Life Sciences & Biotechnology
Title : | Efficient prediction strategy of COVID-19 based on pandemic data and immunoinformatics, integrated on artificial intelligence (AI) platform |
Area of research : | COVID-19 Research, Life Sciences & Biotechnology |
Focus area : | Mathematical modelling for COVID-19 |
Principal Investigator : | Dr Debashree Bandyopadhyay, Assistant Professor, Birla Institute of Technology & Science (BITS), Pilani |
Timeline Start Year : | 2020 |
Contact info : | banerjee.debi@hyderabad.bits-pilani.ac.in |
Details
Executive Summary : | In this study, COVID-19 detection strategy is developed based on clinical features (blood profiles, cytokines levels etc.) obtained from various hospitals across the globe (published data). This study aims to develop an artificial intelligence platform (deep neural network), where the input data set will include samples from COVID-19 positive patients (mild and severe cases), similar respiratory diseases and healthy controls. |
Outcome/Output: | Six different datasets were curated with clinical information from two different countries, namely Brazil and Italy. Different haematology parameters were trained to develop machine learning models, based on the datasets. Deep neural network failed on these datasets, as there were a large number of null entries. Hence, machine learning model have been developed based on XGBoost classifier. The performances of the models based on the above six datasets were compared with the performance of reported models.
Four hematology parameters identified, namely, leukocyte, eosinophil, monocyte and platelet count, can distinguish COVID-19 infection from five other similar respiratory viruses, namely, influenza A (H1N1), influenza B, coronavirus N63, rhinovirus and respiratory syntactical virus. Statistical significance tests validated the differences between comorbidities. |
Organizations involved