Woodhouse Palina, Paez Rafael, Meyers Patrick, Lentz Rob J, Shojaee Samira, Sharp Kenneth, Baldi Nikki, Maldonado Fabien, Grogan Eric L
From the Departments of Thoracic Surgery (Woodhouse, Meyers, Sharp, Grogan), VA Tennessee Valley Healthcare System, Nashville, TN.
Allergy, Pulmonary and Critical Care Medicine (Paez, Lentz, Shojaee, Baldi, Maldonado), VA Tennessee Valley Healthcare System, Nashville, TN.
J Am Coll Surg. 2025 Apr 1;240(4):417-422. doi: 10.1097/XCS.0000000000001275. Epub 2025 Mar 17.
Artificial intelligence (AI)-powered platforms may be used to ensure that clinically significant lung nodules receive appropriate management. We studied the impact of a commercially available AI natural language processing tool on the detection of clinically significant indeterminate pulmonary nodules (IPNs) based on radiology reports and provision of guideline-consistent care.
All CT scans performed at a single tertiary care center in the outpatient or emergency room setting between February 20, 2024, and March 20, 2024, were processed by the AI natural language processing algorithm. CT radiology reports mentioning a lung nodule or focal indeterminate lesion were flagged. All flagged reports were reviewed by a lung nodule expert 2 weeks after nodule identification. IPNs were classified as "appropriately followed" if follow-up imaging, referral to a nodule clinic, or other guideline-consistent care was ordered. IPNs were classified as "not appropriately followed" if no acknowledgment of the reported nodule was documented in the electronic health record within 2 weeks of being flagged.
The AI software processed 76,507 unique radiology reports, identified 2,585 CT scans with chest imaging, and found 389 IPNs. Review determined that 272 (70%) nodules were appropriately followed, whereas 117 (30%) were not appropriately followed. Of the 117 nodules without documented follow-up, 67 (57%) were more than 8 mm and 24 (20.5%) were more than 15 mm. IPNs that would not have received follow-up in the absence of the AI software generated 43 additional clinical appointments and 3 procedures.
At a large tertiary care center, 30% of clinically significant incidental pulmonary nodules that would have otherwise been missed were brought to the attention of lung nodule clinicians by an AI software, allowing for initiation of appropriate follow-up.
人工智能（AI）驱动的平台可用于确保具有临床意义的肺结节得到适当管理。我们研究了一种商用AI自然语言处理工具对基于放射学报告检测具有临床意义的不确定肺结节（IPN）以及提供符合指南的护理的影响。
2024年2月20日至2024年3月20日在单一三级护理中心门诊或急诊室进行的所有CT扫描均由AI自然语言处理算法处理。提及肺结节或局灶性不确定病变的CT放射学报告被标记。所有标记的报告在结节识别后2周由肺结节专家进行审查。如果下令进行随访成像、转诊至结节诊所或采取其他符合指南的护理措施，则IPN被分类为“得到适当随访”。如果在标记后2周内电子健康记录中未记录对报告结节的确认，则IPN被分类为“未得到适当随访”。
AI软件处理了76,507份独特的放射学报告，识别出2,585份有胸部成像的CT扫描，并发现389个IPN。审查确定272个（70%）结节得到了适当随访，而117个（30%）未得到适当随访。在117个无随访记录的结节中，67个（57%）直径大于8毫米，24个（20.5%）直径大于15毫米。在没有AI软件的情况下不会接受随访的IPN额外产生了43次临床预约和3次手术。
在一家大型三级护理中心，一种AI软件使30%本会被漏诊的具有临床意义的偶然发现的肺结节引起了肺结节临床医生的注意，从而得以开始适当的随访。
