Crowd-sourced machine learning prediction of long COVID using data from the National COVID Cohort CollaborativeResearch in context
Background: While many patients seem to recover from SARS-CoV-2 infections, many patients report experiencing SARS-CoV-2 symptoms for weeks or months after their acute COVID-19 ends, even developing new symptoms weeks after infection. These long-term effects are called post-acute sequelae of SARS-Co...
Saved in:
| Published in: | EBioMedicine Vol. 108; p. 105333 |
|---|---|
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier
01-10-2024
|
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Background: While many patients seem to recover from SARS-CoV-2 infections, many patients report experiencing SARS-CoV-2 symptoms for weeks or months after their acute COVID-19 ends, even developing new symptoms weeks after infection. These long-term effects are called post-acute sequelae of SARS-CoV-2 (PASC) or, more commonly, Long COVID. The overall prevalence of Long COVID is currently unknown, and tools are needed to help identify patients at risk for developing long COVID. Methods: A working group of the Rapid Acceleration of Diagnostics-radical (RADx-rad) program, comprised of individuals from various NIH institutes and centers, in collaboration with REsearching COVID to Enhance Recovery (RECOVER) developed and organized the Long COVID Computational Challenge (L3C), a community challenge aimed at incentivizing the broader scientific community to develop interpretable and accurate methods for identifying patients at risk of developing Long COVID. From August 2022 to December 2022, participants developed Long COVID risk prediction algorithms using the National COVID Cohort Collaborative (N3C) data enclave, a harmonized data repository from over 75 healthcare institutions from across the United States (U.S.). Findings: Over the course of the challenge, 74 teams designed and built 35 Long COVID prediction models using the N3C data enclave. The top 10 teams all scored above a 0.80 Area Under the Receiver Operator Curve (AUROC) with the highest scoring model achieving a mean AUROC of 0.895. Included in the top submission was a visualization dashboard that built timelines for each patient, updating the risk of a patient developing Long COVID in response to clinical events. Interpretation: As a result of L3C, federal reviewers identified multiple machine learning models that can be used to identify patients at risk for developing Long COVID. Many of the teams used approaches in their submissions which can be applied to future clinical prediction questions. Funding: Research reported in this RADx® Rad publication was supported by the National Institutes of Health. Timothy Bergquist, Johanna Loomba, and Emily Pfaff were supported by Axle Subcontract: NCATS-STSS-P00438. |
|---|---|
| AbstractList | Background: While many patients seem to recover from SARS-CoV-2 infections, many patients report experiencing SARS-CoV-2 symptoms for weeks or months after their acute COVID-19 ends, even developing new symptoms weeks after infection. These long-term effects are called post-acute sequelae of SARS-CoV-2 (PASC) or, more commonly, Long COVID. The overall prevalence of Long COVID is currently unknown, and tools are needed to help identify patients at risk for developing long COVID. Methods: A working group of the Rapid Acceleration of Diagnostics-radical (RADx-rad) program, comprised of individuals from various NIH institutes and centers, in collaboration with REsearching COVID to Enhance Recovery (RECOVER) developed and organized the Long COVID Computational Challenge (L3C), a community challenge aimed at incentivizing the broader scientific community to develop interpretable and accurate methods for identifying patients at risk of developing Long COVID. From August 2022 to December 2022, participants developed Long COVID risk prediction algorithms using the National COVID Cohort Collaborative (N3C) data enclave, a harmonized data repository from over 75 healthcare institutions from across the United States (U.S.). Findings: Over the course of the challenge, 74 teams designed and built 35 Long COVID prediction models using the N3C data enclave. The top 10 teams all scored above a 0.80 Area Under the Receiver Operator Curve (AUROC) with the highest scoring model achieving a mean AUROC of 0.895. Included in the top submission was a visualization dashboard that built timelines for each patient, updating the risk of a patient developing Long COVID in response to clinical events. Interpretation: As a result of L3C, federal reviewers identified multiple machine learning models that can be used to identify patients at risk for developing Long COVID. Many of the teams used approaches in their submissions which can be applied to future clinical prediction questions. Funding: Research reported in this RADx® Rad publication was supported by the National Institutes of Health. Timothy Bergquist, Johanna Loomba, and Emily Pfaff were supported by Axle Subcontract: NCATS-STSS-P00438. |
| Author | Souradeep Dutta Phoebe Dijour Corneliu Antonescu Albi Domi Eric Wong Neelay Velingker Adit Anand Zeyuan Chen Robert Cockrell Tanner Asmussen Gaurav Shetty Mohamed Ghalwash Danielle Mowery Sanjoy Dey Laila Bekhet Anseh Danesharasteh Parker Combs Solomon Feuerwerker Oluwatobiloba Aminu Samer Hanoudi Ciara Crosby John M. Colford, Jr Yitan Zhu Elif Yildirim Yunwen Ji Mehak Arora Mirna Elizondo Emily Pfaff Ran Dai Elliot Mitchell Ryan Demilt Colby Ham Ravi Parekh Jake Hightower Timothy Bergquist Grant Delong Jennifer Fowler Ataes Aggarwal Phil Greer Frazier Baker Rachael V. Philips Mahdi Baghbanzadeh Logan Gloster Nathaniel Hendrix Andrew Mertens Brian Caffo Richard Dixon Adbul Tariq Tamanna Munia Danica Fliss Kelly Gardner Haodong Li Romain Pirracchio Andrew Dickson Ziyang Li Leeor Hershkovich Jennifer Blase Jenny Blase Jiandong Chen Neil Getty Junjie Hu John Holmes Zeynep Ertem Zixuan Zhao Yinjun Wu Jeremy Harper Adam Stein Seraphina Shi Mark van der Laan Joseph Agor Bridget Bangert Qi Long Jifan Gao Jiani Huang Hao Chang Alan Hubbard Zongyu Dai Peter Cho Fangfang |
| Author_xml | – sequence: 1 fullname: Timothy Bergquist organization: Sage Bionetworks, Seattle, WA, USA; Corresponding author – sequence: 2 fullname: Johanna Loomba organization: University of Virginia, Charlottesville, VA, USA – sequence: 3 fullname: Emily Pfaff organization: University of North Carolina at Chapel Hill, Durham, NC, USA – sequence: 4 fullname: Fangfang Xia organization: University of Chicago, Chicago, IL, USA – sequence: 5 fullname: Zixuan Zhao organization: University of Chicago, Chicago, IL, USA – sequence: 6 fullname: Yitan Zhu organization: University of Chicago, Chicago, IL, USA – sequence: 7 fullname: Elliot Mitchell organization: Geisinger Health System, New York, NY, USA – sequence: 8 fullname: Biplab Bhattacharya organization: Geisinger Health System, New York, NY, USA – sequence: 9 fullname: Gaurav Shetty organization: Geisinger Health System, New York, NY, USA – sequence: 10 fullname: Tamanna Munia organization: Geisinger Health System, New York, NY, USA – sequence: 11 fullname: Grant Delong organization: Geisinger Health System, New York, NY, USA – sequence: 12 fullname: Adbul Tariq organization: Geisinger Health System, New York, NY, USA – sequence: 13 fullname: Zachary Butzin-Dozier organization: University of California Berkeley, Berkeley, CA, USA – sequence: 14 fullname: Yunwen Ji organization: University of California Berkeley, Berkeley, CA, USA – sequence: 15 fullname: Haodong Li organization: University of California Berkeley, Berkeley, CA, USA – sequence: 16 fullname: Jeremy Coyle organization: University of California Berkeley, Berkeley, CA, USA – sequence: 17 fullname: Seraphina Shi organization: University of California Berkeley, Berkeley, CA, USA – sequence: 18 fullname: Rachael V. Philips organization: University of California Berkeley, Berkeley, CA, USA – sequence: 19 fullname: Andrew Mertens organization: University of California Berkeley, Berkeley, CA, USA – sequence: 20 fullname: Romain Pirracchio organization: University of California, San Francisco, San Francisco, CA, USA – sequence: 21 fullname: Mark van der Laan organization: University of California Berkeley, Berkeley, CA, USA – sequence: 22 fullname: John M. Colford, Jr organization: University of California Berkeley, Berkeley, CA, USA – sequence: 23 fullname: Alan Hubbard organization: University of California Berkeley, Berkeley, CA, USA – sequence: 24 fullname: Jifan Gao organization: University of Wisconsin–Madison, Madison, WI, USA – sequence: 25 fullname: Guanhua Chen organization: University of Wisconsin–Madison, Madison, WI, USA – sequence: 26 fullname: Neelay Velingker organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 27 fullname: Ziyang Li organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 28 fullname: Yinjun Wu organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 29 fullname: Adam Stein organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 30 fullname: Jiani Huang organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 31 fullname: Zongyu Dai organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 32 fullname: Qi Long organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 33 fullname: Mayur Naik organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 34 fullname: John Holmes organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 35 fullname: Danielle Mowery organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 36 fullname: Eric Wong organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 37 fullname: Ravi Parekh organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 38 fullname: Emily Getzen organization: University of Pennsylvania, Philadelphia, PA, USA – sequence: 39 fullname: Jake Hightower organization: Ruvos, Tallahassee, FL, USA – sequence: 40 fullname: Jennifer Blase organization: Ruvos, Tallahassee, FL, USA – sequence: 41 fullname: Ataes Aggarwal – sequence: 42 fullname: Joseph Agor – sequence: 43 fullname: Amera Al-Amery – sequence: 44 fullname: Oluwatobiloba Aminu – sequence: 45 fullname: Adit Anand – sequence: 46 fullname: Corneliu Antonescu – sequence: 47 fullname: Mehak Arora – sequence: 48 fullname: Sayed Asaduzzaman – sequence: 49 fullname: Tanner Asmussen – sequence: 50 fullname: Mahdi Baghbanzadeh – sequence: 51 fullname: Frazier Baker – sequence: 52 fullname: Bridget Bangert – sequence: 53 fullname: Laila Bekhet – sequence: 54 fullname: Biplab Bhattacharya – sequence: 55 fullname: Jenny Blase – sequence: 56 fullname: Zachary Butzin-Dozier – sequence: 57 fullname: Brian Caffo – sequence: 58 fullname: Hao Chang – sequence: 59 fullname: Zeyuan Chen – sequence: 60 fullname: Jiandong Chen – sequence: 61 fullname: Jeffrey Chiang – sequence: 62 fullname: Peter Cho – sequence: 63 fullname: Robert Cockrell – sequence: 64 fullname: Parker Combs – sequence: 65 fullname: Jeremy Coyle – sequence: 66 fullname: Ciara Crosby – sequence: 67 fullname: Zongyu Dai – sequence: 68 fullname: Ran Dai – sequence: 69 fullname: Anseh Danesharasteh – sequence: 70 fullname: Elif Yildirim – sequence: 71 fullname: Grant Delong – sequence: 72 fullname: Ryan Demilt – sequence: 73 fullname: Kaiwen Deng – sequence: 74 fullname: Sanjoy Dey – sequence: 75 fullname: Rohan Dhamdhere – sequence: 76 fullname: Andrew Dickson – sequence: 77 fullname: Phoebe Dijour – sequence: 78 fullname: Dong Dinh – sequence: 79 fullname: Richard Dixon – sequence: 80 fullname: Albi Domi – sequence: 81 fullname: Souradeep Dutta – sequence: 82 fullname: Mirna Elizondo – sequence: 83 fullname: Zeynep Ertem – sequence: 84 fullname: Solomon Feuerwerker – sequence: 85 fullname: Danica Fliss – sequence: 86 fullname: Jennifer Fowler – sequence: 87 fullname: Sunyang Fu – sequence: 88 fullname: Kelly Gardner – sequence: 89 fullname: Neil Getty – sequence: 90 fullname: Mohamed Ghalwash – sequence: 91 fullname: Logan Gloster – sequence: 92 fullname: Phil Greer – sequence: 93 fullname: Yuanfang Guan – sequence: 94 fullname: Colby Ham – sequence: 95 fullname: Samer Hanoudi – sequence: 96 fullname: Jeremy Harper – sequence: 97 fullname: Nathaniel Hendrix – sequence: 98 fullname: Leeor Hershkovich – sequence: 99 fullname: Jake Hightower – sequence: 100 fullname: Junjie Hu |
| BookMark | eNqtjN1Kw0AQRhex0Kp9h3mBQP7TXkfF3iiIeBsmk9lmy2an7G79ufXJTaWP4NWBcz6-G3XtxPGVWuVFlSfFti6Xah3CIU3TrCpnuVmpn9bL55AEOXniASak0TgGy-idcXs4eh4MRSMORIOVWbUv77t7OIVzHjAiaC8TxJHhGc9DtJdJK6P4OMNa7MXP8YNfOczXNIJxQOIif8U7tdBoA68vvFW7x4e39ikZBA_d0ZsJ_XcnaLo_IX7foY-GLHeaNv02b6jOm7okzPpGZxn3VFKjK-yx-M-vX64_bkQ |
| ContentType | Journal Article |
| DBID | DOA |
| DatabaseName | Directory of Open Access Journals |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: http://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Biology |
| EISSN | 2352-3964 |
| ExternalDocumentID | oai_doaj_org_article_fc8b927c62764ca1b7f11ebc4c7f5aba |
| GroupedDBID | .1- .FO 0R~ 0SF 457 53G 5VS 6I. AACTN AAEDT AAEDW AAFTH AAIKJ AALRI AAMRU AAXUO ABMAC ACGFS ADBBV ADEZE ADVLN AEXQZ AFCTW AFRHN AFTJW AGHFR AITUG AJUYK AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ AOIJS BCNDV EBS FDB GROUPED_DOAJ HZ~ KQ8 NCXOZ OK1 ROL RPM SSZ Z5R |
| ID | FETCH-doaj_primary_oai_doaj_org_article_fc8b927c62764ca1b7f11ebc4c7f5aba3 |
| IEDL.DBID | DOA |
| IngestDate | Mon Oct 14 19:37:59 EDT 2024 |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-doaj_primary_oai_doaj_org_article_fc8b927c62764ca1b7f11ebc4c7f5aba3 |
| OpenAccessLink | https://doaj.org/article/fc8b927c62764ca1b7f11ebc4c7f5aba |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_fc8b927c62764ca1b7f11ebc4c7f5aba |
| PublicationCentury | 2000 |
| PublicationDate | 2024-10-01 |
| PublicationDateYYYYMMDD | 2024-10-01 |
| PublicationDate_xml | – month: 10 year: 2024 text: 2024-10-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | EBioMedicine |
| PublicationYear | 2024 |
| Publisher | Elsevier |
| Publisher_xml | – name: Elsevier |
| SSID | ssj0001542358 |
| Score | 4.641938 |
| Snippet | Background: While many patients seem to recover from SARS-CoV-2 infections, many patients report experiencing SARS-CoV-2 symptoms for weeks or months after... |
| SourceID | doaj |
| SourceType | Open Website |
| StartPage | 105333 |
| SubjectTerms | Community challenge COVID-19 Evaluation Long COVID Machine learning PASC |
| Title | Crowd-sourced machine learning prediction of long COVID using data from the National COVID Cohort CollaborativeResearch in context |
| URI | https://doaj.org/article/fc8b927c62764ca1b7f11ebc4c7f5aba |
| Volume | 108 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://sdu.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LS8QwEB50QfAiPvHNHLwW01fSPWp3l92LgoqIl5KkySqs7bLrCl795Waa-jp50EsPoTThG0i-ab75BuBEya6KM2OCSCjmEhTBgkyrNChTLqQ7fmPddFEYXouLu6zXJ5ucz1ZfpAnz9sAeuFOrM9WNhOaR4ImWoRI2DI3SiRY2lcpTI8a_JVO-PjihGtAfRvzNiTFYh7WW6uGZn2IDlky1CSu--ePrFrzlLgMuA__3vMSnRtVosG3jMMbpjO5QCDesLU5qN5Rf3o56SFL1MZK0E6k4BB2Fw9beetK-ktcPjlZj_hXkF_OhscPHCkmg7nblbRgN-jf5MKDlF1NvPFGQFXQz4AAqWoCK3wCKd6BT1ZXZBZRcsTKzTFllEs2ZTJmNHQXpUkFsHJo9OP_7fPv_8ZEDWI0ce_CquUPoPM8W5giW5-XiuAm0e96nV-9PIbta |
| link.rule.ids | 315,782,786,2106 |
| linkProvider | Directory of Open Access Journals |
| 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=Crowd-sourced+machine+learning+prediction+of+long+COVID+using+data+from+the+National+COVID+Cohort+CollaborativeResearch+in+context&rft.jtitle=EBioMedicine&rft.au=Timothy+Bergquist&rft.au=Johanna+Loomba&rft.au=Emily+Pfaff&rft.au=Fangfang+Xia&rft.date=2024-10-01&rft.pub=Elsevier&rft.eissn=2352-3964&rft.volume=108&rft.spage=105333&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_fc8b927c62764ca1b7f11ebc4c7f5aba |