The Journal of the American Academy of Orthopaedic Surgeons · 2025
Predictive Analytics in Spine Surgery: How Risk-Taking Behavior Shapes Surgical Decisions.
СтатьяНаблюдательное исследованиеНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Bansal Aiyush, Louie Philip, Alostaz Murad, Kumar Rakesh, Nemani Venu, Yip Evan, Joko James, Michael John, Qiao Mark, Leveque Jean-Christophe
Аннотация
BACKGROUND: Understanding the role of risk-taking personality and tolerance for treatment-related complications in patients with spine pathology may help tailor surgical recommendations. The aim of this study was to develop a predictive model that integrates standard clinical metrics with psychosocial factors, specifically examining whether patients with higher risk-taking tendencies are more likely to choose high-risk, high-reward surgeries.
METHODS: This cross-sectional observational study recruited 1,214 participants from the United States in January 2024 using an online crowdsourcing platform. Participants completed an 84-question survey covering demographics, disability levels, and risk-taking tendencies. They were presented with hypothetical spinal surgery scenarios featuring varying risks of complications (footdrop, paralysis, or death) and chances of improvement. Participants rated their likelihood of choosing surgery on a six-point Likert scale. Predictors included demographics, socioeconomic factors, risk-taking personality (measured by the Domain-Specific Risk-Taking survey), and baseline pain levels (measured by the Oswestry Disability Index). The XGBoost model was used for predictive analysis.
RESULTS: The final sample included 797 (386 male, 411 female) participants. The predictive model achieved an R-squared of 0.75, root mean squared error of 0.81, and mean absolute error of 0.61. Key predictors of the likelihood to opt for surgery included lower complication risk and higher improvement probability, followed by younger age, higher body mass index, and lower scores in Domain-Specific Risk-Taking survey's financial and recreational domains.
CONCLUSION: Incorporating psychosocial dimensions into predictive models enhances the personalization of surgical risk discussions. This approach ensures that treatment recommendations align with patient values and risk perceptions, enabling more patient-centered care in spine surgery.
LEVEL OF EVIDENCE: Level 3 (cross-sectional study).
METHODS: This cross-sectional observational study recruited 1,214 participants from the United States in January 2024 using an online crowdsourcing platform. Participants completed an 84-question survey covering demographics, disability levels, and risk-taking tendencies. They were presented with hypothetical spinal surgery scenarios featuring varying risks of complications (footdrop, paralysis, or death) and chances of improvement. Participants rated their likelihood of choosing surgery on a six-point Likert scale. Predictors included demographics, socioeconomic factors, risk-taking personality (measured by the Domain-Specific Risk-Taking survey), and baseline pain levels (measured by the Oswestry Disability Index). The XGBoost model was used for predictive analysis.
RESULTS: The final sample included 797 (386 male, 411 female) participants. The predictive model achieved an R-squared of 0.75, root mean squared error of 0.81, and mean absolute error of 0.61. Key predictors of the likelihood to opt for surgery included lower complication risk and higher improvement probability, followed by younger age, higher body mass index, and lower scores in Domain-Specific Risk-Taking survey's financial and recreational domains.
CONCLUSION: Incorporating psychosocial dimensions into predictive models enhances the personalization of surgical risk discussions. This approach ensures that treatment recommendations align with patient values and risk perceptions, enabling more patient-centered care in spine surgery.
LEVEL OF EVIDENCE: Level 3 (cross-sectional study).