Panossian Vahe S, Ma Yu, Song Bolin, Proaño-Zamudio Jefferson A, van Zon Veerle P C, Nzenwa Ikemsinachi C, Tabari Azadeh, Velmahos George C, Kaafarani Haytham M A, Bertsimas Dimitris, Daye Dania
Division of Trauma, Emergency Surgery, Surgical Critical Care, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, USA.
Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.
Bioengineering (Basel). 2025 Mar 24;12(4):336. doi: 10.3390/bioengineering12040336.
The identification of the optimal management for blunt splenic trauma-angioembolization (AE), splenectomy, or observation-remains a challenge. This study applies Optimal Policy Trees (OPT), an artificial intelligence (AI) model, to prescribe appropriate management and improve in-hospital mortality.
OPTs were trained on patients with blunt splenic injuries in the ACS-TQIP 2013-2019 to prescribe one of the three interventions: splenectomy, angioembolization (AE), or observation. Prescriptive trees were derived in two separate patient cohorts: those who presented with a systolic blood pressure (SBP) < 70 mmHg and those with an SBP ≥ 70 mmHg. Splenic injury severity was graded using the American Association of Surgical Trauma (AAST) grading scale. Counterfactual estimation was used to predict the effects of interventions on overall in-hospital mortality.
Among 54,345 patients, 3.1% underwent splenic AE, 13.1% splenectomy, and 83.8% were managed with observation. In patients with SBP < 70 mmHg, AE was recommended for shock index (SI) < 1.5 or without transfusion, while splenectomy was indicated for SI ≥ 1.5 with transfusion. For patients with SBP ≥ 70 mmHg, AE was recommended for AAST grades 4-5, or grades 1-3 with SI ≥ 1.2; observation was recommended for grades 1-3 with SI < 1.2. Predicted mortality using OPT-prescribed treatments was 18.4% for SBP < 70 mmHg and 4.97% for SBP ≥ 70 mmHg, compared to observed rates of 36.46% and 7.60%, respectively.
Interpretable AI models may serve as a decision aid to improve mortality in patients presenting with a blunt splenic injury. Our data-driven prescriptive OPT models may aid in prescribing the appropriate management in this patient cohort based on their characteristics.
确定钝性脾损伤的最佳治疗方法——血管栓塞术（AE）、脾切除术或观察治疗——仍然是一项挑战。本研究应用最优策略树（OPT）这一人工智能（AI）模型来制定合适的治疗方案并降低院内死亡率。
在2013 - 2019年美国外科医师学会创伤质量改进计划（ACS - TQIP）中，对钝性脾损伤患者进行OPT训练，以制定三种干预措施之一：脾切除术、血管栓塞术（AE）或观察治疗。在两个独立的患者队列中得出规定性树状图：收缩压（SBP）<70 mmHg的患者和SBP≥70 mmHg的患者。使用美国外科创伤协会（AAST）分级量表对脾损伤严重程度进行分级。采用反事实估计来预测干预措施对总体院内死亡率的影响。
在54345例患者中，3.1%接受了脾血管栓塞术，13.1%接受了脾切除术，83.8%接受了观察治疗。对于SBP <70 mmHg的患者，当休克指数（SI）<1.5或未输血时推荐血管栓塞术，而当SI≥1.5且输血时则建议行脾切除术。对于SBP≥70 mmHg的患者，AAST 4 - 5级或1 - 3级且SI≥1.2时推荐血管栓塞术；1 - 3级且SI <1.2时建议观察治疗。使用OPT规定治疗方法预测的死亡率，SBP <70 mmHg时为18.4%，SBP≥70 mmHg时为4.97%，而观察到的死亡率分别为36.46%和7.60%。
可解释的人工智能模型可作为决策辅助工具，以降低钝性脾损伤患者的死亡率。我们的数据驱动型规定性OPT模型可能有助于根据该患者群体的特征制定合适的治疗方案。
