Research

I am a researcher working at the interface of substance use disorder treatment, artificial intelligence, statistics and neuroscience. The overall goal is to leverage new technology to match patients with substance use disorders to optimal treatment.

Drug Abuse Data Science

Our team is developing new methods and applying existing methods to better predict and tailor treatment for substance use disorders. We work collaboratively with the National Drug Treatment Clinical Trials Network (NIDA-CTN) to build predictive models that make individual level predictions in the treating tobacco use disorder and opioid use disorder. A related line of research involves the development of new longitudinal methods for the analysis of binary multilevel time series data such as urine toxicology data. We are developing both supervised and unsupervised learning algorithms for these datasets. We also directly interface with the Data Science Task Force at the NIDA-CTN to prioritize problems. Our most recent effort involves using CTN datasets for pharmacotherapy of opioid use disorder with methadone and buprenorphine, and predicting who might respond better to one versus the other, with early treatment response as a predictor.

Collaborating Faculty
Adam Ciarleglio, Ph.D.
Jeff Goldsmith, Ph.D.
Yih-Ing Hser, Ph.D.
Edward V. Nunes, M.D.
Andrew J. Saxon, M.D.
Betty Tai, Ph.D.


Retinal Biomarkers for Substance Use and Psychotic Disorders

We are developing new biomarkers that can predict treatment responses in tobacco use disorder. In particular, we are focusing on the neural circuit in the retina as a window to measure various neurotransmitters. There is an ongoing pilot study for using electroretinogram, which records electrical signals from the retina in response to light flashes, as a biomarker for dopamine release.

Collaborating Faculty
Diana Martinez, M.D.
Stephen H. Tsang, M.D., Ph.D.
Ragy Girgis, M.D.


Predictive Modeling of Suicide Behavior in Pharmacotherapy of Complex Psychiatric Illnesses

We are developing new techniques and leveraging data science to make individual level predictions of suicide behavior during the course of treatment of bipolar disorder, major depressive disorder, and co-morbid depression and substance use disorders.

Collaborating Faculty
Hanga Galfalvy, Ph.D.
Maria A. Oquendo, M.D.


Participating In Our Research

You may find and contact us to enroll into one of our current studies through Clinicaltrials.gov:
Electroretinogram: a New Human Biomarker for Smoking Cessation Treatment

Results and Code

You may find the most current results and working code at our Github repository.

Jobs

We are looking for individuals with a strong background in data science and technology devleopment at various training levels both on a part time and full time basis, who are interested in applying their skills to substance abuse treatment and research. Please send an E-mail with your CV and references to xsl2101@columbia.edu.

Service

Data Science Quality Improvement

We collaborate with organizations to provide data-driven services (predictive model construction, evaluation, dissemination) for quality improvement and care delivery. In particular we have expertise in behavioral health data analytics as applied to treatment prediction, delivery, claims analysis, quality of care measures, cost benefit analysis, technology development and related areas. We have ongoing collaborations with NewYork-Presbyterian Hospital (Evaluation Core) and New York State Psychiatric Institute to improve mental health delivery. Please contact us directly if you are interested in an evaluation.


Emerging Addiction Science Workshop

This informal workshop series aims to provide a thoughtful and free-flowing forum for fellows and faculty both within the division and in the department to discuss contemporary issues in research in addiction science. The topics covered have been very broad, from molecular biology of addiction to optimal service delivery in treatment. We also routinely invite and welcome outside speakers, both in the tristate area and nationwide to present the most cutting edge research topics of their interest. The aim for the workshop is to build collaborations, strengthen the addiction research community, and refine novel ideas.

2017-2018 speaker schedule


Other Training Services

I developed a short course for training psychiatry residents on the basics of Data Science. The course material is released in public domain in our Github repository, and can be adapted for any number of executive training program to provide basic proficiency of analytics for mental health professionals.

Becoming a Data Savvy Psychiatrist

About

CV

Contact

xsl2101@columbia.edu
Phone: 646-776-6144
Fax: 646-774-6111
Office Address:
Room 3624
Unit 66, New York State Psychiatric Institute
1051 Riverside Dr.
New York, NY 10033

Elements

Text

This is bold and this is strong. This is italic and this is emphasized. This is superscript text and this is subscript text. This is underlined and this is code: for (;;) { ... }. Finally, this is a link.


Heading Level 2

Heading Level 3

Heading Level 4

Heading Level 5
Heading Level 6

Blockquote

Fringilla nisl. Donec accumsan interdum nisi, quis tincidunt felis sagittis eget tempus euismod. Vestibulum ante ipsum primis in faucibus vestibulum. Blandit adipiscing eu felis iaculis volutpat ac adipiscing accumsan faucibus. Vestibulum ante ipsum primis in faucibus lorem ipsum dolor sit amet nullam adipiscing eu felis.

Preformatted

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';

Lists

Unordered

  • Dolor pulvinar etiam.
  • Sagittis adipiscing.
  • Felis enim feugiat.

Alternate

  • Dolor pulvinar etiam.
  • Sagittis adipiscing.
  • Felis enim feugiat.

Ordered

  1. Dolor pulvinar etiam.
  2. Etiam vel felis viverra.
  3. Felis enim feugiat.
  4. Dolor pulvinar etiam.
  5. Etiam vel felis lorem.
  6. Felis enim et feugiat.

Icons

Actions

Table

Default

Name Description Price
Item One Ante turpis integer aliquet porttitor. 29.99
Item Two Vis ac commodo adipiscing arcu aliquet. 19.99
Item Three Morbi faucibus arcu accumsan lorem. 29.99
Item Four Vitae integer tempus condimentum. 19.99
Item Five Ante turpis integer aliquet porttitor. 29.99
100.00

Alternate

Name Description Price
Item One Ante turpis integer aliquet porttitor. 29.99
Item Two Vis ac commodo adipiscing arcu aliquet. 19.99
Item Three Morbi faucibus arcu accumsan lorem. 29.99
Item Four Vitae integer tempus condimentum. 19.99
Item Five Ante turpis integer aliquet porttitor. 29.99
100.00

Buttons

  • Disabled
  • Disabled

Form