Ensemble learning predicts multiple sclerosis disease course in the SUMMIT study
The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women’s Hospital (...
Saved in:
| Published in: | NPJ digital medicine Vol. 3; no. 1; pp. 135 - 8 |
|---|---|
| Main Authors: | , , , , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
London
Nature Publishing Group UK
16.10.2020
Nature Publishing Group Nature Portfolio |
| Subjects: | |
| ISSN: | 2398-6352, 2398-6352 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women’s Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in
Expanded Disability Status Scale
(
EDSS
) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients’ clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms (
SVM, Logistic Regression,
and
Random Forest
) and three ensemble learning approaches (
XGBoost, LightGBM
, and a Meta-learner
L
). A “threshold” was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS,
Pyramidal Function
, and
Ambulatory Index
were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course. |
|---|---|
| AbstractList | The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women's Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in Expanded Disability Status Scale (EDSS) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients' clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms (SVM, Logistic Regression, and Random Forest) and three ensemble learning approaches (XGBoost, LightGBM, and a Meta-learner L). A "threshold" was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS, Pyramidal Function, and Ambulatory Index were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course.The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women's Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in Expanded Disability Status Scale (EDSS) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients' clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms (SVM, Logistic Regression, and Random Forest) and three ensemble learning approaches (XGBoost, LightGBM, and a Meta-learner L). A "threshold" was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS, Pyramidal Function, and Ambulatory Index were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course. Abstract The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women’s Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in Expanded Disability Status Scale (EDSS) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients’ clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms (SVM, Logistic Regression, and Random Forest) and three ensemble learning approaches (XGBoost, LightGBM, and a Meta-learner L). A “threshold” was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS, Pyramidal Function, and Ambulatory Index were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course. The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women's Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in ( ) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients' clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms ( and ) and three ensemble learning approaches ( , and a Meta-learner ). A "threshold" was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS, , and were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course. The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women’s Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in Expanded Disability Status Scale ( EDSS ) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients’ clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms ( SVM, Logistic Regression, and Random Forest ) and three ensemble learning approaches ( XGBoost, LightGBM , and a Meta-learner L ). A “threshold” was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS, Pyramidal Function , and Ambulatory Index were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course. The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict disease course in MS patients. In our study, 724 patients from the Comprehensive Longitudinal Investigation in MS at Brigham and Women’s Hospital (CLIMB study) and 400 patients from the EPIC dataset, University of California, San Francisco, were included in the analysis. The primary outcome was an increase in Expanded Disability Status Scale (EDSS) ≥ 1.5 (worsening) or not (non-worsening) at up to 5 years after the baseline visit. Classification models were built using the CLIMB dataset with patients’ clinical and MRI longitudinal observations in first 2 years, and further validated using the EPIC dataset. We compared the performance of three popular machine learning algorithms (SVM, Logistic Regression, and Random Forest) and three ensemble learning approaches (XGBoost, LightGBM, and a Meta-learner L). A “threshold” was established to trade-off the performance between the two classes. Predictive features were identified and compared among different models. Machine learning models achieved 0.79 and 0.83 AUC scores for the CLIMB and EPIC datasets, respectively, shortly after disease onset. Ensemble learning methods were more effective and robust compared to standalone algorithms. Two ensemble models, XGBoost and LightGBM were superior to the other four models evaluated in our study. Of variables evaluated, EDSS, Pyramidal Function, and Ambulatory Index were the top common predictors in forecasting the MS disease course. Machine learning techniques, in particular ensemble methods offer increased accuracy for the prediction of MS disease course. |
| ArticleNumber | 135 |
| Author | Zhao, Yijun Bakshi, Rohit Lokhande, Hrishikesh Polgar-Turcsanyi, Mariann Anderson, Mark Chitnis, Tanuja Weiner, Howard L. Bove, Riley Henry, Roland Wang, Tong Cree, Bruce |
| Author_xml | – sequence: 1 givenname: Yijun surname: Zhao fullname: Zhao, Yijun organization: Department of Computer and Information Science, Fordham University – sequence: 2 givenname: Tong surname: Wang fullname: Wang, Tong organization: Department of Computer and Information Science, Fordham University – sequence: 3 givenname: Riley surname: Bove fullname: Bove, Riley organization: University of California, SUMMIT Consortium, SUMMIT Consortium – sequence: 4 givenname: Bruce surname: Cree fullname: Cree, Bruce organization: University of California, SUMMIT Consortium, SUMMIT Consortium – sequence: 5 givenname: Roland surname: Henry fullname: Henry, Roland organization: University of California, SUMMIT Consortium, SUMMIT Consortium – sequence: 6 givenname: Hrishikesh surname: Lokhande fullname: Lokhande, Hrishikesh organization: Brigham Multiple Sclerosis Center, Ann Romney Center, Brigham and Women’s Hospital, Harvard Medical School – sequence: 7 givenname: Mariann orcidid: 0000-0002-1244-1802 surname: Polgar-Turcsanyi fullname: Polgar-Turcsanyi, Mariann organization: SUMMIT Consortium, SUMMIT Consortium, Brigham Multiple Sclerosis Center, Ann Romney Center, Brigham and Women’s Hospital, Harvard Medical School – sequence: 8 givenname: Mark surname: Anderson fullname: Anderson, Mark organization: SUMMIT Consortium, SUMMIT Consortium, Brigham Multiple Sclerosis Center, Ann Romney Center, Brigham and Women’s Hospital, Harvard Medical School – sequence: 9 givenname: Rohit orcidid: 0000-0001-8601-5534 surname: Bakshi fullname: Bakshi, Rohit organization: SUMMIT Consortium, SUMMIT Consortium, Brigham Multiple Sclerosis Center, Ann Romney Center, Brigham and Women’s Hospital, Harvard Medical School – sequence: 10 givenname: Howard L. surname: Weiner fullname: Weiner, Howard L. organization: SUMMIT Consortium, SUMMIT Consortium, Brigham Multiple Sclerosis Center, Ann Romney Center, Brigham and Women’s Hospital, Harvard Medical School – sequence: 11 givenname: Tanuja orcidid: 0000-0002-9897-4422 surname: Chitnis fullname: Chitnis, Tanuja email: tchitnis@rics.bwh.harvard.edu organization: SUMMIT Consortium, SUMMIT Consortium, Brigham Multiple Sclerosis Center, Ann Romney Center, Brigham and Women’s Hospital, Harvard Medical School |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/33083570$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kk9rFTEUxYNUbK39Ai5kwI2b0fybJLMRpFR90KJguw6Z5L7XPGaSZ5IR-u3N67TadtFVQu45P07uva_RQYgBEHpL8EeCmfqUOZFctJjiFmPGVKteoCPKetUK1tGDB_dDdJLzFuMq5arn4hU6ZAwr1kl8hH6ehQzTMEIzgknBh02zS-C8LbmZ5rH4XS1lO0KK2efG-QwmQ2PjnOrhQ1Ouofl1dXGxumxymd3NG_RybcYMJ3fnMbr6enZ5-r09__FtdfrlvLUCi9JKjg1YZbkAZTgTnPdrSSXrqTODg76Tru9V52AQhhPLhOAOKwJYDrTriWHHaLVwXTRbvUt-MulGR-P17UNMG21S8TW5ZoNTRlFOzZpxGLqBSGodl5gT4wjHlfV5Ye3mYQJnIZRkxkfQx5Xgr_Um_tGyE1IqUgEf7gAp_p4hFz35bGEcTYA4Z015R3spBZZV-v6JdFt7GWqrNO2oUqJ-VVXVu4eJ_kW5H1wVqEVg62BygrW2vpji4z6gHzXBer8melkTXWevb9dE79n0ifWe_qyJLaZcxWED6X_sZ1x_AaKUzlY |
| CitedBy_id | crossref_primary_10_1371_journal_pone_0306999 crossref_primary_10_3390_life11020122 crossref_primary_10_1007_s10439_022_02930_3 crossref_primary_10_1055_a_2530_1105 crossref_primary_10_3389_frai_2025_1478068 crossref_primary_10_3390_diagnostics12071771 crossref_primary_10_1186_s12967_022_03339_1 crossref_primary_10_1016_j_cmpb_2025_108624 crossref_primary_10_1007_s00415_023_12132_z crossref_primary_10_1016_j_nicl_2022_103065 crossref_primary_10_3389_fneur_2023_1151326 crossref_primary_10_3390_app14146193 crossref_primary_10_1002_ana_26370 crossref_primary_10_1038_s41746_025_01863_0 crossref_primary_10_1186_s12911_022_02034_x crossref_primary_10_1016_j_lanepe_2024_100978 crossref_primary_10_1007_s00415_024_12651_3 crossref_primary_10_3389_fneur_2023_1165267 crossref_primary_10_1021_acs_jcim_5c00465 crossref_primary_10_1186_s12916_024_03317_y crossref_primary_10_3390_brainsci11111519 crossref_primary_10_1038_s41598_022_11361_y crossref_primary_10_1080_01616412_2025_2532038 crossref_primary_10_1007_s00415_024_12507_w crossref_primary_10_3389_frobt_2022_926255 crossref_primary_10_3390_diagnostics14131339 crossref_primary_10_1177_09612033221114805 |
| Cites_doi | 10.1177/1352458517726657 10.1001/archneurol.65.8.noc80042 10.1145/2939672.2939785 10.1093/brain/awh714 10.1007/3-540-45014-9_1 10.1093/brain/awg081 10.1016/S0893-6080(05)80023-1 10.1002/9781118548387 10.2307/2344614 10.1023/A:1010933404324 10.1016/j.ncl.2011.01.001 10.1016/S0140-6736(07)61194-5 10.1056/NEJMoa067597 10.1016/j.autrev.2006.02.012 10.1093/brain/112.1.133 10.1007/s100720070021 10.1212/WNL.33.11.1444 10.1093/brain/112.6.1419 |
| ContentType | Journal Article |
| Copyright | The Author(s) 2020. corrected publication 2020 The Author(s) 2020. The Author(s) 2020. corrected publication 2020. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. The Author(s) 2020, corrected publication 2020 |
| Copyright_xml | – notice: The Author(s) 2020. corrected publication 2020 – notice: The Author(s) 2020. – notice: The Author(s) 2020. corrected publication 2020. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: The Author(s) 2020, corrected publication 2020 |
| CorporateAuthor | SUMMIT Investigators |
| CorporateAuthor_xml | – name: SUMMIT Investigators |
| DBID | C6C AAYXX CITATION NPM 3V. 7RV 7X7 7XB 8FI 8FJ 8FK ABUWG AFKRA AZQEC BENPR CCPQU DWQXO FYUFA GHDGH K9. KB0 M0S NAPCQ PHGZM PHGZT PIMPY PJZUB PKEHL PPXIY PQEST PQQKQ PQUKI PRINS 7X8 5PM DOA |
| DOI | 10.1038/s41746-020-00338-8 |
| DatabaseName | Springer Nature Open Access Journals CrossRef PubMed ProQuest Central (Corporate) Nursing & Allied Health Database ProQuest Health & Medical Collection ProQuest Central (purchase pre-March 2016) ProQuest Hospital Collection Hospital Premium Collection (Alumni Edition) ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central ProQuest One Community College ProQuest Central Health Research Premium Collection Health Research Premium Collection (Alumni) ProQuest Health & Medical Complete (Alumni) Nursing & Allied Health Database (Alumni Edition) ProQuest Health & Medical Collection Nursing & Allied Health Premium ProQuest Central Premium ProQuest One Academic (New) ProQuest Publicly Available Content ProQuest Health & Medical Research Collection ProQuest One Academic Middle East (New) ProQuest One Health & Nursing ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China MEDLINE - Academic PubMed Central (Full Participant titles) DOAJ Open Access Full Text |
| DatabaseTitle | CrossRef PubMed Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest Central Essentials ProQuest Health & Medical Complete (Alumni) ProQuest Central (Alumni Edition) ProQuest One Community College ProQuest One Health & Nursing ProQuest Central China ProQuest Central ProQuest Health & Medical Research Collection Health Research Premium Collection Health and Medicine Complete (Alumni Edition) ProQuest Central Korea ProQuest Central (New) ProQuest One Academic Eastern Edition ProQuest Nursing & Allied Health Source ProQuest Hospital Collection Health Research Premium Collection (Alumni) ProQuest Hospital Collection (Alumni) Nursing & Allied Health Premium ProQuest Health & Medical Complete ProQuest One Academic UKI Edition ProQuest Nursing & Allied Health Source (Alumni) ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed CrossRef Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: 7RV name: Nursing & Allied Health Database url: https://search.proquest.com/nahs sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 2398-6352 |
| EndPage | 8 |
| ExternalDocumentID | oai_doaj_org_article_3bd8a8242af34eb5b172cd47041ad140 PMC7567781 33083570 10_1038_s41746_020_00338_8 |
| Genre | Journal Article |
| GroupedDBID | 0R~ 53G 7RV 7X7 8FI 8FJ AAJSJ ABUWG ACGFS ACSMW ADBBV AFKRA AJTQC ALIPV ALMA_UNASSIGNED_HOLDINGS AOIJS BCNDV BENPR C6C CCPQU EBLON EBS EIHBH FYUFA GROUPED_DOAJ HMCUK HYE M~E NAO NAPCQ NO~ OK1 PGMZT PIMPY RNT RPM SNYQT UKHRP AASML AAYXX AFFHD CITATION PHGZM PHGZT PPXIY EJD NPM 3V. 7XB 8FK AZQEC DWQXO K9. PJZUB PKEHL PQEST PQQKQ PQUKI PRINS 7X8 PUEGO 5PM |
| ID | FETCH-LOGICAL-c606t-740aec8c46e8a436449f727392dabde957d9985deb6a41c3664d081e07b2591a3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 39 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000583291400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2398-6352 |
| IngestDate | Fri Oct 03 12:52:30 EDT 2025 Tue Nov 04 01:56:01 EST 2025 Wed Oct 01 13:12:06 EDT 2025 Tue Oct 07 06:49:55 EDT 2025 Mon Jul 21 05:47:41 EDT 2025 Sat Nov 29 02:05:37 EST 2025 Tue Nov 18 22:32:54 EST 2025 Fri Feb 21 02:39:51 EST 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Keywords | Multiple sclerosis |
| Language | English |
| License | The Author(s) 2020. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons license, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons license and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c606t-740aec8c46e8a436449f727392dabde957d9985deb6a41c3664d081e07b2591a3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0001-8601-5534 0000-0002-9897-4422 0000-0002-1244-1802 |
| OpenAccessLink | https://doaj.org/article/3bd8a8242af34eb5b172cd47041ad140 |
| PMID | 33083570 |
| PQID | 2528863668 |
| PQPubID | 5061815 |
| PageCount | 8 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_3bd8a8242af34eb5b172cd47041ad140 pubmedcentral_primary_oai_pubmedcentral_nih_gov_7567781 proquest_miscellaneous_2452977607 proquest_journals_2528863668 pubmed_primary_33083570 crossref_citationtrail_10_1038_s41746_020_00338_8 crossref_primary_10_1038_s41746_020_00338_8 springer_journals_10_1038_s41746_020_00338_8 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-10-16 |
| PublicationDateYYYYMMDD | 2020-10-16 |
| PublicationDate_xml | – month: 10 year: 2020 text: 2020-10-16 day: 16 |
| PublicationDecade | 2020 |
| PublicationPlace | London |
| PublicationPlace_xml | – name: London – name: England |
| PublicationTitle | NPJ digital medicine |
| PublicationTitleAbbrev | npj Digit. Med |
| PublicationTitleAlternate | NPJ Digit Med |
| PublicationYear | 2020 |
| Publisher | Nature Publishing Group UK Nature Publishing Group Nature Portfolio |
| Publisher_xml | – name: Nature Publishing Group UK – name: Nature Publishing Group – name: Nature Portfolio |
| References | KrishnanCReduction of disease activity and disability with high-dose cyclophosphamide in patients with aggressive multiple sclerosisArch. Neurol.2008651044105110.1001/archneurol.65.8.noc80042 WeinshenkerBGThe natural history of multiple sclerosis: a geographically based study: I. Clinical course and disabilityBrain198911213314610.1093/brain/112.1.133 Ke, G. et al. Lightgbm: A highly efficient gradient boosting decision tree. In Proc. of the 31st Conference on Neural Information Processing Systems (NIPS, Long Beach, CA, 2017). QuinlanJRInduction of decision treesMach. Learn.1986181106 BoveRSUMMIT (Serially Unified Multicenter Multiple Sclerosis Investigation): creating a repository of deeply phenotyped contemporary multiple sclerosis cohortsMult. Scler.2018241485149810.1177/1352458517726657 Nielsen, D. Tree Boosting with Xgboost-why Does Xgboost Win Every Machine Learning Competition? Master’s thesis, NTNU (2016). FreundYSchapireRAbeNA short introduction to boostingJ.-Jpn. Soc. Artif. Intell.199914771780 Mowry, E. M. Natural history of multiple sclerosis: early prognostic factors. Neurol. Clin. 29, 279–292 (2011). Chen, T. & Guestrin, C. Xgboost: A scalable tree boosting system. In Proc. of the 22nd acm sigkdd International Conference on Knowledge Discovery and Data Mining, 785–794 (KDD, New York, NY, 2016). Amato, M. & Ponziani, G. A prospective study on the prognosis of multiple sclerosis. Neurol. Sci.21, S831–S838 (2000). KurtzkeJFRating neurologic impairment in multiple sclerosis: an expanded disability status scale (EDSS)Neurology198333144414441:STN:280:DyaL2c%2FktValsQ%3D%3D10.1212/WNL.33.11.1444 GauthierSAGlanzBIMandelMWeinerHLA model for the comprehensive investigation of a chronic autoimmune disease: the multiple sclerosis CLIMB studyAutoimmun. Rev.200655325361:CAS:528:DC%2BD28Xht12qtL3E10.1016/j.autrev.2006.02.012 KapposLEffect of early versus delayed interferon beta-1b treatment on disability after a first clinical event suggestive of multiple sclerosis: a 3-year follow-up analysis of the BENEFIT studyLancet20073703893971:CAS:528:DC%2BD2sXosFKktLc%3D10.1016/S0140-6736(07)61194-5 ConfavreuxCVukusicSAdeleinePEarly clinical predictors and progression of irreversible disability in multiple sclerosis: an amnesic processBrain200312677078210.1093/brain/awg081 BreimanLRandom forestsMach. Learn.20014553210.1023/A:1010933404324 CortesCVapnikVSupport-vector networksMach. Learn.199520273297 ConfavreuxCVukusicSAge at disability milestones in multiple sclerosisBrain200612959560510.1093/brain/awh714 Dietterich, T. G. Ensemble methods in machine learning. In Proc. of the International Workshop on Multiple Classifier Systems, Vol. 1857 (MCS, Cagliari, Italy, 2000). Kasturi, S. N. XGBOOST vs LightGBM: Which Algorithm Wins the Race!!! https://towardsdatascience.com/lightgbm-vs-xgboost-which-algorithm-win-the-race-1ff7dd4917d (2019). Hosmer, D. W. Jr, Lemeshow, S. & Sturdivant, R. X. Applied Logistic Regression, Vol. 398 (Wiley, Hoboken, 2013). RenouxCNatural history of multiple sclerosis with childhood onsetN. Engl. J. Med.2007356260326131:CAS:528:DC%2BD2sXmslKjs7w%3D10.1056/NEJMoa067597 Longadge, R., Dongre, S. & Malik, L. Class imbalance problem in data mining: review. Int. J. Comp. Sci. Netw.2, 83 (2013). WeinshenkerBGThe natural history of multiple sclerosis: a geographically based study: 2 predictive value of the early clinical courseBrain19891121419142810.1093/brain/112.6.1419 WolpertDHStacked generalizationNeural Netw.1992524125910.1016/S0893-6080(05)80023-1 NelderJAWedderburnRWGeneralized linear modelsJ. R. Stat. Soc. Ser. A (Gen.)197213537038410.2307/2344614 L Kappos (338_CR9) 2007; 370 BG Weinshenker (338_CR7) 1989; 112 R Bove (338_CR15) 2018; 24 JF Kurtzke (338_CR10) 1983; 33 338_CR22 338_CR21 338_CR20 C Krishnan (338_CR8) 2008; 65 338_CR5 JR Quinlan (338_CR14) 1986; 1 338_CR25 C Cortes (338_CR18) 1995; 20 L Breiman (338_CR19) 2001; 45 DH Wolpert (338_CR23) 1992; 5 338_CR1 C Confavreux (338_CR2) 2006; 129 JA Nelder (338_CR13) 1972; 135 Y Freund (338_CR24) 1999; 14 C Confavreux (338_CR3) 2003; 126 338_CR12 338_CR11 BG Weinshenker (338_CR6) 1989; 112 C Renoux (338_CR4) 2007; 356 SA Gauthier (338_CR16) 2006; 5 338_CR17 33299133 - NPJ Digit Med. 2020 Nov 20;3(1):155 |
| References_xml | – reference: FreundYSchapireRAbeNA short introduction to boostingJ.-Jpn. Soc. Artif. Intell.199914771780 – reference: BoveRSUMMIT (Serially Unified Multicenter Multiple Sclerosis Investigation): creating a repository of deeply phenotyped contemporary multiple sclerosis cohortsMult. Scler.2018241485149810.1177/1352458517726657 – reference: ConfavreuxCVukusicSAge at disability milestones in multiple sclerosisBrain200612959560510.1093/brain/awh714 – reference: QuinlanJRInduction of decision treesMach. Learn.1986181106 – reference: Mowry, E. M. Natural history of multiple sclerosis: early prognostic factors. Neurol. Clin. 29, 279–292 (2011). – reference: RenouxCNatural history of multiple sclerosis with childhood onsetN. Engl. J. Med.2007356260326131:CAS:528:DC%2BD2sXmslKjs7w%3D10.1056/NEJMoa067597 – reference: Nielsen, D. Tree Boosting with Xgboost-why Does Xgboost Win Every Machine Learning Competition? Master’s thesis, NTNU (2016). – reference: ConfavreuxCVukusicSAdeleinePEarly clinical predictors and progression of irreversible disability in multiple sclerosis: an amnesic processBrain200312677078210.1093/brain/awg081 – reference: KrishnanCReduction of disease activity and disability with high-dose cyclophosphamide in patients with aggressive multiple sclerosisArch. Neurol.2008651044105110.1001/archneurol.65.8.noc80042 – reference: NelderJAWedderburnRWGeneralized linear modelsJ. R. Stat. Soc. Ser. A (Gen.)197213537038410.2307/2344614 – reference: Dietterich, T. G. Ensemble methods in machine learning. In Proc. of the International Workshop on Multiple Classifier Systems, Vol. 1857 (MCS, Cagliari, Italy, 2000). – reference: Longadge, R., Dongre, S. & Malik, L. Class imbalance problem in data mining: review. Int. J. Comp. Sci. Netw.2, 83 (2013). – reference: Ke, G. et al. Lightgbm: A highly efficient gradient boosting decision tree. In Proc. of the 31st Conference on Neural Information Processing Systems (NIPS, Long Beach, CA, 2017). – reference: WeinshenkerBGThe natural history of multiple sclerosis: a geographically based study: 2 predictive value of the early clinical courseBrain19891121419142810.1093/brain/112.6.1419 – reference: KurtzkeJFRating neurologic impairment in multiple sclerosis: an expanded disability status scale (EDSS)Neurology198333144414441:STN:280:DyaL2c%2FktValsQ%3D%3D10.1212/WNL.33.11.1444 – reference: WeinshenkerBGThe natural history of multiple sclerosis: a geographically based study: I. Clinical course and disabilityBrain198911213314610.1093/brain/112.1.133 – reference: GauthierSAGlanzBIMandelMWeinerHLA model for the comprehensive investigation of a chronic autoimmune disease: the multiple sclerosis CLIMB studyAutoimmun. Rev.200655325361:CAS:528:DC%2BD28Xht12qtL3E10.1016/j.autrev.2006.02.012 – reference: Hosmer, D. W. Jr, Lemeshow, S. & Sturdivant, R. X. Applied Logistic Regression, Vol. 398 (Wiley, Hoboken, 2013). – reference: KapposLEffect of early versus delayed interferon beta-1b treatment on disability after a first clinical event suggestive of multiple sclerosis: a 3-year follow-up analysis of the BENEFIT studyLancet20073703893971:CAS:528:DC%2BD2sXosFKktLc%3D10.1016/S0140-6736(07)61194-5 – reference: BreimanLRandom forestsMach. Learn.20014553210.1023/A:1010933404324 – reference: WolpertDHStacked generalizationNeural Netw.1992524125910.1016/S0893-6080(05)80023-1 – reference: Chen, T. & Guestrin, C. Xgboost: A scalable tree boosting system. In Proc. of the 22nd acm sigkdd International Conference on Knowledge Discovery and Data Mining, 785–794 (KDD, New York, NY, 2016). – reference: Amato, M. & Ponziani, G. A prospective study on the prognosis of multiple sclerosis. Neurol. Sci.21, S831–S838 (2000). – reference: Kasturi, S. N. XGBOOST vs LightGBM: Which Algorithm Wins the Race!!! https://towardsdatascience.com/lightgbm-vs-xgboost-which-algorithm-win-the-race-1ff7dd4917d (2019). – reference: CortesCVapnikVSupport-vector networksMach. Learn.199520273297 – volume: 24 start-page: 1485 year: 2018 ident: 338_CR15 publication-title: Mult. Scler. doi: 10.1177/1352458517726657 – volume: 65 start-page: 1044 year: 2008 ident: 338_CR8 publication-title: Arch. Neurol. doi: 10.1001/archneurol.65.8.noc80042 – volume: 1 start-page: 81 year: 1986 ident: 338_CR14 publication-title: Mach. Learn. – ident: 338_CR22 doi: 10.1145/2939672.2939785 – volume: 129 start-page: 595 year: 2006 ident: 338_CR2 publication-title: Brain doi: 10.1093/brain/awh714 – volume: 20 start-page: 273 year: 1995 ident: 338_CR18 publication-title: Mach. Learn. – ident: 338_CR12 – ident: 338_CR21 doi: 10.1007/3-540-45014-9_1 – volume: 126 start-page: 770 year: 2003 ident: 338_CR3 publication-title: Brain doi: 10.1093/brain/awg081 – volume: 5 start-page: 241 year: 1992 ident: 338_CR23 publication-title: Neural Netw. doi: 10.1016/S0893-6080(05)80023-1 – ident: 338_CR25 – ident: 338_CR20 doi: 10.1002/9781118548387 – volume: 135 start-page: 370 year: 1972 ident: 338_CR13 publication-title: J. R. Stat. Soc. Ser. A (Gen.) doi: 10.2307/2344614 – volume: 45 start-page: 5 year: 2001 ident: 338_CR19 publication-title: Mach. Learn. doi: 10.1023/A:1010933404324 – ident: 338_CR1 doi: 10.1016/j.ncl.2011.01.001 – ident: 338_CR11 – ident: 338_CR17 – volume: 370 start-page: 389 year: 2007 ident: 338_CR9 publication-title: Lancet doi: 10.1016/S0140-6736(07)61194-5 – volume: 356 start-page: 2603 year: 2007 ident: 338_CR4 publication-title: N. Engl. J. Med. doi: 10.1056/NEJMoa067597 – volume: 5 start-page: 532 year: 2006 ident: 338_CR16 publication-title: Autoimmun. Rev. doi: 10.1016/j.autrev.2006.02.012 – volume: 14 start-page: 771 year: 1999 ident: 338_CR24 publication-title: J.-Jpn. Soc. Artif. Intell. – volume: 112 start-page: 133 year: 1989 ident: 338_CR6 publication-title: Brain doi: 10.1093/brain/112.1.133 – ident: 338_CR5 doi: 10.1007/s100720070021 – volume: 33 start-page: 1444 year: 1983 ident: 338_CR10 publication-title: Neurology doi: 10.1212/WNL.33.11.1444 – volume: 112 start-page: 1419 year: 1989 ident: 338_CR7 publication-title: Brain doi: 10.1093/brain/112.6.1419 – reference: 33299133 - NPJ Digit Med. 2020 Nov 20;3(1):155 |
| SSID | ssj0002048946 |
| Score | 2.35389 |
| Snippet | The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to predict... Abstract The rate of disability accumulation varies across multiple sclerosis (MS) patients. Machine learning techniques may offer more powerful means to... |
| SourceID | doaj pubmedcentral proquest pubmed crossref springer |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 135 |
| SubjectTerms | 692/617/375/1411/1666 692/617/375/1666 Algorithms Biomedicine Biotechnology Datasets Digital technology Health informatics Machine learning Medicine Medicine & Public Health Multiple sclerosis |
| SummonAdditionalLinks | – databaseName: ProQuest Central dbid: BENPR link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwEB7BFqFeeD8CBRmJG0SNYyd2ToiirUCC1QoVqTfLsZ2yUkm2my2_n5mss9Xy6IVrbEd2Zsb5xjP-BuB1LXiZ-5CljbAhlbwpUuuDS5WzTWULUTTNwK7_Wc1m-vS0mscDtz6mVY574rBR-87RGflhXuRal6Is9bvlRUpVoyi6Gkto3IQ9YiqTE9g7ms7mX7enLERLW8ky3pbJhD7sJWJwyrulC9Xon6V65480EPf_DW3-mTT5W-R0-CEd3_3fpdyDOxGKsvcb3bkPN0L7AG5_icH2hzCftn34UZ8HFktLnLHlilrXPRvzEFmPQ3FZi57FUA9zHeWFsEXLEFsy2rU_nbCBxfYRfDuennz4mMYCDKlDv2adKpnZ4LSTZdBWCoROVUN4p8q9rX2oCuXRWyt8qEsrucMVSY8QI2SqRq-KW_EYJm3XhqfAsiBspj0XPnCptLMVD-htKouApapznwAfhWBcZCenIhnnZoiSC202gjMoODMIzugE3mzHLDfcHNf2PiLZbnsSr_bwoFudmWimRtReW42wxTZChrqoEd85L1UmufXoiyZwMIrURGPvzZU8E3i1bUYzpdiLbUN3iX0owK1UmakEnmwUaTsTIQgHK3y52lGxnanutrSL7wMVuCqIAJAn8HZUxqtp_ftTPLt-Fc9hPyf7oLyd8gAm69VleAG33M_1ol-9jCb2C-pjLfU priority: 102 providerName: ProQuest |
| Title | Ensemble learning predicts multiple sclerosis disease course in the SUMMIT study |
| URI | https://link.springer.com/article/10.1038/s41746-020-00338-8 https://www.ncbi.nlm.nih.gov/pubmed/33083570 https://www.proquest.com/docview/2528863668 https://www.proquest.com/docview/2452977607 https://pubmed.ncbi.nlm.nih.gov/PMC7567781 https://doaj.org/article/3bd8a8242af34eb5b172cd47041ad140 |
| Volume | 3 |
| WOSCitedRecordID | wos000583291400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2398-6352 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002048946 issn: 2398-6352 databaseCode: DOA dateStart: 20180101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2398-6352 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002048946 issn: 2398-6352 databaseCode: M~E dateStart: 20180101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Nursing & Allied Health Database customDbUrl: eissn: 2398-6352 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002048946 issn: 2398-6352 databaseCode: 7RV dateStart: 20181201 isFulltext: true titleUrlDefault: https://search.proquest.com/nahs providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2398-6352 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002048946 issn: 2398-6352 databaseCode: BENPR dateStart: 20181201 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Health & Medical Collection customDbUrl: eissn: 2398-6352 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002048946 issn: 2398-6352 databaseCode: 7X7 dateStart: 20181201 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: Publicly Available Content Database customDbUrl: eissn: 2398-6352 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002048946 issn: 2398-6352 databaseCode: PIMPY dateStart: 20181201 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB5BQagXxLuhZWUkbhA1jp3YObZoKyrRVVQVtJwsx3bKVm222mz5_Ywd79LleeESKbGdTMZj-xvN-DPAm4bRMrcuS1umXcppW6TaOpMKo9tKF6xo28Cu_1FMJnI6repbR335nLCBHnhQ3D5rrNQSFxLdMu6aosEV11guMk61Re_Az76Iem45UxchvMZlxcu4SyZjcr_niL19vq3fSI1-WSo3VqJA2P87lPlrsuRPEdOwEB09gocRQZKDQfLHcMd1T-DBSYyRP4V63PXuqrl0JJ4IcU6uF7502ZNV-iDpsSlKNetJjNAQM_fpHGTWEYSExE-2x2ckkM8-g09H47P3H9J4bkJq0B1ZpoJn2hlpeOmk5gwRT9V6mFLlVjfWVYWw6GQV1jWl5tSwsuQWkYHLRIPOENXsOWx1887tAMkc05m0lFlHuZBGV9Shkyg04oyqyW0CdKVDZSKpuD_b4lKF4DaTatC7Qr2roHclE3i7bnM9UGr8tfah75p1TU-HHR6gkahoJOpfRpLA3qpjVRyjvcqLXMoS_x6_8XpdjKPLh0x05-Y3WMfHpYUoM5HAi8EO1pIw5uGrwJeLDQvZEHWzpJt9DQzeovC8fTSBdytb-iHWn1Xx8n-oYhe2cz8IfFJOuQdby8WNewX3zbflrF-M4K44_eyvUxGucgT3DseT-nQUxhfe1ccn9ZfvJ-8kag |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VgoAL70eggJHgRKPGsRM7B4R4tOqq21WFFtSbcWynrFSSZbMF8af4jYzzqpZHbz1wjZ3EcT7PfOMZzwA8yxlNY-uisGDahZwWSaitM6Ewush0wpKiaLLrj8VkIg8Ps4M1-NmfhfFhlb1MbAS1rYzfI9-Kk1jKlKWpfDX_GvqqUd672pfQaGGx5358R5Otfjl6h__3eRzvbE_f7oZdVYHQIFlfhoJH2hlpeOqk5gz5QFZ4JZ7FVufWZYmwaIIk1uWp5tTgG7lFvekikaOpQDXD516AiyjHqQ8hE-8_Dns6PgluxtPubE7E5FbNkfH7KF9_fButwVCu6L-mTMDfuO2fIZq_-Wkb9bdz_X-buBtwrSPa5HW7Mm7CmitvweX9LpTgNhxsl7X7kh870hXOOCLzhW9d1qSPsiQ13orTOKtJ58gipvJRL2RWEmTOxOuk0ZQ0OXrvwIdz-Z67sF5WpbsPJHJMR9JSZh3lQhqdUYe2tNBIx7I8tgHQ_qcr0-Ve9yVAjlUTA8CkaoGiECiqAYqSAbwY7pm3mUfO7P3GY2no6bOGNxeqxZHqhJBiuZVaIinTBeMuT3Jkr8ZyEXGqLVraAWz0EFKdKKvVKX4CeDo0oxDyniVduuoE-3j3vRBpJAK41wJ3GAljnuULfLhYgfTKUFdbytnnJtG5SHx6QxrAZg_-02H9eyoenP0VT-DK7nR_rMajyd5DuBr7tekjlNINWF8uTtwjuGS-LWf14nGzuAl8Ou9F8QszBoiD |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Ensemble+learning+predicts+multiple+sclerosis+disease+course+in+the+SUMMIT+study&rft.jtitle=NPJ+digital+medicine&rft.au=Zhao%2C+Yijun&rft.au=Wang%2C+Tong&rft.au=Bove%2C+Riley&rft.au=Cree%2C+Bruce&rft.date=2020-10-16&rft.pub=Nature+Publishing+Group+UK&rft.eissn=2398-6352&rft.volume=3&rft.issue=1&rft_id=info:doi/10.1038%2Fs41746-020-00338-8&rft.externalDocID=10_1038_s41746_020_00338_8 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2398-6352&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2398-6352&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2398-6352&client=summon |