000163706 001__ 163706
000163706 005__ 20230915090531.0
000163706 0247_ $$2pmc$$apmc:PMC8975993
000163706 0247_ $$2doi$$a10.1038/s41531-022-00288-w
000163706 0247_ $$2altmetric$$aaltmetric:125741739
000163706 0247_ $$2pmid$$apmid:35365675
000163706 037__ $$aDZNE-2022-00445
000163706 082__ $$a610
000163706 1001_ $$00000-0002-7978-1051$$aMakarious, Mary B.$$b0
000163706 245__ $$aMulti-modality machine learning predicting Parkinson’s disease
000163706 260__ $$aLondon [u.a.]$$bNature Publ. Group$$c2022
000163706 3367_ $$2DRIVER$$aarticle
000163706 3367_ $$2DataCite$$aOutput Types/Journal article
000163706 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1657627501_13981
000163706 3367_ $$2BibTeX$$aARTICLE
000163706 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000163706 3367_ $$00$$2EndNote$$aJournal Article
000163706 520__ $$aPersonalized medicine promises individualized disease prediction and treatment. The convergence of machine learning (ML) and available multimodal data is key moving forward. We build upon previous work to deliver multimodal predictions of Parkinson’s disease (PD) risk and systematically develop a model using GenoML, an automated ML package, to make improved multi-omic predictions of PD, validated in an external cohort. We investigated top features, constructed hypothesis-free disease-relevant networks, and investigated drug–gene interactions. We performed automated ML on multimodal data from the Parkinson’s progression marker initiative (PPMI). After selecting the best performing algorithm, all PPMI data was used to tune the selected model. The model was validated in the Parkinson’s Disease Biomarker Program (PDBP) dataset. Our initial model showed an area under the curve (AUC) of 89.72% for the diagnosis of PD. The tuned model was then tested for validation on external data (PDBP, AUC 85.03%). Optimizing thresholds for classification increased the diagnosis prediction accuracy and other metrics. Finally, networks were built to identify gene communities specific to PD. Combining data modalities outperforms the single biomarker paradigm. UPSIT and PRS contributed most to the predictive power of the model, but the accuracy of these are supplemented by many smaller effect transcripts and risk SNPs. Our model is best suited to identifying large groups of individuals to monitor within a health registry or biobank to prioritize for further testing. This approach allows complex predictive models to be reproducible and accessible to the community, with the package, code, and results publicly available.
000163706 536__ $$0G:(DE-HGF)POF4-353$$a353 - Clinical and Health Care Research (POF4-353)$$cPOF4-353$$fPOF IV$$x0
000163706 588__ $$aDataset connected to CrossRef, Journals: pub.dzne.de
000163706 7001_ $$0P:(DE-2719)9001970$$aLeonard, Hampton L.$$b1$$udzne
000163706 7001_ $$aVitale, Dan$$b2
000163706 7001_ $$aIwaki, Hirotaka$$b3
000163706 7001_ $$aSargent, Lana$$b4
000163706 7001_ $$aDadu, Anant$$b5
000163706 7001_ $$aViolich, Ivo$$b6
000163706 7001_ $$aHutchins, Elizabeth$$b7
000163706 7001_ $$aSaffo, David$$b8
000163706 7001_ $$aBandres-Ciga, Sara$$b9
000163706 7001_ $$aKim, Jonggeol Jeff$$b10
000163706 7001_ $$aSong, Yeajin$$b11
000163706 7001_ $$aMaleknia, Melina$$b12
000163706 7001_ $$aBookman, Matt$$b13
000163706 7001_ $$aNojopranoto, Willy$$b14
000163706 7001_ $$00000-0002-3754-7777$$aCampbell, Roy H.$$b15
000163706 7001_ $$aHashemi, Sayed Hadi$$b16
000163706 7001_ $$aBotia, Juan A.$$b17
000163706 7001_ $$aCarter, John F.$$b18
000163706 7001_ $$00000-0003-2040-1955$$aCraig, David W.$$b19
000163706 7001_ $$aVan Keuren-Jensen, Kendall$$b20
000163706 7001_ $$00000-0002-5473-3774$$aMorris, Huw R.$$b21
000163706 7001_ $$aHardy, John A.$$b22
000163706 7001_ $$0P:(DE-2719)2810837$$aBlauwendraat, Cornelis$$b23$$udzne
000163706 7001_ $$00000-0001-5606-700X$$aSingleton, Andrew B.$$b24
000163706 7001_ $$00000-0001-5744-8728$$aFaghri, Faraz$$b25
000163706 7001_ $$aNalls, Mike A.$$b26
000163706 773__ $$0PERI:(DE-600)2819218-7$$a10.1038/s41531-022-00288-w$$gVol. 8, no. 1, p. 35$$n1$$p35$$tnpj Parkinson's Disease$$v8$$x2373-8057$$y2022
000163706 8564_ $$uhttps://pub.dzne.de/record/163706/files/DZNE-2022-00445.pdf$$yOpenAccess
000163706 8564_ $$uhttps://pub.dzne.de/record/163706/files/DZNE-2022-00445.pdf?subformat=pdfa$$xpdfa$$yOpenAccess
000163706 909CO $$ooai:pub.dzne.de:163706$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000163706 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)9001970$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b1$$kDZNE
000163706 9101_ $$0I:(DE-HGF)0$$6P:(DE-2719)2810837$$aExternal Institute$$b23$$kExtern
000163706 9131_ $$0G:(DE-HGF)POF4-353$$1G:(DE-HGF)POF4-350$$2G:(DE-HGF)POF4-300$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$aDE-HGF$$bGesundheit$$lNeurodegenerative Diseases$$vClinical and Health Care Research$$x0
000163706 9141_ $$y2022
000163706 915__ $$0LIC:(DE-HGF)CCBYNV$$2V:(DE-HGF)$$aCreative Commons Attribution CC BY (No Version)$$bDOAJ$$d2020-09-03
000163706 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2020-09-03
000163706 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2020-09-03
000163706 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2020-09-03
000163706 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000163706 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2020-09-03
000163706 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bNPJ PARKINSONS DIS : 2021$$d2023-03-31
000163706 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2023-03-31
000163706 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2023-03-31
000163706 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2021-10-13T14:34:28Z
000163706 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2021-10-13T14:34:28Z
000163706 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Blind peer review$$d2021-10-13T14:34:28Z
000163706 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2023-03-31
000163706 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2023-03-31
000163706 915__ $$0StatID:(DE-HGF)1030$$2StatID$$aDBCoverage$$bCurrent Contents - Life Sciences$$d2023-03-31
000163706 915__ $$0StatID:(DE-HGF)9905$$2StatID$$aIF >= 5$$bNPJ PARKINSONS DIS : 2021$$d2023-03-31
000163706 9201_ $$0I:(DE-2719)6000018$$kTübingen common$$lTübingen common$$x0
000163706 9201_ $$0I:(DE-2719)1210000$$kAG Gasser$$lParkinson Genetics$$x1
000163706 980__ $$ajournal
000163706 980__ $$aVDB
000163706 980__ $$aI:(DE-2719)6000018
000163706 980__ $$aI:(DE-2719)1210000-7
000163706 980__ $$aUNRESTRICTED
000163706 9801_ $$aFullTexts