Your browser doesn't support javascript.
Triage and monitoring of COVID-19 patients in intensive care using unsupervised machine learning.
Boussen, Salah; Cordier, Pierre-Yves; Malet, Arthur; Simeone, Pierre; Cataldi, Sophie; Vaisse, Camille; Roche, Xavier; Castelli, Alexandre; Assal, Mehdi; Pepin, Guillaume; Cot, Kevin; Denis, Jean-Baptiste; Morales, Timothée; Velly, Lionel; Bruder, Nicolas.
  • Boussen S; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France; Aix Marseille Université, IFSTTAR, LBA UMR_T 24, 13916, Marseille, France. Electronic address: salah.boussen@univ-eiffel.f
  • Cordier PY; Aix Marseille Université, IFSTTAR, LBA UMR_T 24, 13916, Marseille, France; Intensive Care Unit, Laveran Military Teaching Hospital, 34, boulevard Laveran, 13384, Marseille, France.
  • Malet A; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Simeone P; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France; Institut des Neurociences de la Timone, CNRS UMR1106 - Aix-Marseille Université - Faculté de Médecine, 27, Boulevard Jean
  • Cataldi S; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Vaisse C; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Roche X; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Castelli A; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Assal M; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Pepin G; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Cot K; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Denis JB; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Morales T; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
  • Velly L; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France; Aix Marseille Université, IFSTTAR, LBA UMR_T 24, 13916, Marseille, France; Intensive Care Unit, Laveran Military Teaching
  • Bruder N; Department of Anesthesiology and Intensive Care, CHU Timone, Assistance Publique Hôpitaux de Marseille, Aix Marseille Université, 264 rue Saint-Pierre, 13005, Marseille, France.
Comput Biol Med ; 142: 105192, 2022 03.
Article in English | MEDLINE | ID: covidwho-1588022
ABSTRACT

BACKGROUND:

We designed an algorithm to assess COVID-19 patients severity and dynamic intubation needs and predict their length of stay using the breathing frequency (BF) and oxygen saturation (SpO2) signals.

METHODS:

We recorded the BF and SpO2 signals for confirmed COVID-19 patients admitted to the ICU of a teaching hospital during both the first and subsequent outbreaks of the pandemic in France. An unsupervised machine-learning algorithm (the Gaussian mixture model) was applied to the patients' data for clustering. The algorithm's robustness was ensured by comparing its results against actual intubation rates. We predicted intubation rates using the algorithm every hour, thus conducting a severity evaluation. We designed a S24 severity score that represented the patient's severity over the previous 24 h; the validity of MS24, the maximum S24 score, was checked against rates of intubation risk and prolonged ICU stay.

RESULTS:

Our sample included 279 patients. . The unsupervised clustering had an accuracy rate of 87.8% for intubation recognition (AUC = 0.94, True Positive Rate 86.5%, true Negative Rate 90.9%). The S24 score of intubated patients was significantly higher than that of non-intubated patients at 48 h before intubation. The MS24 score allowed for the distinguishing between three severity levels with an increased risk of intubation green (3.4%), orange (37%), and red (77%). A MS24 score over 40 was highly predictive of an ICU stay greater than 5 days at an accuracy rate of 81.0% (AUC = 0.87).

CONCLUSIONS:

Our algorithm uses simple signals and seems to efficiently visualize the patients' respiratory situations, meaning that it has the potential to assist staffs' in decision-making. Additionally, real-time computation is easy to implement.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: Triage / COVID-19 Type of study: Experimental Studies / Observational study / Prognostic study Limits: Humans Language: English Journal: Comput Biol Med Year: 2022 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Triage / COVID-19 Type of study: Experimental Studies / Observational study / Prognostic study Limits: Humans Language: English Journal: Comput Biol Med Year: 2022 Document Type: Article