Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384156904> ?p ?o ?g. }
Showing items 1 to 74 of
74
with 100 items per page.
- W4384156904 endingPage "182" @default.
- W4384156904 startingPage "182" @default.
- W4384156904 abstract "Iain S Forrest and colleagues1Forrest IS Petrazzini BO Duffy Á et al.Machine learning-based marker for coronary artery disease: derivation and validation in two longitudinal cohorts.Lancet. 2023; 401: 215-225Summary Full Text Full Text PDF PubMed Scopus (0) Google Scholar present a novel method for predicting the risk of coronary artery disease (CAD) using machine learning algorithms. However, there are several potential limitations that should be considered. First, the authors rely on a small sample size of 35 749 individuals in the BioMe Biobank and a limited external validation dataset of 500 000 individuals in the UK Biobank. Whether these samples are representative of the larger population is unclear, and further studies with larger, more diverse samples will be necessary to confirm the generalisability of the findings. Second, the use of electronic health record data could be subject to bias and confounding due to incomplete or inconsistent data collection and recording.2Verheij RA Curcin V Delaney BC McGilchrist MM Possible sources of bias in primary care electronic health record data use and reuse.J Med Internet Res. 2018; 20: e185Crossref PubMed Scopus (49) Google Scholar The authors do address some of these issues through data cleaning and imputation techniques, but these methods might not fully address all sources of bias. Third, the authors focus on the predictive ability of their machine learning model, but do not provide much detail on the interpretability or clinical use of the model. In the clinical context, interpretability is particularly important, as it allows medical professionals to understand how the model is making its recommendations and to use the model in a way that is consistent with their clinical expertise and judgement. Finally, the potential ethical implications of using machine learning and in-silico scores in the management of CAD are important to consider.3Ngiam KY Khor IW Big data and machine learning algorithms for health-care delivery.Lancet Oncol. 2019; 20: e262-e273Summary Full Text Full Text PDF PubMed Scopus (476) Google Scholar For example, there might be concerns about bias in the training data or in the algorithms themselves, or about the use of these approaches to stratify patients based on risk. I declare no competing interests. Machine learning-based marker for coronary artery disease: derivation and validation in two longitudinal cohortsElectronic health record-based machine learning was used to generate an in-silico marker for coronary artery disease that can non-invasively quantify atherosclerosis and risk of death on a continuous spectrum, and identify underdiagnosed individuals. Full-Text PDF Machine learning-based markers for CAD – Authors' replyRegarding our Article on in-silico scores for coronary artery disease (ISCAD),1 Linghua Yu suggests limitations with the study populations, dataset, and model. We evaluated 95 935 electronic health records across two large-scale biobanks: a diverse cohort representative of its New York City, USA, community (BioMe Biobank) and a cohort of volunteers from community centres across the UK (UK Biobank). We applied quality control steps on the dataset and imputed missing data as described in the methods of our Article. Full-Text PDF" @default.
- W4384156904 created "2023-07-14" @default.
- W4384156904 creator A5019649061 @default.
- W4384156904 date "2023-07-01" @default.
- W4384156904 modified "2023-09-30" @default.
- W4384156904 title "Machine learning-based markers for CAD" @default.
- W4384156904 cites W2805587876 @default.
- W4384156904 cites W2943491685 @default.
- W4384156904 cites W4312085640 @default.
- W4384156904 doi "https://doi.org/10.1016/s0140-6736(23)01060-7" @default.
- W4384156904 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37453747" @default.
- W4384156904 hasPublicationYear "2023" @default.
- W4384156904 type Work @default.
- W4384156904 citedByCount "0" @default.
- W4384156904 crossrefType "journal-article" @default.
- W4384156904 hasAuthorship W4384156904A5019649061 @default.
- W4384156904 hasBestOaLocation W43841569041 @default.
- W4384156904 hasConcept C116567970 @default.
- W4384156904 hasConcept C119857082 @default.
- W4384156904 hasConcept C126322002 @default.
- W4384156904 hasConcept C142724271 @default.
- W4384156904 hasConcept C151730666 @default.
- W4384156904 hasConcept C154945302 @default.
- W4384156904 hasConcept C2522767166 @default.
- W4384156904 hasConcept C2779343474 @default.
- W4384156904 hasConcept C2780148112 @default.
- W4384156904 hasConcept C2781067378 @default.
- W4384156904 hasConcept C2908647359 @default.
- W4384156904 hasConcept C41008148 @default.
- W4384156904 hasConcept C60644358 @default.
- W4384156904 hasConcept C71924100 @default.
- W4384156904 hasConcept C77350462 @default.
- W4384156904 hasConcept C86803240 @default.
- W4384156904 hasConcept C98559332 @default.
- W4384156904 hasConcept C99454951 @default.
- W4384156904 hasConceptScore W4384156904C116567970 @default.
- W4384156904 hasConceptScore W4384156904C119857082 @default.
- W4384156904 hasConceptScore W4384156904C126322002 @default.
- W4384156904 hasConceptScore W4384156904C142724271 @default.
- W4384156904 hasConceptScore W4384156904C151730666 @default.
- W4384156904 hasConceptScore W4384156904C154945302 @default.
- W4384156904 hasConceptScore W4384156904C2522767166 @default.
- W4384156904 hasConceptScore W4384156904C2779343474 @default.
- W4384156904 hasConceptScore W4384156904C2780148112 @default.
- W4384156904 hasConceptScore W4384156904C2781067378 @default.
- W4384156904 hasConceptScore W4384156904C2908647359 @default.
- W4384156904 hasConceptScore W4384156904C41008148 @default.
- W4384156904 hasConceptScore W4384156904C60644358 @default.
- W4384156904 hasConceptScore W4384156904C71924100 @default.
- W4384156904 hasConceptScore W4384156904C77350462 @default.
- W4384156904 hasConceptScore W4384156904C86803240 @default.
- W4384156904 hasConceptScore W4384156904C98559332 @default.
- W4384156904 hasConceptScore W4384156904C99454951 @default.
- W4384156904 hasIssue "10397" @default.
- W4384156904 hasLocation W43841569041 @default.
- W4384156904 hasLocation W43841569042 @default.
- W4384156904 hasOpenAccess W4384156904 @default.
- W4384156904 hasPrimaryLocation W43841569041 @default.
- W4384156904 hasRelatedWork W1990316914 @default.
- W4384156904 hasRelatedWork W2748952813 @default.
- W4384156904 hasRelatedWork W3006943036 @default.
- W4384156904 hasRelatedWork W4200511449 @default.
- W4384156904 hasRelatedWork W4206534706 @default.
- W4384156904 hasRelatedWork W4229079080 @default.
- W4384156904 hasRelatedWork W4299487748 @default.
- W4384156904 hasRelatedWork W4385957992 @default.
- W4384156904 hasRelatedWork W4385965371 @default.
- W4384156904 hasRelatedWork W4386025632 @default.
- W4384156904 hasVolume "402" @default.
- W4384156904 isParatext "false" @default.
- W4384156904 isRetracted "false" @default.
- W4384156904 workType "article" @default.