Artificial Intelligence Techniques
The application of artificial intelligence, machine learning, and Big Data analytics is ubiquitous, touching all sectors of the society, and medicine and biomedical informatics are no different. While many extant AI techniques can be applied to clinical problems, there are many unique challenges associated with the medical domain that limit direct application. These include regulatory restriction such as HIPAA making it difficult to collect and share data, data persistence issues due to the sheer volume of data generated by the hospitals and other health care providers, and contending with missing or incomplete data. Moreover, there are epistemological issues surrounding medical conditions and diagnoses themselves, in that many common conditions have unclear definitions, making supervised learning challenging.
To address these issues, our lab is developing novel techniques in data analysis, machine learning, and time series analysis. These include creating new models that can handle uncertainty in data labels and data availability, mathematical techniques for handling missing or noisy data, and preserving the underlying structural or temporal nature of data within our analysis.
Decision Support Systems
Novel physiological monitoring systems producing highly informative signals and images, as well as machines collecting molecular data with high-throughput techniques, have provided researchers with a wealth of new knowledge. However, in order to conduct an in-depth study of the causes and mechanisms for many diseases and illnesses and design reliable decision support systems, the analysis of the data from a single high-throughput system or a single image/signal modality may not suffice. It has become evident that integration and processing of all sources of information, from molecular to macroscopic level is the only method of forming an accurate model and therefore generating reliable clinical recommendations.
On multiple clinical applications and in collaboration with researchers from diverse fields of research, we have been designing integrative frameworks to create computational models that integrate and process all typical sources of information including clinical images, clinical signals, proteomic and genomic data, and prior clinical knowledge, in order to form a single multi-faceted model of the process under study. Examples of such ensemble decision support systems include designing computational models for the wound healing process, signal processing methods to predict hemodynamic instability, computer aided decision support systems for traumatic brain injuries and computer aided decision support systems for traumatic pelvic/abdominal injuries.
The race is on to develop autonomous vehicles, with traditional automotive manufactures competing against technology companies both small and large. There is a wide range of what is meant by an "autonomous vehicle". The Society of Automotive Engineers (SAE) has sought to standardize this terminology by devising a scale (J3016) that delineates the degree of automation within a vehicle. The scale ranges from 0 (no automation) to 5 (full automation). Levels 1 and 2 contain technologies that are already commonplace within vehicles, such as cruise control and parking assistance. However, these levels of autonomy still assume that the driver is ultimately responsible for monitoring the driving environment. From level three and up, the responsibility for monitor the environment, including the driver's fitness to operate the vehicle, is placed upon the in-vehicle system.
The ability of a driver to safely operate the vehicle is comprised of many factors, including the driver's attention to the road, level of alertness, and health. By integrating various imaging and health sensors, along with analytical software, into the vehicle’s onboard computing systems, vehicles at all levels of autonomy can improve driver safety and reduced accidents and mortality. Even when vehicles reach full autonomy (level 5), there will still be a need for vehicles to monitor the health and wellbeing of its passengers, and potentially alert public safety officials or health experts of threats to physical safety or medical emergencies.
Wearable devices deemed to monitor the health and well-being of an individual are ubiquitous in the consumer market. Devices such as Fitbit, the Apple Watch, and others, tend to use simple sensors such as EDA and PPG to derive a variety of health signals. In the clinical setting, there is a strong need to use non-invasive and potentially more cost effective monitoring device. However, many of the consumer grade devices are of insufficient quality to be used in a clinical setting. For clinical grade devices, there are still issues concerning battery life, sensor noise, and ease of use.
Our lab has taken a two-prong approach to improving the use of wearable devices in the clinical setting. We have developed our own wearables sensors, and are actively working on showing the clinical significance of the measurements the sensors produce. We have also worked on improving extant sensor technology by de-noising the signals generated by the various sensors in a device, as well as optimizing their use with respect to battery life.