Cleaning Up the MESS: Can Machine Learning Be Used to Predict Lower Extremity Amputation after Trauma-Associated Arterial Injury?
- 3 October 2020
- journal article
- conference paper
- Published by Ovid Technologies (Wolters Kluwer Health) in Journal of the American College of Surgeons
- Vol. 232 (1), 102-113e4
- https://doi.org/10.1016/j.jamcollsurg.2020.09.014
Abstract
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.Keywords
This publication has 28 references indexed in Scilit:
- Damage control surgery in the era of damage control resuscitationBritish Journal of Anaesthesia, 2014
- Traumatic amputationsBritish Journal of Pain, 2013
- Type et épidémiologie des blessures de guerre, à propos de deux conflits actuels : Irak et AfghanistanAnnales Françaises dʼAnesthésie et de Réanimation, 2011
- National trauma databank analysis of mortality and limb loss in isolated lower extremity vascular traumaJournal of Vascular Surgery, 2011
- Clopidogrel is not associated with major bleeding complications during peripheral arterial surgeryJournal of Vascular Surgery, 2011
- Results of the randomized, placebo-controlled clopidogrel and acetylsalicylic acid in bypass surgery for peripheral arterial disease (CASPAR) trialJournal of Vascular Surgery, 2010
- The Use of Temporary Vascular Shunts in Military Extremity Wounds: A Preliminary Outcome Analysis With 2-Year Follow-UpThe Journal of Trauma and Acute Care Surgery, 2010
- Incidence and Epidemiology of Combat Injuries Sustained During “The Surge” Portion of Operation Iraqi Freedom by a U.S. Army Brigade Combat TeamThe Journal of Trauma and Acute Care Surgery, 2010
- A Decade's Experience With Temporary Intravascular Shunts at a Civilian Level I Trauma CenterThe Journal of Trauma and Acute Care Surgery, 2008
- Combat Wounds in Operation Iraqi Freedom and Operation Enduring FreedomThe Journal of Trauma and Acute Care Surgery, 2008