Red Cell Distribution Width at Admission Predicts the Frequency of Acute Kidney Injury and 28-Day Mortality in Patients With Acute Respiratory Distress Syndrome

OBJECTIVES

To determine the association of red cell distribution width (RDW) at admission with frequency of acute kidney injury (AKI) and 28-day mortality in acute respiratory distress syndrome (ARDS) patients.

METHODS

Two hundred fifty-eight ARDS patients were investigated in retrospective and prospective studies. The primary outcome was frequency of AKI. The secondary outcome was 28-day mortality.

RESULTS

The retrospective study included 193 ARDS patients, of which 67 (34.7%) were confirmed AKI and 76 (39.4%) died within 28 days. The RDW level in the AKI group was significantly higher than in the non-AKI group ([15.15 ± 2.59]% vs. [13.95 ± 1.89]%). Increased RDW was a significant predictor of frequency of AKI (odds ratio: 1.247, 95% confidence interval [CI]: 1.044, 1.489). The area under the receiver operating characteristic curve of RDW for predicting AKI was 0.687 (95%CI: 0.610, 0.764) and the cut-off value was 14.45 (sensitivity, 56.7%; specificity, 72.8%). In addition, the proportion of patients with RDW ≥ 14.45% in the non-survival group was notably higher compared with the survival group (48.7% vs. 29.1%). Furthermore, cox regression analysis revealed that RDW ≥ 14.45% was associated with 28-day mortality (hazard ratio: 1.817, 95%CI: 1.046, 3.158), while Kaplan-Meier analysis showed patients with RDW ≥ 14.45% had a significantly lower survival rate than those with RDW < 14.45%. The prospective study, on the other hand, included 65 ARDS patients, with frequency of AKI and 28-day mortality in the RDW ≥ 14.45% group significantly higher than in RDW < 14.45%.

CONCLUSION

RDW was a significant, independent predictor for frequency of AKI and 28-day mortality in ARDS patients.

Examining the Ability of Artificial Neural Networks Machine Learning Models to Accurately Predict Complications Following Posterior Lumbar Spine Fusion

STUDY DESIGN

A cross-sectional database study.

OBJECTIVE

The aim of this study was to train and validate machine learning models to identify risk factors for complications following posterior lumbar spine fusion.

SUMMARY OF BACKGROUND DATA

Machine learning models such as artificial neural networks (ANNs) are valuable tools for analyzing and interpreting large and complex datasets. ANNs have yet to be used for risk factor analysis in orthopedic surgery.

METHODS

The American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database was queried for patients who underwent posterior lumbar spine fusion. This query returned 22,629 patients, 70% of whom were used to train our models, and 30% were used to evaluate the models. The predictive variables used included sex, age, ethnicity, diabetes, smoking, steroid use, coagulopathy, functional status, American Society for Anesthesiology (ASA) class ≥3, body mass index (BMI), pulmonary comorbidities, and cardiac comorbidities. The models were used to predict cardiac complications, wound complications, venous thromboembolism (VTE), and mortality. Using ASA class as a benchmark for prediction, area under receiver operating curves (AUC) was used to determine the accuracy of our machine learning models.

RESULTS

On the basis of AUC values, ANN and LR both outperformed ASA class for predicting all four types of complications. ANN was the most accurate for predicting cardiac complications, and LR was most accurate for predicting wound complications, VTE, and mortality, though ANN and LR had comparable AUC values for predicting all types of complications. ANN had greater sensitivity than LR for detecting wound complications and mortality.

CONCLUSION

Machine learning in the form of logistic regression and ANNs were more accurate than benchmark ASA scores for identifying risk factors of developing complications following posterior lumbar spine fusion, suggesting they are potentially great tools for risk factor analysis in spine surgery.

LEVEL OF EVIDENCE

3.