AI + Health

Penn scientists who are using AI to improve our understanding of fundamental discovery to understand biological systems. AI is a tool being deployed for drug discovery and development as well as identifying patterns in high throughput molecular and cellular data.

Penn scientists focused on identifying risk factors for human disease. These research efforts may include understanding disease heterogeneity using multiomics data in complex disease. These research efforts may also include the development of precision diagnostics and patient stratification approaches. From using supervised machine learning to detect genetic, genomic, or other omics predictors of disease to using weakly supervised and unsupervised machine learning to identify patient subtypes of disease in electronic health record data, there are many diverse research programs using AI/ML in translational research.

Penn scientists who are using AI for developing disease risk prediction models are common applications of AI for precision medicine. Others in clinical science are using AI for developing clinical trial stratification and discovering personalized treatment guidance.  Other Penn scientists are using AI for implementation science, predictive analytics, prospective health outcomes, health services research, and more.  This includes using AI for how we understand, implement, and optimize healthcare practices. AI facilitates real-time monitoring and feedback mechanisms, enabling continuous assessment of interventions. This iterative loop of data-driven insights ensures that clinical implementation research remains dynamic and responsive, adapting to the evolving needs of patients and healthcare systems.

Penn scientists are using AI to analyze massive datasets to gain a comprehensive understanding of population health dynamics. By scrutinizing diverse sources of health and non-health related information, AI has the potential to capture a holistic perspective on the health status of communities, identifying potential risks and facilitating proactive interventions. In the realm of population health, AI contributes to the development of personalized healthcare strategies by analyzing demographic information, socioeconomic factors, and health behaviors. This personalized approach allows for the tailoring of public health interventions to specific population groups, addressing disparities and promoting health equity.

Penn researchers and providers who are using AI to develop clinical decision support as well as healthcare delivery optimization. Some examples include exploring the use of AI for remote patient monitoring and telemedicine, and how AI might improve both patient and provider experience. Others are using AI that informs implementation to improve health care delivery. Penn researchers are also implementing automated AI pipelines that populate next-generation clinical reports.