Use of machine learning to assess the prognostic utility of radiomic features for in-hospital COVID-19 mortality

Sun, Yuming; Salerno, Stephen; He, Xinwei; Pan, Ziyang; Yang, Eileen; Sujimongkol, Chinakorn; Song, Jiyeon; Wang, Xinan; Han, Peisong; Kang, Jian; Sjoding, Michael W.; Jolly, Shruti; Christiani, David C.; Li, Yang

doi:10.1038/s41598-023-34559-0

Cited by 7 publications

(2 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most of the COVID-19 prognostic models reported in the literature, especially for hospitalized patients, base their predictions on demographics (with age and sex as the most determinant variables), comorbidities (with special focus on hypertension, cardiovascular disease, hypertension and diabetes), laboratory indicators (e.g., lymphocyte/platelet counts, creatinine, interleukin 6 (IL-6), procalcitonin (PCT), d-dimer, ferritin etc.) (139,140) and medical imaging (141). In a recent systematic and extensive review about the various COVID-19 prognostic models presented in the literature, the divergence between the reported performance statistics is highlighted (142).…”

Section: Scov2 Diagnostic and Prognostic Modelling: A Machine Learnin...mentioning

confidence: 99%

The two-stage molecular scenery of SARS-CoV-2 infection with implications to disease severity: An in-silico quest

Potamias,

Gkoublia,

Kanterakis

2023

Front. Immunol.

View full text Add to dashboard Cite

IntroductionThe two-stage molecular profile of the progression of SARS-CoV-2 (SCOV2) infection is explored in terms of five key biological/clinical questions: (a) does SCOV2 exhibits a two-stage infection profile? (b) SARS-CoV-1 (SCOV1) vs. SCOV2: do they differ? (c) does and how SCOV2 differs from Influenza/INFL infection? (d) does low viral-load and (e) does COVID-19 early host response relate to the two-stage SCOV2 infection profile? We provide positive answers to the above questions by analyzing the time-series gene-expression profiles of preserved cell-lines infected with SCOV1/2 or, the gene-expression profiles of infected individuals with different viral-loads levels and different host-response phenotypes.MethodsOur analytical methodology follows an in-silico quest organized around an elaborate multi-step analysis pipeline including: (a) utilization of fifteen gene-expression datasets from NCBI’s gene expression omnibus/GEO repository; (b) thorough designation of SCOV1/2 and INFL progression stages and COVID-19 phenotypes; (c) identification of differentially expressed genes (DEGs) and enriched biological processes and pathways that contrast and differentiate between different infection stages and phenotypes; (d) employment of a graph-based clustering process for the induction of coherent groups of networked genes as the representative core molecular fingerprints that characterize the different SCOV2 progression stages and the different COVID-19 phenotypes. In addition, relying on a sensibly selected set of induced fingerprint genes and following a Machine Learning approach, we devised and assessed the performance of different classifier models for the differentiation of acute respiratory illness/ARI caused by SCOV2 or other infections (diagnostic classifiers), as well as for the prediction of COVID-19 disease severity (prognostic classifiers), with quite encouraging results.ResultsThe central finding of our experiments demonstrates the down-regulation of type-I interferon genes (IFN-1), interferon induced genes (ISGs) and fundamental innate immune and defense biological processes and molecular pathways during the early SCOV2 infection stages, with the inverse to hold during the later ones. It is highlighted that upregulation of these genes and pathways early after infection may prove beneficial in preventing subsequent uncontrolled hyperinflammatory and potentially lethal events.DiscussionThe basic aim of our study was to utilize in an intuitive, efficient and productive way the most relevant and state-of-the-art bioinformatics methods to reveal the core molecular mechanisms which govern the progression of SCOV2 infection and the different COVID-19 phenotypes.

show abstract

Section: Scov2 Diagnostic and Prognostic Modelling: A Machine Learnin...mentioning

confidence: 99%

The two-stage molecular scenery of SARS-CoV-2 infection with implications to disease severity: An in-silico quest

Potamias,

Gkoublia,

Kanterakis

2023

Front. Immunol.

View full text Add to dashboard Cite

show abstract

“…Using various machine learning approaches, the prognostic value for survival of COVID-19 patients based on known in-hospital mortality risk factors and chest radiographs was assessed. It was found that the indicators should include age, oxygen saturation, blood pressure, and some concomitant diseases, as well as image features related to the intensity and variability of the pixel distribution [126].…”

mentioning

confidence: 99%

Patent and Bibliometric Analysis of the Scientific Landscape of the Use of Pulse Oximeters and Their Prospects in the Field of Digital Medicine

Litvinova,

Hammerle,

Stoyanov

et al. 2023

Healthcare

View full text Add to dashboard Cite

This study conducted a comprehensive patent and bibliometric analysis to elucidate the evolving scientific landscape surrounding the development and application of pulse oximeters, including in the field of digital medicine. Utilizing data from the Lens database for the period of 2000–2023, we identified the United States, China, the Republic of Korea, Japan, Canada, Australia, Taiwan, and the United Kingdom as the predominant countries in patent issuance for pulse oximeter technology. Our bibliometric analysis revealed a consistent temporal trend in both the volume of publications and citations, underscoring the growing importance of pulse oximeters in digitally-enabled medical practice. Using the VOSviewer software(version 1.6.18), we discerned six primary research clusters: (1) measurement accuracy; (2) integration with the Internet of Things; (3) applicability across diverse pathologies; (4) telemedicine and mobile applications; (5) artificial intelligence and deep learning; and (6) utilization in anesthesiology, resuscitation, and intensive care departments. The findings of this study indicate the prospects for leveraging digital technologies in the use of pulse oximetry in various fields of medicine, with implications for advancing the understanding, diagnosis, prevention, and treatment of cardio-respiratory pathologies. The conducted patent and bibliometric analysis allowed the identification of technical solutions to reduce the risks associated with pulse oximetry: improving precision and validity, technically improved clinical diagnostic use, and the use of machine learning.

show abstract

Predicting oxygen needs in COVID-19 patients using chest radiography multi-region radiomics

Netprasert,

Khongwirotphan,

Seangsawang

et al. 2024

Radiol Phys Technol

View full text Add to dashboard Cite

Use of machine learning to assess the prognostic utility of radiomic features for in-hospital COVID-19 mortality

Cited by 7 publications

References 86 publications

The two-stage molecular scenery of SARS-CoV-2 infection with implications to disease severity: An in-silico quest

The two-stage molecular scenery of SARS-CoV-2 infection with implications to disease severity: An in-silico quest

Patent and Bibliometric Analysis of the Scientific Landscape of the Use of Pulse Oximeters and Their Prospects in the Field of Digital Medicine

Predicting oxygen needs in COVID-19 patients using chest radiography multi-region radiomics

Contact Info

Product

Resources

About