Prediction of COVID-19 deterioration in high-risk patients at diagnosis: an early warning score for advanced COVID-19 developed by machine learning

  1. Mahajan, Ujjwal Mukund
  2. Oswald, Marcus
  3. Mayerle, Julia
  4. Pletz, Mathias
  5. Spinner, Christoph D.
  6. Scherer, Clemens
  7. Rüthrich, Maria
  8. Massberg, Steffen
  9. Er, Ahmet Görkem
  10. Stubbe, Hans
  11. König, Rainer
  12. Tometten, Lukas
  13. Rieg, Siegbert
  14. Merle, Uta
  15. Wille, Kai
  16. Borgmann, Stefan
  17. Spinner, Christoph
  18. Dolff, Sebastian
  19. Rüthrich, Maria Madeleine
  20. Hanses, Frank
  21. Hower, Martin
  22. Strauß, Richard
  23. Akova, Murat
  24. Jung, Norma
  25. von Bergwelt-Baildon, Michael
  26. Vehreschild, Maria
  27. Grüner, Beate
  28. Haselberger, Martina
  29. Isberner, Nora
  30. Piepel, Christiane
  31. Hellwig, Kerstin
  32. Rauschning, Dominic
  33. Eberwein, Lukas
  34. Jensen, Björn
  35. Raichle, Claudia
  36. Müller-Jörger, Gabriele
  37. Stieglitz, Sven
  38. Kratz, Thomas
  39. Degenhardt, Christian
  40. Friedrichs, Anette
  41. Bals, Robert
  42. Rüger, Susanne
  43. With, Katja
  44. Rothfuss, Katja
  45. Goepel, Siri
  46. Nattermann, Jacob
  47. Jordan, Sabine
  48. Rüddel, Jessica
  49. Trauth, Janina
  50. Beutel, Gernot
  51. Aydin, Ozlem Altuntas
  52. Milovanovic, Milena
  53. Doll, Michael
  54. Vehreschild, Jörg Janne
  55. Pilgram, Lisa
  56. Stecher, Melanie
  57. Jakob, Carolin E. M.
  58. Schons, Maximilian
  59. Claßen, Annika
  60. Fuhrmann, Sandra
  61. de Miranda, Susana Nunes
  62. Franke, Bernd
  63. Schulze, Nick
  64. Prasser, Fabian
  65. Lablans, Martin

Download
s15010-021-01656-z.pdf 1,49MB
WeightNameValue
1000 Titel
  • Prediction of COVID-19 deterioration in high-risk patients at diagnosis: an early warning score for advanced COVID-19 developed by machine learning
1000 Autor/in
  1. Mahajan, Ujjwal Mukund |
  2. Oswald, Marcus |
  3. Mayerle, Julia |
  4. Pletz, Mathias |
  5. Spinner, Christoph D. |
  6. Scherer, Clemens |
  7. Rüthrich, Maria |
  8. Massberg, Steffen |
  9. Er, Ahmet Görkem |
  10. Stubbe, Hans |
  11. König, Rainer |
  12. Tometten, Lukas |
  13. Rieg, Siegbert |
  14. Merle, Uta |
  15. Wille, Kai |
  16. Borgmann, Stefan |
  17. Spinner, Christoph |
  18. Dolff, Sebastian |
  19. Rüthrich, Maria Madeleine |
  20. Hanses, Frank |
  21. Hower, Martin |
  22. Strauß, Richard |
  23. Akova, Murat |
  24. Jung, Norma |
  25. von Bergwelt-Baildon, Michael |
  26. Vehreschild, Maria |
  27. Grüner, Beate |
  28. Haselberger, Martina |
  29. Isberner, Nora |
  30. Piepel, Christiane |
  31. Hellwig, Kerstin |
  32. Rauschning, Dominic |
  33. Eberwein, Lukas |
  34. Jensen, Björn |
  35. Raichle, Claudia |
  36. Müller-Jörger, Gabriele |
  37. Stieglitz, Sven |
  38. Kratz, Thomas |
  39. Degenhardt, Christian |
  40. Friedrichs, Anette |
  41. Bals, Robert |
  42. Rüger, Susanne |
  43. With, Katja |
  44. Rothfuss, Katja |
  45. Goepel, Siri |
  46. Nattermann, Jacob |
  47. Jordan, Sabine |
  48. Rüddel, Jessica |
  49. Trauth, Janina |
  50. Beutel, Gernot |
  51. Aydin, Ozlem Altuntas |
  52. Milovanovic, Milena |
  53. Doll, Michael |
  54. Vehreschild, Jörg Janne |
  55. Pilgram, Lisa |
  56. Stecher, Melanie |
  57. Jakob, Carolin E. M. |
  58. Schons, Maximilian |
  59. Claßen, Annika |
  60. Fuhrmann, Sandra |
  61. de Miranda, Susana Nunes |
  62. Franke, Bernd |
  63. Schulze, Nick |
  64. Prasser, Fabian |
  65. Lablans, Martin |
1000 Erscheinungsjahr 2021
1000 Publikationstyp
  1. Artikel |
1000 Online veröffentlicht
  • 2021-07-19
1000 Erschienen in
1000 Quellenangabe
  • 50(2):359-370
1000 Copyrightjahr
  • 2021
1000 Lizenz
1000 Verlagsversion
  • https://doi.org/10.1007/s15010-021-01656-z |
  • https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8287547/ |
1000 Publikationsstatus
1000 Sprache der Publikation
1000 Abstract/Summary
  • Purpose!#!While more advanced COVID-19 necessitates medical interventions and hospitalization, patients with mild COVID-19 do not require this. Identifying patients at risk of progressing to advanced COVID-19 might guide treatment decisions, particularly for better prioritizing patients in need for hospitalization.!##!Methods!#!We developed a machine learning-based predictor for deriving a clinical score identifying patients with asymptomatic/mild COVID-19 at risk of progressing to advanced COVID-19. Clinical data from SARS-CoV-2 positive patients from the multicenter Lean European Open Survey on SARS-CoV-2 Infected Patients (LEOSS) were used for discovery (2020-03-16 to 2020-07-14) and validation (data from 2020-07-15 to 2021-02-16).!##!Results!#!The LEOSS dataset contains 473 baseline patient parameters measured at the first patient contact. After training the predictor model on a training dataset comprising 1233 patients, 20 of the 473 parameters were selected for the predictor model. From the predictor model, we delineated a composite predictive score (SACOV-19, Score for the prediction of an Advanced stage of COVID-19) with eleven variables. In the validation cohort (n = 2264 patients), we observed good prediction performance with an area under the curve (AUC) of 0.73 ± 0.01. Besides temperature, age, body mass index and smoking habit, variables indicating pulmonary involvement (respiration rate, oxygen saturation, dyspnea), inflammation (CRP, LDH, lymphocyte counts), and acute kidney injury at diagnosis were identified. For better interpretability, the predictor was translated into a web interface.!##!Conclusion!#!We present a machine learning-based predictor model and a clinical score for identifying patients at risk of developing advanced COVID-19.
1000 Sacherschließung
lokal COVID-19/diagnosis [MeSH]
gnd 1206347392 COVID-19
lokal Advanced stage
lokal Area Under Curve [MeSH]
lokal Machine learning
lokal LEOSS
lokal Humans [MeSH]
lokal Retrospective Studies [MeSH]
lokal COVID-19
lokal COVID-19 / SARS-CoV-2
lokal Early Warning Score [MeSH]
lokal Original Paper
lokal Predictive model
lokal Machine Learning [MeSH]
lokal SARS-CoV-2 [MeSH]
lokal Complicated stage
1000 Liste der Beteiligten
  1. https://frl.publisso.de/adhoc/uri/TWFoYWphbiwgVWpqd2FsIE11a3VuZA==|https://frl.publisso.de/adhoc/uri/T3N3YWxkLCBNYXJjdXM=|https://frl.publisso.de/adhoc/uri/TWF5ZXJsZSwgSnVsaWE=|https://frl.publisso.de/adhoc/uri/UGxldHosIE1hdGhpYXM=|https://frl.publisso.de/adhoc/uri/U3Bpbm5lciwgQ2hyaXN0b3BoIEQu|https://frl.publisso.de/adhoc/uri/U2NoZXJlciwgQ2xlbWVucw==|https://frl.publisso.de/adhoc/uri/UsO8dGhyaWNoLCBNYXJpYQ==|https://frl.publisso.de/adhoc/uri/TWFzc2JlcmcsIFN0ZWZmZW4=|https://frl.publisso.de/adhoc/uri/RXIsIEFobWV0IEfDtnJrZW0=|https://frl.publisso.de/adhoc/uri/U3R1YmJlLCBIYW5z|https://frl.publisso.de/adhoc/uri/S8O2bmlnLCBSYWluZXI=|https://frl.publisso.de/adhoc/uri/VG9tZXR0ZW4sIEx1a2Fz|https://frl.publisso.de/adhoc/uri/UmllZywgU2llZ2JlcnQ=|https://frl.publisso.de/adhoc/uri/TWVybGUsIFV0YQ==|https://frl.publisso.de/adhoc/uri/V2lsbGUsIEthaQ==|https://frl.publisso.de/adhoc/uri/Qm9yZ21hbm4sIFN0ZWZhbg==|https://frl.publisso.de/adhoc/uri/U3Bpbm5lciwgQ2hyaXN0b3Bo|https://frl.publisso.de/adhoc/uri/RG9sZmYsIFNlYmFzdGlhbg==|https://frl.publisso.de/adhoc/uri/UsO8dGhyaWNoLCBNYXJpYSBNYWRlbGVpbmU=|https://frl.publisso.de/adhoc/uri/SGFuc2VzLCBGcmFuaw==|https://frl.publisso.de/adhoc/uri/SG93ZXIsIE1hcnRpbg==|https://frl.publisso.de/adhoc/uri/U3RyYXXDnywgUmljaGFyZA==|https://frl.publisso.de/adhoc/uri/QWtvdmEsIE11cmF0|https://frl.publisso.de/adhoc/uri/SnVuZywgTm9ybWE=|https://frl.publisso.de/adhoc/uri/dm9uIEJlcmd3ZWx0LUJhaWxkb24sIE1pY2hhZWw=|https://frl.publisso.de/adhoc/uri/VmVocmVzY2hpbGQsIE1hcmlh|https://frl.publisso.de/adhoc/uri/R3LDvG5lciwgQmVhdGU=|https://frl.publisso.de/adhoc/uri/SGFzZWxiZXJnZXIsIE1hcnRpbmE=|https://frl.publisso.de/adhoc/uri/SXNiZXJuZXIsIE5vcmE=|https://frl.publisso.de/adhoc/uri/UGllcGVsLCBDaHJpc3RpYW5l|https://frl.publisso.de/adhoc/uri/SGVsbHdpZywgS2Vyc3Rpbg==|https://frl.publisso.de/adhoc/uri/UmF1c2NobmluZywgRG9taW5pYw==|https://frl.publisso.de/adhoc/uri/RWJlcndlaW4sIEx1a2Fz|https://frl.publisso.de/adhoc/uri/SmVuc2VuLCBCasO2cm4=|https://frl.publisso.de/adhoc/uri/UmFpY2hsZSwgQ2xhdWRpYQ==|https://frl.publisso.de/adhoc/uri/TcO8bGxlci1Kw7ZyZ2VyLCBHYWJyaWVsZQ==|https://frl.publisso.de/adhoc/uri/U3RpZWdsaXR6LCBTdmVu|https://frl.publisso.de/adhoc/uri/S3JhdHosIFRob21hcw==|https://frl.publisso.de/adhoc/uri/RGVnZW5oYXJkdCwgQ2hyaXN0aWFu|https://frl.publisso.de/adhoc/uri/RnJpZWRyaWNocywgQW5ldHRl|https://frl.publisso.de/adhoc/uri/QmFscywgUm9iZXJ0|https://frl.publisso.de/adhoc/uri/UsO8Z2VyLCBTdXNhbm5l|https://frl.publisso.de/adhoc/uri/V2l0aCwgS2F0amE=|https://frl.publisso.de/adhoc/uri/Um90aGZ1c3MsIEthdGph|https://frl.publisso.de/adhoc/uri/R29lcGVsLCBTaXJp|https://frl.publisso.de/adhoc/uri/TmF0dGVybWFubiwgSmFjb2I=|https://frl.publisso.de/adhoc/uri/Sm9yZGFuLCBTYWJpbmU=|https://frl.publisso.de/adhoc/uri/UsO8ZGRlbCwgSmVzc2ljYQ==|https://frl.publisso.de/adhoc/uri/VHJhdXRoLCBKYW5pbmE=|https://frl.publisso.de/adhoc/uri/QmV1dGVsLCBHZXJub3Q=|https://frl.publisso.de/adhoc/uri/QXlkaW4sIE96bGVtIEFsdHVudGFz|https://frl.publisso.de/adhoc/uri/TWlsb3Zhbm92aWMsIE1pbGVuYQ==|https://frl.publisso.de/adhoc/uri/RG9sbCwgTWljaGFlbA==|https://frl.publisso.de/adhoc/uri/VmVocmVzY2hpbGQsIErDtnJnIEphbm5l|https://frl.publisso.de/adhoc/uri/UGlsZ3JhbSwgTGlzYQ==|https://frl.publisso.de/adhoc/uri/U3RlY2hlciwgTWVsYW5pZQ==|https://frl.publisso.de/adhoc/uri/SmFrb2IsIENhcm9saW4gRS4gTS4=|https://frl.publisso.de/adhoc/uri/U2Nob25zLCBNYXhpbWlsaWFu|https://frl.publisso.de/adhoc/uri/Q2xhw59lbiwgQW5uaWth|https://frl.publisso.de/adhoc/uri/RnVocm1hbm4sIFNhbmRyYQ==|https://frl.publisso.de/adhoc/uri/ZGUgTWlyYW5kYSwgU3VzYW5hIE51bmVz|https://frl.publisso.de/adhoc/uri/RnJhbmtlLCBCZXJuZA==|https://frl.publisso.de/adhoc/uri/U2NodWx6ZSwgTmljaw==|https://frl.publisso.de/adhoc/uri/UHJhc3NlciwgRmFiaWFu|https://frl.publisso.de/adhoc/uri/TGFibGFucywgTWFydGlu
1000 Hinweis
  • DeepGreen-ID: 26e1a891e9d045169b3a9c892d85a90d ; metadata provieded by: DeepGreen (https://www.oa-deepgreen.de/api/v1/), LIVIVO search scope life sciences (http://z3950.zbmed.de:6210/livivo), Crossref Unified Resource API (https://api.crossref.org/swagger-ui/index.html), to.science.api (https://frl.publisso.de/), ZDB JSON-API (beta) (https://zeitschriftendatenbank.de/api/), lobid - Dateninfrastruktur für Bibliotheken (https://lobid.org/resources/search)
1000 Label
1000 Dateien
1000 Objektart article
1000 Beschrieben durch
1000 @id frl:6444032.rdf
1000 Erstellt am 2023-04-27T11:44:40.692+0200
1000 Erstellt von 322
1000 beschreibt frl:6444032
1000 Zuletzt bearbeitet Fri Oct 20 11:53:19 CEST 2023
1000 Objekt bearb. Fri Oct 20 11:53:19 CEST 2023
1000 Vgl. frl:6444032
1000 Oai Id
  1. oai:frl.publisso.de:frl:6444032 |
1000 Sichtbarkeit Metadaten public
1000 Sichtbarkeit Daten public
1000 Gegenstand von

View source