Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Observational Study
. 2025 May 23;104(21):e41928.
doi: 10.1097/MD.0000000000041928.

Diagnostic accuracy of artificial intelligence-based multi-spectrum analysis for molecular fingerprint detection of SARS-CoV-2

Ismail Tayfur  1 , Burcu Bayramoglu  1 , Ramazan Guven  2 , Akkan Avci  3
Affiliations
Observational Study

Diagnostic accuracy of artificial intelligence-based multi-spectrum analysis for molecular fingerprint detection of SARS-CoV-2

Ismail Tayfur et al. Medicine (Baltimore). .

Abstract

Reverse transcription-polymerase chain reaction (RT-PCR) is the reference standard for COVID-19 diagnosis, but the need for rapid, reproducible, and cost-effective diagnostic tools remains. This study investigated the diagnostic performance of a novel artificial intelligence-based multispectrum analysis (MSA, AP23) technique that detects the biomolecular fingerprint of severe acute respiratory syndrome coronavirus 2. A prospective, double-blinded observational design was used, involving 3614 volunteers. The artificial intelligence was trained with 2448 samples, validated with 816, and tested against RT-PCR using a blinded set of 350 samples. Sensitivity, specificity, positive predictive value, and negative predictive value were calculated. During validation, MSA achieved 88.4% sensitivity, 88.76% specificity, 86.77% positive predictive value, and 90.18% negative predictive value. In the blinded comparison phase, these values were 81.73%, 81.99%, 75.16%, and 87.81%, respectively, with an area under the receiver operating characteristic curve of 0.89. These findings suggest that MSA offers reliable diagnostic performance and may be a promising alternative to RT-PCR in COVID-19 diagnosis. The study was registered on ClinicalTrials.gov (NCT04860895).

Keywords: SARS-CoV-2; artificial intelligence; molecular fingerprint; multi-spectrum analysis.

PubMed Disclaimer

Conflict of interest statement

The authors have no funding and conflicts of interest to disclose.

Figures

Figure 1.
Figure 1.
STARD FLOW/flow chart of the included and excluded patients from the study.
Figure 2.
Figure 2.
Results of the test stage. Blue dots represent the values obtained from AI and show the probability of positivity or negativity. These values are interpreted as negative if they are below 0.5 and positive if above or equal to 0.5. The RT-PCR results are shown with orange lines since they are entered into the system as either positive or negative. AI = artificial intelligence, RT-PCR = reverse transcription-polymerase chain reaction.
Figure 3.
Figure 3.
Area under the curve graph showing the agreement in the positive and negative probability values in the double-blinded test.
See this image and copyright information in PMC

Similar articles

  • Signs and symptoms to determine if a patient presenting in primary care or hospital outpatient settings has COVID-19.
    Struyf T, Deeks JJ, Dinnes J, Takwoingi Y, Davenport C, Leeflang MM, Spijker R, Hooft L, Emperador D, Domen J, Tans A, Janssens S, Wickramasinghe D, Lannoy V, Horn SRA, Van den Bruel A; Cochrane COVID-19 Diagnostic Test Accuracy Group. Struyf T, et al. Cochrane Database Syst Rev. 2022 May 20;5(5):CD013665. doi: 10.1002/14651858.CD013665.pub3. Cochrane Database Syst Rev. 2022. PMID: 35593186 Free PMC article.
  • Rapid, point-of-care antigen tests for diagnosis of SARS-CoV-2 infection.
    Dinnes J, Sharma P, Berhane S, van Wyk SS, Nyaaba N, Domen J, Taylor M, Cunningham J, Davenport C, Dittrich S, Emperador D, Hooft L, Leeflang MM, McInnes MD, Spijker R, Verbakel JY, Takwoingi Y, Taylor-Phillips S, Van den Bruel A, Deeks JJ; Cochrane COVID-19 Diagnostic Test Accuracy Group. Dinnes J, et al. Cochrane Database Syst Rev. 2022 Jul 22;7(7):CD013705. doi: 10.1002/14651858.CD013705.pub3. Cochrane Database Syst Rev. 2022. PMID: 35866452 Free PMC article.
  • Antibody tests for identification of current and past infection with SARS-CoV-2.
    Fox T, Geppert J, Dinnes J, Scandrett K, Bigio J, Sulis G, Hettiarachchi D, Mathangasinghe Y, Weeratunga P, Wickramasinghe D, Bergman H, Buckley BS, Probyn K, Sguassero Y, Davenport C, Cunningham J, Dittrich S, Emperador D, Hooft L, Leeflang MM, McInnes MD, Spijker R, Struyf T, Van den Bruel A, Verbakel JY, Takwoingi Y, Taylor-Phillips S, Deeks JJ; Cochrane COVID-19 Diagnostic Test Accuracy Group. Fox T, et al. Cochrane Database Syst Rev. 2022 Nov 17;11(11):CD013652. doi: 10.1002/14651858.CD013652.pub2. Cochrane Database Syst Rev. 2022. PMID: 36394900 Free PMC article.
  • Thoracic imaging tests for the diagnosis of COVID-19.
    Ebrahimzadeh S, Islam N, Dawit H, Salameh JP, Kazi S, Fabiano N, Treanor L, Absi M, Ahmad F, Rooprai P, Al Khalil A, Harper K, Kamra N, Leeflang MM, Hooft L, van der Pol CB, Prager R, Hare SS, Dennie C, Spijker R, Deeks JJ, Dinnes J, Jenniskens K, Korevaar DA, Cohen JF, Van den Bruel A, Takwoingi Y, van de Wijgert J, Wang J, Pena E, Sabongui S, McInnes MD; Cochrane COVID-19 Diagnostic Test Accuracy Group. Ebrahimzadeh S, et al. Cochrane Database Syst Rev. 2022 May 16;5(5):CD013639. doi: 10.1002/14651858.CD013639.pub5. Cochrane Database Syst Rev. 2022. PMID: 35575286 Free PMC article.
  • Evaluation of the Seegene Allplex™ RV master assay for one-step simultaneous detection of eight respiratory viruses in nasopharyngeal specimens.
    Mdunyelwa A, Seema C, Mabaso A, Mlambo K, Mtsweni M, Maphanga M, Rammutla E, Tempelman HA, Umunnakwe CN. Mdunyelwa A, et al. J Virol Methods. 2025 Jan;331:115042. doi: 10.1016/j.jviromet.2024.115042. Epub 2024 Oct 9. J Virol Methods. 2025. PMID: 39384158
See all similar articles

References

    1. WHO. Coronovirus (COVID-19) dashboard. https://covid19.who.int/. Accessed August 9, 2022.
    1. Fernandes RS, de Oliveira Silva J, Gomes KB, et al. . Recent advances in point of care testing for COVID-19 detection. Biomed Pharmacother. 2022;153:113538. - PMC - PubMed
    1. Ludolf F, Ramos FF, Bagno FF, et al. . Detecting anti–SARS-CoV-2 antibodies in urine samples: a noninvasive and sensitive way to assay COVID-19 immune conversion. Sci Adv. 2022;8:eabn7424. - PMC - PubMed
    1. Gabaldó X, Juanpere M, Castañé H, et al. . Measurement of serum paraoxonase-1 arylesterase activity as a screening test for the diagnosis of COVID-19. Biomolecules. 2022;12:879. - PMC - PubMed
    1. Zhou JQ, Liu GX, Huang XL, Gan HT. The importance of fecal nucleic acid detection in patients with coronavirus disease (COVID-19): a systematic review and meta-analysis. J Med Virol. 2022;94:2317–30. - PMC - PubMed

Publication types

Associated data