Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network
Abstract
:1. Introduction
2. Materials and Methods
2.1. Characteristic of Participants, Workflow and Define Datasets
2.2. LogNNet Architecture
Algorithm 1. Algorithm of matrix W filling. |
xn: = C; |
for j: = 1 to P do |
for i: = 0 to N do |
begin |
xn: = (D−K * xn) mod L; // Congruential generator formula |
W [i,j]: = xn/L; |
end; |
2.3. Optimization of Reservoir Parameters
2.4. Classification Accuracy, K-Fold Cross-Validation and Balancing Techniques
2.5. Threshold Approach
2.6. Feature Selection Method
3. Results
3.1. Dataset SARS-CoV-2-RBV1
Threshold Accuracy on One Feature
3.2. Dataset SARS-CoV-2-RBV2
Threshold Accuracy on One Feature
4. Discussion
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
Appendix A
№ | Feature | Ath, % | Vth | Units | Type | Min | Max | Bin Size |
---|---|---|---|---|---|---|---|---|
43 | LDL | 96.47 | 116.14 | mg/dL | 2 | −83 | 258 | 3.4 |
36 | HDL-C | 94.73 | 43.09 | mg/dL | 2 | 8 | 115 | 1 |
39 | Cholesterol | 94.47 | 206.33 | mg/dL | 2 | 5 | 606 | 6 |
20 | MCHC | 94.35 | 31.31 | g/dL | 1 | 15.9 | 38.6 | 0.2 |
48 | Triglyceride | 90.96 | 163.35 | mg/dL | 2 | 34 | 1782 | 17 |
31 | Amylase | 85.1 | 76.35 | u/L | 1 | 0 | 1193 | 3 |
51 | UA | 81.12 | 5.39 | mg/dL | 1 | 0 | 14.3 | |
47 | TP | 79.68 | 68.05 | g/L | 2 | 15 | 96 | |
32 | CK-MB | 78.91 | 19.87 | u/L | 2 | 0 | 685.5 | |
42 | LDH | 74.98 | 258.40 | u/L | 1 | 0 | 2749 | |
29 | Albumin | 74.91 | 39.61 | g/L | 2 | 0 | 55.87 | |
37 | Calcium | 74.21 | 9.01 | mg/dL | 2 | 0 | 12.55 | |
30 | ALP | 74.13 | 154.35 | u/L | 1 | 0 | 3150 | |
38 | Chlorine | 72.62 | 103.47 | mmol/L | 2 | 79 | 345 | |
34 | GGT | 71.6 | 35.51 | u/L | 1 | 0 | 2732 | |
1 | CRP | 70.54 | 4.29 | mg/L | 1 | 1 | 1650 | |
41 | CK | 70.47 | 111.96 | u/L | 2 | 0 | 4665 | |
45 | Sodium | 69.24 | 139.02 | mmol/L | 1 | 108 | 175 | |
3 | Ferritin | 68.75 | 49.69 | μg/L | 1 | 0.2 | 1650 | |
46 | T-Bil | 68.52 | 0.58 | mg/dL | 2 | −0.35 | 20.95 | |
33 | D-Bil | 66.09 | 0.16 | mg/dL | 2 | −0.06 | 20 | |
11 | LYM | 66.01 | 1.50 | 103/μL | 2 | 0.08 | 715 | |
40 | Creatinine | 64.03 | 1.01 | mg/dL | 1 | 0 | 202 | |
7 | PCT | 63.22 | 0.12 | ng/mL | 1 | 0.12 | 1500 | |
4 | Fibrinogen | 63.18 | 307.94 | mg/dL | 2 | 10.9 | 668.07 | |
35 | Glucose | 62.42 | 122.05 | mg/dL | 1 | 11 | 846 | |
49 | eGFR | 61.48 | 87.22 | no unıt | 2 | 3.483 | 561.746 | |
27 | ALT | 61.35 | 29.54 | u/L | 1 | 0 | 2110 | |
28 | AST | 60.65 | 32.19 | u/L | 1 | 0 | 2927 | |
2 | D-Dimer | 60.37 | 385.41 | μg/L | 2 | 1.06 | 9610 | |
50 | Urea | 58.19 | 40.99 | mg/dL | 1 | 0 | 427 | |
14 | WBC | 58.08 | 5.71 | 103/μL | 2 | 0.4 | 127 | |
13 | PLT | 57.46 | 200.26 | 103/μL | 2 | 9 | 768 | |
8 | ESR | 57.38 | 14.07 | mm/hr | 1 | 2 | 124 | |
16 | EOS | 56.4 | 0 | 103/μL | 1 | 0 | 4.41 | |
21 | MCV | 56.25 | 84.03 | fL | 1 | 56.7 | 122.1 | |
22 | MONO | 56.25 | 0.54 | 103/μL | 2 | 0.03 | 6.4 | 0.06 |
44 | Potassium | 55.63 | 4.36 | mmol/L | 1 | 0 | 59 | |
26 | RDW | 55.49 | 13.21 | % | 2 | 0 | 30.8 | |
15 | BASO | 55.04 | 0.029 | 103/μL | 2 | 0 | 0.38 | |
17 | HCT | 55 | 38.33 | % | 1 | 11.4 | 60.1 | 60 |
10 | aPTT | 56.51 | 31.06 | Sec | 1 | 12 | 23,843.7 | 238 |
12 | NEU | 54.8 | 2.60 | 103/μL | 2 | 0.49 | 66.43 | |
18 | HGB | 54.12 | 12.31 | g/L | 1 | 3.7 | 19 | |
5 | INR | 53.15 | 0.735 | no unit | 2 | 0.12 | 88 | |
25 | RBC | 53 | 4.29 | 106/μL | 1 | 1.24 | 7.48 | 0.06 |
19 | MCH | 52.66 | 28.51 | pg | 1 | 15.9 | 41.9 | 0.2 |
24 | PDW | 51.93 | 11.89 | fL | 1 | 0 | 25.3 | |
23 | MPV | 51.79 | 9.81 | fL | 1 | 0 | 15 | |
6 | PT | 51.79 | 13.09 | Sec | 1 | 2 | 181 | |
9 | Troponin | 50.19 | 25 | ng/L | 1 | 0.01 | 25,000 |
№ | Feature | Ath, % | Vth | Units | Type | Min | Max | Bin Size |
---|---|---|---|---|---|---|---|---|
36 | NEU | 78.23 | 6.20 | 103/μL | 1 | 0.1 | 31.26 | 0.3 |
3 | Albumin | 76.87 | 32.20 | g/L | 2 | 0.08 | 55 | 0.5 |
41 | WBC | 74.28 | 7.93 | 103/μL | 1 | 0.4 | 68.3 | 0.6 |
42 | CRP | 74.03 | 15.051 | mg/L | 1 | 0.15 | 514 | 5 |
24 | Urea | 73.92 | 46.95 | mg/dL | 1 | 6 | 339 | 3 |
11 | Calcium | 72.14 | 8.50 | mg/dL | 2 | 0.6 | 12.43 | 0.1 |
21 | TP | 71.57 | 67.00 | g/L | 2 | 15 | 96 | 0.8 |
30 | LYM | 71.48 | 1.02 | 103/μL | 2 | 0.08 | 58.87 | |
40 | RDW | 68.89 | 13.30 | % | 1 | 11 | 27 | 0.16 |
48 | PCT | 67.85 | 0.151 | ng/mL | 1 | 0.052 | 100 | |
2 | AST | 66.39 | 44.92 | u/L | 1 | 4 | 2927 | |
16 | LDH | 66.11 | 267.37 | u/L | 1 | 20 | 1547 | |
9 | Glucose | 65.46 | 118.13 | mg/dL | 1 | 17 | 846 | 8 |
7 | D-Bil | 65.04 | 0.209 | mg/dL | 1 | 0.01 | 20 | |
44 | Ferritin | 64.17 | 238.116 | μg/L | 1 | 2.4 | 2000 | |
15 | CK | 63.66 | 99.92 | u/L | 1 | 2 | 4665 | |
43 | D-Dimer | 63.61 | 1074 | μg/L | 1 | 1.06 | 37,000 | |
29 | HGB | 62.82 | 12.20 | g/L | 2 | 4 | 19 | 0.15 |
47 | PT | 62.78 | 14.30 | Sec | 1 | 9.4 | 129 | |
23 | eGFR | 62.55 | 80.47 | no unıt | 2 | 4.724 | 561.746 | |
35 | MPV | 62.37 | 10.30 | fL | 1 | 8.1 | 15 | 0.07 |
39 | RBC | 62.37 | 4.28 | 106/μL | 2 | 1.24 | 7.22 | 0.06 |
50 | Troponin | 61.86 | 10.19 | ng/L | 1 | 1 | 4600 | |
20 | T-Bil | 61.81 | 0.58 | mg/dL | 1 | 0.01 | 29 | |
8 | GGT | 61.41 | 57.36 | u/L | 1 | 1 | 1085 | |
19 | Sodium | 61.01 | 145 | mmol/L | 1 | 112 | 175 | |
37 | PDW | 60.86 | 11.51 | fL | 1 | 7.6 | 25.3 | |
32 | MCHC | 60.72 | 32.11 | g/dL | 2 | 3.6 | 39.2 | |
28 | HCT | 59.71 | 36.63 | % | 2 | 12 | 56.3 | |
1 | ALT | 59.02 | 39.80 | u/L | 1 | 0.7 | 1349 | |
33 | MCV | 58.79 | 85.93 | fL | 1 | 55.8 | 117.8 | |
6 | CK-MB | 58.72 | 19.38 | u/L | 1 | 1 | 575.4 | |
14 | Creatinine | 58.39 | 1.26 | mg/dL | 1 | 0.46 | 202 | |
12 | Chlorine | 58.21 | 107 | mmol/L | 1 | 79 | 137 | 0.58 |
45 | Fibrinogen | 57.22 | 334 | mg/dL | 1 | 70.56 | 681.88 | |
49 | ESR | 57.2 | 38.03 | mm/hr | 1 | 2 | 139 | 1.37 |
5 | Amylase | 56.46 | 75.7 | 103/μL | 2 | 11 | 874 | |
46 | INR | 56.38 | 1.42 | no unit | 1 | 0.77 | 110 | |
51 | aPTT | 56.33 | 36.12 | Sec | 2 | 12 | 414 | |
25 | UA | 55.92 | 5.412 | mg/dL | 1 | 0.9 | 15 | |
38 | PLT | 55.61 | 160 | % | 2 | 5 | 1199 | |
34 | MONO | 55.22 | 0.474 | sec | 2 | 0.03 | 6.29 | |
18 | Potassium | 54.99 | 3.815 | mmol/L | 2 | 2.4 | 59 | |
27 | EOS | 54.72 | 0.111 | 103/Μl | 2 | 0.01 | 4.41 | |
4 | ALP | 54.35 | 63.98 | u/L | 1 | 1 | 3150 | 31 |
22 | Triglyceride | 53.27 | 141.6 | 106/μL | 1 | 32 | 1402 | |
31 | MCH | 53.11 | 28.22 | pg | 2 | 15.6 | 41.9 | |
13 | Cholesterol | 53.11 | 170 | mg/dL | 2 | 5 | 354 | |
10 | HDL-C | 53.02 | 34.69 | mg/dL | 2 | 8 | 93 | |
26 | BASO | 52.75 | 0.01 | 103/μL | 1 | 0.01 | 0.38 | |
17 | LDL | 51.26 | 115.1 | mg/dL | 1 | 15 | 258 |
References
- Mertoglu, C.; Huyut, M.; Olmez, H.; Tosun, M.; Kantarci, M.; Coban, T. COVID-19 is more dangerous for older people and its severity is increasing: A case-control study. Med. Gas Res. 2022, 12, 51–54. [Google Scholar] [CrossRef] [PubMed]
- Mertoglu, C.; Huyut, M.T.; Arslan, Y.; Ceylan, Y.; Coban, T.A. How do routine laboratory tests change in coronavirus disease 2019? Scand. J. Clin. Lab. Investig. 2021, 81, 24–33. [Google Scholar] [CrossRef]
- Huyut, M.T.; İlkbahar, F. The effectiveness of blood routine parameters and some biomarkers as a potential diagnostic tool in the diagnosis and prognosis of Covid-19 disease. Int. Immunopharmacol. 2021, 98, 107838. [Google Scholar] [CrossRef] [PubMed]
- Huyut, M.T.; Huyut, Z. Forecasting of Oxidant/Antioxidant levels of COVID-19 patients by using Expert models with biomarkers used in the Diagnosis/Prognosis of COVID-19. Int. Immunopharmacol. 2021, 100, 108127. [Google Scholar] [CrossRef]
- Huyut, M.; Üstündaǧ, H. Prediction of diagnosis and prognosis of COVID-19 disease by blood gas parameters using decision trees machine learning model: A retrospective observational study. Med. Gas Res. 2022, 12, 60–66. [Google Scholar] [CrossRef]
- Tahir Huyut, M.; Huyut, Z.; İlkbahar, F.; Mertoğlu, C. What is the impact and efficacy of routine immunological, biochemical and hematological biomarkers as predictors of COVID-19 mortality? Int. Immunopharmacol. 2022, 105, 108542. [Google Scholar] [CrossRef]
- Guan, W.; Ni, Z.; Hu, Y.; Liang, W.; Ou, C.; He, J.; Liu, L.; Shan, H.; Lei, C.; Hui, D.S.C.; et al. Clinical Characteristics of Coronavirus Disease 2019 in China. N. Engl. J. Med. 2020, 382, 1708–1720. [Google Scholar] [CrossRef]
- Banerjee, A.; Ray, S.; Vorselaars, B.; Kitson, J.; Mamalakis, M.; Weeks, S.; Baker, M.; Mackenzie, L.S. Use of Machine Learning and Artificial Intelligence to predict SARS-CoV-2 infection from Full Blood Counts in a population. Int. Immunopharmacol. 2020, 86, 106705. [Google Scholar] [CrossRef]
- Huyut, M.T.; Soygüder, S. The Multi-Relationship Structure between Some Symptoms and Features Seen during the New Coronavirus 19 Infection and the Levels of Anxiety and Depression post-Covid. East. J. Med. 2022, 27, 1–10. [Google Scholar] [CrossRef]
- Amgalan, A.; Othman, M. Hemostatic laboratory derangements in COVID-19 with a focus on platelet count. Platelets 2020, 31, 740–745. [Google Scholar] [CrossRef]
- Li, X.; Wang, L.; Yan, S.; Yang, F.; Xiang, L.; Zhu, J.; Shen, B.; Gong, Z. Clinical characteristics of 25 death cases with COVID-19: A retrospective review of medical records in a single medical center, Wuhan, China. Int. J. Infect. Dis. 2020, 94, 128–132. [Google Scholar] [CrossRef] [PubMed]
- Kukar, M.; Gunčar, G.; Vovko, T.; Podnar, S.; Černelč, P.; Brvar, M.; Zalaznik, M.; Notar, M.; Moškon, S.; Notar, M. COVID-19 diagnosis by routine blood tests using machine learning. Sci. Rep. 2021, 11, 10738. [Google Scholar] [CrossRef]
- Jiang, S.Q.; Huang, Q.F.; Xie, W.M.; Lv, C.; Quan, X.Q. The association between severe COVID-19 and low platelet count: Evidence from 31 observational studies involving 7613 participants. Br. J. Haematol. 2020, 190, e29–e33. [Google Scholar] [CrossRef]
- Zheng, Y.; Zhang, Y.; Chi, H.; Chen, S.; Peng, M.; Luo, L.; Chen, L.; Li, J.; Shen, B.; Wang, D. The hemocyte counts as a potential biomarker for predicting disease progression in COVID-19: A retrospective study. Clin. Chem. Lab. Med. 2020, 58, 1106–1115. [Google Scholar] [CrossRef] [PubMed]
- Lippi, G.; Plebani, M.; Henry, B.M. Thrombocytopenia is associated with severe coronavirus disease 2019 (COVID-19) infections: A meta-analysis. Clin. Chim. Acta 2020, 506, 145–148. [Google Scholar] [CrossRef]
- Mousavi, S.A.; Rad, S.; Rostami, T.; Rostami, M.; Mousavi, S.A.; Mirhoseini, S.A.; Kiumarsi, A. Hematologic predictors of mortality in hospitalized patients with COVID-19: A comparative study. Hematology 2020, 25, 383–388. [Google Scholar] [CrossRef]
- Beck, B.R.; Shin, B.; Choi, Y.; Park, S.; Kang, K. Predicting commercially available antiviral drugs that may act on the novel coronavirus (SARS-CoV-2) through a drug-target interaction deep learning model. Comput. Struct. Biotechnol. J. 2020, 18, 784–790. [Google Scholar] [CrossRef]
- Xu, X.; Jiang, X.; Ma, C.; Du, P.; Li, X.; Lv, S.; Yu, L.; Ni, Q.; Chen, Y.; Su, J.; et al. A Deep Learning System to Screen Novel Coronavirus Disease 2019 Pneumonia. Engineering 2020, 6, 1122–1129. [Google Scholar] [CrossRef]
- Brinati, D.; Campagner, A.; Ferrari, D.; Locatelli, M.; Banfi, G.; Cabitza, F. Detection of COVID-19 Infection from Routine Blood Exams with Machine Learning: A Feasibility Study. J. Med. Syst. 2020, 44, 135. [Google Scholar] [CrossRef]
- Cabitza, F.; Campagner, A.; Ferrari, D.; Di Resta, C.; Ceriotti, D.; Sabetta, E.; Colombini, A.; De Vecchi, E.; Banfi, G.; Locatelli, M.; et al. Development, evaluation, and validation of machine learning models for COVID-19 detection based on routine blood tests. Clin. Chem. Lab. Med. 2021, 59, 421–431. [Google Scholar] [CrossRef]
- Yang, H.S.; Hou, Y.; Vasovic, L.V.; Steel, P.A.D.; Chadburn, A.; Racine-Brzostek, S.E.; Velu, P.; Cushing, M.M.; Loda, M.; Kaushal, R.; et al. Routine Laboratory Blood Tests Predict SARS-CoV-2 Infection Using Machine Learning. Clin. Chem. 2020, 66, 1396–1404. [Google Scholar] [CrossRef] [PubMed]
- Joshi, R.P.; Pejaver, V.; Hammarlund, N.E.; Sung, H.; Kyu, S.; Lee, H.; Scott, G.; Gombar, S.; Shah, N.; Shen, S.; et al. Short communication A predictive tool for identi fi cation of SARS-CoV-2 PCR-negative emergency department patients using routine test results. J. Clin. Virol. 2020, 129, 104502. [Google Scholar] [CrossRef] [PubMed]
- Mei, X.; Lee, H.C.; Diao, K.Y.; Huang, M.; Lin, B.; Liu, C.; Xie, Z.; Ma, Y.; Robson, P.M.; Chung, M.; et al. Artificial intelligence–enabled rapid diagnosis of patients with COVID-19. Nat. Med. 2020, 26, 1224–1228. [Google Scholar] [CrossRef]
- Soares, F. A novel specific artificial intelligence-based method to identify COVID-19 cases using simple blood exams. medRxiv 2020. [Google Scholar] [CrossRef]
- Soltan, A.A.; Kouchaki, S.; Zhu, T.; Kiyasseh, D.; Taylor, T.; Hussain, Z.B.; Peto, T.; Brent, A.J.; Eyre, D.W.; Clifton, D. Artificial intelligence driven assessment of routinely collected healthcare data is an effective screening test for COVID-19 in patients presenting to hospital. medRxiv 2020. [Google Scholar] [CrossRef]
- Remeseiro, B.; Bolon-Canedo, V. A review of feature selection methods in medical applications. Comput. Biol. Med. 2019, 112, 103375. [Google Scholar] [CrossRef]
- Bikku, T. Multi-layered deep learning perceptron approach for health risk prediction. J. Big Data 2020, 7, 50. [Google Scholar] [CrossRef]
- Battineni, G.; Chintalapudi, N.; Amenta, F. Machine learning in medicine: Performance calculation of dementia prediction by support vector machines (SVM). Inform. Med. Unlocked 2019, 16, 100200. [Google Scholar] [CrossRef]
- Xing, W.; Bei, Y. Medical Health Big Data Classification Based on KNN Classification Algorithm. IEEE Access 2020, 8, 28808–28819. [Google Scholar] [CrossRef]
- Hoodbhoy, Z.; Noman, M.; Shafique, A.; Nasim, A.; Chowdhury, D.; Hasan, B. Use of machine learning algorithms for prediction of fetal risk using cardiotocographic data. Int. J. Appl. Basic Med. Res. 2019, 9, 226. [Google Scholar] [CrossRef]
- Alam, M.Z.; Rahman, M.S.; Rahman, M.S. A Random Forest based predictor for medical data classification using feature ranking. Inform. Med. Unlocked 2019, 15, 100180. [Google Scholar] [CrossRef]
- Schober, P.; Vetter, T.R. Logistic Regression in Medical Research. Anesth. Analg. 2021, 132, 365–366. [Google Scholar] [CrossRef] [PubMed]
- Podgorelec, V.; Kokol, P.; Stiglic, B.; Rozman, I. Decision trees: An overview and their use in medicine. J. Med. Syst. 2002, 26, 445–463. [Google Scholar] [CrossRef]
- Guyon, I.; Gunn, S.; Nikravesh, M.; Zadeh, L.A. Feature Extraction: Foundations and Applications; Studies in Fuzziness and Soft Computing; Springer: Berlin/Heidelberg, Germany, 2008; ISBN 9783540354888. [Google Scholar]
- Hall, M.A. Correlation-based Feature Selection for Machine Learning. Ph.D. Thesis, Department of Computer Science, The University of Waikato, Hamilton, NewZealand, April 1999; pp. 51–69. [Google Scholar]
- Dash, M.; Liu, H. Consistency-based search in feature selection. Artif. Intell. 2003, 151, 155–176. [Google Scholar] [CrossRef]
- Zhao, Z.; Liu, H. Searching for interacting features. In Proceedings of the 20th International Joint Conference on Artificial Intelligence, Hyderabad, India, 6–12 January 2007; pp. 1156–1161. [Google Scholar]
- Hall, M.A.; Smith, L.A. Practical feature subset selection for machine learning. In Proceedings of the Computer Science ’98, 21st Australasian Computer Science Conference ACSC’98, Perth, Australia, 4–6 February 1998; Volume 20, pp. 181–191. [Google Scholar]
- Kononenko, I. Estimating attributes: Analysis and extensions of RELIEF. In European Conference on Machine Learning; Springer: Berlin/Heidelberg, Germany, 1994; Volume 784, pp. 171–182. [Google Scholar] [CrossRef]
- Le Thi, H.A.; Nguyen, V.V.; Ouchani, S. Gene selection for cancer classification using DCA. In International Conference on Advanced Data Mining and Applications; Springer: Berlin/Heidelberg, Germany, 2008; Volume 5139, pp. 62–72. [Google Scholar] [CrossRef]
- Tibshirani, R. Regression Shrinkage and Selection via the Lasso. J. R. Stat. Soc. Ser. B 1996, 58, 267–288. [Google Scholar] [CrossRef]
- Velichko, A. Neural network for low-memory IoT devices and MNIST image recognition using kernels based on logistic map. Electronics 2020, 9, 1432. [Google Scholar] [CrossRef]
- Velichko, A. A method for medical data analysis using the lognnet for clinical decision support systems and edge computing in healthcare. Sensors 2021, 21, 6209. [Google Scholar] [CrossRef]
- Velichko, A.; Heidari, H. A Method for Estimating the Entropy of Time Series Using Artificial Neural Networks. Entropy 2021, 23, 1432. [Google Scholar] [CrossRef]
- Izotov, Y.A.; Velichko, A.A.; Boriskov, P.P. Method for fast classification of MNIST digits on Arduino UNO board using LogNNet and linear congruential generator. J. Phys. Conf. Ser. 2021, 2094, 32055. [Google Scholar] [CrossRef]
- Heidari, H.; Velichko, A. An improved LogNNet classifier for IoT application. J. Phys. Conf. Ser. 2021, 2094, 032015. [Google Scholar] [CrossRef]
- Mattiuzzi, C.; Lippi, G. Which lessons shall we learn from the 2019 novel coronavirus outbreak? Ann. Transl. Med. 2020, 8, 48. [Google Scholar] [CrossRef] [PubMed]
- Kim, S.; Kim, D.-M.; Lee, B. Insufficient Sensitivity of RNA Dependent RNA Polymerase Gene of SARS-CoV-2 Viral Genome as Confirmatory Test using Korean COVID-19 Cases. Preprints 2020, 1–4. [Google Scholar] [CrossRef]
- Zhang, J.J.; Cao, Y.Y.; Tan, G.; Dong, X.; Wang, B.C.; Lin, J.; Yan, Y.Q.; Liu, G.H.; Akdis, M.; Akdis, C.A.; et al. Clinical, radiological, and laboratory characteristics and risk factors for severity and mortality of 289 hospitalized COVID-19 patients. Allergy Eur. J. Allergy Clin. Immunol. 2021, 76, 533–550. [Google Scholar] [CrossRef] [PubMed]
- Teymouri, M.; Mollazadeh, S.; Mortazavi, H.; Naderi Ghale-noie, Z.; Keyvani, V.; Aghababaei, F.; Hamblin, M.R.; Abbaszadeh-Goudarzi, G.; Pourghadamyari, H.; Hashemian, S.M.R.; et al. Recent advances and challenges of RT-PCR tests for the diagnosis of COVID-19. Pathol. Res. Pract. 2021, 221, 153443. [Google Scholar] [CrossRef]
- D’Cruz, R.J.; Currier, A.W.; Sampson, V.B. Laboratory Testing Methods for Novel Severe Acute Respiratory Syndrome-Coronavirus-2 (SARS-CoV-2). Front. Cell Dev. Biol. 2020, 8, 468. [Google Scholar] [CrossRef]
- Yang, A.P.; Liu, J.P.; Tao, W.Q.; Li, H.M. The diagnostic and predictive role of NLR, d-NLR and PLR in COVID-19 patients. Int. Immunopharmacol. 2020, 84, 106504. [Google Scholar] [CrossRef]
- Huyut, M.T. Automatic Detection of Severely and Mildly Infected COVID-19 Patients with Supervised Machine Learning Models. IRBM 2022, 1, 1–12. [Google Scholar] [CrossRef]
- Zhang, C.; Shi, L.; Wang, F.S. Liver injury in COVID-19: Management and challenges. Lancet Gastroenterol. Hepatol. 2020, 5, 428–430. [Google Scholar] [CrossRef]
- Zheng, M.; Gao, Y.; Wang, G.; Song, G.; Liu, S.; Sun, D.; Xu, Y.; Tian, Z. Functional exhaustion of antiviral lymphocytes in COVID-19 patients. Cell. Mol. Immunol. 2020, 17, 533–535. [Google Scholar] [CrossRef]
- Luo, J.; Zhou, L.; Feng, Y.; Li, B.; Guo, S. The selection of indicators from initial blood routine test results to improve the accuracy of early prediction of COVID-19 severity. PLoS ONE 2021, 16, e0253329. [Google Scholar] [CrossRef]
- Ma, Y.; Hou, L.; Yang, X.; Huang, Z.; Yang, X.; Zhao, N.; He, M.; Shi, Y.; Kang, Y.; Yue, J.; et al. The association between frailty and severe disease among COVID-19 patients aged over 60 years in China: A prospective cohort study. BMC Med. 2020, 18, 274. [Google Scholar] [CrossRef] [PubMed]
- Lai, C.C.; Shih, T.P.; Ko, W.C.; Tang, H.J.; Hsueh, P.R. Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and coronavirus disease-2019 (COVID-19): The epidemic and the challenges. Int. J. Antimicrob. Agents 2020, 55, 105924. [Google Scholar] [CrossRef] [PubMed]
- Feld, J.; Tremblay, D.; Thibaud, S.; Kessler, A.; Naymagon, L. Ferritin levels in patients with COVID-19: A poor predictor of mortality and hemophagocytic lymphohistiocytosis. Int. J. Lab. Hematol. 2020, 42, 773–779. [Google Scholar] [CrossRef]
- Zhou, F.; Yu, T.; Du, R.; Fan, G.; Liu, Y.; Liu, Z.; Xiang, J.; Wang, Y.; Song, B.; Gu, X.; et al. Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: A retrospective cohort study. Lancet 2020, 395, 1054–1062. [Google Scholar] [CrossRef]
- Chen, G.; Wu, D.; Guo, W.; Cao, Y.; Huang, D.; Wang, H.; Wang, T.; Zhang, X.; Chen, H.; Yu, H.; et al. Clinical and immunological features of severe and moderate coronavirus disease 2019. J. Clin. Investig. 2020, 130, 2620–2629. [Google Scholar] [CrossRef] [PubMed]
- Cheng, L.; Li, H.; Li, L.; Liu, C.; Yan, S.; Chen, H.; Li, Y. Ferritin in the coronavirus disease 2019 (COVID-19): A systematic review and meta-analysis. J. Clin. Lab. Anal. 2020, 34, 1–18. [Google Scholar] [CrossRef]
- Cavalcante-Silva, L.H.A.; Carvalho, D.C.M.; Lima, É.D.A.; Galvão, J.G.; da Silva, J.S.d.F.; de Sales-Neto, J.M.; Rodrigues-Mascarenhas, S. Neutrophils and COVID-19: The road so far. Int. Immunopharmacol. 2021, 90, 107233. [Google Scholar] [CrossRef]
- Pan, F.; Ye, T.; Sun, P.; Gui, S.; Liang, B.; Li, L.; Zheng, D.; Wang, J.; Hesketh, R.L.; Yang, L.; et al. Time Course of Lung Changes on Chest CT During Recovery From 2019 Novel Coronavirus (COVID-19) Pneumonia. Radiology 2020, 295, 200370. [Google Scholar] [CrossRef]
- Zhao, D.; Yao, F.; Wang, L.; Zheng, L.; Gao, Y.; Ye, J.; Guo, F.; Zhao, H.; Gao, R. A Comparative Study on the Clinical Features of Coronavirus 2019 (COVID-19) Pneumonia with Other Pneumonias. Clin. Infect. Dis. 2020, 71, 756–761. [Google Scholar] [CrossRef]
- Rabanser, S.; Günnemann, S.; Lipton, Z.C. Failing loudly: An empirical study of methods for detecting dataset shift. Adv. Neural Inf. Process. Syst. 2019, 32. [Google Scholar] [CrossRef]
- Al-Aubidy, K.M.; Derbas, A.M.; Al-Mutairi, A.W. Real-time patient health monitoring and alarming using wireless-sensor-network. In Proceedings of the 2016 13th International Multi-Conference on Systems, Signals & Devices (SSD), Leipzig, Germany, 21–24 March 2016; pp. 416–423. [Google Scholar] [CrossRef]
- Taiwo, O.; Ezugwu, A.E. Smart healthcare support for remote patient monitoring during Covid-19 quarantine. Inform. Med. Unlocked 2020, 20, 100428. [Google Scholar] [CrossRef] [PubMed]
- Lamonaca, F.; Balestrieri, E.; Tudosa, I.; Picariello, F.; Carnì, D.L.; Scuro, C.; Bonavolontà, F.; Spagnuolo, V.; Grimaldi, G.; Colaprico, A. An Overview on Internet of Medical Things in Blood Pressure Monitoring. In Proceedings of the 2019 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Istanbul, Turkey, 26–28 June 2019; pp. 1–6. [Google Scholar]
- Hu, F.; Xiao, Y.; Hao, Q. Congestion-aware, loss-resilient bio-monitoring sensor networking for mobile health applications. IEEE J. Sel. Areas Commun. 2009, 27, 450–465. [Google Scholar] [CrossRef]
- Vizbaras, A.; Simonyte, I.; Droz, S.; Torcheboeuf, N.; Miasojedovas, A.; Trinkunas, A.; Buciunas, T.; Dambrauskas, Z.; Gulbinas, A.; Boiko, D.L.; et al. GaSb Swept-Wavelength Lasers for Biomedical Sensing Applications. IEEE J. Sel. Top. Quantum Electron. 2019, 25, 1–12. [Google Scholar] [CrossRef]
- Clifton, L.; Clifton, D.A.; Pimentel, M.A.F.; Watkinson, P.J.; Tarassenko, L. Predictive monitoring of mobile patients by combining clinical observations with data from wearable sensors. IEEE J. Biomed. Health Inform. 2014, 18, 722–730. [Google Scholar] [CrossRef]
- Pfeil, J.; Nechyporenko, A.; Frohme, M.; Hufert, F.T.; Schulze, K. Examination of blood samples using deep learning and mobile microscopy. BMC Bioinform. 2022, 23, 1–14. [Google Scholar] [CrossRef]
- Chan, J.; Michaelsen, K.; Estergreen, J.K.; Sabath, D.E.; Gollakota, S. Micro-mechanical blood clot testing using smartphones. Nat. Commun. 2022, 13, 1–12. [Google Scholar] [CrossRef]
- Farooqi, M.H.; Abdelmannan, D.K.; Mubarak, M.; Abdalla, M.; Hamed, A.; Xavier, M.; Joyce, T.; Cadiz, S.; Nawaz, F.A. The Impact of Telemonitoring on Improving Glycemic and Metabolic Control in Previously Lost-to-Follow-Up Patients with Type 2 Diabetes Mellitus: A Single-Center Interventional Study in the United Arab Emirates. Int. J. Clin. Pract. 2022, 2022, 6286574. [Google Scholar] [CrossRef]
- Zhang, Y.; Zhang, Y.; Li, H.; Cao, Y.; Han, S.; Zhang, K.; He, W. Covalent Biosensing Polymer Chain Reaction Enabling Periphery Blood Testing to Predict Tumor Invasiveness with a Platelet Procancerous Protein. Anal. Chem. 2022, 94, 1983–1989. [Google Scholar] [CrossRef]
№ | Feature | № | Feature | № | Feature | № | Feature | № | Feature |
---|---|---|---|---|---|---|---|---|---|
1 | CRP | 12 | NEU | 23 | MPV | 34 | GGT | 45 | Sodium |
2 | D-Dimer | 13 | PLT | 24 | PDW | 35 | Glucose | 46 | T-Bil |
3 | Ferritin | 14 | WBC | 25 | RBC | 36 | HDL-C | 47 | TP |
4 | Fibrinogen | 15 | BASO | 26 | RDW | 37 | Calcium | 48 | Triglyceride |
5 | INR | 16 | EOS | 27 | ALT | 38 | Chlorine | 49 | eGFR |
6 | PT | 17 | HCT | 28 | AST | 39 | Cholesterol | 50 | Urea |
7 | PCT | 18 | HGB | 29 | Albumin | 40 | Creatinine | 51 | UA |
8 | ESR | 19 | MCH | 30 | ALP | 41 | CK | ||
9 | Troponin | 20 | MCHC | 31 | Amylase | 42 | LDH | ||
10 | aPTT | 21 | MCV | 32 | CK-MB | 43 | LDL | ||
11 | LYM | 22 | MONO | 33 | D-Bil | 44 | Potassium |
№ | Feature | № | Feature | № | Feature | № | Feature | № | Feature |
---|---|---|---|---|---|---|---|---|---|
1 | ALT | 12 | Chlorine | 23 | eGFR | 34 | MONO | 45 | Fibrinogen |
2 | AST | 13 | Cholesterol | 24 | Urea | 35 | MPV | 46 | INR |
3 | Albumin | 14 | Creatinine | 25 | UA | 36 | NEU | 47 | PT |
4 | ALP | 15 | CK | 26 | BASO | 37 | PDW | 48 | PCT |
5 | Amylase | 16 | LDH | 27 | EOS | 38 | PLT | 49 | ESR |
6 | CK-MB | 17 | LDL | 28 | HCT | 39 | RBC | 50 | Troponin |
7 | D-Bil | 18 | Potassium | 29 | HGB | 40 | RDW | 51 | aPTT |
8 | GGT | 19 | Sodium | 30 | LYM | 41 | WBC | ||
9 | Glucose | 20 | T-Bil | 31 | MCH | 42 | CRP | ||
10 | HDL-C | 21 | TP | 32 | MCHC | 43 | D-Dimer | ||
11 | Calcium | 22 | Triglyceride | 33 | MCV | 44 | Ferritin |
Chaotic Map | List of Optimized Parameters (Limits) | Equation | |
---|---|---|---|
Congruent generator | K (−100 to 100) D (−100 to 100) L (2 to 10,000) C (−100 to 100) | (1) |
Dataset SARS-CoV-2-RBV1 | Dataset SARS-CoV-2-RBV2 | ||||||
---|---|---|---|---|---|---|---|
K | D | L | C | K | D | L | C |
93 | 68 | 9276 | 73 | 47 | 99 | 8941 | 56 |
Ep | A46(FR [21,37,40,42,49]) | Precision “Non-COVID-19” | Precision “COVID-19” | Recall “Non-COVID-19” | Recall “COVID-19” | F1 “Non-COVID-19” | F1 “COVID-19” |
---|---|---|---|---|---|---|---|
10 | 98.376 | 0.978 | 0.99 | 0.991 | 0.977 | 0.984 | 0.984 |
30 | 99.339 | 0.992 | 0.995 | 0.995 | 0.992 | 0.993 | 0.993 |
100 | 99.509 | 0.994 | 0.996 | 0.996 | 0.994 | 0.995 | 0.995 |
150 | 99.49 | 0.994 | 0.996 | 0.996 | 0.994 | 0.995 | 0.995 |
200 | 99.471 | 0.994 | 0.995 | 0.995 | 0.994 | 0.995 | 0.995 |
Number | dA46 | Features |
---|---|---|
20 | 8.007 | MCHC |
19 | 3.399 | MCH |
10 | 3.022 | aPTT |
17 | 0.359 | HCT |
36 | 0.208 | HDL-C |
22 | 0.17 | MONO |
25 | 0.151 | RBC |
Combinations of Features | A | Precision “Non-COVID-19” | Precision “COVID-19” | Recall “Non-COVID-19” | Recall “COVID-19” | F1 “Non-COVID-19” | F1 “COVID-19” |
---|---|---|---|---|---|---|---|
A46(FR [21,37,40,42,49]) | 99.509 | 0.994 | 0.996 | 0.996 | 0.994 | 0.995 | 0.995 |
A7(FS [10,17,19,20,22,25,36]) | 99.358 | 0.991 | 0.996 | 0.996 | 0.991 | 0.994 | 0.994 |
A1(FS [>20]) | 94.279 | 0.930 | 0.958 | 0.959 | 0.926 | 0.944 | 0.942 |
A1(FS [>19]) | 52.418 | 0.526 | 0.524 | 0.500 | 0.548 | 0.509 | 0.532 |
A1(FS [10]) | 52.398 | 0.516 | 0.947 | 0.972 | 0.075 | 0.672 | 0.100 |
A1(FS [36]) | 94.429 | 0.935 | 0.955 | 0.956 | 0.932 | 0.945 | 0.943 |
A2(FS [19,20]) | 99.150 | 0.989 | 0.994 | 0.994 | 0.989 | 0.992 | 0.991 |
A2(FS [20,36]) | 97.583 | 0.973 | 0.979 | 0.979 | 0.972 | 0.976 | 0.976 |
A2(FS [19,36]) | 94.373 | 0.934 | 0.955 | 0.957 | 0.931 | 0.945 | 0.943 |
A3(FS [10,19,20]) | 99.169 | 0.989 | 0.995 | 0.995 | 0.989 | 0.992 | 0.992 |
A5(FS [10,17,19,22,25]) | 51.699 | 0.526 | 0.546 | 0.784 | 0.250 | 0.604 | 0.277 |
Ep | A48(FR [14,44,45]) | Precision “Non-ICU” | Precision “ICU” | Recall “Non-ICU” | Recall “ICU” | F1 “Non-ICU” | F2 “ICU” |
---|---|---|---|---|---|---|---|
10 | 88.715 | 0.993 | 0.307 | 0.887 | 0.881 | 0.937 | 0.451 |
30 | 90.459 | 0.993 | 0.347 | 0.906 | 0.876 | 0.947 | 0.492 |
100 | 93.306 | 0.990 | 0.433 | 0.939 | 0.821 | 0.964 | 0.562 |
150 | 94.434 | 0.989 | 0.49 | 0.952 | 0.797 | 0.97 | 0.599 |
200 | 94.486 | 0.987 | 0.495 | 0.955 | 0.767 | 0.97 | 0.592 |
Number | dA48 | Features |
---|---|---|
49 | 2.18 | ESR |
36 | 1.872 | NEU |
42 | 1.59 | CRP |
3 | 1.359 | Albumin |
39 | 1.154 | RBC |
12 | 0.974 | Chlorine |
40 | 0.872 | RDW |
4 | 0.795 | ALP |
21 | 0.795 | TP |
9 | 0.769 | Glucose |
35 | 0.744 | MPV |
29 | 0.718 | HGB |
Combinations of Features | A | Precision “Non-ICU” | Precision “ICU” | Recall “Non-ICU” | Recall “ICU” | F1 “Non-ICU” | F1 “ICU” |
---|---|---|---|---|---|---|---|
A48(FR [14,44,45]) | 94.434 | 0.989 | 0.49 | 0.952 | 0.797 | 0.97 | 0.599 |
A12(FS [3,4,9,12,21,29,35,36,39,40,42,49]) | 90.946 | 0.990 | 0.364 | 0.914 | 0.831 | 0.950 | 0.499 |
A1(FS [49]) | 59.598 | 0.950 | 0.059 | 0.605 | 0.418 | 0.694 | 0.097 |
A1(FS [49]) | 75.040 | 0.955 | 0.085 | 0.773 | 0.341 | 0.851 | 0.133 |
A3(FS [36,42,49]) | 82.712 | 0.989 | 0.210 | 0.827 | 0.826 | 0.900 | 0.334 |
A7(FS [3,12,36,39,40,42,49]) | 89.355 | 0.991 | 0.341 | 0.896 | 0.846 | 0.940 | 0.469 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Huyut, M.T.; Velichko, A. Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network. Sensors 2022, 22, 4820. https://doi.org/10.3390/s22134820
Huyut MT, Velichko A. Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network. Sensors. 2022; 22(13):4820. https://doi.org/10.3390/s22134820
Chicago/Turabian StyleHuyut, Mehmet Tahir, and Andrei Velichko. 2022. "Diagnosis and Prognosis of COVID-19 Disease Using Routine Blood Values and LogNNet Neural Network" Sensors 22, no. 13: 4820. https://doi.org/10.3390/s22134820