当前位置: X-MOL 学术Neurosurgery › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Commentary: Machine Learning With Feature Domains Elucidates Candidate Drivers of Hospital Readmission Following Spine Surgery in a Large Single-Center Patient Cohort.
Neurosurgery ( IF 3.9 ) Pub Date : 2020-05-23 , DOI: 10.1093/neuros/nyaa209
Rafael De la Garza Ramos 1, 2 , Reza Yassari 1, 2
Affiliation  

Unplanned hospital readmissions comp-rise a significant cost burden in our current healthcare system, with an average readmission cost of $14 400 for any diagnosis—national estimates are over 40 billion per year.1,2 For patients undergoing spinal surgery, studies have estimated unplanned readmissions to occur in 4.2% to 7.3% of patients.3-5 In addition, there is evidence that readmitted patients experience less improvement in health-related quality-of-outcome scores compared to nonreadmitted patients.6 Given this significant impact, the Hospital Readmissions Reduction Program (HRRP) was developed in 2012 to penalize hospitals for excessive readmissions.7 As of 2017, an estimated 80% of hospitals in the United States were impacted to some extent by this program.8

中文翻译:

评论:具有特征域的机器学习阐明了大型单中心患者队列中脊柱手术后医院再次入院的候选驱动因素。

计划外的住院再住院在我们当前的医疗保健系统中构成了巨大的成本负担,任何诊断的平均再住院费用为14400美元-全国估计每年超过400亿美元。1,2对于接受脊柱外科手术的患者,研究估计有4.2%至7.3%的患者计划外再次入院。3-5此外,有证据表明,与未再入院的患者相比,再入院的患者与健康相关的结果质量得分的改善较少。6鉴于这一重大影响,2012年制定了减少医院再入院计划(HRRP),以惩罚医院因过高的再入院率。7截至2017年,美国估计有80%的医院在一定程度上受到了该计划的影响。8
更新日期:2020-05-23
down
wechat
bug