手术治疗后过度分诊、分诊不足与护理价值：一种自动化、可解释的深度学习赋能分类系统。

Overtriage, Undertriage, and Value of Care after Major Surgery: An Automated, Explainable Deep Learning-Enabled Classification System.

机构信息

From the University of Florida Intelligent Critical Care Center, Gainesville, FL (Loftus, Ruppert, Shickel, Ozrazgat-Baslanti, Balch, Hu, Rashidi, Bihorac).

Departments of Surgery (Loftus, Balch, Hu, Efron, Upchurch, Bihorac), University of Florida Health, Gainesville, FL.

出版信息

J Am Coll Surg. 2023 Feb 1;236(2):279-291. doi: 10.1097/XCS.0000000000000471. Epub 2022 Nov 8.

DOI:10.1097/XCS.0000000000000471

PMID:36648256

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9993068/

Abstract

BACKGROUND

In single-institution studies, overtriaging low-risk postoperative patients to ICUs has been associated with a low value of care; undertriaging high-risk postoperative patients to general wards has been associated with increased mortality and morbidity. This study tested the reproducibility of an automated postoperative triage classification system to generating an actionable, explainable decision support system.

STUDY DESIGN

This longitudinal cohort study included adults undergoing inpatient surgery at two university hospitals. Triage classifications were generated by an explainable deep learning model using preoperative and intraoperative electronic health record features. Nearest neighbor algorithms identified risk-matched controls. Primary outcomes were mortality, morbidity, and value of care (inverted risk-adjusted mortality/total direct costs).

RESULTS

Among 4,669 ICU admissions, 237 (5.1%) were overtriaged. Compared with 1,021 control ward admissions, overtriaged admissions had similar outcomes but higher costs ($15.9K [interquartile range $9.8K to $22.3K] vs $10.7K [$7.0K to $17.6K], p < 0.001) and lower value of care (0.2 [0.1 to 0.3] vs 1.5 [0.9 to 2.2], p < 0.001). Among 8,594 ward admissions, 1,029 (12.0%) were undertriaged. Compared with 2,498 control ICU admissions, undertriaged admissions had longer hospital length-of-stays (6.4 [3.4 to 12.4] vs 5.4 [2.6 to 10.4] days, p < 0.001); greater incidence of hospital mortality (1.7% vs 0.7%, p = 0.03), cardiac arrest (1.4% vs 0.5%, p = 0.04), and persistent acute kidney injury without renal recovery (5.2% vs 2.8%, p = 0.002); similar costs ($21.8K [$13.3K to $34.9K] vs $21.9K [$13.1K to $36.3K]); and lower value of care (0.8 [0.5 to 1.3] vs 1.2 [0.7 to 2.0], p < 0.001).

CONCLUSIONS

Overtriage was associated with low value of care; undertriage was associated with both low value of care and increased mortality and morbidity. The proposed framework for generating automated postoperative triage classifications is reproducible.

摘要

背景

在单机构研究中，将低风险术后患者过度分诊到 ICU 与护理价值较低有关；将高风险术后患者分诊到普通病房与死亡率和发病率增加有关。本研究测试了一种自动术后分诊分类系统生成可操作、可解释的决策支持系统的重现性。

研究设计

这项纵向队列研究纳入了在两家大学医院接受住院手术的成年人。术前和术中电子健康记录特征使用可解释的深度学习模型生成分诊分类。最近邻算法确定了风险匹配的对照组。主要结局是死亡率、发病率和护理价值（风险调整后死亡率/总直接成本的倒数）。

结果

在 4669 例 ICU 入院中，237 例（5.1%）为过度分诊。与 1021 例普通病房入院相比，过度分诊的入院患者具有相似的结局，但费用更高（15900 美元[四分位距 9800 美元至 22300 美元] vs. 10700 美元[7000 美元至 17600 美元]，p < 0.001），护理价值更低（0.2 [0.1 至 0.3] vs. 1.5 [0.9 至 2.2]，p < 0.001）。在 8594 例病房入院中，1029 例（12.0%）为分诊不足。与 2498 例普通 ICU 入院相比，分诊不足的入院患者的住院时间更长（6.4 [3.4 至 12.4] 天 vs. 5.4 [2.6 至 10.4] 天，p < 0.001）；住院死亡率（1.7% vs. 0.7%，p = 0.03）、心脏骤停（1.4% vs. 0.5%，p = 0.04）和持续急性肾损伤无肾功能恢复（5.2% vs. 2.8%，p = 0.002）的发生率更高；费用相似（21800 美元[13300 美元至 34900 美元] vs. 21900 美元[13100 美元至 36300 美元]）；护理价值更低（0.8 [0.5 至 1.3] vs. 1.2 [0.7 至 2.0]，p < 0.001）。