College of Computer Science and Mathematics

Defense of a master’s thesis in the College of Computer Science and Mathematics – Department of Computer Science entitled:
(Developing a Deep Learning AI-based data analytics technique of Electronic Health Records)
Developing AI-based data analytics technology for deep learning of e-health records

In continuation of the scientific research movement and the follow-up and presence of the Dean of the Faculty of Computer Science and Mathematics, Prof. Dr. Duha Bashir Abdel Allah

The master’s thesis (Developing a Deep Learning AI-based data analytics technique of Electronic Health Records) was discussed in the discussion hall of the College of Computer Science and Mathematics at the University of Mosul on Thursday 1/8/2024 by student Dalal Nofal Hamid Al-Rawi under the supervision of Assistant Professor Dr. Mohamed Jagan Younis.

The thesis submitted by the student dealt with the creation of a new intelligence technology based on deep learning to predict the duration of stay of diabetics in the hospital, after analyzing the data of people with this disease according to the available electronic health records.
The study looked at the use of four groups of deep neural network technologies (FCNN, LSTM, RNN and DBNs). The results showed that the FCNN neural network performed better than other networks on the UC Irvine diabetic dataset. This dataset contains detailed records of 130 hospitals in the United States over a nine-year period. The data includes various traits related to patients’ acceptance of treatment, demographics, laboratory tests of drugs, and others.

The study aims to analyze and test data on drugs used to treat diabetics (clinical tests) using artificial intelligence techniques in the field of health care in order to predict the duration of diabetic stay in the hospital, which contributes to improving the quality of health care and reducing costs.