Individualized Prospective Prediction of Opioid Use Disorder.

Individualized Prospective Prediction of Opioid Use Disorder.
复制标题

DOI:
10.1177/07067437221114094
复制
发表时间:
2023-01
影响因子:
4
通讯作者:
Cao, Bo
Cao, Bo
中科院分区:
医学3区
文献类型:
--
作者:
Liu, Yang S.;Kiyang, Lawrence;Hayward, Jake;Zhang, Yanbo;Metes, Dan;Wang, Mengzhe;Svenson, Lawrence W.;Talarico, Fernanda;Chue, Pierre;Li, Xin-Min;Greiner, Russell;Greenshaw, Andrew J.;Cao, Bo

文献摘要

参考文献

被引文献

相似文献

阿片使用障碍(OUD)是一种慢性复发性障碍,阿片类药物的使用模式存在问题,全世界有近2700万人受到影响。基于机器学习(ML)的OUD预测可能导致早期发现和干预。然而,大多数ML预测研究并不是基于有代表性的数据源和前瞻性验证,限制了它们预测未来新病例的潜力。在目前的研究中,我们的目标是开发并前瞻性地验证ML模型,该模型可以基于具有代表性的大规模健康数据来预测单个OUD病例。我们提出了一个在2014年至2018年交叉链接的加拿大行政健康数据集(n  =  699,164)上训练的集成机器学习模型,并在2014年至2018年的坚持样本(n  =  174,791)上验证了模型预测的OUD病例(n  =  174,791),并在2019年非重叠样本上对OUD病例进行了预期预测(n  =  316,039)。我们根据国际疾病分类(ICD)代码为每个受试者使用OUD诊断的行政记录。2019年有6409例OUD病例(平均[SD],45.34[14.28],3400名男性),我们的模型前瞻性地预测了OUD病例的高准确性(平衡准确率,86%,敏感度,93%,特异度79%)。与先前的发现一致,在这个模型中,OUD的最大风险因素是阿片类药物使用指标和其他物质使用障碍的病史。我们的研究通过将最大似然法应用于大型行政健康数据集,提出了对OUD病例的个性化前瞻性预测。这种基于ML的前瞻性预测对于未来在OUD早期检测方面的潜在临床应用是必不可少的。
Opioid use disorder (OUD) is a chronic relapsing disorder with a problematic pattern of opioid use, affecting nearly 27 million people worldwide. Machine learning (ML)-based prediction of OUD may lead to early detection and intervention. However, most ML prediction studies were not based on representative data sources and prospective validations, limiting their potential to predict future new cases. In the current study, we aimed to develop and prospectively validate an ML model that could predict individual OUD cases based on representative large-scale health data. We present an ensemble machine-learning model trained on a cross-linked Canadian administrative health data set from 2014 to 2018 (n  =  699,164), with validation of model-predicted OUD cases on a hold-out sample from 2014 to 2018 (n  =  174,791) and prospective prediction of OUD cases on a non-overlapping sample from 2019 (n  =  316,039). We used administrative records of OUD diagnosis for each subject based on International Classification of Diseases (ICD) codes. With 6409 OUD cases in 2019 (mean [SD], 45.34 [14.28], 3400 males), our model prospectively predicted OUD cases at a high accuracy (balanced accuracy, 86%, sensitivity, 93%; specificity 79%). In accord with prior findings, the top risk factors for OUD in this model were opioid use indicators and a history of other substance use disorders. Our study presents an individualized prospective prediction of OUD cases by applying ML to large administrative health datasets. Such prospective predictions based on ML would be essential for potential future clinical applications in the early detection of OUD.
DOI: 10.1186/s12916-018-1058-y
发表时间: 2018-05-16
期刊: BMC medicine
影响因子: 9.3
作者:
Chang HY;Kharrazi H;Bodycombe D;Weiner JP;Alexander GC
通讯作者: Alexander GC
DOI: 10.1186/s13722-021-00229-7
发表时间: 2021-03-17
影响因子: 3.7
作者:
Afshar M;Sharma B;Bhalla S;Thompson HM;Dligach D;Boley RA;Kishen E;Simmons A;Perticone K;Karnik NS
通讯作者: Karnik NS
DOI: 10.1016/s0140-6736(19)32229-9
发表时间: 2019-10-26
期刊: LANCET
影响因子: 168.9
作者:
Degenhardt, Louisa;Grebely, Jason;Larney, Sarah
通讯作者: Larney, Sarah
DOI: 10.1097/mlr.0000000000000625
发表时间: 2016-10
期刊: Medical care
影响因子: 3
作者:
Florence CS;Zhou C;Luo F;Xu L
通讯作者: Xu L
DOI: 10.1073/pnas.1905355117
发表时间: 2020-01-28
影响因子: 11.1
作者:
Hastings, Justine S.;Howison, Mark;Inman, Sarah E.
通讯作者: Inman, Sarah E.