Preventing Heterotopic Ossification in Combat Casualties—Which Models Are Best Suited for Clinical Use?

Abstract

Background To prevent symptomatic heterotopic ossification (HO) and guide primary prophylaxis in patients with combat wounds, physicians require risk stratification methods that can be used early in the postinjury period. There are no validated models to help guide clinicians in the treatment for this common and potentially disabling condition. Questions/purposes We developed three prognostic models designed to estimate the likelihood of woundspecific HO formation and compared them using receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) to determine (1) which model is most accurate; and (2) which technique is best suited for clinical use. Methods We obtained muscle biopsies from 87 combat wounds during the first débridement in the United States, all of which were evaluated radiographically for development of HO at a minimum of 2 months postinjury. The criterion for determining the presence of HO was the ability to see radiographic evidence of ectopic bone formation within the zone of injury. We then quantified relative gene expression from 190 wound healing, osteogenic, and vascular genes. Using these data, we developed an Artificial Neural Network, Random Forest, and a Least Absolute Shrinkage and Selection Operator (LASSO) Logistic Regression model designed to estimate the likelihood of eventual woundspecific HO formation. HO was defined as any HO visible on the plain film within the zone of injury. We compared the models accuracy using area under the ROC curve (area under the curve [AUC]) as well as DCA to determine which model, if any, was better suited for clinical use. In general, the AUC compares models based solely on accuracy, whereas DCA compares their clinical utility after weighing the consequences of under-or overtreatment of a particular disorder. Results Both the Artificial Neural Network and the LASSO logistic regression models were relatively accurate with AUCs of 0.78 (95% confidence interval [CI], 0.72-0.83) and 0.75 (95% CI, 0.71-0.78), respectively. The Random Forest model returned an AUC of only 0.53 (95% CI, 0.48-0.59), marginally better than chance alone. Using DCA, the Artificial Neural Network model demonstrated the highest net benefit over the broadest range of threshold probabilities, indicating that it is perhaps better suited for clinical use than the LASSO logistic regression model. Specifically, if only patients with greater than 25% risk of developing HO received prophylaxis, for every 100 patients, use of the Artificial Network Model would result in six fewer patients who unnecessarily receive prophylaxis compared with using the LASSO regression model while not missing any patients who might benefit from it. Conclusions Our findings suggest that it is possible to risk-stratify combat wounds with regard to eventual HO formation early in the débridement process. Using these data, the Artificial Neural Network model may lead to better patient selection when compared with the LASSO logistic regression approach. Future prospective studie...

Use of artificial neural networks in the prognosis of musculoskeletal diseases—a scoping review

“…The included studies were from sixteen journals, with only 2 articles each were published in Clinical Orthopaedics and Related Research [ 24 , 25 ] and Medicina [ 26 , 27 ]. Thirty-three percent of these studies (7/18) were conducted in the United States [ 24 , 25 , 28 – 32 ], with 17% (3) in China [ 26 , 33 , 34 ]. Study designs included cohort study (83%; 15) and cross-sectional database study (17%; 3).…”

“…The mean age of the patients ranged from 12.5 to 100.0 years [ 35 , 36 ] (Table 2 ). Two of the studies included exclusively female or male participants [ 24 , 37 ]. The sample size ranged from 58 to 10534 [ 26 , 36 ].…”

“…Compared to the other included studies, in which the ANN model prediction accuracy was higher than 0.7, a relatively low number of features was used in the ANN model. While in this study [ 43 ] 8 features were used to predict 4 different symptoms, other studies used 10 [ 24 ] to 25 [ 37 ] features to predict one symptom. A possible reason for the discrepancy in accuracy may thus be that insufficient relevant features were included in ANN models.…”

Metagenomic features of bioburden serve as outcome indicators in combat extremity wounds

“…Machine learning classifiers have been applied to combat injuries for prediction of pneumonia 19 , infection 48 , closure timing 29 , venous thromboembolism 18 , and heterotopic ossification 49 . The utility of clinical variables for predicting outcomes was demonstrated in these studies, thus the current study employed a microbe-centric focus.…”

Characterization of Brown Adipose–Like Tissue in Trauma-Induced Heterotopic Ossification in Humans

“…HO most frequently occurs after traumatic injury to the brain and spinal cord, 1 burns, 2 fractures, 3 and blasts. 4,5 Within the military, the prevalence of HO has been shown to be 64% in soldiers experiencing severe combatrelated injuries. 6 In some instances, this ectopic bone formation can surround nerves and vessels, resulting in their dysfunction.…”