Hybrid Deep Learning Models for AIDS Prediction

Acquired immunodeficiency syndrome (AIDS) consistently ranks as a leading cause of mortality. Effective prevention methodologies include early detection techniques. Controlling infectious diseases is important due to their potential to cause epidemics or pandemics, emphasizing the importance of early diagnosis. This necessity has prompted researchers to develop models aimed at improving disease diagnosis. Traditional clinical prediction models rely on patient-specific characteristics. For infectious illnesses, sources other than the patient, such as previous patient characteristics and seasonal variables, may increase prediction performance. This study predicts infectious diseases by optimizing the settings of deep learning algorithms while taking into account big data, which includes social media data. The collected findings indicate the proposed LSTM model achieves the highest accuracy rate of 92%.