Associated factors of white matter hyperintensity volume: a machine-learning approach
Abstract To identify the most important parameters associated with cerebral white matter hyperintensities (WMH), in consideration of potential collinearity, we used a data-driven machine-learning approach. We analysed two independent cohorts (KORA and SHIP). WMH volumes were derived from cMRI-images...
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
Nature Portfolio
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/3e861650a14c4153b0cc0080e7208f3d |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:3e861650a14c4153b0cc0080e7208f3d |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:3e861650a14c4153b0cc0080e7208f3d2021-12-02T14:16:06ZAssociated factors of white matter hyperintensity volume: a machine-learning approach10.1038/s41598-021-81883-42045-2322https://doaj.org/article/3e861650a14c4153b0cc0080e7208f3d2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-81883-4https://doaj.org/toc/2045-2322Abstract To identify the most important parameters associated with cerebral white matter hyperintensities (WMH), in consideration of potential collinearity, we used a data-driven machine-learning approach. We analysed two independent cohorts (KORA and SHIP). WMH volumes were derived from cMRI-images (FLAIR). 90 (KORA) and 34 (SHIP) potential determinants of WMH including measures of diabetes, blood-pressure, medication-intake, sociodemographics, life-style factors, somatic/depressive-symptoms and sleep were collected. Elastic net regression was used to identify relevant predictor covariates associated with WMH volume. The ten most frequently selected variables in KORA were subsequently examined for robustness in SHIP. The final KORA sample consisted of 370 participants (58% male; age 55.7 ± 9.1 years), the SHIP sample comprised 854 participants (38% male; age 53.9 ± 9.3 years). The most often selected and highly replicable parameters associated with WMH volume were in descending order age, hypertension, components of the social environment (i.e. widowed, living alone) and prediabetes. A systematic machine-learning based analysis of two independent, population-based cohorts showed, that besides age and hypertension, prediabetes and components of the social environment might play important roles in the development of WMH. Our results enable personal risk assessment for the development of WMH and inform prevention strategies tailored to the individual patient.Sergio GrosuSusanne RospleszczFelix HartmannMohamad HabesFabian BambergChristopher L. SchlettFranziska GalieRoberto LorbeerSigrid AuweterSonja SelderRobin BuelowMargit HeierWolfgang RathmannKatharina Mueller-PeltzerKarl-Heinz LadwigHans J. GrabeAnnette PetersBirgit B. Ertl-WagnerSophia StoeckleinNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-12 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Medicine R Science Q |
| spellingShingle |
Medicine R Science Q Sergio Grosu Susanne Rospleszcz Felix Hartmann Mohamad Habes Fabian Bamberg Christopher L. Schlett Franziska Galie Roberto Lorbeer Sigrid Auweter Sonja Selder Robin Buelow Margit Heier Wolfgang Rathmann Katharina Mueller-Peltzer Karl-Heinz Ladwig Hans J. Grabe Annette Peters Birgit B. Ertl-Wagner Sophia Stoecklein Associated factors of white matter hyperintensity volume: a machine-learning approach |
| description |
Abstract To identify the most important parameters associated with cerebral white matter hyperintensities (WMH), in consideration of potential collinearity, we used a data-driven machine-learning approach. We analysed two independent cohorts (KORA and SHIP). WMH volumes were derived from cMRI-images (FLAIR). 90 (KORA) and 34 (SHIP) potential determinants of WMH including measures of diabetes, blood-pressure, medication-intake, sociodemographics, life-style factors, somatic/depressive-symptoms and sleep were collected. Elastic net regression was used to identify relevant predictor covariates associated with WMH volume. The ten most frequently selected variables in KORA were subsequently examined for robustness in SHIP. The final KORA sample consisted of 370 participants (58% male; age 55.7 ± 9.1 years), the SHIP sample comprised 854 participants (38% male; age 53.9 ± 9.3 years). The most often selected and highly replicable parameters associated with WMH volume were in descending order age, hypertension, components of the social environment (i.e. widowed, living alone) and prediabetes. A systematic machine-learning based analysis of two independent, population-based cohorts showed, that besides age and hypertension, prediabetes and components of the social environment might play important roles in the development of WMH. Our results enable personal risk assessment for the development of WMH and inform prevention strategies tailored to the individual patient. |
| format |
article |
| author |
Sergio Grosu Susanne Rospleszcz Felix Hartmann Mohamad Habes Fabian Bamberg Christopher L. Schlett Franziska Galie Roberto Lorbeer Sigrid Auweter Sonja Selder Robin Buelow Margit Heier Wolfgang Rathmann Katharina Mueller-Peltzer Karl-Heinz Ladwig Hans J. Grabe Annette Peters Birgit B. Ertl-Wagner Sophia Stoecklein |
| author_facet |
Sergio Grosu Susanne Rospleszcz Felix Hartmann Mohamad Habes Fabian Bamberg Christopher L. Schlett Franziska Galie Roberto Lorbeer Sigrid Auweter Sonja Selder Robin Buelow Margit Heier Wolfgang Rathmann Katharina Mueller-Peltzer Karl-Heinz Ladwig Hans J. Grabe Annette Peters Birgit B. Ertl-Wagner Sophia Stoecklein |
| author_sort |
Sergio Grosu |
| title |
Associated factors of white matter hyperintensity volume: a machine-learning approach |
| title_short |
Associated factors of white matter hyperintensity volume: a machine-learning approach |
| title_full |
Associated factors of white matter hyperintensity volume: a machine-learning approach |
| title_fullStr |
Associated factors of white matter hyperintensity volume: a machine-learning approach |
| title_full_unstemmed |
Associated factors of white matter hyperintensity volume: a machine-learning approach |
| title_sort |
associated factors of white matter hyperintensity volume: a machine-learning approach |
| publisher |
Nature Portfolio |
| publishDate |
2021 |
| url |
https://doaj.org/article/3e861650a14c4153b0cc0080e7208f3d |
| work_keys_str_mv |
AT sergiogrosu associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT susannerospleszcz associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT felixhartmann associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT mohamadhabes associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT fabianbamberg associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT christopherlschlett associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT franziskagalie associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT robertolorbeer associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT sigridauweter associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT sonjaselder associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT robinbuelow associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT margitheier associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT wolfgangrathmann associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT katharinamuellerpeltzer associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT karlheinzladwig associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT hansjgrabe associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT annettepeters associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT birgitbertlwagner associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach AT sophiastoecklein associatedfactorsofwhitematterhyperintensityvolumeamachinelearningapproach |
| _version_ |
1718391720277704704 |