利用自动管道从电子健康记录中提取数据,可提供有关各种青光眼手术成功与否的真实信息,与小梁切除术相比,分流管植入与故障率增加相关。
我们的目标是使用自动管道从电子健康记录中提取结果来评估青光眼手术的长期生存率。
来自单个学术中心的回顾性观察研究。接受小梁切除术的患者,Ex-PRESS分流器,Baerveldt,从电子健康记录程序代码中确定了2009年至2018年的Ahmed管分流管插入。使用先前验证的自然语言处理管道从结构化和非结构化字段中识别患者特征。
五百十二名患者接受了711例青光眼手术:287例小梁切除术,47前媒体分流,274Baerveldt和103Ahmed管植入。中位随访时间为359天。平均基线眼压为24.4mmHg(SD10.9),73.1%的患者服用≥3种药物。与小梁切除术相比,管分流手术的失败风险较高(Baerveldt:危险比(HR)1.44,95%CI1.02~2.02;Ahmed:HR2.01,95%CI1.28~3.17).先前的青光眼手术与失败增加相关(≥2次先前手术:HR2.74,95%CI1.62至4.64),基线药物(<3种药物:HR2.96,95%CI2.12~4.13)和男性(HR1.40,95%CI1.03~1.90)较少。在1年,与小梁切除术患者相比,分流管患者的IOP高2.53mmHg(P=0.002).
与小梁切除术相比,Baerveldt和Ahmed分流管植入与失败增加相关。基线药物越少,以前的青光眼手术,男性也是失败的危险因素。这些结果证明了将信息学管道应用于电子健康记录以使用真实世界证据调查关键临床问题的实用性。
Utilizing an automated pipeline for data extraction from electronic health records provides real-world information on the success of various glaucoma procedures, with tube shunt implantation associated with increased failure rates compared with trabeculectomy.
We aimed to evaluate the long-term survival of glaucoma surgeries using an automated pipeline for extraction of outcomes from electronic health records.
A retrospective observational
study from a single academic center. Patients undergoing trabeculectomy, Ex-PRESS shunt, Baerveldt, and Ahmed tube shunt insertion from 2009 to 2018 were identified from electronic health record procedure codes. Patient characteristics were identified from structured and unstructured fields using a previously validated natural language processing pipeline.
Five hundred twelve patients underwent 711 glaucoma surgeries: 287 trabeculectomies, 47 Ex-PRESS shunts, 274 Baerveldt and 103 Ahmed tube implantations. The Median follow-up was 359 days. The mean baseline IOP was 24.4 mm Hg (SD 10.9), and 73.1% were on ≥3 medications. Compared with trabeculectomy, tube shunt surgery had a higher risk of failure (Baerveldt: Hazard Ratio (HR) 1.44, 95% CI 1.02 to 2.02; Ahmed: HR 2.01, 95% CI 1.28 to 3.17). Previous glaucoma surgery was associated with increased failure (≥2 previous surgeries: HR 2.74, 95% CI 1.62 to 4.64), as were fewer baseline medications (<3 medications: HR 2.96, 95% CI 2.12 to 4.13) and male sex (HR 1.40, 95% CI 1.03 to 1.90). At 1 year, tube shunt patients had a 2.53 mm Hg ( P =0.002) higher IOP compared with trabeculectomy patients.
Baerveldt and Ahmed tube shunt implantation was associated with increased failure compared with trabeculectomy. Fewer baseline medications, previous glaucoma surgeries, and male sex were also risk factors for failure. These results demonstrate the utility of applying an informatics pipeline to electronic health records to investigate key clinical questions using real-world evidence.