MLHI 2020 - 2020 -International Symposium on Machine Learning and Health Informatics

Machine Learning (ML) has played an important role in the advancement of health informatics (HI). ML algorithms are bottom-up approaches in which learning takes place from data in order to make decisions and predictions. These days healthcare systems deal with immense proportions of data which require intelligent techniques in order to glean insights for decision making. Healthcare data pose a set of unique challenges such as data which is incomplete, noisy, missing, dirty and unwanted that leads to sub-optimal modeling artefacts. Apart from the aforementioned challenges, most of the data originating from biomedical/bioinformatics domain is high throughput i.e. a small number of samples characterized by a high number of attributes.
ML applications have revolutionized the HI domain; a number of advanced applications can be found in various branches of healthcare. These applications assist physicians in complex diagnosis, selecting among treatment regimens, monitoring patients, evidence-based decision making, personalized medicine, drug development, to name a few. ML pertaining to diagnosis deals with identifying patterns of certain diseases within Electronic Medical Record (EMR) data. Such applications are useful for identifying anomalies in patients’ health records which can be flagged for further investigation by clinicians. Prognosis for a disease such as cancer is highly complicated process. In this regard, ML applications assist the physician in modeling the prognosis through a number of clinical variables such as gene expression profiles, histological parameters and other relevant factors. Likewise, drug discovery processes are long and complex. ML techniques can assist in decision making in all stages of the discovery process such as identification of biomarkers, digital pathology in clinical trials, target validations, and others.
In this workshop, we invite novel contributions in the area of ML to discuss the advances, challenges and future prospects of HI applications such as diagnosis, prognosis and drug development. The relevant topics include but are not limited to;
Machine learning in health informatics
COVID-19 pandemic evidence and analysis
Internet of Medical Things
Deep learning for medical imaging
Security and privacy in health-care
Blockchain in health-care
Medical knowledge creation and maintenance
Knowledge graphs for health informatics
Big Medical Data and analytic
Case studies of machine learning and health informatics