SUpPress SSI - Single Use Negative Pressure Wound Therapy (NPWT) to Reduce Surgical Site Infections

SUpPress SSI -一次性负压伤口治疗（NPWT），以减少手术部位 感染 拟议工作具体目标1是评价一次性NPWT对C- 高危患者的剖腹产、腹式子宫切除术和结肠手术。为了实现这一目标，我们将 进行一项多中心、阶梯楔形、准实验性试验，评估125 mm 接受手术的肥胖（BMI >30）和/或糖尿病患者中持续7天的Hg负压 感兴趣这是一项评价一次性NPWT对高风险患者SSI发生率的影响的有效性试验 患者使用随机阶梯楔形设计。将包括六家中心医院： 伊利诺伊医院（UIH）、爱荷华州大学医院和诊所（UIHC）、犹他州大学医院（UUH）、 埃默里大学医院（EUHM）、格雷迪纪念医院（GMH）和马里兰州大学 医疗中心（UMMC）。如果SSI发生率的拟议改善得到证实， 使用NPWT的指导。 具体目标2是调查患者使用NPWT的经验。一组患者将 调查以评估其术后护理知识，识别与NPWT相关的并发症 使用，并了解患者如何评价该器械的易用性、易移除性和舒适性。这将 查明执行障碍。 具体目标3是评估通过机器学习建模的实时决策支持是否可以 帮助外科医生识别SSI高风险患者，这些患者可以从NWPT或其他术后治疗中获益 预防措施这将评估是否可以使用提升树建模技术“在 通过电子医疗记录数据馈送，为特定患者定制术后护理和预防护理， 患者将对参与的医院进行调查，以评估他们是否准备好向数据集市提交数据。我们 将依次为每家医院建立数据馈送。将从数据集市中为SSI构建一个模型， NPWT可以预防。通过这种方式，它将细化模型对这一具体问题的预测价值。 干预使用这种建模将有助于最大限度地为患者提供更个性化的护理计划。 SSI风险。

SUpPress SSI – Single Use Negative Pressure Wound Therapy (NPWT) to Reduce Surgical Site Infections The proposed work Specific Aim 1 is to evaluate the effect of single-use NPWT on SSI rates after C- section, abdominal hysterectomy, and colon procedures in at risk patients. To address this aim, we will conduct a multicenter, stepped-wedge, quasi-experimental trial evaluating use of the PrevenaTM with 125 mm Hg negative pressure for 7 days among obese (BMI >30) and/or diabetic patients undergoing the procedures of interest. This is an effectiveness trial evaluating the effect of single-use NPWT on SSI rates among high-risk patients using a randomized stepped wedge design. Six Epicenter hospitals will be included: University of Illinois Hospital (UIH), University of Iowa Hospital and Clinics (UIHC), University of Utah Hospital (UUH), Emory University Hospital Midtown (EUHM), Grady Memorial Hospital (GMH), and University of Maryland Medical Center (UMMC). If proposed improvement in SSI rates are demonstrated this will provide more clear guidance for the use of the NPWT. Specific Aim 2 is to investigate the patients’ experience of using the NPWT. A sub-set of patients will be surveyed to assess their knowledge of post-operative care, to identify complications associated with NPWT use, and to learn how patients evaluated the device’s ease of use, ease of removal, and comfort. This will identify barriers to implementation. Specific Aim 3 is to assess whether real-time decision support through machine-learning modeling can help surgeons identify patients at high risk of SSI who could benefit from NWPT or other post-surgical preventive measures. This will evaluate whether boosted tree modeling techniques can be used “at the bedside” via electronic medical record data feeds to tailor post-operative care and preventive care for specific patients. Participating hospitals will be surveyed to assess their readiness to submit data to the datamart. We will sequentially establish the data feed for each hospital. From the datamart a model will be built for SSIs that could be prevented by the NPWT. In this way, it will refine the predictive value of the model for this specific intervention. The use of this modeling will help provide more personalized care plans for patients at greatest risk of SSI.