Akademik Veri Yönetim Sistemi
Journal of Medical Biochemistry, cilt.43, sa.3, ss.372-377, 2024 (SCI-Expanded)
Background: Laboratory professionals aim to provide a reli-able laboratory service using public resources efficiently while planning a test's procurement. This intuitive approach is ineffective, as seen in the COVID-19 pandem- ic, where the dramatic changes in admissions (e.g. decreased patient admissions) and the purpose of testing (e.g. D-dimer) were experienced. A model based on objec- tive data was developed that predicts the future test con- sumption of coagulation tests whose consumptions were highly variable during the pandemic. Methods: Between December 2018 and July 2021, month-ly consumptions of coagulation tests (PTT, aPTT, D-dimer, fibrinogen), total-, inpatient-, outpatient-, emergency-, non-emergency -admission numbers were collected. The relationship between input and output is modeled with an external input nonlinear autoregressive artificial neural net- work (NARX) using the MATLAB program. Monthly test consumption between January and July 2021 was used to test the power of the forecasting model.Results: According to the co-integration analysis, the total number as well as the number of emergency and non- urgent examinations and the number of working days per month are included in the model. When the consumption of aPTT and fibrinogen was estimated, it was possible to predict the consumption of other tests. Fifty months of data were used to predict consumption over the next six months, and prediction based on NARX was the more robust approach for both tests. Conclusion: The deep learning model gives better results than the intuitive approach in forecasting, even in the pan- demic era, and it shows that more effective and efficient planning will be possible if ANN-supported decision mech- anisms are used in forecasting.