• 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

在临床机器学习开发中拥抱队列异质性:迈向可推广模型的一步。

Embracing cohort heterogeneity in clinical machine learning development: a step toward generalizable models.

机构信息

Center for Experimental and Molecular Medicine (CEMM), Location Academic Medical Center, Amsterdam UMC Location University of Amsterdam, Meibergdreef 9, 1105 AZ, Amsterdam, The Netherlands.

Quantitative Data Analytics Group, Department of Computer Science, Vrije Universiteit Amsterdam, De Boelelaan 1105, Amsterdam, The Netherlands.

出版信息

Sci Rep. 2023 May 24;13(1):8363. doi: 10.1038/s41598-023-35557-y.

DOI:10.1038/s41598-023-35557-y
PMID:37225751
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10209202/
Abstract

This study is a simple illustration of the benefit of averaging over cohorts, rather than developing a prediction model from a single cohort. We show that models trained on data from multiple cohorts can perform significantly better in new settings than models based on the same amount of training data but from just a single cohort. Although this concept seems simple and obvious, no current prediction model development guidelines recommend such an approach.

摘要

本研究简单说明了对队列进行平均化的益处,而不是从单个队列中开发预测模型。我们表明,从多个队列的数据中训练出的模型在新环境中的表现明显优于基于相同数量训练数据但仅来自单个队列的模型。虽然这个概念似乎很简单且显而易见,但目前没有预测模型开发指南推荐这种方法。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9582/10209202/a28be7ef230b/41598_2023_35557_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9582/10209202/2c5acb4dd7ce/41598_2023_35557_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9582/10209202/a28be7ef230b/41598_2023_35557_Fig2_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9582/10209202/2c5acb4dd7ce/41598_2023_35557_Fig1_HTML.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9582/10209202/a28be7ef230b/41598_2023_35557_Fig2_HTML.jpg

相似文献

1
Embracing cohort heterogeneity in clinical machine learning development: a step toward generalizable models.在临床机器学习开发中拥抱队列异质性:迈向可推广模型的一步。
Sci Rep. 2023 May 24;13(1):8363. doi: 10.1038/s41598-023-35557-y.
2
Outcome prediction of intracranial aneurysm treatment by flow diverters using machine learning.使用机器学习对颅内动脉瘤血管内治疗的结果预测。
Neurosurg Focus. 2018 Nov 1;45(5):E7. doi: 10.3171/2018.8.FOCUS18332.
3
Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven, Machine Learning Approach.急诊科脓毒症患者院内死亡率的预测:一种基于本地大数据驱动的机器学习方法。
Acad Emerg Med. 2016 Mar;23(3):269-78. doi: 10.1111/acem.12876. Epub 2016 Feb 13.
4
Explainable machine learning for chronic lymphocytic leukemia treatment prediction using only inexpensive tests.仅使用廉价检测指标进行慢性淋巴细胞白血病治疗预测的可解释机器学习
Comput Biol Med. 2022 Jun;145:105490. doi: 10.1016/j.compbiomed.2022.105490. Epub 2022 Apr 6.
5
An Assessment of the Predictive Performance of Current Machine Learning-Based Breast Cancer Risk Prediction Models: Systematic Review.基于当前机器学习的乳腺癌风险预测模型的预测性能评估:系统评价。
JMIR Public Health Surveill. 2022 Dec 29;8(12):e35750. doi: 10.2196/35750.
6
Machine learning approaches for prediction of early death among lung cancer patients with bone metastases using routine clinical characteristics: An analysis of 19,887 patients.利用常规临床特征预测肺癌伴骨转移患者早期死亡的机器学习方法:对 19887 例患者的分析。
Front Public Health. 2022 Oct 6;10:1019168. doi: 10.3389/fpubh.2022.1019168. eCollection 2022.
7
Prediction of Maternal Hemorrhage Using Machine Learning: Retrospective Cohort Study.利用机器学习预测产妇出血:回顾性队列研究。
J Med Internet Res. 2022 Jul 18;24(7):e34108. doi: 10.2196/34108.
8
Machine Learning-based Prediction Models for Diagnosis and Prognosis in Inflammatory Bowel Diseases: A Systematic Review.基于机器学习的炎症性肠病诊断和预后预测模型:系统评价。
J Crohns Colitis. 2022 Mar 14;16(3):398-413. doi: 10.1093/ecco-jcc/jjab155.
9
Cohort-Derived Machine Learning Models for Individual Prediction of Chronic Kidney Disease in People Living With Human Immunodeficiency Virus: A Prospective Multicenter Cohort Study.队列研究衍生的机器学习模型在人类免疫缺陷病毒感染者中对慢性肾脏病的个体预测:一项前瞻性多中心队列研究。
J Infect Dis. 2021 Oct 13;224(7):1198-1208. doi: 10.1093/infdis/jiaa236.
10
Assessing the effects of data drift on the performance of machine learning models used in clinical sepsis prediction.评估数据漂移对临床脓毒症预测中使用的机器学习模型性能的影响。
Int J Med Inform. 2023 May;173:104930. doi: 10.1016/j.ijmedinf.2022.104930. Epub 2022 Nov 19.

引用本文的文献

1
Electroencephalogram features support the retrogenesis hypothesis of Alzheimer's disease: Exploratory comparison of brain changes in aging and childhood.脑电图特征支持阿尔茨海默病的逆向发生假说:衰老与儿童期大脑变化的探索性比较。
J Alzheimers Dis. 2025 Jun 30;106(4):13872877251352119. doi: 10.1177/13872877251352119.
2
The Transition From Homogeneous to Heterogeneous Machine Learning in Neuropsychiatric Research.神经精神医学研究中从同质机器学习到异质机器学习的转变
Biol Psychiatry Glob Open Sci. 2024 Sep 26;5(1):100397. doi: 10.1016/j.bpsgos.2024.100397. eCollection 2025 Jan.
3
Risk-Specific Training Cohorts to Address Class Imbalance in Surgical Risk Prediction.

本文引用的文献

1
Diagnostic stewardship for blood cultures in the emergency department: A multicenter validation and prospective evaluation of a machine learning prediction tool.急诊科血培养的诊断管理:机器学习预测工具的多中心验证和前瞻性评估。
EBioMedicine. 2022 Aug;82:104176. doi: 10.1016/j.ebiom.2022.104176. Epub 2022 Jul 16.
2
External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients.在住院患者中验证广泛实施的专有脓毒症预测模型的外部有效性。
JAMA Intern Med. 2021 Aug 1;181(8):1065-1070. doi: 10.1001/jamainternmed.2021.2626.
3
The Epic Sepsis Model Falls Short-The Importance of External Validation.
针对手术风险预测中类别不平衡问题的特定风险训练队列
JAMA Surg. 2024 Dec 1;159(12):1424-1431. doi: 10.1001/jamasurg.2024.4299.
“脓毒症的史诗模型”存在不足——外部验证的重要性。
JAMA Intern Med. 2021 Aug 1;181(8):1040-1041. doi: 10.1001/jamainternmed.2021.3333.
4
Developing more generalizable prediction models from pooled studies and large clustered data sets.从汇集的研究和大型聚类数据集开发更具通用性的预测模型。
Stat Med. 2021 Jul 10;40(15):3533-3559. doi: 10.1002/sim.8981. Epub 2021 May 5.
5
Assessment of heterogeneity in an individual participant data meta-analysis of prediction models: An overview and illustration.个体参与者数据荟萃分析中预测模型异质性的评估:概述和实例。
Stat Med. 2019 Sep 30;38(22):4290-4309. doi: 10.1002/sim.8296. Epub 2019 Aug 2.
6
Predictive analytics in health care: how can we know it works?医疗保健中的预测分析:我们如何知道它是否有效?
J Am Med Inform Assoc. 2019 Dec 1;26(12):1651-1654. doi: 10.1093/jamia/ocz130.
7
High-performance medicine: the convergence of human and artificial intelligence.高性能医学:人机智能融合。
Nat Med. 2019 Jan;25(1):44-56. doi: 10.1038/s41591-018-0300-7. Epub 2019 Jan 7.