Automated Diagnostic System for Medical Treatment of Infectious Diseases using Causal transfer learning and biological knowledge graph embedding


Abstract: In infectious diseases, molecular diagnostics are revolutionizing clinical practice by helping doctors understand a patient's cases caused by infection before symptoms and complications. Moreover, using machine learning algorithms to assist doctors in clinical decision-making and diagnosis is critical for patient treatment decisions and outcomes. However, current automated diagnosis systems only utilize associative deep learning methods that identify diseases strongly correlated with a patient's symptoms without considering the genetic risk factors that may cause complications. Alternatively, they could be related to other complex disorders affecting the patient's situation. In that case, understanding how different viral strains affect individual patients and, in particular, how they interact with different human host cells and immune responses is a fundamental step in order to formulate accurate treatment plans. Since the outbreak of the COVID-19 disease, host genetic variations play a significant role in the manifestation of different degrees of severity of illness among different individuals. It is crucial to use this disease as the first case study in our research. Thus, we develop a deep learning model that provides automated medical plans and predicts the severity score as well as multi-organs dysfunction scores during infection by integrating genetic and viral data with metadata and analyzing risk factors. Our preliminary result shows that our model performs better than state-of-the-art on synthetic data. The data was generated based on descriptive information that explained the severity of COVID-19 patients from scientific articles and medical reports. In addition, we test models on actual medical records of the sensitivity of obtaining medical reports. The predicted scores assist doctors in having a better understanding of the COVID-19 cases and provide an accurate treatment plan that could eventually reduce the severity and complication of infectious diseases

Bio: Sakhaa Al-Saedi is a Ph.D. student and the founder of the startup Medvation, inventing educational kits that teach children concepts of robotics and machine learning through fun and engaging methods. She completed her bachelor's degree in Computer Science in 2017 at Taibah University. Before starting her master's degree at KAUST in 2018, she worked as a product developer at the prototyping lab of the Namma Al-Munawara company in Madinah. She completed her master's degree in Computer Science at KAUST in 2020. There, she worked on human genome sequencing to evaluate the impact of Saudi-specific allele frequencies on variant calling. Sakhaa's research interests include applying deep learning algorithms in the development of genetic variant calling workflows for analyzing human genome sequencing data, developing a platform for integrating multi-omics data, as well as generating AI art from biomedical and genetic data. She is currently working in the Comparative Genomics and Genetics Lab (CGG) and Structural and Functional Bioinformatics Group (SFB) of Professor Takashi Gojobori and Professor Xin Gao, developing an automated genetic-based medical diagnostic system for treatment of infectious diseases using causal deep learning.

Abstract:  In infectious diseases, molecular diagnostics are revolutionizing clinical practice by helping doctors understand a patient's cases caused by infection before symptoms and complications.  Moreover, using machine learning algorithms to assist doctors in clinical decision-making and diagnosis is critical for patient treatment decisions and outcomes. However, current automated diagnosis systems only utilize associative deep learning methods that identify diseases strongly correlated with a patient's symptoms without considering the genetic risk factors that may cause complications. Alternatively, they could be related to other complex disorders affecting the patient's situation. In that case, understanding how different viral strains affect individual patients and, in particular, how they interact with different human host cells and immune responses is a fundamental step in order to formulate accurate treatment plans. Since the outbreak of the COVID-19 disease, host genetic variations play a significant role in the manifestation of different degrees of severity of illness among different individuals. It is crucial to use this disease as the first case study in our research. Thus, we develop a deep learning model that provides automated medical plans and predicts the severity score as well as multi-organs dysfunction scores during infection by integrating genetic and viral data with metadata and analyzing risk factors. Our preliminary result shows that our model performs better than state-of-the-art on synthetic data. The data was generated based on descriptive information that explained the severity of COVID-19 patients from scientific articles and medical reports. In addition, we test models on actual medical records of the sensitivity of obtaining medical reports. The predicted scores assist doctors in having a better understanding of the COVID-19 cases and provide an accurate treatment plan that could eventually reduce the severity and complication of infectious diseases

  • Share this: