37, p = 0.001) and moderate-severe anemia (β: 1.07, p < 0.001) were independently associated with length of hospital stay.

CONCLUSION

Patients with moderate-severe preoperative anemia are at increased risk for longer length of stay, transfusions, and non-home discharge. Improved optimization of preoperative anemia may significantly reduce healthcare utilization, and surgeons should consider these risks in preoperative planning.

LEVEL OF EVIDENCE

III.

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.

Systematic review highlights high risk of bias of clinical prediction models for blood transfusion in patients undergoing elective surgery

BACKGROUND

Blood transfusion can be a lifesaving intervention after perioperative blood loss. Many prediction models have been developed to identify patients most likely to require blood transfusion during elective surgery, but it is unclear whether any are suitable for clinical practice.

STUDY DESIGN AND SETTING

We conducted a systematic review, searching MEDLINE, Embase, PubMed, The Cochrane Library, Transfusion Evidence Library, Scopus, and Web of Science databases for studies reporting the development or validation of a blood transfusion prediction model in elective surgery patients between January 1, 2000 and June 30, 2021. We extracted study characteristics, discrimination performance (c-statistics) of final models, and data, which we used to perform risk of bias assessment using the Prediction model risk of bias assessment tool (PROBAST).

RESULTS

We reviewed 66 studies (72 developed and 48 externally validated models). Pooled c-statistics of externally validated models ranged from 0.67 to 0.78. Most developed and validated models were at high risk of bias due to handling of predictors, validation methods, and too small sample sizes.

CONCLUSION

Most blood transfusion prediction models are at high risk of bias and suffer from poor reporting and methodological quality, which must be addressed before they can be safely used in clinical practice.

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.

Development and validation of a risk-based algorithm for preoperative type and screen testing in spine surgery

BACKGROUND CONTEXT

With improvements in surgical techniques and perioperative management, transfusion rates after spine surgery have decreased over time. Given this trend, routine preoperative ABO/Rh type and antibody screen (T&S) laboratory testing may not be warranted in all patients undergoing spine surgery.

PURPOSE

The aim of the current study is to evaluate risk factors for intra/postoperative transfusion in patients undergoing a variety of spine procedures and to develop an algorithm for selectively ordering preoperative T&S testing in appropriate patients.

STUDY DESIGN/SETTING

This is a single institution, retrospective observational study of patients undergoing emergent or elective spine surgery. External validation of the algorithm was performed on a national sample of patients undergoing spine surgery from the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) national database.

PATIENT SAMPLE

A total of 5,947 surgeries from January 1, 2016 to December 31, 2019 at a single institution, and 166,113 surgeries from the 2016 to 2018 ACS-NSQIP database.

OUTCOME MEASURES

The primary outcome measure was performance of intraoperative or postoperative transfusion.

METHODS

Using the institutional sample, univariate statistics (chi-square tests, fisher's exact test, 2-sided independent sample tests) were performed to compare demographics, comorbidities, and surgical details (case type, number of levels treated, etc.) between patients who did and did not require intra- or postoperative transfusion. Transfusion rates were calculated and compared across procedure types. Multivariate logistic regression was performed to identify independent predictors of transfusion and the model's accuracy was evaluated using the area under the curve (AUC) of the receiver operating characteristics (ROC) curve. A risk-based algorithm suggesting no preoperative T&S in low transfusion risk procedures, routine preoperative T&S in high-risk procedures, and further assessment in medium risk thoracolumbar fusion procedures was created. The algorithm's sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were evaluated when it was applied to both the institutional and national samples. Potential cost savings from reducing T&S orders were calculated.

RESULTS

In the institutional sample, 120 patients (2.0%) required intraoperative or postoperative transfusion. The highest rates of transfusion were found in corpectomy (10.5%) and anterior/posterior cervical fusion (6.9%) procedures. In the multivariate logistic regression model, the presence of a preoperative coagulation defect or hemorrhagic condition (OR: 7.149, p<.001) and 6+ level surgery (OR: 7.511, p<.001) were the strongest predictors of transfusion. Overall, the model generated an AUC of 0.882, indicating excellent predictive accuracy. When applied to the institutional cohort, the risk-based algorithm had a sensitivity of 78.3%, specificity of 80.5%, PPV of 7.6%, and NPV of 99.4% for evaluating likelihood of transfusion. Using the algorithm 4,717 T&S tests would have been eliminated (79.3%), resulting in a cost savings of $179,246. Application of the model to the ACS-NSQIP cohort resulted in a sensitivity of 61.9%, specificity of 84.6%, PPV of 15.6%, and NPV of 98.0%.

CONCLUSIONS

The routine use of preoperative ABO/Rh type and antibody screen testing does not appear to be warranted in patients undergoing spine surgery. A risk-based approach to preoperative type and screen testing may eliminate unnecessary tests and generate significant cost savings with minimal disruption to clinical care.

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

Objective: We aimed to analyze the related risk factors for blood transfusion and establish a blood transfusion risk model during the per-ioperative period of posterior lumbar interbody fusion (PLIF). It could provide a reference for clinical prevention and reduction of the risk of blood transfusion during the peri-operative period. Methods: We retrospectively analyzed 4,378 patients who underwent PLIF in our hospital. According to whether they were transfused blood or not, patients were divided into the non-blood transfusion group and the blood transfusion group. We collected variables of each patient, including age, sex, BMI, current medical history, past medical history, surgical indications, surgical information, and preoperative routine blood testing. We randomly divide the whole population into training group and test group according to the ratio of 4:1. We used the multivariate regression analyses get the independent predictors in the training set. The nomogram was established based on these independent predictors. Then, we used the AUC, calibration curve and DCA to evaluate the nomogram. Finally, we verified the performance of the nomogram in the validation set. Results: Three or more lumbar fusion segments, preoperative low hemoglobin, with hypertension, lower BMI, and elder people were risk factors for blood transfusion. For the training and validation sets, the AUCs of the nomogram were 0.881 (95% CI: 0.865-0.903) and 0.890 (95% CI: 0.773-0.905), respectively. The calibration curve shows that the nomogram is highly consistent with the actual observed results. The DCA shows that the nomogram has good clinical application value. The AUC of the nomogram is significantly larger than the AUCs of independent risk factors in the training and validation set. Conclusion: Three or more lumbar fusion segments, preoperative low hemoglobin, with hypertension, lower BMI, and elder people are associated with blood transfusion during the peri-operative period. Based on these factors, we established a blood transfusion nomogram and verified that it can be used to assess the risk of blood transfusion after PLIF. It could help clinicians to make clinical decisions and reduce the incidence of peri-operative blood transfusion.

Analysis of risk factors for perioperative hidden blood loss in unilateral biportal endoscopic spine surgery: a retrospective multicenter study

Background

Hidden blood loss (HBL) represents an important complication of unilateral biportal endoscopic (UBE) spine surgery. This study aimed to evaluate HBL and its possible risk factors among patients undergoing UBE surgery for lumbar degenerative diseases.

Methods

This multicentric retrospective study was conducted in 3 different medical centers between July 2020 and April 2021. Data of patients who underwent UBE surgery were extracted by electronic medical record system. The patient’s demographic characteristics and blood loss-related parameters were recorded. We calculated the amount of HBL and explored the association between patient’s characteristics and HBL using Pearson or Spearman correlation analysis. Multivariate linear regression analysis was conducted to identify independent risk factors of HBL.

Results

A total of 136 patients (55 females and 81 males, age range 43 to 74 years) were included in this study. A substantial amount of HBL (469.5 ± 195.3 ml, 57.6% of TBL, total blood loss) occurred following UBE surgery. Multiple linear regression analysis indicated that the risk factors of HBL were as follows: age (P = 0.000), number of fusion levels (P = 0.015), American Society of Anesthesiologists (ASA) classification (P = 0.046), surgery time (P = 0.017), patient’s blood volume (PBV, P = 0.026), total blood loss (TBL, P = 0.001), postoperative (i.e., day 2 or 3) hematocrit (Hct, P = 0.034), Hct loss (P = 0.005), and fibrinogen (P = 0.028).

Conclusions

A certain amount of HBL occurs in UBE surgery and cannot be ignored in daily clinical practice. The age, number of fusion levels, ASA classification, surgery time, PBV, TBL, postoperative Hct, Hct loss, and fibrinogen are independent risk factors for HBL.