• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

使用计算建模预防多病种患者的非计划性住院:观察性回顾性队列研究。

Prevention of Unplanned Hospital Admissions in Multimorbid Patients Using Computational Modeling: Observational Retrospective Cohort Study.

机构信息

Hospital Clínic de Barcelona, Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Universitat de Barcelona, Barcelona, Spain.

Consorci d'Atenció Primària de Salut Barcelona Esquerra (CAPSBE), Primary Healthcare Transversal Research Group, Institut d'Investigacions Biomèdiques August Pi i Sunyer (IDIBAPS), Barcelona, Spain.

出版信息

J Med Internet Res. 2023 Feb 16;25:e40846. doi: 10.2196/40846.

DOI:10.2196/40846
PMID:36795471
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9982720/
Abstract

BACKGROUND

Enhanced management of multimorbidity constitutes a major clinical challenge. Multimorbidity shows well-established causal relationships with the high use of health care resources and, specifically, with unplanned hospital admissions. Enhanced patient stratification is vital for achieving effectiveness through personalized postdischarge service selection.

OBJECTIVE

The study has a 2-fold aim: (1) generation and assessment of predictive models of mortality and readmission at 90 days after discharge; and (2) characterization of patients' profiles for personalized service selection purposes.

METHODS

Gradient boosting techniques were used to generate predictive models based on multisource data (registries, clinical/functional and social support) from 761 nonsurgical patients admitted in a tertiary hospital over 12 months (October 2017 to November 2018). K-means clustering was used to characterize patient profiles.

RESULTS

Performance (area under the receiver operating characteristic curve, sensitivity, and specificity) of the predictive models was 0.82, 0.78, and 0.70 and 0.72, 0.70, and 0.63 for mortality and readmissions, respectively. A total of 4 patients' profiles were identified. In brief, the reference patients (cluster 1; 281/761, 36.9%), 53.7% (151/281) men and mean age of 71 (SD 16) years, showed 3.6% (10/281) mortality and 15.7% (44/281) readmissions at 90 days following discharge. The unhealthy lifestyle habit profile (cluster 2; 179/761, 23.5%) predominantly comprised males (137/179, 76.5%) with similar age, mean 70 (SD 13) years, but showed slightly higher mortality (10/179, 5.6%) and markedly higher readmission rate (49/179, 27.4%). Patients in the frailty profile (cluster 3; 152/761, 19.9%) were older (mean 81 years, SD 13 years) and predominantly female (63/152, 41.4%, males). They showed medical complexity with a high level of social vulnerability and the highest mortality rate (23/152, 15.1%), but with a similar hospitalization rate (39/152, 25.7%) compared with cluster 2. Finally, the medical complexity profile (cluster 4; 149/761, 19.6%), mean age 83 (SD 9) years, 55.7% (83/149) males, showed the highest clinical complexity resulting in 12.8% (19/149) mortality and the highest readmission rate (56/149, 37.6%).

CONCLUSIONS

The results indicated the potential to predict mortality and morbidity-related adverse events leading to unplanned hospital readmissions. The resulting patient profiles fostered recommendations for personalized service selection with the capacity for value generation.

摘要

背景

对多种疾病的强化管理是一项重大的临床挑战。多种疾病与医疗资源的大量使用有着明确的因果关系,特别是与非计划性住院有关。为了通过个性化的出院后服务选择实现效果,对患者进行分层至关重要。

目的

本研究有两个目的:(1)生成和评估出院后 90 天内死亡率和再入院率的预测模型;(2)为个性化服务选择目的对患者特征进行分类。

方法

使用梯度提升技术基于 761 名非手术患者的多源数据(来自登记处、临床/功能和社会支持)生成预测模型,这些患者在一家三级医院住院 12 个月(2017 年 10 月至 2018 年 11 月)。使用 K-均值聚类对患者特征进行分类。

结果

预测模型的性能(接收者操作特征曲线下的面积、敏感性和特异性)为 0.82、0.78 和 0.70 以及 0.72、0.70 和 0.63 分别用于死亡率和再入院率。共确定了 4 种患者特征。简而言之,参考患者(第 1 组;761 例患者中的 281 例,36.9%),53.7%(281 例中的 151 例)为男性,平均年龄为 71 岁(标准差为 16 岁),出院后 90 天的死亡率为 3.6%(281 例中的 10 例),再入院率为 15.7%(281 例中的 44 例)。不健康生活方式习惯特征(第 2 组;761 例患者中的 179 例,23.5%)主要由男性(179 例中的 137 例,76.5%)组成,年龄相似,平均为 70 岁(标准差为 13 岁),但死亡率略高(179 例中的 10 例,5.6%),再入院率明显更高(179 例中的 49 例,27.4%)。衰弱特征患者(第 3 组;761 例患者中的 152 例,19.9%)年龄较大(平均 81 岁,标准差 13 岁),主要为女性(152 例中的 63 例,41.4%,男性)。他们表现出较高的医疗复杂性,具有较高的社会脆弱性,死亡率最高(152 例中的 23 例,15.1%),但与第 2 组相比,住院率相似(152 例中的 39 例,25.7%)。最后,医疗复杂性特征(第 4 组;761 例患者中的 149 例,19.6%),平均年龄 83 岁(标准差 9 岁),55.7%(149 例中的 83 例)为男性,表现出最高的临床复杂性,导致 12.8%(149 例中的 19 例)的死亡率和最高的再入院率(149 例中的 56 例,37.6%)。

结论

结果表明有可能预测导致非计划性住院再入院的死亡率和发病率相关不良事件。由此产生的患者特征促进了个性化服务选择的建议,具有产生价值的能力。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d9c9/9982720/edb60dd9df11/jmir_v25i1e40846_fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d9c9/9982720/39bbd207dc98/jmir_v25i1e40846_fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d9c9/9982720/b72041448216/jmir_v25i1e40846_fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d9c9/9982720/edb60dd9df11/jmir_v25i1e40846_fig3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d9c9/9982720/39bbd207dc98/jmir_v25i1e40846_fig1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d9c9/9982720/b72041448216/jmir_v25i1e40846_fig2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d9c9/9982720/edb60dd9df11/jmir_v25i1e40846_fig3.jpg

相似文献

1
Prevention of Unplanned Hospital Admissions in Multimorbid Patients Using Computational Modeling: Observational Retrospective Cohort Study.使用计算建模预防多病种患者的非计划性住院:观察性回顾性队列研究。
J Med Internet Res. 2023 Feb 16;25:e40846. doi: 10.2196/40846.
2
Unplanned 30-day readmissions, comorbidity and impact on one-year mortality following incident heart failure hospitalisation in Western Australia, 2001-2015.2001-2015 年澳大利亚西部因心力衰竭入院的患者中,30 天内非计划性再入院、合并症及对一年死亡率的影响。
BMC Cardiovasc Disord. 2023 Jan 16;23(1):25. doi: 10.1186/s12872-022-03020-x.
3
Readmissions and postdischarge mortality by race and ethnicity among Medicare beneficiaries with multimorbidity.医疗保险多重疾病患者的种族和民族对再入院和出院后死亡率的影响。
J Am Geriatr Soc. 2023 Jun;71(6):1749-1758. doi: 10.1111/jgs.18251. Epub 2023 Jan 27.
4
Predictive modeling for 14-day unplanned hospital readmission risk by using machine learning algorithms.基于机器学习算法的 14 天内非计划性住院再入院风险预测模型。
BMC Med Inform Decis Mak. 2021 Oct 20;21(1):288. doi: 10.1186/s12911-021-01639-y.
5
Unplanned readmission prevention by a geriatric emergency network for transitional care (URGENT): a prospective before-after study.老年急诊网络进行过渡性护理以预防非计划性再入院(URGENT):一项前瞻性前后对照研究。
BMC Geriatr. 2019 Aug 7;19(1):215. doi: 10.1186/s12877-019-1233-9.
6
Multimorbidity and prior falls correlate with risk of 30-day hospital readmission in aged 80+: A prospective cohort study.80 岁及以上老年人多病共存和既往跌倒与 30 天内再次住院风险相关:一项前瞻性队列研究。
J Formos Med Assoc. 2023 Nov;122(11):1111-1116. doi: 10.1016/j.jfma.2023.03.009. Epub 2023 Mar 27.
7
Evaluation of an intervention targeted with predictive analytics to prevent readmissions in an integrated health system: observational study.基于预测分析的干预措施评估,以预防综合卫生系统中的再入院:观察性研究。
BMJ. 2021 Aug 11;374:n1747. doi: 10.1136/bmj.n1747.
8
Effects of a home-based intervention among patients with congestive heart failure discharged from acute hospital care.急性医院护理出院的充血性心力衰竭患者居家干预的效果
Arch Intern Med. 1998 May 25;158(10):1067-72. doi: 10.1001/archinte.158.10.1067.
9
Applying the Integrated Practice Unit Concept to a Modified Virtual Ward Model of Care for Patients at Highest Risk of Readmission: A Randomized Controlled Trial.将综合实践单元概念应用于针对再入院风险最高患者的改良虚拟病房护理模式:一项随机对照试验。
PLoS One. 2017 Jan 3;12(1):e0168757. doi: 10.1371/journal.pone.0168757. eCollection 2017.
10
Avoidable readmission in Hong Kong--system, clinician, patient or social factor?香港可避免的再入院——制度、临床医生、患者还是社会因素?
BMC Health Serv Res. 2010 Nov 17;10:311. doi: 10.1186/1472-6963-10-311.

引用本文的文献

1
Strategies to Reduce Hospital Length of Stay: Evidence and Challenges.缩短住院时间的策略:证据与挑战
Medicina (Kaunas). 2025 May 20;61(5):922. doi: 10.3390/medicina61050922.
2
Protocol for the enhanced management of multimorbid patients with COPD and severe asthma: role of indoor air quality.慢性阻塞性肺疾病(COPD)和重度哮喘合并症患者强化管理方案:室内空气质量的作用
BMJ Open Respir Res. 2025 Jan 20;12(1):e002589. doi: 10.1136/bmjresp-2024-002589.
3
Toward Sustainable Adoption of Integrated Care for Prevention of Unplanned Hospitalizations: A Qualitative Analysis.

本文引用的文献

1
Prospective cohort study for assessment of integrated care with a triple aim approach: hospital at home as use case.前瞻性队列研究评估以三重目标方法为基础的整合照护:以医院到家为例。
BMC Health Serv Res. 2022 Sep 7;22(1):1133. doi: 10.1186/s12913-022-08496-z.
2
Performance of Three Measures of Comorbidity in Predicting Critical COVID-19: A Retrospective Analysis of 4607 Hospitalized Patients.三种合并症测量方法在预测重症新型冠状病毒肺炎中的表现:对4607例住院患者的回顾性分析
Risk Manag Healthc Policy. 2021 Nov 23;14:4729-4737. doi: 10.2147/RMHP.S326132. eCollection 2021.
3
Characteristics and Service Utilization by Complex Chronic and Advanced Chronic Patients in Catalonia: A Retrospective Seven-Year Cohort-Based Study of an Implemented Chronic Care Program.
迈向可持续采用综合护理以预防非计划住院:一项定性分析。
Int J Integr Care. 2024 Jun 28;24(2):28. doi: 10.5334/ijic.7724. eCollection 2024 Apr-Jun.
4
Multicentric Assessment of a Multimorbidity-Adjusted Disability Score to Stratify Depression-Related Risks Using Temporal Disease Maps: Instrument Validation Study.基于时间疾病图谱的多中心评估调整多种疾病的残疾评分对抑郁相关风险的分层:仪器验证研究。
J Med Internet Res. 2024 Jun 24;26:e53162. doi: 10.2196/53162.
5
Toward Adoption of Health Risk Assessment in Population-Based and Clinical Scenarios: Lessons From JADECARE.迈向在基于人群和临床场景中采用健康风险评估:来自JADECARE的经验教训。
Int J Integr Care. 2024 Jun 4;24(2):23. doi: 10.5334/ijic.7701. eCollection 2024 Apr-Jun.
6
The value of admission avoidance: cost-consequence analysis of one-year activity in a consolidated service.避免入院的价值:综合服务机构一年活动的成本效益分析
Cost Eff Resour Alloc. 2024 Apr 15;22(1):30. doi: 10.1186/s12962-024-00536-1.
加泰罗尼亚复杂慢性和晚期慢性患者的特征和服务利用情况:实施慢性护理计划的回顾性七年队列研究。
Int J Environ Res Public Health. 2021 Sep 8;18(18):9473. doi: 10.3390/ijerph18189473.
4
Digital Support to Multimodal Community-Based Prehabilitation: Looking for Optimization of Health Value Generation.对基于社区的多模式预康复的数字支持:寻求健康价值生成的优化
Front Oncol. 2021 Jun 17;11:662013. doi: 10.3389/fonc.2021.662013. eCollection 2021.
5
Postoperative Home Monitoring After Joint Replacement: Feasibility Study.关节置换术后的家庭监测:可行性研究
JMIR Perioper Med. 2018 Sep 5;1(2):e10168. doi: 10.2196/10168.
6
Health Outcomes from Home Hospitalization: Multisource Predictive Modeling.家庭住院的健康结果:多源预测建模。
J Med Internet Res. 2020 Oct 7;22(10):e21367. doi: 10.2196/21367.
7
Predicting 30-day hospital readmissions using artificial neural networks with medical code embedding.利用医学编码嵌入的人工神经网络预测 30 天内的医院再入院率。
PLoS One. 2020 Apr 15;15(4):e0221606. doi: 10.1371/journal.pone.0221606. eCollection 2020.
8
Performance of Comprehensive Risk Adjustment for the Prediction of In-Hospital Events Using Administrative Healthcare Data: The Queralt Indices.利用行政医疗保健数据进行综合风险调整以预测住院事件的性能:夸拉特指数
Risk Manag Healthc Policy. 2020 Mar 26;13:271-283. doi: 10.2147/RMHP.S228415. eCollection 2020.
9
Multimorbidity as a predictor of health service utilization in primary care: a registry-based study of the Catalan population.多病共存作为初级保健中卫生服务利用的预测因素:基于登记的加泰罗尼亚人群研究。
BMC Fam Pract. 2020 Feb 17;21(1):39. doi: 10.1186/s12875-020-01104-1.
10
Class Imbalance Impact on the Prediction of Complications during Home Hospitalization: A Comparative Study.类不平衡对家庭住院期间并发症预测的影响:一项比较研究
Annu Int Conf IEEE Eng Med Biol Soc. 2019 Jul;2019:3446-3449. doi: 10.1109/EMBC.2019.8857746.