Academic Journal
View in EDS

Artificial intelligence-based prediction of transfusion in the intensive care unit in patients with gastrointestinal bleeding

Bibliographic Details
Title: Artificial intelligence-based prediction of transfusion in the intensive care unit in patients with gastrointestinal bleeding
Authors: Levi R., Carli F., Arevalo A. R., Altinel Y., Stein D. J., Naldini M. M., Grassi F., Zanoni A., Finkelstein S., Vieira S. M., Sousa J., Barbieri R., Celi L. A.
Contributors: Levi, R., Carli, F., Arevalo, A. R., Altinel, Y., Stein, D. J., Naldini, M. M., Grassi, F., Zanoni, A., Finkelstein, S., Vieira, S. M., Sousa, J., Barbieri, R., Celi, L. A.
Publication Year: 2021
Collection: RE.PUBLIC@POLIMI - Research Publications at Politecnico di Milano
Subject Terms: BMJ health informatics, computer methodologies, Female, Humans, Male, Prospective Studies, ROC Curve, Artificial Intelligence, Blood Transfusion, Gastrointestinal Hemorrhage, Intensive Care Units
Description: Objective Gastrointestinal (GI) bleeding commonly requires intensive care unit (ICU) in cases of potentialhaemodynamiccompromise or likely urgent intervention. However, manypatientsadmitted to the ICU stop bleeding and do not require further intervention, including blood transfusion. The present work proposes an artificial intelligence (AI) solution for the prediction of rebleeding in patients with GI bleeding admitted to ICU. Methods A machine learning algorithm was trained and tested using two publicly available ICU databases, the Medical Information Mart for Intensive Care V.1.4 database and eICU Collaborative Research Database using freedom from transfusion as a proxy for patients who potentially did not require ICU-level care. Multiple initial observation time frames were explored using readily available data including labs, demographics and clinical parameters for a total of 20 covariates. Results The optimal model used a 5-hour observation period to achieve an area under the curve of the receiving operating curve (ROC-AUC) of greater than 0.80. The model was robust when tested against both ICU databases with a similar ROC-AUC for all. Conclusions The potential disruptive impact of AI in healthcare innovation is acknowledge, but awareness of AI-related risk on healthcare applications and current limitations should be considered before implementation and deployment. The proposed algorithm is not meant to replace but to inform clinical decision making. Prospective clinical trial validation as a triage tool is warranted.
Document Type: article in journal/newspaper
Language: English
Relation: info:eu-repo/semantics/altIdentifier/pmid/33455913; info:eu-repo/semantics/altIdentifier/wos/WOS:000612101300001; volume:28; issue:1; firstpage:1; lastpage:8; numberofpages:8; journal:BMJ HEALTH & CARE INFORMATICS; https://hdl.handle.net/11311/1203741
DOI: 10.1136/bmjhci-2020-100245
Availability: https://hdl.handle.net/11311/1203741
https://doi.org/10.1136/bmjhci-2020-100245
Rights: info:eu-repo/semantics/openAccess
Accession Number: edsbas.D493A3E3
Database: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://hdl.handle.net/11311/1203741#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.D493A3E3
RelevancyScore: 906
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 906.347900390625
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Artificial intelligence-based prediction of transfusion in the intensive care unit in patients with gastrointestinal bleeding
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Levi+R%2E%22">Levi R.</searchLink><br /><searchLink fieldCode="AR" term="%22Carli+F%2E%22">Carli F.</searchLink><br /><searchLink fieldCode="AR" term="%22Arevalo+A%2E+R%2E%22">Arevalo A. R.</searchLink><br /><searchLink fieldCode="AR" term="%22Altinel+Y%2E%22">Altinel Y.</searchLink><br /><searchLink fieldCode="AR" term="%22Stein+D%2E+J%2E%22">Stein D. J.</searchLink><br /><searchLink fieldCode="AR" term="%22Naldini+M%2E+M%2E%22">Naldini M. M.</searchLink><br /><searchLink fieldCode="AR" term="%22Grassi+F%2E%22">Grassi F.</searchLink><br /><searchLink fieldCode="AR" term="%22Zanoni+A%2E%22">Zanoni A.</searchLink><br /><searchLink fieldCode="AR" term="%22Finkelstein+S%2E%22">Finkelstein S.</searchLink><br /><searchLink fieldCode="AR" term="%22Vieira+S%2E+M%2E%22">Vieira S. M.</searchLink><br /><searchLink fieldCode="AR" term="%22Sousa+J%2E%22">Sousa J.</searchLink><br /><searchLink fieldCode="AR" term="%22Barbieri+R%2E%22">Barbieri R.</searchLink><br /><searchLink fieldCode="AR" term="%22Celi+L%2E+A%2E%22">Celi L. A.</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Levi, R.<br />Carli, F.<br />Arevalo, A. R.<br />Altinel, Y.<br />Stein, D. J.<br />Naldini, M. M.<br />Grassi, F.<br />Zanoni, A.<br />Finkelstein, S.<br />Vieira, S. M.<br />Sousa, J.<br />Barbieri, R.<br />Celi, L. A.
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2021
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: RE.PUBLIC@POLIMI - Research Publications at Politecnico di Milano
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22BMJ+health+informatics%22">BMJ health informatics</searchLink><br /><searchLink fieldCode="DE" term="%22computer+methodologies%22">computer methodologies</searchLink><br /><searchLink fieldCode="DE" term="%22Female%22">Female</searchLink><br /><searchLink fieldCode="DE" term="%22Humans%22">Humans</searchLink><br /><searchLink fieldCode="DE" term="%22Male%22">Male</searchLink><br /><searchLink fieldCode="DE" term="%22Prospective+Studies%22">Prospective Studies</searchLink><br /><searchLink fieldCode="DE" term="%22ROC+Curve%22">ROC Curve</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+Intelligence%22">Artificial Intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Blood+Transfusion%22">Blood Transfusion</searchLink><br /><searchLink fieldCode="DE" term="%22Gastrointestinal+Hemorrhage%22">Gastrointestinal Hemorrhage</searchLink><br /><searchLink fieldCode="DE" term="%22Intensive+Care+Units%22">Intensive Care Units</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Objective Gastrointestinal (GI) bleeding commonly requires intensive care unit (ICU) in cases of potentialhaemodynamiccompromise or likely urgent intervention. However, manypatientsadmitted to the ICU stop bleeding and do not require further intervention, including blood transfusion. The present work proposes an artificial intelligence (AI) solution for the prediction of rebleeding in patients with GI bleeding admitted to ICU. Methods A machine learning algorithm was trained and tested using two publicly available ICU databases, the Medical Information Mart for Intensive Care V.1.4 database and eICU Collaborative Research Database using freedom from transfusion as a proxy for patients who potentially did not require ICU-level care. Multiple initial observation time frames were explored using readily available data including labs, demographics and clinical parameters for a total of 20 covariates. Results The optimal model used a 5-hour observation period to achieve an area under the curve of the receiving operating curve (ROC-AUC) of greater than 0.80. The model was robust when tested against both ICU databases with a similar ROC-AUC for all. Conclusions The potential disruptive impact of AI in healthcare innovation is acknowledge, but awareness of AI-related risk on healthcare applications and current limitations should be considered before implementation and deployment. The proposed algorithm is not meant to replace but to inform clinical decision making. Prospective clinical trial validation as a triage tool is warranted.
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article in journal/newspaper
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: info:eu-repo/semantics/altIdentifier/pmid/33455913; info:eu-repo/semantics/altIdentifier/wos/WOS:000612101300001; volume:28; issue:1; firstpage:1; lastpage:8; numberofpages:8; journal:BMJ HEALTH & CARE INFORMATICS; https://hdl.handle.net/11311/1203741
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.1136/bmjhci-2020-100245
– Name: URL
  Label: Availability
  Group: URL
  Data: https://hdl.handle.net/11311/1203741<br />https://doi.org/10.1136/bmjhci-2020-100245
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: info:eu-repo/semantics/openAccess
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.D493A3E3
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.D493A3E3
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1136/bmjhci-2020-100245
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: BMJ health informatics
        Type: general
      – SubjectFull: computer methodologies
        Type: general
      – SubjectFull: Female
        Type: general
      – SubjectFull: Humans
        Type: general
      – SubjectFull: Male
        Type: general
      – SubjectFull: Prospective Studies
        Type: general
      – SubjectFull: ROC Curve
        Type: general
      – SubjectFull: Artificial Intelligence
        Type: general
      – SubjectFull: Blood Transfusion
        Type: general
      – SubjectFull: Gastrointestinal Hemorrhage
        Type: general
      – SubjectFull: Intensive Care Units
        Type: general
    Titles:
      – TitleFull: Artificial intelligence-based prediction of transfusion in the intensive care unit in patients with gastrointestinal bleeding
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Levi R.
      – PersonEntity:
          Name:
            NameFull: Carli F.
      – PersonEntity:
          Name:
            NameFull: Arevalo A. R.
      – PersonEntity:
          Name:
            NameFull: Altinel Y.
      – PersonEntity:
          Name:
            NameFull: Stein D. J.
      – PersonEntity:
          Name:
            NameFull: Naldini M. M.
      – PersonEntity:
          Name:
            NameFull: Grassi F.
      – PersonEntity:
          Name:
            NameFull: Zanoni A.
      – PersonEntity:
          Name:
            NameFull: Finkelstein S.
      – PersonEntity:
          Name:
            NameFull: Vieira S. M.
      – PersonEntity:
          Name:
            NameFull: Sousa J.
      – PersonEntity:
          Name:
            NameFull: Barbieri R.
      – PersonEntity:
          Name:
            NameFull: Celi L. A.
      – PersonEntity:
          Name:
            NameFull: Levi, R.
      – PersonEntity:
          Name:
            NameFull: Carli, F.
      – PersonEntity:
          Name:
            NameFull: Arevalo, A. R.
      – PersonEntity:
          Name:
            NameFull: Altinel, Y.
      – PersonEntity:
          Name:
            NameFull: Stein, D. J.
      – PersonEntity:
          Name:
            NameFull: Naldini, M. M.
      – PersonEntity:
          Name:
            NameFull: Grassi, F.
      – PersonEntity:
          Name:
            NameFull: Zanoni, A.
      – PersonEntity:
          Name:
            NameFull: Finkelstein, S.
      – PersonEntity:
          Name:
            NameFull: Vieira, S. M.
      – PersonEntity:
          Name:
            NameFull: Sousa, J.
      – PersonEntity:
          Name:
            NameFull: Barbieri, R.
      – PersonEntity:
          Name:
            NameFull: Celi, L. A.
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2021
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
ResultId 1