Machine Learning Prediction of SARS-CoV-2 Polymerase Chain Reaction Results with Routine Blood Tests

Abstract Objective The diagnosis of COVID-19 is based on the detection of SARS-CoV-2 in respiratory secretions, blood, or stool. Currently, reverse transcription polymerase chain reaction (RT-PCR) is the most commonly used method to test for SARS-CoV-2. Methods In this retrospective cohort analysis, we evaluated whether machine learning could exclude SARS-CoV-2 infection using routinely available laboratory values. A Random Forests algorithm with 1353 unique features was trained to predict the RT-PCR results. Results Out of 12,848 patients undergoing SARS-CoV-2 testing, routine blood tests were simultaneously performed in 1528 patients. The machine learning model could predict SARS-CoV-2 test results with an accuracy of 86% and an area under the receiver operating characteristic curve of 0.90. Conclusion Machine learning methods can reliably predict a negative SARS-CoV-2 RT-PCR test result using standard blood tests.

Download Full-text

COVID-19 diagnosis by routine blood tests using machine learning

Scientific Reports ◽

10.1038/s41598-021-90265-9 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Matjaž Kukar ◽

Gregor Gunčar ◽

Tomaž Vovko ◽

Simon Podnar ◽

Peter Černelč ◽

...

Keyword(s):

Machine Learning ◽

Viral Infections ◽

Blood Parameters ◽

Rt Pcr ◽

Prothrombin Activity ◽

Blood Tests ◽

Routine Blood ◽

Machine Learning Model ◽

Feature Importance ◽

Ct Studies

AbstractPhysicians taking care of patients with COVID-19 have described different changes in routine blood parameters. However, these changes hinder them from performing COVID-19 diagnoses. We constructed a machine learning model for COVID-19 diagnosis that was based and cross-validated on the routine blood tests of 5333 patients with various bacterial and viral infections, and 160 COVID-19-positive patients. We selected the operational ROC point at a sensitivity of 81.9% and a specificity of 97.9%. The cross-validated AUC was 0.97. The five most useful routine blood parameters for COVID-19 diagnosis according to the feature importance scoring of the XGBoost algorithm were: MCHC, eosinophil count, albumin, INR, and prothrombin activity percentage. t-SNE visualization showed that the blood parameters of the patients with a severe COVID-19 course are more like the parameters of a bacterial than a viral infection. The reported diagnostic accuracy is at least comparable and probably complementary to RT-PCR and chest CT studies. Patients with fever, cough, myalgia, and other symptoms can now have initial routine blood tests assessed by our diagnostic tool. All patients with a positive COVID-19 prediction would then undergo standard RT-PCR studies to confirm the diagnosis. We believe that our results represent a significant contribution to improvements in COVID-19 diagnosis.

Download Full-text

Optimizing Polymerase Chain Reaction (PCR) using Machine Learning

10.1101/2021.08.12.455589 ◽

2021 ◽

Author(s):

Nicholas J. Cordaro ◽

Andrew J. Kavran ◽

Michael Smallegan ◽

Megan Palacio ◽

Nickolaus Lammer ◽

...

Keyword(s):

Machine Learning ◽

Polymerase Chain Reaction ◽

Similar Data ◽

Success Rates ◽

Chain Reaction ◽

Data Set ◽

Machine Learning Model ◽

Crowdsourced Data ◽

Polymerase Chain ◽

Active Research

Despite substantial standardization, polymerase chain reaction (PCR) experiments frequently fail. Troubleshooting failed PCRs can be costly in both time and money. Using a crowdsourced data set spanning 290 real PCRs from six active research laboratories, we investigate the degree to which PCR success rates can be improved by machine learning. While human designed PCRs succeed at a rate of 55-64%, we find that a machine learning model can accurately predict reaction outcome 81% of the time. We validate this level of improvement by then using the model to guide the design and predict the outcome of 39 new PCR experiments. In addition to improving outcomes, the model identifies 15 features of PCRs that researchers did not optimize well compared to the learned model. These results suggest that PCR success rates can easily be improved by 17-26%, potentially saving millions of dollars and thousands of hours of researcher time each year across the scientific community. Other common laboratory methods may benefit from similar data-driven optimization effort.

Download Full-text

1504: Molecular Diagnosis and Staging of Prostate Cancer Using Clusterin in Real Time Reverse Transcription Polymerase Chain Reaction (RT-PCR)

The Journal of Urology ◽

10.1016/s0022-5347(18)33708-x ◽

2006 ◽

Vol 175 (4S) ◽

pp. 485-486

Author(s):

Sabarinath B. Nair ◽

Christodoulos Pipinikas ◽

Roger Kirby ◽

Nick Carter ◽

Christiane Fenske

Keyword(s):

Prostate Cancer ◽

Polymerase Chain Reaction ◽

Real Time ◽

Molecular Diagnosis ◽

Reverse Transcription ◽

Rt Pcr ◽

Chain Reaction ◽

Polymerase Chain

Download Full-text

Polymerase chain reaction amplification and typing of rotavirus in environmental samples

Water Science & Technology ◽

10.2166/wst.1995.0643 ◽

1995 ◽

Vol 31 (5-6) ◽

pp. 371-374 ◽

Cited By ~ 5

Author(s):

R. Gajardo ◽

R. M. Pintó ◽

A. Bosch

Keyword(s):

Polymerase Chain Reaction ◽

Environmental Samples ◽

Polymerase Chain Reaction Amplification ◽

Rt Pcr ◽

Chain Reaction ◽

Pcr Assay ◽

Group A ◽

Reaction Amplification ◽

Stool Specimens ◽

Polymerase Chain

A reverse transcription polymerase chain reaction (RT-PCR) assay is described that has been developed for the detection and serotyping of group A rotavirus in stool specimens and concentrated and non-concentrated sewage specimens.

Download Full-text

A meta-analysis of accuracy and sensitivity of chest CT and RT-PCR in COVID-19 diagnosis

Scientific Reports ◽

10.1038/s41598-020-80061-2 ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Fatemeh Khatami ◽

Mohammad Saatchi ◽

Seyed Saeed Tamehri Zadeh ◽

Zahra Sadat Aghamir ◽

Alireza Namazi Shabestari ◽

...

Keyword(s):

Polymerase Chain Reaction ◽

Reverse Transcriptase ◽

Ct Scan ◽

Predictive Value ◽

Meta Analysis ◽

Chest Ct ◽

Rt Pcr ◽

Chain Reaction ◽

Polymerase Chain ◽

Chest Ct Scan

AbstractNowadays there is an ongoing acute respiratory outbreak caused by the novel highly contagious coronavirus (COVID-19). The diagnostic protocol is based on quantitative reverse-transcription polymerase chain reaction (RT-PCR) and chests CT scan, with uncertain accuracy. This meta-analysis study determines the diagnostic value of an initial chest CT scan in patients with COVID-19 infection in comparison with RT-PCR. Three main databases; PubMed (MEDLINE), Scopus, and EMBASE were systematically searched for all published literature from January 1st, 2019, to the 21st May 2020 with the keywords "COVID19 virus", "2019 novel coronavirus", "Wuhan coronavirus", "2019-nCoV", "X-Ray Computed Tomography", "Polymerase Chain Reaction", "Reverse Transcriptase PCR", and "PCR Reverse Transcriptase". All relevant case-series, cross-sectional, and cohort studies were selected. Data extraction and analysis were performed using STATA v.14.0SE (College Station, TX, USA) and RevMan 5. Among 1022 articles, 60 studies were eligible for totalizing 5744 patients. The overall sensitivity, specificity, positive predictive value, and negative predictive value of chest CT scan compared to RT-PCR were 87% (95% CI 85–90%), 46% (95% CI 29–63%), 69% (95% CI 56–72%), and 89% (95% CI 82–96%), respectively. It is important to rely on the repeated RT-PCR three times to give 99% accuracy, especially in negative samples. Regarding the overall diagnostic sensitivity of 87% for chest CT, the RT-PCR testing is essential and should be repeated to escape misdiagnosis.

Download Full-text

Evaluation of Sandwich Enzyme-Linked Immunosorbent Assay and Reverse Transcription Polymerase Chain Reaction for the Diagnosis of Foot-and-Mouth Disease

Intervirology ◽

10.1159/000517003 ◽

2021 ◽

pp. 1-6

Author(s):

Salman Khan ◽

Syed Asad Ali Shah ◽

Syed Muhammad Jamal

Keyword(s):

Polymerase Chain Reaction ◽

Viral Genome ◽

Foot And Mouth Disease ◽

Enzyme Linked Immunosorbent Assay ◽

Rt Pcr ◽

Chain Reaction ◽

Kappa Value ◽

Polymerase Chain ◽

Pcr Assays ◽

Level Of Agreement

Background: Foot-and-mouth disease (FMD) is an infectious and highly contagious disease of cloven-hoofed domestic and wild animals, causing heavy economic losses to the livestock industry. Rapid and reliable diagnosis of the disease is essential for the implementation of effective control measures. This study compared sandwich enzyme-linked immunosorbent assay (S-ELISA) and conventional reverse transcription polymerase chain reaction (RT-PCR) for the diagnosis of FMD. Methods: A total of 60 epithelial samples from suspected cases of FMD were tested using both S-ELISA and RT-PCR assays. The level of agreement between the assays was assessed by calculating the Kappa value. Results: S-ELISA detected 38 (63%) samples positive for FMD virus (FMDV). Being predominant, serotype O was detected in 22 (57.9%) of the total samples tested positive, whereas 9 (23.7%) and 7 (18.4%) samples were found positive for serotypes A and Asia-1, respectively. RT-PCR detected viral genome in 51 (85%) of the samples using pan-FMDV primers set, 1F/1R. Thirty-six samples were found positive and 7 negative by both the tests. The level of agreement between the tests was assessed by calculating the Kappa value, which was found to be fair (Kappa value = 0.303 and 95% CI = 0.089; 0.517) and significant (p = 0.009). However, 2 samples, which were found positive on S-ELISA tested negative on RT-PCR. This may be attributed to the presence of nucleotide mismatch(es) in the primer-binding sites that may have resulted in failure of amplification of the viral genome. The serotype-specific RT-PCR assays not only confirmed serotyping results of S-ELISA but were also able to establish serotype in 9 S-ELISA-negative but pan-FMDV RT-PCR-positive samples. Conclusions: The RT-PCR assay contributes significantly to establishing a quick, sensitive, and definitive diagnosis of FMD in resource-constrained countries. Samples giving negative results in S-ELISA should be tested in RT-PCR for the disease detection and virus typing.

Download Full-text

Detection of specific mRNAs in single nephron segments by use of the polymerase chain reaction

AJP Renal Physiology ◽

10.1152/ajprenal.1990.258.5.f1470 ◽

1990 ◽

Vol 258 (5) ◽

pp. F1470-F1474 ◽

Cited By ~ 4

Author(s):

T. Moriyama ◽

H. R. Murphy ◽

B. M. Martin ◽

A. Garcia-Perez

Keyword(s):

Polymerase Chain Reaction ◽

Aldose Reductase ◽

Collecting Duct ◽

Specific Gene ◽

Rt Pcr ◽

Chain Reaction ◽

Nephron Segments ◽

Single Nephron ◽

Specific Mrnas ◽

Polymerase Chain

We have developed a procedure to detect specific mRNAs in single renal nephron segments. This approach combines microdissection, reverse transcription (RT) of the target mRNA, and amplification of the resulting cDNA using the polymerase chain reaction (PCR). After microdissection, the sample is placed in a tube where it is permeabilized and where all reactions are performed directly without the need for isolation of the RNA. Our model target was the mRNA for aldose reductase. This enzyme catalyzes the conversion of glucose to sorbitol. Its expression is modulated by changes in extracellular osmolality in the renal medulla. RT-PCR of inner medullary collecting duct (1 mm) and glomeruli (6-10) yielded a product of the predicted length (670 base pairs) defined by the PCR primers. Its identity was confirmed by a specific oligonucleotide probe that differed from the primers. RT-PCR of proximal tubules (1 mm) resulted in no aldose reductase-specific amplification product. RT-PCR is generally applicable for measuring specific gene expression in single nephron segments or small numbers of cultured cells. Utility, limitations, and refinements of this approach are discussed.

Download Full-text

Expression of hyaluronan synthase-3 in porcine oviducal epithelium during oestrus

Reproduction Fertility and Development ◽

10.1071/rd02100 ◽

2003 ◽

Vol 15 (2) ◽

pp. 99 ◽

Cited By ~ 22

Author(s):

Paisan Tienthai ◽

Naoko Kimura ◽

Paraskevi Heldin ◽

Eimei Sato ◽

Heriberto Rodriguez-Martinez

Keyword(s):

Polymerase Chain Reaction ◽

Reverse Transcription ◽

Hyaluronan Synthase ◽

Critical Periods ◽

Rt Pcr ◽

Chain Reaction ◽

Mean Values ◽

Polymerase Chain ◽

Sperm Reservoir ◽

Oviduct Fluid

Hyaluronan (HA) has been related to fertilization and embryo development in the pig. Furthermore, HA is present in pig oviduct fluid and the lining epithelium, particularly of the pre-ovulatory sperm reservoir. Because the mechanisms that regulate HA synthesis have not yet been clarified, semiquantitative reverse transcription-polymerase chain reaction (RT-PCR) was conducted to assess the expression of mRNAs of two HA-synthesizing enzymes (has2 and has3) in the oviduct epithelium (uterotubal junction, isthmus, ampullary–isthmic junction and ampulla segments) of non-inseminated (control) and inseminated (treatment) sows at pre-, peri- and post-ovulatory oestrus. Only has3 mRNA was detected; it was present in all tubal segments of both control and treatment samples. The level of has3 expression did not vary significantly between non-inseminated and inseminated specimens, but there was a tendency (NS) for increased mean values during the peri- and post-ovulatory stages compared with pre-ovulation. It is concluded that has3 is expressed by the porcine endosalpinx epithelium and the levels of expression do not vary during the critical periods of sperm transport and fertilization, despite fluctuating levels of HA in the tubal fluid at corresponding periods.

Download Full-text