Health Informatics - overview

The Health Informatics Professional Interest Community embraces activities at IBM Research worldwide. Health Informatics is the study of how computer systems can manage and analyze the complex processes inherent in the field of medicine.

Naturally this emergence is of critical importance due to the huge volume of data flooding in from biology including the genome projects, proteomics, protein structure determination and the rapid expansion in digitalization of patient biomedical data. CompBio is inherently a multi-disciplinary field with important applications in medicine, agriculture, chemistry and ultimately nanotechnology.

Health Informatics includes knowledge discovery and mining of clinical data, and clinical genomic data, together with the integration and presentation of that information in useful ways applied to patients in a clinical setting. Although these are most commonly viewed as a hybrid of biology, medicine, and computer science, and draws upon work in pattern recognition, simulation science, databases, knowledge discovery, data mining, and statistics and information theory, it has a flavor of its own much as biochemistry acquired its own character after arising from the overlap of biology and chemistry. In addition, with the emergence of consumer trends and the shifting of the healthcare landscape towards an outcome-based model, health informatics also impacts wellness/prevention via the curation of exogneous data sources (including patient-generated information and mobile/wearable/sensor data).  

Health Informatics research at IBM spans pattern recognition, data analysis, and interpretation of physiological signals and images, and an ongoing study of how the algorithms developed at IBM can be used to analyze the content of patient records, so enabling the path to a rational, computer and genomics based personalized medicine.


Watson HI PIC chairs: Pei-Yun Sabrina Hsueh (, Amos Cahan