Your browser doesn't support javascript.
Development of machine learning models to predict RT-PCR results for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) in patients with influenza-like symptoms using only basic clinical data.
Langer, Thomas; Favarato, Martina; Giudici, Riccardo; Bassi, Gabriele; Garberi, Roberta; Villa, Fabiana; Gay, Hedwige; Zeduri, Anna; Bragagnolo, Sara; Molteni, Alberto; Beretta, Andrea; Corradin, Matteo; Moreno, Mauro; Vismara, Chiara; Perno, Carlo Federico; Buscema, Massimo; Grossi, Enzo; Fumagalli, Roberto.
  • Langer T; Department of Medicine and Surgery, University of Milan-Bicocca, Monza, Italy. Thomas.Langer@unimib.it.
  • Favarato M; Department of Anaesthesia and Intensive Care Medicine, Niguarda Ca' Granda, Milan, Italy. Thomas.Langer@unimib.it.
  • Giudici R; Department of Medicine and Surgery, University of Milan-Bicocca, Monza, Italy.
  • Bassi G; Department of Anaesthesia and Intensive Care Medicine, Niguarda Ca' Granda, Milan, Italy.
  • Garberi R; Department of Anaesthesia and Intensive Care Medicine, Niguarda Ca' Granda, Milan, Italy.
  • Villa F; Department of Anaesthesia and Intensive Care Medicine, Niguarda Ca' Granda, Milan, Italy.
  • Gay H; Department of Medicine and Surgery, University of Milan-Bicocca, Monza, Italy.
  • Zeduri A; Department of Medicine and Surgery, University of Milan-Bicocca, Monza, Italy.
  • Bragagnolo S; Department of Medicine and Surgery, University of Milan-Bicocca, Monza, Italy.
  • Molteni A; Department of Anaesthesia and Intensive Care Medicine, Niguarda Ca' Granda, Milan, Italy.
  • Beretta A; Department of Medicine and Surgery, University of Milan-Bicocca, Monza, Italy.
  • Corradin M; Department of Medicine and Surgery, University of Milan-Bicocca, Monza, Italy.
  • Moreno M; Department of General oncologic and mini-invasive Surgery, Niguarda Ca'Granda, Milan, Italy.
  • Vismara C; Department of Emergency Medicine, Niguarda Ca' Granda, Milan, Italy.
  • Perno CF; Medical Department, Niguarda Ca' Granda, Milan, Italy.
  • Buscema M; Medical Department, Niguarda Ca' Granda, Milan, Italy.
  • Grossi E; Department of Laboratory Medicine, ASST Niguarda Hospital, University of Milan, Milan, Italy.
  • Fumagalli R; Department of Laboratory Medicine, ASST Niguarda Hospital, University of Milan, Milan, Italy.
Scand J Trauma Resusc Emerg Med ; 28(1): 113, 2020 Dec 01.
Article in English | MEDLINE | ID: covidwho-954012
ABSTRACT

BACKGROUND:

Reverse Transcription-Polymerase Chain Reaction (RT-PCR) for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) diagnosis currently requires quite a long time span. A quicker and more efficient diagnostic tool in emergency departments could improve management during this global crisis. Our main goal was assessing the accuracy of artificial intelligence in predicting the results of RT-PCR for SARS-COV-2, using basic information at hand in all emergency departments.

METHODS:

This is a retrospective study carried out between February 22, 2020 and March 16, 2020 in one of the main hospitals in Milan, Italy. We screened for eligibility all patients admitted with influenza-like symptoms tested for SARS-COV-2. Patients under 12 years old and patients in whom the leukocyte formula was not performed in the ED were excluded. Input data through artificial intelligence were made up of a combination of clinical, radiological and routine laboratory data upon hospital admission. Different Machine Learning algorithms available on WEKA data mining software and on Semeion Research Centre depository were trained using both the Training and Testing and the K-fold cross-validation protocol.

RESULTS:

Among 199 patients subject to study (median [interquartile range] age 65 [46-78] years; 127 [63.8%] men), 124 [62.3%] resulted positive to SARS-COV-2. The best Machine Learning System reached an accuracy of 91.4% with 94.1% sensitivity and 88.7% specificity.

CONCLUSION:

Our study suggests that properly trained artificial intelligence algorithms may be able to predict correct results in RT-PCR for SARS-COV-2, using basic clinical data. If confirmed, on a larger-scale study, this approach could have important clinical and organizational implications.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: Software / Diagnosis, Computer-Assisted / Machine Learning / COVID-19 Type of study: Diagnostic study / Observational study / Prognostic study / Randomized controlled trials / Reviews Topics: Long Covid Limits: Aged / Female / Humans / Male / Middle aged Language: English Journal: Scand J Trauma Resusc Emerg Med Journal subject: Emergency Medicine / Traumatology Year: 2020 Document Type: Article Affiliation country: S13049-020-00808-8

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Software / Diagnosis, Computer-Assisted / Machine Learning / COVID-19 Type of study: Diagnostic study / Observational study / Prognostic study / Randomized controlled trials / Reviews Topics: Long Covid Limits: Aged / Female / Humans / Male / Middle aged Language: English Journal: Scand J Trauma Resusc Emerg Med Journal subject: Emergency Medicine / Traumatology Year: 2020 Document Type: Article Affiliation country: S13049-020-00808-8