Rutin kan testleriyle COVID-19 tanı tahmininde makine öğrenmesi yöntemleriyle bir mobil uygulama geliştirilmesi
Öz
Amaç: Tüm dünya Aralık 2019'dan bu yana SARS-CoV-2 virüsü ile başa çıkmaya çalışmaktadır. Hastalığın erken belirtileri, soğuk algınlığı ve grip gibi diğer yaygın durumlarla örtüştüğünden, hekimler için erken tanının önemi büyüktür. Bu çalışmada, genel kullanıma açık anonim bir veri seti kullanılarak, rutin kan testleri sonuçları üzerinden Yeni Koronavirüs Hastalığı (COVID-19) tanısının (pozitif/negatif) makine öğrenmesi algoritmaları yardımıyla tahmin edilmesine yönelik bir mobil uygulama geliştirilmesi amaçlanmaktadır.
Gereç ve Yöntem: Veri setinde yer alan, kayıp gözlem, sınıf dengesizliği, aykırı gözlem ve ilgisiz değişken problemleri giderildikten sonra makine öğrenmesi yöntemlerinin sınıflandırma performansları test edilmiş, ardından uygun değişkenlerle COVID-19 tanısı için lojistik regresyon modeli kurulmuştur. Bu model kullanılarak makine öğrenmesi tabanlı mobil uygulaması tasarlanmıştır.
Bulgular: Tanı koymada en iyi sonuç veren değişkenler, eozinofil, lökosit, trombosit, monosit, kırmızı kan hücresi, bazofildir. Veri ön işleme problemleri giderildikten sonra kullanılan algoritmaların sınıflandırma performansları, ham verideki performans değerlerine göre oldukça yükselmiştir.
Sonuç: Geliştirilen mobil uygulama ile rutin kan testi sonuçları kullanılarak, hızlı ve kolay bir şekilde Covid-19 tanısı tahmininde bulunulması mümkündür.
Anahtar Kelimeler
Covid-19 makine öğrenmesi yöntemleri rutin kan testi mobil uygulama tanı
Kaynakça
- WHO Coronavirus (COVID-19) Dashboard Website [cited 27 April 2021]. Available from: https://covid19.who.int/
- Alballa, N., & Al-Turaiki, I. Machine Learning Approaches in COVID-19 Diagnosis, Mortality, and Severity Risk Prediction: A Review. Informatics in Medicine Unlocked 2021; 100564.
- Zhou, Z. H. Ensemble methods: Foundations and algorithms. In Ensemble Methods: Foundations and Algorithms. 1st Edition. New York: Chapman and Hall/CRC. 2012..
- Zhou F, Yu T, Du R, et al. Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study. The Lancet 2020; 395(10229):1054-62.
- Open Datasets and Machine Learning Projects|Kaggle [Internet]. Available from: https://www.kaggle.com/datasets
- García, Salvador, Julián Luengo, and Francisco Herrera. Data preprocessing in data mining. Vol. 72. Cham, Switzerland: Springer International Publishing, 2015.
- Demirarslan, M., & Suner, A. A Proposal of New Feature Selection Method Sensitive to Outliers and Correlation 2021; bioRxiv 2021.03.11.434934; doi: https://doi.org/10.1101/2021.03.11.434934
- Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. Random Forests for land cover classification. Pattern Recognit Lett. 2005; 27 (4): 294-300. https://doi.org/10.1016/j.patrec.2005.08.011
- Ke, G., Meng, Q., Finley, T., et al. LightGBM: A highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst. 2017; 30: 3146-54.
- Chen, T., & Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–94). New York, NY, USA: ACM; 2016 https://doi.org/10.1145/2939672.2939785
- Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V. and Gulin, A. CatBoost: unbiased boosting with categorical features. Adv Neural Inf Process Syst. 2018; 31.
- Breiman,L. Bagging predictors. Machine Learning 1996; 24 (2): 123–40. https://doi.org/10.1007/bf00058655.
- Ian Goodfellow, Yoshua Bengio, A. C. Deep Learning Book. Deep Learning 2015 https://doi.org/10.1016/B978-0-12-391420-0.09987-X.
- Powers D. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation. J of Machine Learn Tech 2011; 2 (1): 37-63.
- Delgado R & Tibau X-A. Why Cohen’s Kappa should be avoided as performance measure in classification. PLoS ONE 2019; 14 (9): e0222916. https://doi.org/10.1371/journal.pone.0222916
- Cohen J. A Coefficient of Agreement for Nominal Scales. Educ Psychol Meas. 1960; 20 (1): 37-46. https://doi.org/10.1177/001316446002000104
- Yavaş M, Güran A, ve Uysal M. Covid-19 Veri Kümesinin SMOTE Tabanlı Örnekleme Yöntemi Uygulanarak Sınıflandırılması. Avrupa Bilim ve Teknoloji Dergisi. 2020:258-64. https://doi.org/10.31590/ejosat.779952
- Banerjee A, Ray S, Vorselaars B, et al. 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. https://doi.org/10.1016/j.intimp.2020.106705
- Yaşar, Ş. & Çolak, C. A Proposed Model Can Classify the Covid-19 Pandemic Based on the Laboratory Test Results. Journal of Cognitive Syst 2020; 5 (2): 60-3.
Development of a mobile application by using machine learning methods for the prediction of COVID-19 diagnosis with routine blood tests
Öz
Objective: The whole world has been dealing with the SARS-CoV-2 virus since December 2019. Early diagnosis is of great importance for physicians, as the early symptoms of the disease overlap with other common conditions such as cold and flu. In this study, we aimed to develop a mobile application to diagnose COVID-19 with machine learning algorithms that use anonymized publicly available routine blood tests results.
Materials and Methods: After eliminating the missing observation, class imbalance, outlier observation, and unrelated variable problems in the data set, the classification performances of machine learning methods were tested, and then a logistic regression model was established for the detection of COVID-19 with appropriate variables. Using this model, a machine learning-based mobile application has been designed.
Results: The variables that gave the best results in diagnosis were eosinophils, leukocytes, thrombocytes, monocytes, red blood cells, and basophils. After solving the data pre-processing problems, the classification performance of the algorithms used has increased considerably compared to the performance values in the raw data.
Conclusion: With the developed mobile application, it is possible to estimate the diagnosis of Covid-19 quickly and easily by using routine blood test results.
Anahtar Kelimeler
Covid-19 machine learning methods routine blood test mobile application diagnosis
Kaynakça
- WHO Coronavirus (COVID-19) Dashboard Website [cited 27 April 2021]. Available from: https://covid19.who.int/
- Alballa, N., & Al-Turaiki, I. Machine Learning Approaches in COVID-19 Diagnosis, Mortality, and Severity Risk Prediction: A Review. Informatics in Medicine Unlocked 2021; 100564.
- Zhou, Z. H. Ensemble methods: Foundations and algorithms. In Ensemble Methods: Foundations and Algorithms. 1st Edition. New York: Chapman and Hall/CRC. 2012..
- Zhou F, Yu T, Du R, et al. Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study. The Lancet 2020; 395(10229):1054-62.
- Open Datasets and Machine Learning Projects|Kaggle [Internet]. Available from: https://www.kaggle.com/datasets
- García, Salvador, Julián Luengo, and Francisco Herrera. Data preprocessing in data mining. Vol. 72. Cham, Switzerland: Springer International Publishing, 2015.
- Demirarslan, M., & Suner, A. A Proposal of New Feature Selection Method Sensitive to Outliers and Correlation 2021; bioRxiv 2021.03.11.434934; doi: https://doi.org/10.1101/2021.03.11.434934
- Gislason, P. O., Benediktsson, J. A., & Sveinsson, J. R. Random Forests for land cover classification. Pattern Recognit Lett. 2005; 27 (4): 294-300. https://doi.org/10.1016/j.patrec.2005.08.011
- Ke, G., Meng, Q., Finley, T., et al. LightGBM: A highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst. 2017; 30: 3146-54.
- Chen, T., & Guestrin, C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–94). New York, NY, USA: ACM; 2016 https://doi.org/10.1145/2939672.2939785
- Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A.V. and Gulin, A. CatBoost: unbiased boosting with categorical features. Adv Neural Inf Process Syst. 2018; 31.
- Breiman,L. Bagging predictors. Machine Learning 1996; 24 (2): 123–40. https://doi.org/10.1007/bf00058655.
- Ian Goodfellow, Yoshua Bengio, A. C. Deep Learning Book. Deep Learning 2015 https://doi.org/10.1016/B978-0-12-391420-0.09987-X.
- Powers D. Evaluation: From Precision, Recall and F-Measure to ROC, Informedness, Markedness & Correlation. J of Machine Learn Tech 2011; 2 (1): 37-63.
- Delgado R & Tibau X-A. Why Cohen’s Kappa should be avoided as performance measure in classification. PLoS ONE 2019; 14 (9): e0222916. https://doi.org/10.1371/journal.pone.0222916
- Cohen J. A Coefficient of Agreement for Nominal Scales. Educ Psychol Meas. 1960; 20 (1): 37-46. https://doi.org/10.1177/001316446002000104
- Yavaş M, Güran A, ve Uysal M. Covid-19 Veri Kümesinin SMOTE Tabanlı Örnekleme Yöntemi Uygulanarak Sınıflandırılması. Avrupa Bilim ve Teknoloji Dergisi. 2020:258-64. https://doi.org/10.31590/ejosat.779952
- Banerjee A, Ray S, Vorselaars B, et al. 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. https://doi.org/10.1016/j.intimp.2020.106705
- Yaşar, Ş. & Çolak, C. A Proposed Model Can Classify the Covid-19 Pandemic Based on the Laboratory Test Results. Journal of Cognitive Syst 2020; 5 (2): 60-3.