Cleaning Up the MESS: Can Machine Learning Be Used to Predict Lower Extremity Amputation after Trauma-Associated Arterial Injury?

Systematic review of machine-learning models in orthopaedic trauma

Aims

Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool.

Methods

A systematic search screening 3,252 studies identified 45 ML-based prediction models in orthopaedic trauma up to January 2023. The TRIPOD statement assessed transparent reporting and the PROBAST tool the risk of bias.

Results

A total of 40 studies reported on training and internal validation; four studies performed both development and external validation, and one study performed only external validation. The most commonly reported outcomes were mortality (33%, 15/45) and length of hospital stay (9%, 4/45), and the majority of prediction models were developed in the hip fracture population (60%, 27/45). The overall median completeness for the TRIPOD statement was 62% (interquartile range 30 to 81%). The overall risk of bias in the PROBAST tool was low in 24% (11/45), high in 69% (31/45), and unclear in 7% (3/45) of the studies. High risk of bias was mainly due to analysis domain concerns including small datasets with low number of outcomes, complete-case analysis in case of missing data, and no reporting of performance measures.

Conclusion

The results of this study showed that despite a myriad of potential clinically useful applications, a substantial part of ML studies in orthopaedic trauma lack transparent reporting, and are at high risk of bias. These problems must be resolved by following established guidelines to instil confidence in ML models among patients and clinicians. Otherwise, there will remain a sizeable gap between the development of ML prediction models and their clinical application in our day-to-day orthopaedic trauma practice.

Mangled extremity: limb salvage for reconstruction versus primary amputation

PURPOSE OF REVIEW

While MESS has historically influenced limb salvage versus amputation decisions, its universal applicability remains uncertain. With trauma systems expanding and advancements in trauma care, the need for a nuanced understanding of limb salvage has become paramount.

RECENT FINDINGS

Recent literature reflects a shift in the management of mangled extremities. Vascular surgery, plastic surgery, and technological advancements have garnered attention. The MESS's efficacy in predicting amputation postvascular reconstruction has been questioned. Machine learning techniques have emerged as a means to predict peritraumatic amputation, incorporating a broader set of variables. Additionally, advancements in socket design, such as automated adjustments and bone-anchored prosthetics, show promise in enhancing prosthetic care. Surgical strategies to mitigate neuropathic pain, including targeted muscle reinnervation (TMR), are evolving and may offer relief for amputees. Predicting the long-term course of osteomyelitis following limb salvage is challenging, but it significantly influences patient quality of life.

SUMMARY

The review underscores the evolving landscape of limb salvage decision-making, emphasizing the need for personalized, patient-centered approaches. The Ganga Hospital Score (GHS) introduces a nuanced approach with a 'grey zone' for patients requiring individualized assessments. Future research may leverage artificial intelligence (AI) and predictive models to enhance decision support. Overall, the care of mangled extremities extends beyond a binary choice of limb salvage or amputation, necessitating a holistic understanding of patients' injury patterns, expectations, and abilities for optimal outcomes.

Predicting amputation using machine learning: A systematic review

Amputation is an irreversible, last-line treatment indicated for a multitude of medical problems. Delaying amputation in favor of limb-sparing treatment may lead to increased risk of morbidity and mortality. This systematic review aims to synthesize the literature on how ML is being applied to predict amputation as an outcome. OVID Embase, OVID Medline, ACM Digital Library, Scopus, Web of Science, and IEEE Xplore were searched from inception to March 5, 2023. 1376 studies were screened; 15 articles were included. In the diabetic population, models ranged from sub-optimal to excellent performance (AUC: 0.6-0.94). In trauma patients, models had strong to excellent performance (AUC: 0.88-0.95). In patients who received amputation secondary to other etiologies (e.g.: burns and peripheral vascular disease), models had similar performance (AUC: 0.81-1.0). Many studies were found to have a high PROBAST risk of bias, most often due to small sample sizes. In conclusion, multiple machine learning models have been successfully developed that have the potential to be superior to traditional modeling techniques and prospective clinical judgment in predicting amputation. Further research is needed to overcome the limitations of current studies and to bring applicability to a clinical setting.

Concomitant Orthopedic Injury is the Strongest Predictor of Amputation in Extremity Vascular Trauma

BACKGROUND

Although the risk of extremity amputation related to an isolated vascular injury is low, it increases significantly with concomitant orthopedic injury. Our study aims to evaluate and quantify the impact of risk factors associated with trauma-related extremity amputation in patients with vascular injury. We sought to determine whether there are other potential predictors of amputation.

METHODS

A retrospective review of patients with extremity vascular injury presenting to a single level 1 academic trauma center between January 1, 2007, and December 31, 2018, was performed. All patients diagnosed with major vascular injury to the upper or lower extremity were included. Data on patient demographics, medical comorbidities, anatomic location of vascular injury, and the presence of soft tissue or orthopedic injury were collected. The main outcome measure was major amputation of the affected extremity. Major amputation included below-the-knee amputation, above-the-knee amputation, as well as any amputation of the upper extremity at or proximal to the wrist.

RESULTS

We identified 250 extremities with major vascular injury in 234 patients. Of these, 216 (86.4%) were male and 34 (13.6%) female. The mean age was 32.2 years (range 18-79 years) and mean follow-up was 6.9 (standard deviation: 3.3) years. Just over half of injuries, 130 (52.0%) involved the lower extremity. Forty extremities (29 lower and 11 upper), or 16.0%, of total injured extremities, required major amputation during the follow-up period. Concomitant orthopedic injury was present in 106 of 250 (42%) injured extremities. Using univariable logistic regression models, variables with a significant association with major amputation included older age, higher body mass index, blunt mechanism of injury, concomitant orthopedic injury, soft tissue injury, and nerve injury, and the need for fasciotomy (P < 0.05). In multivariable analyses, blunt mechanism of injury (odds ratio [OR] (confidence ratio {CI}): 6.51 (2.29, 18.46), P < 0.001) and concomitant orthopedic injury (OR [CI]: 7.23 [2.22, 23.55], P = 0.001) remained significant predictors of amputation.

CONCLUSIONS

Concomitant orthopedic injury and blunt mechanism in the setting of vascular injury are associated with a higher likelihood of amputation in patients with extremity vascular injury. Further development of a vascular extremity injury protocol may be needed to enhance limb salvage. Findings may guide patient discussion regarding limb-salvage decision-making.