Automated COVID-19 diagnosis and prognosis with medical imaging and who is publishing: a systematic review
Abstract Objectives: To conduct a systematic survey of published techniques for automated diagnosis and prognosis of COVID-19 diseases using medical imaging, assessing the validity of reported performance and investigating the proposed clinical use-case. To conduct a scoping review into the authors publishing such work. Methods: The Scopus database was queried and studies were screened for article type, and minimum source normalized impact per paper and citations, before manual relevance assessment and a bias assessment derived from a subset of the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). The number of failures of the full CLAIM was adopted as a surrogate for risk-of-bias. Methodological and performance measurements were collected from each technique. Each study was assessed by one author. Comparisons were evaluated for significance with a two-sided independent t-test. Findings: Of 1002 studies identified, 390 remained after screening and 81 after relevance and bias exclusion. The ratio of exclusion for bias was 71%, indicative of a high level of bias in the field. The mean number of CLAIM failures per study was 8.3 ± 3.9 [1,17] (mean ± standard deviation [min,max]). 58% of methods performed diagnosis versus 31% prognosis. Of the diagnostic methods, 38% differentiated COVID-19 from healthy controls. For diagnostic techniques, area under the receiver operating curve (AUC) = 0.924 ± 0.074 [0.810,0.991] and accuracy = 91.7% ± 6.4 [79.0,99.0]. For prognostic techniques, AUC = 0.836 ± 0.126 [0.605,0.980] and accuracy = 78.4% ± 9.4 [62.5,98.0]. CLAIM failures did not correlate with performance, providing confidence that the highest results were not driven by biased papers. Deep learning techniques reported higher AUC (p < 0.05) and accuracy (p < 0.05), but no difference in CLAIM failures was identified. Interpretation: A majority of papers focus on the less clinically impactful diagnosis task, contrasted with prognosis, with a significant portion performing a clinically unnecessary task of differentiating COVID-19 from healthy. Authors should consider the clinical scenario in which their work would be deployed when developing techniques. Nevertheless, studies report superb performance in a potentially impactful application. Future work is warranted in translating techniques into clinical tools..
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2021 |
---|---|
Erschienen: |
2021 |
Enthalten in: |
Zur Gesamtaufnahme - volume:45 |
---|---|
Enthalten in: |
Australasian physical & engineering sciences in medicine - 45(2021), 1 vom: 17. Dez., Seite 13-29 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Gillman, Ashley G. [VerfasserIn] |
---|
Links: |
Volltext [lizenzpflichtig] |
---|
Themen: |
Chest X-ray |
---|
Anmerkungen: |
© Australasian College of Physical Scientists and Engineers in Medicine 2021 |
---|
doi: |
10.1007/s13246-021-01093-0 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
SPR046416005 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | SPR046416005 | ||
003 | DE-627 | ||
005 | 20230519143204.0 | ||
007 | cr uuu---uuuuu | ||
008 | 220308s2021 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/s13246-021-01093-0 |2 doi | |
035 | |a (DE-627)SPR046416005 | ||
035 | |a (SPR)s13246-021-01093-0-e | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Gillman, Ashley G. |e verfasserin |0 (orcid)0000-0001-9130-1092 |4 aut | |
245 | 1 | 0 | |a Automated COVID-19 diagnosis and prognosis with medical imaging and who is publishing: a systematic review |
264 | 1 | |c 2021 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a Computermedien |b c |2 rdamedia | ||
338 | |a Online-Ressource |b cr |2 rdacarrier | ||
500 | |a © Australasian College of Physical Scientists and Engineers in Medicine 2021 | ||
520 | |a Abstract Objectives: To conduct a systematic survey of published techniques for automated diagnosis and prognosis of COVID-19 diseases using medical imaging, assessing the validity of reported performance and investigating the proposed clinical use-case. To conduct a scoping review into the authors publishing such work. Methods: The Scopus database was queried and studies were screened for article type, and minimum source normalized impact per paper and citations, before manual relevance assessment and a bias assessment derived from a subset of the Checklist for Artificial Intelligence in Medical Imaging (CLAIM). The number of failures of the full CLAIM was adopted as a surrogate for risk-of-bias. Methodological and performance measurements were collected from each technique. Each study was assessed by one author. Comparisons were evaluated for significance with a two-sided independent t-test. Findings: Of 1002 studies identified, 390 remained after screening and 81 after relevance and bias exclusion. The ratio of exclusion for bias was 71%, indicative of a high level of bias in the field. The mean number of CLAIM failures per study was 8.3 ± 3.9 [1,17] (mean ± standard deviation [min,max]). 58% of methods performed diagnosis versus 31% prognosis. Of the diagnostic methods, 38% differentiated COVID-19 from healthy controls. For diagnostic techniques, area under the receiver operating curve (AUC) = 0.924 ± 0.074 [0.810,0.991] and accuracy = 91.7% ± 6.4 [79.0,99.0]. For prognostic techniques, AUC = 0.836 ± 0.126 [0.605,0.980] and accuracy = 78.4% ± 9.4 [62.5,98.0]. CLAIM failures did not correlate with performance, providing confidence that the highest results were not driven by biased papers. Deep learning techniques reported higher AUC (p < 0.05) and accuracy (p < 0.05), but no difference in CLAIM failures was identified. Interpretation: A majority of papers focus on the less clinically impactful diagnosis task, contrasted with prognosis, with a significant portion performing a clinically unnecessary task of differentiating COVID-19 from healthy. Authors should consider the clinical scenario in which their work would be deployed when developing techniques. Nevertheless, studies report superb performance in a potentially impactful application. Future work is warranted in translating techniques into clinical tools. | ||
650 | 4 | |a Coronavirus |7 (dpeaa)DE-He213 | |
650 | 4 | |a Computed tomography |7 (dpeaa)DE-He213 | |
650 | 4 | |a Chest X-ray |7 (dpeaa)DE-He213 | |
650 | 4 | |a Prognosis |7 (dpeaa)DE-He213 | |
650 | 4 | |a Staging |7 (dpeaa)DE-He213 | |
650 | 4 | |a Diagnosis |7 (dpeaa)DE-He213 | |
700 | 1 | |a Lunardo, Febrio |4 aut | |
700 | 1 | |a Prinable, Joseph |4 aut | |
700 | 1 | |a Belous, Gregg |4 aut | |
700 | 1 | |a Nicolson, Aaron |4 aut | |
700 | 1 | |a Min, Hang |4 aut | |
700 | 1 | |a Terhorst, Andrew |4 aut | |
700 | 1 | |a Dowling, Jason A. |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Australasian physical & engineering sciences in medicine |d Cham : Springer, 2001 |g 45(2021), 1 vom: 17. Dez., Seite 13-29 |w (DE-627)SPR031009085 |w (DE-600)2003728-4 |x 1879-5447 |7 nnns |
773 | 1 | 8 | |g volume:45 |g year:2021 |g number:1 |g day:17 |g month:12 |g pages:13-29 |
856 | 4 | 0 | |u https://dx.doi.org/10.1007/s13246-021-01093-0 |z lizenzpflichtig |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_SPRINGER | ||
912 | |a SSG-OLC-PHA | ||
951 | |a AR | ||
952 | |d 45 |j 2021 |e 1 |b 17 |c 12 |h 13-29 |