Comparison of the Turnaround Times of COVID-19 Real Time PCR Data on the PCR Instrument and the Catena Smart PCR Bioinformatics Program

Öz

The COVID-19 pandemic, which was caused by the SARS-CoV-2 virus, emerged in Wuhan, China in December 2019, and has had a detrimental impact worldwide. The nucleic acid amplification tests are the recommended method for the diagnosis of COVID-19. CAtenA Smart PCR is an artificial intelligence-based bioinformatics tool that assists with PCR data interpretation and offers conclusion preferences before transaction to the web-based result systems. The aim of this study was to compare the turnaround times between the data analysis on a PCR instrument, including result submission, and the CAtenA Smart PCR-assisted analysis. The specialists assessed 139 PCR data sets, each with 94 samples and two internal controls, that were performed in the COVID-19 PCR Diagnostic Laboratory at Meram State Hospital in Konya between 1 September and 30 November 2021. The data analysis times for the PCR tool (Bio-Rad CFX96 Touch, Singapore) and the CAtenA Smart PCR Bioinformatics Program (Ventura, Ankara, Turkey) were recorded. The mean time duration of the 139 PCR data analyses for the PCR device was 14.05 ± 7.55 and 8.04 ± 3.93 minutes for the CAtenA. The Wilcoxon signed ranks test was used for the statistical analysis. The difference between the turnaround times for the PCR instrument and CAtenA Smart PCR was found to be statistically significant (p = 0.0001). We further divided the study period into two groups: the high-positivity phase and the low-positivity phase. We compared the two phases in order to assess the effect of the case positivity rates on the turnaround times. There was a significant difference between the turnaround times of the two groups (p = 0.0001). The findings showed that the positivity rate has affected the time duration of data analysis on both the PCR instrument and the CAtenA program. As a result, employing artificial intelligence-based CAtenA Smart PCR to interpret PCR data and send transactions to the web-based result systems reduces the time it takes to complete the task and gives the user more convenience.

Anahtar Kelimeler

• CAtenA Smart PCR
• Covid-19
• Data analysis

COVID-19 Real Time PCR Test Sonuçlarının PCR Cihazı ve CAtenA Smart PCR Bioinformatik Programı Üzerinden Değerlendirme Sürelerinin Karşılaştırılması

Öz

İlk kez Aralık 2019’da, Çin’in Wuhan eyaletinde ortaya çıkan ve SARS-CoV-2 kaynaklı COVID-19 enfeksiyonu, tüm dünyada yııkıcı etkisini hala devam ettiren bir pandemiye neden olmuştur. COVID-19 tanısında kullanılan standart tanı yöntemi polimeraz zincir reaksiyonu yöntemidir. CAtenA Smart PCR, yapay zeka kullanarak veri analizi yapan ve kullanıcıya sonuç önerisinde bulunan bir bioinformatik programdır. Bu çalışmanın amacı uzman hekimin, cihaz başında PCR test verilerini değerlendirerek sisteme aktarma süresi ile, CAtenA Smart PCR üzerinden değerlendirmesi arasındaki süre farkının kıyaslanmasıdır. Meram Devlet Hastanesi COVID-19 PCR Tanı Laboratuvarı’nda 1 Eylül-30 Kasım 2021 tarihleri arasında çalışılmış ve her biri 94 farklı örnek ve iki iç kalite kontrolden oluşan 139 PCR çalışma verisi uzman hekimler tarafından PCR cihazından (Bio-Rad CFX96 Touch, Singapore) ve CAtenA programı (Ventura, Ankara, Turkey) üzerinden analiz edilmiş ve analiz süreleri kayıt altına alınmıştır. Analiz süreleri, Wilcoxon signed ranks test ile araştırılmıştır. PCR cihazı üzerinden yapılan 139 teste ait ortalama analiz süresi 14,05 ± 7,55 dak. iken, CAtenA programı üzerinden yapılan ortalama analiz süresi 8,04 ± 3,93 dak. olarak bulunmuştur. PCR cihazı ve CAtenA programı üzerinden yapılan analiz süreleri arasında istatistiksel olarak fark belirlenmiştir (p = 0,0001). Sonuç olarak, PCR verilerini ön analizden geçirerek uzman onayına sunan ve sonuçları web tabanlı sonuç sistemine doğrudan aktarabilen CAtenA Smart PCR bioinformatik programının, veri analiz süresini kısalttığı ve kullanıcıya kolaylık sağladığı belirlenmiştir.

Anahtar Kelimeler

• CAtenA Smart PCR
• COVID-19
• Data analysis
• Artificial intelligence
• Turnaround time

Kaynakça

1. Ding W., Nayak J., Swapnarekha H., Abraham A., Naik B., Pelusi, D. Fusion of intelligent learning for COVID-19: A state-of-the-art review and analysis on real medical data. Neurocomputing 2021; 457: 40-66. https://doi.org/10.1016/j.neucom.2021.06.024
2. Egli A., Schrenzel J., Greub G. Digital microbiology. Clinical microbiology and infection: the official publication of the European Society of Clinical Microbiology and Infectious Diseases 2020; 26(10): 1324-1331. https://doi.org/10.1016/j.cmi.2020.06.023
3. Kho AN., Doebbeling BN., Cashy JP., Rosenman MB., Dexter PR., Shepherd DC., Lemmon L., Teal E., Khokar S., Overhage JM. A regional informatics platform for coordinated antibiotic-resistant infection tracking, alerting, and prevention. Clinical infectious diseases: an official publication of the Infectious Diseases Society of America 2013; 57(2): 254-262. https://doi.org/10.1093/cid/cit229
4. Peiffer-Smadja N., Dellière S., Rodriguez C., Birgand G., Lescure FX., Fourati S., Ruppé E. Machine learning in the clinical microbiology laboratory: has the time come for routine practice? Clinical microbiology and infection: the official publication of the European Society of Clinical Microbiology and Infectious Diseases 2020; 26(10): 1300-1309. https://doi.org/10.1016/j.cmi.2020.02.006
5. Rhoads DD., Novak SM., Pantanowitz L. A review of the current state of digital plate reading of cultures in clinical microbiology. Journal of Pathology Informatics 2015; 6: 23). https://doi.org/10.4103/2153-3539.157789
6. Rhoads DD., Sintchenko V., Rauch CA., Pantanowitz L. Clinical microbiology informatics. Clinical microbiology reviews 2014; 27(4): 1025-1047. https://doi.org/10.1128/CMR.00049-14
7. Sintchenko V., Gallego B. Laboratory-guided detection of disease outbreaks: three generations of surveillance systems. Archives of Pathology & Laboratory Medicine 2009; 133(6): 916-925. https://doi.org/10.5858/133.6.916
8. Smith KP., Wang H., Durant TJS., Mathison BA., Sharpeh SE., Kirby JE., et al. Application of artificial intelligence in clinical microbiology diagnostic testing. Clin. Microbiol. Newsletter 2020; 42: 61-70.

9. Tasdelen A. Ugur AR. Artificial Intelligence Research on COVID-19 Pandemic: A Bibliometric Analysis, 5th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) 2021; 693-699. doi: 10.1109/ISMSIT52890.2021.9604573.
10. Uğur AR. Taşdelen A. COVID-19 PCR Testi Veri Analizinde CAtenA Smart PCR Bioinformatik Programının Sunduğu Ön Değerlendirme Sonuçlarının Uzman Sonuçları ile Uyumunun Araştırılması. Avrupa Bilim ve Teknoloji Dergisi, Ejosat Özel Sayı 2021 (ISMSIT) 2021; 327-330. DOI: 10.31590/ejosat.1024190
11. URL_1: https://covid19.saglik.gov.tr/TR-66935/genel-koronavirus-tablosu.html, (Date of Access: 30 November 2021).
12. URL_2: https://www.who.int/publications/i/item/laboratory-testing-of-2019-novel-coronavirus-(-2019-ncov)-in-suspected-human-cases-interim-guidance-17-january-2020, (Date of Access: 2 December 2021).
13. URL_3: https://ventura.com.tr/?page_id=1528, (Date of Access: 2 December 2021).
14. URL_4: https://data.oecd.org/healthres/health-spending.html, (Date of Access: 30 November 2021).
15. van Oosten LN., Klein CD. Machine Learning in Mass Spectrometry: A MALDI-TOF MS Approach to Phenotypic Antibacterial Screening. Journal of medicinal chemistry 2020; 63(16): 8849-8856. https://doi.org/10.1021/acs.jmedchem.0c00040
16. Xu Z., Su C., Xiao Y., Wang F. AI for COVID-19: Battling the pandemic with computational intelligence. Intelligent Medicine 2021;10.1016/j.imed.2021.09.001. doi:10.1016/j.imed.2021.09.001