The matrix factorization is an important way to analyze co-regulation patterns in transcriptomic data, which can reveal the tumor signal perturbation status and subtype classification. However, current matrix factorization methods do not provide clear bicluster structure.
Model organisms have been widely used in biomedical research to replace human studies and to reduce cost and experimental time in initial biomedical exploration. Recent contradictory reports on whether mouse models mimic human in transcriptomic response (PNAS, 2013 3507-3512; PNAS, 2015 1167-1172) have created debates on usefulness of animal models.
The Benos’ group develops computational, machine learning methods to address important questions in medicine. We are interested in identifying the factors that affect chronic disease onset and progression and cancer survival. We also develop predictive methods and tools that can directly improve health. To do so, we use probabilistic graphical models and other machine learning methods that can integrate and mine high-dimensional, multi-modal data.
Dr. Shou-Jiang Gao’s laboratory is interested in cancer viruses and their associated cancers with the current focus on Kaposi’s sarcoma-associated herpesvirus (KSHV) and AIDS-related malignancies. Dr. Gao’s lab uses a systems approach to dissect KSHV-cell interactions and delineate the mechanisms of KSHV infection and cellular transformation.
The University of Pittsburgh School of Pharmacy is connecting data and design to address the numerous opportunities to improve healthcare. Leveraging design-thinking, collaborations across the University, and partnerships with external partners the School of Pharmacy is engaging across a variety of projects to leverage the scale of technology to improve healthcare.
In this talk, I present a clinical monitoring and alerting framework that aims to identify unusual patient management actions in electronic health record data. Our hypothesis is that patient-management actions that are unusual with respect to past patients may be due to medical errors and that it is worthwhile to raise an alert if such a condition is encountered prospectively.
With the rapid growth of electronic health records and the advancement of machine learning technologies, needs for AI-enabled clinical decision-making support is emerging.
Effective exchange of information in doctor-patient conversations is critical for building trust and compliance with medical advice. In our past work, we have explored how patterns of information flow practices within doctor-patient interactions predict self-reported measures of trust from patients. Now we are building on extensive work modeling consensus-building practices in conversational interactions to work towards a conversational mea
Infectious disease modelers depend on real-world data to create model estimates of infectious disease transmission and control interventions. Modelers often collect data from multiple sources, such as population demographics, disease surveillance, vaccination programs, etc. and integrate data into one model to inform health policy.