Back to Search
Start Over
Machine learning‐based analysis of alveolar and vascular injury in <scp>SARS‐CoV</scp> ‐2 acute respiratory failure
- Source :
- The Journal of Pathology
- Publication Year :
- 2021
- Publisher :
- Wiley, 2021.
-
Abstract
- Severe acute respiratory syndrome‐coronavirus‐2 (SARS‐CoV‐2) pneumopathy is characterized by a complex clinical picture and heterogeneous pathological lesions, both involving alveolar and vascular components. The severity and distribution of morphological lesions associated with SARS‐CoV‐2 and how they relate to clinical, laboratory, and radiological data have not yet been studied systematically. The main goals of the present study were to objectively identify pathological phenotypes and factors that, in addition to SARS‐CoV‐2, may influence their occurrence. Lungs from 26 patients who died from SARS‐CoV‐2 acute respiratory failure were comprehensively analysed. Robust machine learning techniques were implemented to obtain a global pathological score to distinguish phenotypes with prevalent vascular or alveolar injury. The score was then analysed to assess its possible correlation with clinical, laboratory, radiological, and tissue viral data. Furthermore, an exploratory random forest algorithm was developed to identify the most discriminative clinical characteristics at hospital admission that might predict pathological phenotypes of SARS‐CoV‐2. Vascular injury phenotype was observed in most cases being consistently present as pure form or in combination with alveolar injury. Phenotypes with more severe alveolar injury showed significantly more frequent tracheal intubation; longer invasive mechanical ventilation, illness duration, intensive care unit or hospital ward stay; and lower tissue viral quantity (p
- Subjects :
- Male
0301 basic medicine
Respiratory rate
medicine.medical_treatment
Aspiration pneumonia
Machine learning
computer.software_genre
SARS‐CoV‐2
Pathology and Forensic Medicine
law.invention
Machine Learning
03 medical and health sciences
0302 clinical medicine
COVID‐19
law
medicine
Humans
Respiratory system
Pathological
vascular injury
Aged
Aged, 80 and over
Mechanical ventilation
Respiratory Distress Syndrome
Original Paper
acute respiratory failure
SARS-CoV-2
business.industry
Tracheal intubation
COVID-19
alveolar injury
Vascular System Injuries
medicine.disease
Original Papers
Intensive care unit
030104 developmental biology
030220 oncology & carcinogenesis
Female
Artificial intelligence
Respiratory Insufficiency
business
Body mass index
computer
Subjects
Details
- ISSN :
- 10969896 and 00223417
- Volume :
- 254
- Database :
- OpenAIRE
- Journal :
- The Journal of Pathology
- Accession number :
- edsair.doi.dedup.....236cbfa1196c40479a4fcabcef287aa7