RRIDs are persistent unique identifiers that track the use of key biological resources such as antibodies, cell lines, organisms and software and data projects in the biomedical literature. Reproducibility is a very hard problem to solve, but there are some aspects that will improve reproducibility very quickly that we can implement today.
Health IT and particularly the electronic health record must meet many needs unique to healthcare, and this has typically been fraught with difficulty. This includes assisting work that is extremely complex, high-stakes, collaborative, rapidly changing, and with many stakeholders. Ongoing protests by provider groups at the national level have called attention to the difficulties in current systems, particularly with regard to safety and usability. This talk will describe a different, user-composable approach to the design of healthcare software, with details about our AHRQ-funded studies examining its advantages of human-computer interaction and cognition, safety, fit to task, communication/collaboration, and rapid change to meet emergent needs. It will also describe opportunities for future work which may be conducted at Pittsburgh.
In the world of ever growing biomedical data, patient care can be improved with multidisciplinary science including information science, medicine, genetics, and epidemiology. The concept of translational epidemiology has been defined as a fundamental science for moving laboratory discoveries into public health practice.
Physicians spend only about 33% percent of their time on direct clinical interactions and nearly 49% on EHR and desk work. In this talk I will discuss how technologies such as artificial intelligence and natural language technologies can help physicians to spend more time with the patient and less time in front of the computer. I will discuss some of M*Modals core artificial intelligence and natural language understanding technologies.
Structural localization of anatomy provides an essential framework to develop image-derived biomarkers, perform image quantification, assess longitudinal changes within a patient, and understand group differences through imaging.
Integration of complex interacting mechanisms is needed to fully understand how toxic environmental contaminants cause human diseases. Proving association of exposure with risk may help formulate polices that identify the exposures or exposure levels to avoid, but they cannot address reducing disease burden in those who were unaware of exposures or when exposures cannot be reduced below safe levels. Mechanistic studies can identify
Sequencing applications such as Whole Genome Seq (WGS), Whole Exome Seq (WES), ChiP Seq, RNA Seq and others are revolutionizing life science research. However, analysis of the Big Data produced from these diverse applications require specialized skills in genomics and create data analysis bottlenecks for most research laboratories.
Autism spectrum disorder is a lifelong neurodevelopmental disorder that is typically diagnosed by 2-3 years of age. Despite the early age of clinical diagnosis, relatively few neuroimaging studies have focused on evaluating the neural basis of autism in very young infants and children. The identification of imaging markers of ASD that precede clinical diagnosis could have great impact in identifying infants at risk for ASD and initiating early interventions.