Biomedical Informatics is the discipline that applies principles of computer and information science to the advancement of life sciences research, health professions education, and patient care. A major strength of Biomedical Informatics at Vanderbilt is the development and evaluation of real-world systems in each of these mission areas. Enterprise strategies reflect “the art of the possible” through Biomedical Informatics. The clinical enterprise is committed to delivering documented quality at an affordable cost through systematic evidence-based personalized care. Research is targeted on breakthroughs in population health, diagnostic and therapeutic discovery, and personalized medicine. Education programs are evolving to spiral curricula leveraging just-in-time information access, simulation and continuous competency assessment.
The Department of Biomedical Informatics is home to an interdisciplinary faculty of over 65. Its training programs include research-oriented MS and PhD degrees, as well as non-degree postdoctoral training, and were awarded an institutional training grant from the National Library of Medicine in 2002.
See a list of our faculty and their research interests below:
Medical education informatics, personalized learning technologies, natural language processing, information retrieval, adaptive user interfaces, and mHealth.
Health numeracy and literacy and their relationship with information technology design and use; application of human factors and behavioral economics to consumer and clinical informatics; health services research and health information technology evaluation; health equity and social determinants of health; educational research, particularly on teaching and learning of quantitative methods.
Natural language processing, designing phenotypes for use in genetic association studies, developing methods to identify Mendelian disease patterns in the electronic health record to help interpret rare genetic variants of uncertain significance and characterize the problem of his- or under-diagnosis in clinical populations.
The intersection of natural language processing, biomedical informatics, and applied machine learning. Current research efforts focus on developing text mining algorithms for identifying clinical phenotypes from big collections of narrative reports and for facilitating translational studies of large patient cohorts.
Developing privacy-protecting technologies that provide rigorous privacy protection for biomedical applications. Data privacy research is vital in enabling a sustainable and responsible use of health data. Developing innovative methods for integrating fragmented data and effective approaches for data sharing and predictive modeling.
The development and application of controlled terminologies and informatics-enabled approaches to quality improvement. Active participant in national standards efforts, in particular those related to the pharmaceutical coding system RxNorm. Dr. Brown studies lexical semantic processing that integrates problem statement analysis with medical knowledge bases.
Phenotyping in the EHR and analysis of linked genetic data. Current research involves working with electronic health record data and genetics data to study complex disease and drug response/effects, and participating in projects to facilitate such research, from local resources including the synthetic derivative and BioVU to research networks including eMERGE and the PGRN, to the nationwide Precision Medicine Cohort Program initiative.
Artificial intelligence, network analysis, care coordination, patient safety, perinatal care, ICU care, drug-drug interaction, data mining, and machine learning.
Clinical research informatics, specifically using the HL7 FHIR standard to get data in and out of the EHR for embedded clinical trials. Development of technology, common data elements, and common data models to enable multi-center studies. All with the goal of improving the efficiency, accuracy, and usability from clinical information systems for research.
Developing methods for evaluating and maintaining the diversity of clinical prediction models based on biostatistical and machine learning algorithms. Emphasis on practical, implementable predictive analytics to support decision-making for both individual patients and populations.
Clinical research informatics in global health settings. Current work revolves around data quality assessment and improvement, audit tool development, informatics support for observational research (specifically HIV and TB studies), and the implementation of data coordinating centers at Vanderbilt.
Biomedical and clinical research informatics, biostatistics, epidemiology, programming, database design, change management, and more.
Computer science, machine learning and data management, and healthcare. Current research involves applying and developing computational methods to a wide range of healthcare issues from discharge prediction to cancer recovery times.
Neuropsychology and informatics. Currently in VA Central Office managing national mental health projects, and at Vanderbilt DBMI developing software in the Personalized Medicine Initiative.
Clinical information systems and architectures that support interrupt-driven health care workflows; high availability in EHRs; conceptual indexing of clinical documentation; and, the interaction between technology, organization, and people that goes into successful clinical informatics implementations.
Medical knowledge-base acquisition, promotion of life-long learning, innovative approaches to addressing the evolving and time-sensitive evidence and information needs of both the clinical and research enterprises, addressing the needs of underserved populations via health and genetic literacy, social and behavioral determinants of health, and, more recently, equity of race-adjusted medical equations. Dr. Giuse integrates knowledge management scientists' expertise in key initiatives throughout the medical center including patient communication, data management, evidence synthesis, and personalization of consumer health and precision medicine.
Real-time natural language processing for clinical data analytics, automated enhancement of documentation quality, and statistical characterization of clinical free text.
Disease-neutral informatics tools supporting clinical and translational research; novel strategies for data collection, analysis and dissemination in patient-oriented and translational research; large-scale software collaboration and dissemination models (e.g. REDCap, ResearchMatch, Trials Today, MyCap); and global health technology transfer and training initiatives.
My group uses computation - machine learning, mathematical modeling, etc. - to understand dynamic biological systems relevant to human health and disease. The computational tools we develop and apply are designed for various types of data, from transcriptomes to electronic health records. We are particularly interested in the mammalian circadian system, the network of oscillators that drives daily rhythms in our physiology and behavior.
Defining the use of technology to advance care and communication in health. Current research involves the development of Voice Assistant Interface Technology to augment the usability of the EHR through Natural language communication. Operational focus on data capture and information rendering to relate the true patient story.
Strategies for optimizing patient communication and tools for assessing social and behavioral determinants of health.
Medical machine learning with the goal of improving clinical diagnosis, prognosis, or treatment decisions. Especially the unsupervised, data-driven discovery of meaningful patterns in clinical data, with specific interest in discovering the observable fingerprints of disease subtypes that we haven’t yet learned to distinguish clinically. Standard, supervised prediction models using clinical data that can improve practice. Design of data displays, especially of data patterns discovered through machine learning, that can increase the usefulness of EHRs.
Dr. Lorenzi is internationally recognized as an expert in the areas of managing technological change related to information technology, especially the organizational and people-process components. She is responsible for coordinating the Vanderbilt University Medical Center's overall organizational culture strategy that has 6 major components and has had many successes.
Big data management, health data analytics, privacy and security. Current research interests are in the design and application data privacy risk assessment and protection methods, machine learning over clinical databases and social media platforms, and workflow discovery and anomaly detection in electronic medical record systems.
Predictive analytics, machine learning and data mining, medical device surveillance, and natural language processing. Involved in a variety of diabetes and acute kidney injury health services research, as well as statistical and informatics tool development related to medical product surveillance.
Electronic health records, clinical decision support, implementation, optimization, and evaluation. Current research focuses on improving access to EHR data for clinical and informatics research, implementing clinical decision support and predictive models in the EHR and evaluating their use in real-world clinical settings, and identifying best practices for health information technology across multiple EHRs and healthcare organizations.
Development of provider-facing tools to improve quality and efficiency of care delivery through appropriate clinical workflow integration. Her current research involves the development of a prediction model for disease-specific 30-day readmission in patients with type 2 diabetes.
Leveraging informatics and data to improve medication safety. Current work involves medication reconciliation, medication alerts, clinical decision support (CDS), e-prescribing, opioids, medication terminologies/ontologies, and all things pharmacy informatics.
Qualitative research and evaluation of the relationship between information systems and work in clinical settings, social construction of risk and safety among clinicians and patients, and strategies employed by clinicians to create safety and time during the implementation of new technology.
Using informatics methods to improve care across the cancer care continuum. Current research efforts focus on extracting detailed tobacco exposure from clinical notes and developing clinical decision support to promote lung cancer screening.
Improving data quality and interoperability with the use of machine learning and standards in laboratory data. Dr. Parr has expertise in clinical informatics, health services research, data standards and terminologies, data architecture and common data models.
Value of broad genetic testing in populations and systems barriers to implementation, evaluation of drug safety, computerized prescribing, and clinical decision support systems for drug therapy. Recent projects include implementation of sequencing in an average risk population, implementation of pharmcogenomics, guided drug selection and dosing for geriatric patients, and guided drug selection and dosing for patients with acute kidney injury.
Enhancing the human-computer interaction through interoperable clinical decision support and designing and developing integrated information displays for critical care and shared decision-making tools for drug-drug interactions. Using health information technology to implement evidence-based practice in contextually and theoretically informed ways.
Language modelling, temporal reasoning in medical narratives, automated inferencing techniques in medical informatics, clinical knowledge representation. Current research involves leveraging clinical data for maximum informativity, e.g., cross-validating information from divergent modalities and sources, such as radiographic imaging information in relation to textual description of the same phenomena.
Patient engaging technologies, including patient portals and patient generated health data; informatics evaluation; pediatric informatics, including automated growth charts, summer camp medical records; studying how healthcare providers, patients and caregivers interact with health information technologies when providing and documenting patient care, and when making clinical decisions.
Primary research interest is in clinical informatics, specifically the use of Natural Language Processing (NLP) and Data Mining of clinical notes to provide decision support and improve quality of care. Current research focuses on the study of adverse drug effects (ADEs), including discovery, detection, and the development of an automated monitoring system to detect potential ADEs in hospitalized patients.
System-based care and research leading toward personalized care and population health management, complex adaptive systems, informatics architectures, and innovation life cycle management.
Electronic prescribing, clinical decision support, mobile health care applications, and natural language processing.
Applying temporal mining and machine learning to build prediction modeling to identify the patients' risk, and text mining using deep learning.
Interaction between clinical workflow and health information technology and improving the fit between technology and work practices through the development of health information technology design and implementation strategies. Currently works on ways to expand and diversify the pipeline into the biomedical informatics field through outreach to undergraduate and high school students and by improving how communication with nontechnical audiences.
Applying machine learning to predictive modeling problems for under-served/vulnerable populations (mental illness, suicide, adolescents, homelessness), value-based care, and implementation gaps.
Developing new informatics tools/resources to optimize phenotyping performance or enable deep phenotyping through terminology/ontology, NLP, and machine learning. Current research also focuses on enabling precision medicine through making pharmacogenomics discoveries that may favorably affect a patient's treatment outcome using big EHR data.
Sustainable and sharable decision support, knowledge engineering, clinical knowledge management processes. Current research effort focuses on clinical knowledge management best practices within the framework of migrating legacy clinical decision support knowledge to a commercial HER.
Global health informatics, computerized decision support, mHealth, and capacity building in Health Informatics. Current research involves the breath of application and implementation of health information technologies in resource-limited settings.
Electronic health records, clinical decision support, machine learning. Current research focuses include using data to make clinical decision support systems more effective and to detect malfunctions; using machine learning to predict and detect adverse events; driving high-quality care and eliminating medical errors through advanced information technology.
The use of technology to prevent medical errors, data mining in health care, and drug safety.
Research mainly focuses on developing and applying data mining and machine learning techniques for modeling, analyzing, and predicting health-related behaviors and outcomes using data in online environments (e.g., in social media platforms, online health communities, or patient portals). He is also interested in intensive data processing systems and social computing.
Leveraging machine learning, data mining, and natural language processing techniques on Electronic health records and omics data to advance deep phenotyping and disease prediction. Also interested in Blockchain technology in healthcare and Internet-of-Things (IoT).
Last updated: 1/13/22
Dr. Aldrich's research focuses on nursing informatics, interoperability, usability and advocating for front line clinicians who need data liquidity to provide person centered care.
Dr. Aldrich leads a research program focused on lung cancer and chronic obstructive pulmonary disease (COPD), primarily in racially diverse populations. She uses large epidemiologic cohorts and electronic health records to identify genetic, social/behavioral, and environmental risk factors and to improve screening and clinical outcomes. She currently has ongoing lung cancer and COPD projects using biospecimens and data from large consortia, the Vanderbilt biobank, and the Southern Community Cohort Study.
Dr. Alrifai's research is focused on using health information technology to improve care in neonatal and pediatric populations with a focus on quality, safety, and reduction of cost. In his most recent effort, he developed and evaluated novel clinical decision support systems to improve the safety and efficacy of care in the Neonatal Intensive Care Unit (NICU).
Dr. Anders's research applies approached from human factors engineering to improve patient safety in healthcare. She is interested in research on system design, individual and team performance and decision making, and improvements in patients safety and care quality.
Dr. Bachmann's research is focused on using behavioral interventions to increase participation in cardiac rehabilitation, a widely underutilized therapy for patients with cardiovascular disease. He also has interests in cardiovascular health services research and operations research.
Dr. Barnado's clinical research interests include developing methods to use the electronic health record to study outcomes in systemic lupus erythematosus (SLE). She has developed algorithms that incorporate billing codes, labs, and medications to identify SLE patients accurately in the EHR. She also has interests in systemic sclerosis and pregnancy in autoimmune diseases.
His research lies at the intersection of next generation artificial intelligence in healthcare, machine learning, predictive modeling, big data analytics, precision medicine, and EHR data mining.
Dr. Capra focuses on human evolution, bioinformatics, and machine learning. He also uses the tools of computer science and statistics to address problems in genetics, evolution and biomedicine.
Dr. Carr's research is focused on developing quantitative imaging based biomarkers that can be used to predict future disease risk or to support clinical decision making in populations or for personalized medicine applications.
Dr. Chen's research lands on both novel statistical research and impactful biomedical research. Currently, her statistical research focuses on missing data, survival analysis, Bayesian methods in big data, and penalized approach for 1<n/p<10. She also devotes time to develop statistical methods in using electronic health records (EHRs) and genetics information in precision medicine. Her other significant biomedical research areas include cancer, ophthalmology, infection disease, cardiovascular diseases, and suicide.
Dr. Davis's work employs a population level approach to the investigation of the genetic basis of a wide range of complex phenotypes. Her research aims to discover how polygenic risk, rare variant risk, and environment interact to result in common complex diseases. To accomplish this goal, she applies genomic and bioinformatic approaches to biobank data and phenotypes extracted from the electronic health record. In addition to her work on complex trait genomic, Dr. Davis has long-standing interests in social justice, research ethics, genomic privacy, and data sharing.
Dr. Do's clinical interests and expertise include congenital cardiothoracic surgery, transplantation and mechanical support, and adult congential heart surgery. His research interests include outcomes improvement, tissue engineering and innovate data analytics.
Medical education, bioethics, and equity.
Dr. Velez Edward's research is focused on understanding and identifying genetic risk factors for complex diseases with a specific focus on diseases that disproportionately impact minorities and genetic factors related to women's health and reproductive outcomes. She utilizes large clinical databases that link EHR information to DNA to conduct genomic studies. Current research projects include genetic studies of preterm birth, miscarriage, uterine fibroids, pelvic organ prolapse, preeclampsia, and keloids. These studies include genome-wide association analyses, next-generation sequencing, evaluation of biomarkers, clinical and polygenic risk prediction, and phenome-wide association studies.
Dr. Freundlich is the medical director of the Vanderbilt Anesthesiology and Perioperative Informatics Research Division (VAPIR). VAPIR works closely with investigators across the institution to leverage informatics-based data analytics to improve the care of perioperative and acute patients.
Dr. Guo's research interests include cancer etiology, prevention and precision medicine through developing bioinformatic and statistical approaches and integrating multi-omics data, with a major goal of identifying genetic susceptibility factors for human cancers.
Dr. Hardin's research interests include discrete minimum energy problems, interacting particle systems, inverse problems, wavelets, and machine learning. He has published more than 120 mathematical research papers and coauthored three books.
Dr. Ivory's research interests focus on using data generated by nurses to demonstrate the unique contribution of nursing to outcomes. Clinical areas of interest include reducing maternal morbidity and mortality and impacts of structural racism.
Dr. Purcell Jackson's research is focused on evaluating clinical decision support systems and empowering patients and families through health information technologies.
Dr. Jeffrey focuses on the design, development, and evaluation of probability-based clinical decision support tools. He leverages machine learning and data science techniques for developing prediction models, and he incorporates qualitative methods for exploring how to implement CDS tolls within nurses' cognitive and physical workflows.
Dr. Jones's research interests include using informatics to tools to enhance patient care, streamlining documentation, and patient flow as well as limiting some of the burdens of the EHR on providers and nurses.
Dr. Kerchberger's research interests include how common genetic variation influences risk and outcomes during critical illness syndromes including the acute respiratory distress syndrome and sepsis.
Dr. Khan's research interests include developing computational solutions to problems affecting patients, providers, and the health care system at large, as well as the application of informatics and data science methods for cardiovascular disease detention, risk stratification, and improving the adoption of optimal therapies.
Nursing informatics and education, nursing professional development, integration of informatics into practice to support improvement of patient outcomes.
Dr. Landman chairs the Electrical and Computer Engineering Department and leads the Medical Image Analysis and Statistical Interpretation Lab. His research concentrates on applying image-processing technologies to leverage large-scale imaging studies to improve the understanding of individual anatomy and personalize medicine.
Dr. Lindsell's research focuses on learning health systems, clinical trials, and infectious disease surveillance. His emphasis is on leveraging existing workflows and clinical data processes to enhance learning from pragmatic effectiveness trials and observational studies, and for designing and implementing dissemination and implementation research. His portfolio includes precision clinical trials, pragmatic clinical trials, and decentralized clinical trials, as well as traditional studies.
Dr. Liu's research interests include integrative system biology approaches to the biological basis of complex diseases, and transcriptional and post-transcriptional regulation networks.
The overarching goal of the Lopez Lab is to develop and apply modeling, numerical, and statistical methods to understand cellular processes and their dysregulation. Dr. Lopez's group efforts comprise a tri-partite approach to study cellular biology: 1. Develop modeling and simulation tools necessary to study network-driven processes across multiple scales. 2. Use computational tools to understand information flow in signaling processes relevant to cancer phenotypes. 3. Collaborate with experimental and theoretical groups to test and expand our hypotheses to develop a fundamental understanding of the rules that govern functional genomics and systems biology.
Dr. Mallal has championed research that has driven improvement in clinical practice in HIV and infectious diseases since the early years of the AIDS epidemic. He provides scientific vision and leadership, promoting collaborations on all types of HIV research within and across the institutions (especially translation and disparities-related research), improving communications and outreach to the community, and fostering productive interactions with colleagues at other academic institutions.
Dr. Mayberry's research focuses on families' experiences with the health and mental health care systems, and interactions between family members and health care providers in the context of chronic illness. Her current work focuses on the role of family member support in diabetes self-management behaviors among adults to inform the development of family-based interventions.
Research in Dr. Meiler's laboratory seeks to fuse computational and experimental efforts to investigate proteins, the fundamental molecules of biology, and their interactions with small molecule substrates, therapeutics, or probes. Dr. Meiler's group develops computational methods with three major ambitions in mind:
1. To enable protein structure elucidation of membrane proteins the primary target of most therapeutics and large macromolecular complexes, such as viruses; 2. Design proteins with novel structure and/or function to explore novel approaches to protein therapeutics and deepen our understanding of protein folding pathways. 3. Understand the relation between chemical structure and biological activity quantitatively in order to design more efficient and more specific drugs. Crucial for success is the experimental validation of our computational approaches which they pursue in their laboratory or in collaboration with other scientists.
Dr. Misulis focuses on neurology, preventative medicine, public health and biomedical informatics. He is also a published author and standup comedian!
Dr. Mixon conducts federally-funded health services research, focusing on the impact of medication management on patient outcomes. She has expertise in quality improvement, implementation science, and has mentored health care providers in quality improvement projects. She also focuses on medication management and reconciliation and care transitions.
Dr. Morris's research interest is applying artificial intelligence to forecast poor patient outcomes within 24 hours of admission. He and his group have developed algorithms incorporating demographic, clinical data and social determinants to identify subgroups of patients with expected and unexpected death. It is his goal/hypothesis to identify expected deaths early to enable goals of care discussions with family. By identifying patients at risk for unexpected death, they can efficiently deploy additional clinical resources to lower the observed to expected mortality for the enterprise.
Dr. Mosley is interested in using data from EHR data sets, which represent real-world populations, to examine how common genetic variation influences both health and disease risk. Research areas of interest include leveraging the shared genetics between diseases and biomarkers to identify new biomarker-disease associations and using genetics to identify specific risk mechanisms that contribute to disease risk in selected EHR populations. Finally, he is interested in characterizing how benign genetic variation drives unnecessary and potentially harmful healthcare utilization.
Dr. Mulvaney's interests include development and testing of technology-assisted (internet, mobile, informatics) patient and family health-related behavior change systems.
Dr. Ortiz has expertise in evidence-based medicine, systematic review methodology, guideline development, quality and safety, quality measures, informatics, outcomes research, and blood pressure.
As CIO of HealthIT, Dr. Patel provides leadership for translating VUMC health care delivery, quality, and patient safety goals into informatics strategies to optimize the delivery of patient care.
Dr. Roden is a clinician-scientist whose laboratory currently focuses on establishing the functional consequences of genetic variation in humans. The lab uses a range of contemporary techniques, such as induced pluripotent stem cells, gene editing, deep mutational scanning, high-throughput automated electrophysiology, probing the relationship between genetic variants and phenotypes in EHRs and other biobanks, and most recently understanding the structural correlates of genomics particularly in ion channels. Dr. Roden also co-directs the All of Us Data and Research Center and is co-PI for the Vanderbilt site in the electronic Medical Records and Genomics (eMERGE) network.
Dr. Rokas's research combines computational and experimental approaches to investigate the factors influencing phylogenetic accuracy and their usefulness in obtaining more robust phylogenies, the molecular origins of human pregnancy, and the molecular foundations of the fungal lifestyle.
Dr. Rothman is focused on multispecialty adult and ambulatory anesthesiology, perioperative informatics and critical care medicine.
Dr. Ruderfer's lab has two broad research interests: (1) Capturing and extracting information to aid in elucidating genetic etiology of behavioral health traits and psychiatric diagnoses. (2) Utilizing genetics/genomic to understand biological mechanism and interventional strategies of psychiatric disorders.
Dr. Salwei's research is focused on applying human factors engineering methods and principles to improve the design of health information technology to support clinician's work and improve patient safety. She is interested in how to successfully integrate advanced technologies, such as those based on machine learning and artificial intelligence, into clinical workflow. She is also interested in the design of health IT to support the work of health care teams.
Dr. Sandberg's specific research interests include: the development and use of clinical informatics in anesthesiology, quality and health outcomes research, factors affecting physician-patient communication, patient care technology, perioperative systems design and OR workflow management.
Dr. Semler's research is on sepsis, acute respiratory distress syndrome, fluid management, crystalloids, acute kidney injury, and airway management.
Reducing the documentation burden for nurses in the EHR, optimization of clinical systems to improve patient safety, evaluating the effectiveness of clinical decision support in an EHR, and developing informatics structures and processes to support a geographically disperse integrated healthcare delivery system.
Dr. Shepherd's research interests include causal inference, observational data analysis, ordinal data analysis, applications in HIV and other infectious diseases, measurement error, and global health.
Dr. Shyr's current research interests focus on developing statistical bioinformatic methods for analyzing next-generation sequencing data based on single cell technology, including a series of papers on estimating the sample size requirements for studies conducting sequencing analysis and novel statistical methods for analyzing the single-cell RNA sequencing (scRNA-seq) data.
Interests include the development of EHRs for the perioperative space and integration of quality and safety metrics and tracking algorithms in the EHRs.
Dr. Tiwari's research interests are in operational improvement and capacity management of healthcare delivery systems. He heads the Operations Research group of the Department of Anesthesiology and supports systems engineering projects across the VUMC enterprise. He received the "OR Business Manager of the Year" award in 2020 from the OR Managers Society for his contributions towards developing and disseminating new knowledge for management of operating rooms through data-based decision making.
Dr. Wanderer's research interests include understanding the impact of informatics interventions on perioperative operations, such as implementation of risk scores and decision support systems. Additionally, he has specific interest in the development and implementation of predictive analytic tools within the perioperative and acute clinical arenas.
Examining the intersection of healthcare delivery and informatics through mixed methods research primarily in emergency and urgent care clinical settings. Areas of focus include communication during care transitions and user-centered design to enhance clinician feedback for medication prescribing.
Dr. Warner's clinical focus is malignant hematology. His primary research goal is to make sense of the structure and unstructured data present in EHRs and clinical knowledge bases to directly improve clinical care for cancer patients.
Dr. Weinger has been teaching and conducting research in human factors engineering and human-centered design in healthcare, clinical informatics, decision making, patient safety, and healthcare simulation for three decades. His current interests are in the design and implementation of technology that improves the ability of clinicians and patients to enhance individual and population health.
Dr. Wells focuses on precision medicine for cardiovascular disease, with a special interest in arrhythmic and cardiomyopathic phenotypes. He also has a major interest in leveraging the power of the electronic health record.
Computer science, cybersecurity, cyber-physical systems, mobile cloud computing, deep learning, and software engineering.
Dr. Xu's research interests include translating big biomedical genomic data (e.g., BioVU, TCGA, UKBiobank) into precision medicine discoveries.
Last updated: 1/13/22