000282301 001__ 282301
000282301 005__ 20251117100334.0
000282301 0247_ $$2doi$$a10.1016/j.ebiom.2025.105962
000282301 0247_ $$2pmid$$apmid:41075354
000282301 0247_ $$2pmc$$apmc:PMC12547709
000282301 037__ $$aDZNE-2025-01271
000282301 041__ $$aEnglish
000282301 082__ $$a610
000282301 1001_ $$aWeinreich, Marcel$$b0
000282301 245__ $$aOptimised machine learning for time-to-event prediction in healthcare applied to timing of gastrostomy in ALS: a multi-centre, retrospective model development and validation study.
000282301 260__ $$aAmsterdam [u.a.]$$bElsevier$$c2025
000282301 3367_ $$2DRIVER$$aarticle
000282301 3367_ $$2DataCite$$aOutput Types/Journal article
000282301 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1763370093_17168
000282301 3367_ $$2BibTeX$$aARTICLE
000282301 3367_ $$2ORCID$$aJOURNAL_ARTICLE
000282301 3367_ $$00$$2EndNote$$aJournal Article
000282301 520__ $$aAmyotrophic lateral sclerosis (ALS) is invariably fatal but there are large variations in the rate of progression. The lack of predictability can make it difficult to plan clinical interventions. This includes the requirement for gastrostomy where early or late placement can adversely impact quality of life and survival.We designed a model to predict the timing of gastrostomy requirement in ALS as indicated by 5% weight loss from diagnosis. We considered >5000 different prediction model configurations including spline models and a set of deep learning (DL) models designed for time-to-event prediction. The optimal prediction model was chosen via a Bayesian framework to avoid overfitting. Model covariates were measurements routinely collected at diagnosis; a separate longitudinal model also incorporated weight at six months. We employed a training dataset of 3000 patients from Europe, and two external validation cohorts spanning distinct populations and clinical contexts (United States, n = 299; and Sweden, n = 215). Missing data was imputed using a random forest model.The optimal model configuration was a logistic hazard DL model. The optimal model achieved a median absolute error (MAE) between predicted and measured time of 3.7 months, with AUROC 0.75 for gastrostomy requirement at 12 months. To increase accuracy we updated predictions for those who had not received gastrostomy at six months after diagnosis: here MAE was 2.6 months (AUROC 0.86). Combining both models achieved MAE of 1.2 months for the modal group of patients. Prediction performance is stable across both validation cohorts. Missing data was imputed without degrading model performance.To enter routine clinical practice a prospective study will be required, but we have demonstrated stable performance across multiple populations and clinical contexts suggesting that our prediction model can be used to guide individualised gastrostomy decision making for patients with ALS.Research Ireland (RI) and Biogen have supported the PRECISION ALS programme.
000282301 536__ $$0G:(DE-HGF)POF4-353$$a353 - Clinical and Health Care Research (POF4-353)$$cPOF4-353$$fPOF IV$$x0
000282301 588__ $$aDataset connected to CrossRef, PubMed, , Journals: pub.dzne.de
000282301 650_7 $$2Other$$aAmyotrophic lateral sclerosis (ALS)
000282301 650_7 $$2Other$$aGastrostomy
000282301 650_7 $$2Other$$aMachine learning
000282301 650_7 $$2Other$$aPersonalised medicine
000282301 650_7 $$2Other$$aTime-to-event prediction
000282301 650_2 $$2MeSH$$aHumans
000282301 650_2 $$2MeSH$$aGastrostomy: methods
000282301 650_2 $$2MeSH$$aAmyotrophic Lateral Sclerosis: diagnosis
000282301 650_2 $$2MeSH$$aAmyotrophic Lateral Sclerosis: surgery
000282301 650_2 $$2MeSH$$aAmyotrophic Lateral Sclerosis: therapy
000282301 650_2 $$2MeSH$$aMachine Learning
000282301 650_2 $$2MeSH$$aMale
000282301 650_2 $$2MeSH$$aFemale
000282301 650_2 $$2MeSH$$aRetrospective Studies
000282301 650_2 $$2MeSH$$aMiddle Aged
000282301 650_2 $$2MeSH$$aAged
000282301 650_2 $$2MeSH$$aEurope
000282301 650_2 $$2MeSH$$aBayes Theorem
000282301 7001_ $$aMcDonough, Harry$$b1
000282301 7001_ $$aHeverin, Mark$$b2
000282301 7001_ $$aDomhnaill, Éanna Mac$$b3
000282301 7001_ $$aYacovzada, Nancy$$b4
000282301 7001_ $$aMagen, Iddo$$b5
000282301 7001_ $$aCohen, Yahel$$b6
000282301 7001_ $$aHarvey, Calum$$b7
000282301 7001_ $$aElazzab, Ahmed$$b8
000282301 7001_ $$aGornall, Sarah$$b9
000282301 7001_ $$aBoddy, Sarah$$b10
000282301 7001_ $$aAlix, James J P$$b11
000282301 7001_ $$aKurz, Julian M$$b12
000282301 7001_ $$aKenna, Kevin P$$b13
000282301 7001_ $$aZhang, Sai$$b14
000282301 7001_ $$aIacoangeli, Alfredo$$b15
000282301 7001_ $$aAl-Khleifat, Ahmad$$b16
000282301 7001_ $$aSnyder, Michael P$$b17
000282301 7001_ $$aHobson, Esther$$b18
000282301 7001_ $$aChio, Adriano$$b19
000282301 7001_ $$aMalaspina, Andrea$$b20
000282301 7001_ $$0P:(DE-2719)2811732$$aHermann, Andreas$$b21$$udzne
000282301 7001_ $$aIngre, Caroline$$b22
000282301 7001_ $$aCosta, Juan Vazquez$$b23
000282301 7001_ $$avan den Berg, Leonard$$b24
000282301 7001_ $$aPanadés, Monica Povedano$$b25
000282301 7001_ $$avan Damme, Philip$$b26
000282301 7001_ $$aCorcia, Phillipe$$b27
000282301 7001_ $$ade Carvalho, Mamede$$b28
000282301 7001_ $$aAl-Chalabi, Ammar$$b29
000282301 7001_ $$aHornstein, Eran$$b30
000282301 7001_ $$aElhaik, Eran$$b31
000282301 7001_ $$aShaw, Pamela J$$b32
000282301 7001_ $$aHardiman, Orla$$b33
000282301 7001_ $$aMcDermott, Christopher$$b34
000282301 7001_ $$aCooper-Knock, Johnathan$$b35
000282301 773__ $$0PERI:(DE-600)2799017-5$$a10.1016/j.ebiom.2025.105962$$gVol. 121, p. 105962 -$$p105962$$tEBioMedicine$$v121$$x2352-3964$$y2025
000282301 8564_ $$uhttps://pub.dzne.de/record/282301/files/DZNE-2025-01271.pdf$$yRestricted
000282301 8564_ $$uhttps://pub.dzne.de/record/282301/files/DZNE-2025-01271.pdf?subformat=pdfa$$xpdfa$$yRestricted
000282301 9101_ $$0I:(DE-588)1065079516$$6P:(DE-2719)2811732$$aDeutsches Zentrum für Neurodegenerative Erkrankungen$$b21$$kDZNE
000282301 9131_ $$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$$x0
000282301 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bEBIOMEDICINE : 2022$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2023-05-02T08:51:17Z
000282301 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2023-05-02T08:51:17Z
000282301 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bDOAJ : Anonymous peer review$$d2023-05-02T08:51:17Z
000282301 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)9910$$2StatID$$aIF >= 10$$bEBIOMEDICINE : 2022$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2025-01-07
000282301 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2025-01-07
000282301 9201_ $$0I:(DE-2719)1511100$$kAG Hermann$$lTranslational Neurodegeneration$$x0
000282301 980__ $$ajournal
000282301 980__ $$aEDITORS
000282301 980__ $$aVDBINPRINT
000282301 980__ $$aI:(DE-2719)1511100
000282301 980__ $$aUNRESTRICTED