دورية أكاديمية
أعرض في EDS

Development and validation of a patient-level model to predict dementia across a network of observational databases.

التفاصيل البيبلوغرافية
العنوان: Development and validation of a patient-level model to predict dementia across a network of observational databases.
المؤلفون: John LH; Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands. l.john@erasmusmc.nl., Fridgeirsson EA; Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands., Kors JA; Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands., Reps JM; Janssen Research and Development, Raritan, NJ, USA., Williams RD; Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands., Ryan PB; Janssen Research and Development, Raritan, NJ, USA., Rijnbeek PR; Department of Medical Informatics, Erasmus University Medical Center, Rotterdam, The Netherlands.
المصدر: BMC medicine [BMC Med] 2024 Jul 29; Vol. 22 (1), pp. 308. Date of Electronic Publication: 2024 Jul 29.
نوع المنشور: Journal Article; Validation Study
اللغة: English
بيانات الدورية: Publisher: BioMed Central Country of Publication: England NLM ID: 101190723 Publication Model: Electronic Cited Medium: Internet ISSN: 1741-7015 (Electronic) Linking ISSN: 17417015 NLM ISO Abbreviation: BMC Med Subsets: MEDLINE
أسماء مطبوعة: Original Publication: [London] : BioMed Central, 2003-
مواضيع طبية MeSH: Dementia*/diagnosis , Dementia*/epidemiology , Databases, Factual*, Humans ; Aged ; Female ; Male ; Aged, 80 and over ; Middle Aged ; Electronic Health Records ; Risk Assessment/methods ; Risk Factors
مستخلص: Background: A prediction model can be a useful tool to quantify the risk of a patient developing dementia in the next years and take risk-factor-targeted intervention. Numerous dementia prediction models have been developed, but few have been externally validated, likely limiting their clinical uptake. In our previous work, we had limited success in externally validating some of these existing models due to inadequate reporting. As a result, we are compelled to develop and externally validate novel models to predict dementia in the general population across a network of observational databases. We assess regularization methods to obtain parsimonious models that are of lower complexity and easier to implement.
Methods: Logistic regression models were developed across a network of five observational databases with electronic health records (EHRs) and claims data to predict 5-year dementia risk in persons aged 55-84. The regularization methods L1 and Broken Adaptive Ridge (BAR) as well as three candidate predictor sets to optimize prediction performance were assessed. The predictor sets include a baseline set using only age and sex, a full set including all available candidate predictors, and a phenotype set which includes a limited number of clinically relevant predictors.
Results: BAR can be used for variable selection, outperforming L1 when a parsimonious model is desired. Adding candidate predictors for disease diagnosis and drug exposure generally improves the performance of baseline models using only age and sex. While a model trained on German EHR data saw an increase in AUROC from 0.74 to 0.83 with additional predictors, a model trained on US EHR data showed only minimal improvement from 0.79 to 0.81 AUROC. Nevertheless, the latter model developed using BAR regularization on the clinically relevant predictor set was ultimately chosen as best performing model as it demonstrated more consistent external validation performance and improved calibration.
Conclusions: We developed and externally validated patient-level models to predict dementia. Our results show that although dementia prediction is highly driven by demographic age, adding predictors based on condition diagnoses and drug exposures further improves prediction performance. BAR regularization outperforms L1 regularization to yield the most parsimonious yet still well-performing prediction model for dementia.
(© 2024. The Author(s).)
References: BMC Med Inform Decis Mak. 2021 Feb 6;21(1):43. (PMID: 33549087)
Nat Rev Neurol. 2010 Jun;6(6):318-26. (PMID: 20498679)
Med Care. 2013 Aug;51(8 Suppl 3):S30-7. (PMID: 23774517)
PLoS One. 2016 Feb 22;11(2):e0138866. (PMID: 26901338)
Alzheimers Dement. 2019 Aug;15(8):1059-1070. (PMID: 31201098)
BMC Med. 2023 Sep 4;21(1):339. (PMID: 37667344)
Int J Med Inform. 2022 Jul;163:104762. (PMID: 35429722)
J Am Med Inform Assoc. 2012 Jan-Feb;19(1):54-60. (PMID: 22037893)
Lancet. 2020 Aug 8;396(10248):413-446. (PMID: 32738937)
J Am Med Inform Assoc. 2018 Aug 1;25(8):969-975. (PMID: 29718407)
ACM Trans Model Comput Simul. 2013 Jan;23(1):. (PMID: 25328363)
Int J Epidemiol. 2022 Dec 13;51(6):e314-e323. (PMID: 35182144)
Lancet Digit Health. 2022 Dec;4(12):e853-e855. (PMID: 36270955)
PLoS One. 2019 Jul 5;14(7):e0203246. (PMID: 31276468)
J Multivar Anal. 2018 Nov;168:334-351. (PMID: 30911202)
Comput Methods Programs Biomed. 2021 Nov;211:106394. (PMID: 34560604)
PLoS One. 2015 Sep 03;10(9):e0136181. (PMID: 26334524)
J Neurol Neurosurg Psychiatry. 2019 Apr;90(4):373-379. (PMID: 29954871)
J Alzheimers Dis. 2015;49(2):423-32. (PMID: 26519436)
BMC Med Res Methodol. 2022 Jan 30;22(1):35. (PMID: 35094685)
J Am Med Inform Assoc. 2022 Apr 13;29(5):983-989. (PMID: 35045179)
Stat Med. 2019 Sep 20;38(21):4051-4065. (PMID: 31270850)
J Alzheimers Dis. 2018;61(4):1301-1310. (PMID: 29376854)
BMC Med. 2016 Jan 21;14:6. (PMID: 26797096)
Circulation. 2015 Jan 13;131(2):211-9. (PMID: 25561516)
Alzheimers Dement (N Y). 2019 Oct 08;5:563-569. (PMID: 31646170)
Stat Med. 2020 Jan 30;39(2):103-113. (PMID: 31660633)
BMC Med Res Methodol. 2022 Dec 5;22(1):311. (PMID: 36471238)
BMC Med Res Methodol. 2021 Aug 28;21(1):180. (PMID: 34454423)
فهرسة مساهمة: Keywords: Dementia prediction; External validation; Logistic regression model; Observational data
تواريخ الأحداث: Date Created: 20240729 Date Completed: 20240730 Latest Revision: 20240801
رمز التحديث: 20240801
مُعرف محوري في PubMed: PMC11288076
DOI: 10.1186/s12916-024-03530-9
PMID: 39075527
قاعدة البيانات: MEDLINE
الوصف
تدمد:1741-7015
DOI:10.1186/s12916-024-03530-9