Over the past decade, in collaboration with Co-PI Gary Rosen, Ph.D., USC professor of mathematics and head of the Modeling and Simulation Laboratory (MSL), our research team has conducted research to establish real-time data collection protocols that obtain objective measures of alcohol levels in the body via breath analyzer and transdermal alcohol sensors to produce meaningful quantitative measures of alcohol consumption in naturalistic settings. This work combines the collection of highly detailed alcohol consumption data with sophisticated mathematical modeling of these data to produce an enhanced BrAC Estimator software data assimilation program that will make it possible for researchers, clinicians, and the lay public to use transdermal alcohol sensor devices to obtain quantitative BrAC/BAC measurements.

Current R01 Research

Our current R01 Research Project Grant “Estimating BrAC/BAC from Transdermal Alcohol: Combining First-Principles Physiological Models with Machine Learning to Create Software to Optimally Process and Quantitatively Interpret Biosensor Data” funded by the National Institute on Alcohol Abuse and Alcoholism (R01 AA026368, MPIs Luczak, Rosen) now advances the deterministic models we created earlier to include population-based models and machine learning techniques and provides credible bands around our estimates of BrAC (as shown in this figure).

This collaborative research effort includes Co-Is and USC math professors Chunming Wang, Ph.D., Larry Goldstein, Ph.D., and Jay Bartroff, Ph.D., and PA Georgia Wong and (previously) Emily Saldich along with Melike Sirlanci, Ph.D., Bob Swift, M.D., Ph.D., Nancy Barnett, Ph.D., Sean O’Connor, M.D., Tamara L. Wall, Ph.D., and Catharine Fairbairn, Ph.D., among many other graduate and undergraduate students who have devoted their dissertations, master’s theses, honor theses, and laboratory time to this research program.

This research has been supported by NIAAA (R01 AA026368, MPIs Luczak, Rosen; R21 AA017711, PI Luczak; R21AA020493, PI Barnett; R01AA025969, PI Fairbairn; N01AA033002, PI Swift; R44AA014118, PI Tempelman), the Alcoholic Beverage Medical Research Foundation (PI Luczak), and USC internal support (SURF, SOAR, PURF, WiSE, and Provost Awards to undergraduate students supervised by Luczak, Rosen, and Wang).

Equipment

Various equipment used in our current R01 Research Project.

SCRAM Continuous Alcohol Monitoring Device

Collects transdermal alcohol concentration via skin.

Kestrel Weather Tracking Device

Monitors and records temperature and humidity.

Zephyr Heart Monitor Device

Records heart rate

Intoximeter Alco Sensor IV

Collects breath alcohol concentration.

Omron Blood Pressure Monitor

Records blood pressure.

Selected Research Papers (student/trainee denoted with *)

    Alcohol-focused Research Papers

    Walden, K.-R.*, Saldich, E. B.*, Wong, G.*, Liu, H., Wang, C., Rosen, I. G., & Luczak, S. E. (2023). Momentary assessment of drinking: Past methods, current approaches incorporating biosensors, and future directions. In C. Fairbairn & K. Federmeier (Eds.), Special issue on new developments in addiction science, Psychology of Learning and Motivation.

    Saldich, E. B.*, Wang, C., Rosen, I. G., Bartroff, J., & Luczak, S. E. (2021). Effects of stomach content on the breath-transdermal alcohol concentration (BrAC-TAC) relationship. Manuscript for Special Issue on Beyond Self-Reports—Ways to Obtain More Comprehensive Insights into Substance Use Events in Drug and Alcohol Review. Available at: doi:10.1111/dar.13267.

    Sirlanci, M.*, Rosen, I. G., Wall., T. L., & Luczak, S. E. (2019). Applying a novel population-based model approach to estimating breath alcohol concentration (BrAC) from transdermal alcohol concentration (TAC) biosensor data. Invited manuscript for Special Issue on Alcohol Biosensors: Development, Use, and State of the Field. Alcohol: An International Biomedical Journal, 81, 117-129. https://pubmed.ncbi.nlm.nih.gov/30244026/

    Luczak, S. E., Hawkins, A. L.*, Dai, Z.*, Wichmann, R., Wang, C., & Rosen, I. G. (2018). Obtaining continuous BrAC estimates in the field: A hybrid system integrating transdermal alcohol biosensor, Intellidrink smartphone app, and BrAC Estimator software tools. Invited manuscript for Special Issue: Ambulatory Assessment of Addictive Disorders, Addictive Behaviors, 83, 48-55. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6022751/

    Luczak, S. E., Rosen, I. G., & Wall, T. L. (2015). Development of a real-time repeated-measures assessment protocol to capture change over the course of drinking episodes. Alcohol and Alcoholism, 50, 1-8. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4327345/

    Luczak, S. E., & Rosen, I. G. (2014). Estimating BrAC from transdermal alcohol concentration data using the BrAC Estimator software program. Alcoholism: Clinical and Experimental Research, 38, 2243-2252. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4159387/

    Leffingwell, T. R., Cooney, N. J., Murphy, J. G., Luczak, S. E., Rosen, I. G., Dougherty, D. M., & Barnett, N. P. (2013). Continuous objective monitoring of alcohol use: 21st century measurement using transdermal sensors. Alcoholism: Clinical and Experimental Research, 37, 16-22.

    Math/Applied Math/Engineering-focused Research Papers

    Oszkinat, C.*, Luczak, S. E., & Rosen, I. G. (2022). An Abstract Parabolic System-Based Physics-Informed Long Short-Term Memory Network for Estimating Breath Alcohol Concentration from Transdermal Alcohol Biosensor Data. Neural Computing and Applications. Available online at: https://doi.org/10.1007/s00521-022-07505-w.

    Oszkinat, C.*, Luczak, S. E., & Rosen, I. G. (2022). Uncertainty quantification for the estimation of blood alcohol concentration using physics-informed neural network. IEEE Transactions on Neural Networks and Learning Systems. Available at: https://ieeexplore.ieee.org/ stamp/stamp. jsp?arnumber=9684015. doi: 10.1109/TNNLS.2022.3140726, 1-8.

    Oszkinat, C.*, Shao, T.*, Wang, C., Rosen, I. G., Rosen, A. D.*, Saldich, E. B.*, & Luczak, S. E. (2022). Blood and breath alcohol concentration from transdermal alcohol biosensor data: Estimation and uncertainty quantification via forward and inverse filtering for a covariate-dependent, physics-informed, hidden Markov model. Inverse Problems, 38, 055002.

    Hawekotte, K.*, Luczak, S. E., & Rosen, I. G. (2021). Obtaining breath alcohol concentration from transdermal alcohol concentration using a Bayesian approach. Mathematical Biosciences and Engineering, 18, 6739-6770. 

    Sirlanci, M.*, Luczak, S. E., Fairbairn, C. E., Kang, D., Pan, R.*, Yu, X.*, & Rosen, I. G. (2019). Estimating the distribution of random parameters in a diffusion equation forward model for a transdermal alcohol biosensor. Automatica, 106, 101-109.

    Li, A.*, Luczak, S. E., & Rosen, I. G. (2019). Distributed parameter model-based system identification and input determination in the estimation of blood alcohol concentration from transdermal alcohol biosensor data. Journal of Inverse and Ill-Posed Problems, aop, 1-15. Available at: https://doi.org/10.1515/jiip-2018-0006

    Sirlanci, M.*, Luczak, S. E., & Rosen, I. G. (2019). Estimation of the distribution of random parameters in discrete time abstract parabolic systems with unbounded input and output: Approximation and convergence. Communications in Applied Analysis, 23, 287-329.

    Sirlanci, M.*, Luczak, S. E., Fairbairn, C. E., Bresin, K., Kang, D., & Rosen, I. G. (2018). Deconvolving the input to random abstract parabolic systems; a population model-based approach to estimating blood/breath alcohol concentration from transdermal alcohol biosensor data. Inverse Problems, 34 (12), 125006.

    Sirlanci, M.*, Luczak, S., & Rosen, I. G. (2017). Approximation and convergence in the estimation of random parameters in linear holomorphic semigroups generated by regularly dissipative operators.Proceedings of the 2017 American Control Conference, IEEE Control Systems Society, 3171-3176. Available at: http://ieeexplore.ieee.org/document/7963435/

    Dai, Z.*, Rosen, I. G., Wang, C., Barnett, N. P., & Luczak, S. E. (2016). Using drinking data and pharmacokinetic modeling to calibrate transport model- and blind deconvolution-based data analysis software for transdermal alcohol biosensors. Mathematical Biosciences and Engineering, 13, 911-934.

    Rosen, I. G., Luczak, S. E., & Weiss, J.* (2014). Blind deconvolution for distributed parameter systems with unbounded input and output and determining blood alcohol concentration from transdermal biosensor data. Applied Math and Computation, 231, 357-376.

    Rosen, I. G., Luczak, S. E., Hu, W.*, & Hankin, M.* (2013). Discrete-time blind deconvolution for distributed parameter systems with dirichlet boundary input and unbounded output with application to a transdermal biosensor data. Proceedings of the 2013 SIAM Conference on Control and its Application, 160-167. Available at:http://epubs.siam.org/doi/pdf/10.1137/1.9781611973273.22

    Contact Details

    Susan Luczak Faculty Page

    Susan E. Luczak Ph.D.

    Dornsife College of Letters, Arts, and Sciences

    Department of Psychology
    3620 McClintock Ave.
    SGM 501
    Los Angeles, CA 90089

    (213) 740 – 2203

    Luczak Lab

    Luczak Laboratory

    3620 McClintock Ave.
    SGM 826
    Los Angeles, CA 90089