Dr. Sean X. Luo was born in Shanghai, China. He received primary and secondary education in West Lafayette, Indiana. He subsequently studied physics and mathematics at the University of Chicago. He conducted research at McLean Hospital, Harvard Medical School and the Semel Institute of Neuroscience and Behavior at UCLA. He received an M.D. and a Ph.D. degree in theoretical and computational neuroscience from Columbia University, under supervision from Nobel laureate Richard Axel and noted theoretical neuroscientist L. F. Abbott, and collaborated with a number of scientists from Rockefeller University, Harvard Medical School, California Institute of Technology and Yale University. The resulting work was published in a number of leading journals, including Nature, Nature Neuroscience and the Proceedings of National Academy of Sciences.

Dr. Luo has been focusing on translating computational neuroscience and machine learning techniques to large scale clinical research and clinical trial datasets, especially in the field of substance use disorders. In part supported by the Leon Levy Foundation, his work during residency training at Columbia Univesrity/New York State Psychiatric Institute has received a number of awards, including the APA/Eli Lily Research Award and the American Academy of Addiction Psychiatry Young Investigator Award. He is currently working on a number of new manuscripts and has most recently been the lead-author for a new chapter on Internet Addiction.

What is your practice philosophy?

I provide a full spectrum of psychiatric and mental health care for my patients. From the initial evaluation, careful attention is paid to details in the history and mental status examination, and a comprehensive treatment plan is designed and optimized to individual needs and resources. In addition, because of the limited number of patients I carry, I can provide attention and time at the boutique service level.

What are some of the unique aspects of your practice?

I am dually trained as both a clinician and a researcher. My Ph.D. is at the intersection of neuroscience and a number of quantitative disciplines such as statistics and artificial intelligence. This allows me a rare fluency in current scientific literature both in fundamental research in biological psychiatry, medication development and neuroscience and in large clinical studies and longitudinal studies. On the one hand, I can explain complex and nuanced scientific results in a comprehensible way to facilitate joint decision-making. On the other hand, I am informed by both the strengths and pitfalls of the most current treatment strategies.

Secondly, being a full time academic researcher at Columbia University provides a unique system for networks of referral. Many of my mentors and colleagues that I interact with on a regular basis are leading experts in their respective subspecialties. This system-based practice makes it especially advantageous for challenging and complex cases or second opinion consultations.

Can you tell me a bit about your research in a simple way?

I conduct research at the interface of statistics, computer science, neuroscience and clinical psychiatry. What I am interested in is the intriguing question of why and how. Why does a psychotropic medication work for one patient but not for another? How can we make predictions about whether someone will respond to a psychotherapeutic treatment? The approach I am taking is one that leverages large datasets and pattern recognition methods derived from research in artificial intelligence and machine learning, methods that also allow the new ATMs to read your handwriting and Google Car to drive itself. My hope is that these algorithms that enable computers to learn from large datasets can eventually illuminate pathways with which we can find psychiatric treatments that are more personalized and reveal underlying brain circuit abnormalities that are both fascinating and informative.

The data sources my colleagues and I are examining now involve a number of research modalities including neuroimaging, large-scale genetics/pharmacogenetics, large multi-center randomized clinical trial data and longitudinal epidemiological data. I am applying existing methods and developing new analytic strategies.

In addition, I am interested in evidence-based policy and implementation work. If we (and our smarter algorithms) can estimate individual responses in a more precise, quantitative way, we can make policy recommendations that are intelligent and adaptive, customizable to macroscopic trends in demographics and etiologic shifts, and in turn substantially improve outcome and alleviate suffering.