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

BACKGROUND: Thirty years after the Mangled Extremity Severity Score was developed, advances in vascular, trauma, and orthopaedic surgery have rendered the sensitivity of this score obsolete. A significant number of patients receive amputation during subsequent admissions, which are often missed in the analysis of amputation at the index admission. We aimed to identify risk factors for and predict amputation on initial admission or within 30 days of discharge (peritraumatic amputation [PTA]). STUDY DESIGN: The Nationwide Readmission Database for 2016 and 2017 was used in our analysis. Factors associated with PTA were identified. We used XGBoost, random forest, and logistic regression methods to develop a framework for machine learning-based prediction models for PTA. RESULTS: We identified 1,098 adult patients with traumatic lower extremity fracture and arterial injuries; 206 underwent amputation. One hundred and seventy-six patients (85.4%) underwent amputation during the index admission and 30 (14.6%) underwent amputation within a 30-day readmission period. After identifying factors associated with PTA, we constructed machine learning models based on random forest, XGBoost, and logistic regression to predict PTA. We discovered that logistic regression had the most robust predictive ability, with an accuracy of 0.88, sensitivity of 0.47, and specificity of 0.98. We then built on the logistic regression by the NearMiss algorithm, increasing sensitivity to 0.71, but decreasing accuracy to 0.74 and specificity to 0.75. CONCLUSIONS: Machine learning-based prediction models combined with sampling algorithms (such as the NearMiss algorithm in this study), can help identify patients with traumatic arterial injuries at high risk for amputation and guide targeted intervention in the modern age of vascular surgery.

A rare case of Polyarteritis Nodosa associated with autoimmune hepatitis: a case report.

BACKGROUND: Polyarteritis nodosa is a type of vasculitis affecting medium- and small-sized arteries that has been associated with hepatitis B but does not have an established relationship with autoimmune hepatitis. Here we report the case of an adult patient with autoimmune hepatitis who, shortly after diagnosis, developed life-threatening polyarteritis nodosa. CASE PRESENTATION: A 45-year-old woman was diagnosed with autoimmune hepatitis after initially presenting with a two-month history of fatigue, nausea, and anorexia and a three-week history of scleral icterus. Her liver biopsy showed mild portal fibrosis and her liver chemistries improved with prednisone and azathioprine. Three months later, she presented to the emergency department with fever, bilateral ankle pain, rash, oral ulcers, and poor vision. Physical examination was notable for erythema nodosum, anterior uveitis, retinal vasculitis, and frosted branch angiitis (frosted branch angiitis (a widespread florid translucent perivascular exudate). She subsequently developed repeated episodes of ischemic acute bowel necrosis that required multiple surgeries and extensive small bowel resections. Surgical pathology of the small bowel resection revealed ischemic necrosis, medium and small vessel vasculitis with microvascular thrombi consistent with polyarteritis nodosa. Azathioprine was discontinued and she was treated with pulse steroids followed by a prednisone taper, cyclophosphamide, and intravenous immune globulin with overall improvement in her symptomatology. Since her hospitalization, she has been maintained on low-dose prednisone and mycophenolate mofetil. CONCLUSIONS: In patients with recent diagnosis of autoimmune hepatitis, there should be a modest suspicion for concomitant polyarteritis nodosa if symptoms and signs of multisystem vasculitis develop.