Thomas A. Lasko, MD, PhD
(Email address is obfuscated. Make the obvious replacement.)
I am an Associate Professor of Biomedical Informatics in the School of Medicine at Vanderbilt University. I earned an MD from the UCSD School of Medicine, an SM in Medical Informatics from the Harvard-MIT Division of Health Sciences and Technology, and a PhD in Computer Science from MIT's Computer Science and Artificial Intelligence Laboratory, advised by Pete Szolovits and Staal Vinterbo. I completed my clinical internship at the wonderful Gundersen Lutheran Medical Center (where I learned all of the ways that working on a farm can be harmful or fatal. Such as falling into a manure pit and asphyxiating on the hydrogen sulfide. Or jumping in to rescue that person and suffering the same fate. The third guy usually decides not to jump in.) and a postdoctoral fellowship with Octo Barnett in Harvard's Laboratory of Computer Science at Massachusetts General Hospital. Before switching to computational medicine, my first career was as an optical engineer; I designed and built prototype fiberoptic sensors for aircraft at Science Applications International Corporation and developed the optics for a high-speed optical genetic sequencer at a (now defunct!) startup. My bachelor's degree is in Physics.
Following grad school, where my computer science degree focused on medical machine learning, I was a software engineer at Google, where I worked on unsupervised methods to learn clinically relevant patterns from the thousands of medical books in Google Books and from the mind-bogglingly-massive Google query stream. I also developed the algorithm and prototype for Google Symptom Search, a purely data-driven computational diagnosis engine that uses the entire Web as its input dataset.
My current research interests are in the computational aspects of precision medicine. In particular, I am working on the phenotype discovery problem, which is the effort to infer all existing phenotypes from large amounts of Electronic Medical Record data. I am exploring the use of Gaussian Processes and Deep Learning to do this.
I am/have been funded by generous grants from the Edward Mallinckrodt, Jr. Foundation, and the NIH.
Current primary trainees
Kim Kondratieff (PhD Student)
Diego Mesa (Postdoc)
Students currently advising, but not as primary mentor
Students previously advised, now graduated (and where they went next)
Robert Carroll, PhD 2015. (Research Assistant Professor, Vanderbilt Biomedical Informatics)
Yukun Chen, PhD 2016. (NLP Scientist, Parkland Center for Clinical Innovation)
Ravi Atreya, (MSTP) PhD, 2016. (Co-founder and CTO, PredictionHealth)
Dan Putnam, PhD 2016. (Research Scientist, St. Jude's Children's Research Hospital)
Pedro Teixeira, (MSTP) PhD, 2016. (Co-founder and CEO, PredictionHealth)
Jacob VanHouten, (MSTP) PhD, 2016. (Resident, Yale Griffin Internal Medicine/Preventive Medicine)
Morgan Harrell, PhD 2017. (Clinical Data Scientist, Roam Analytics)
Julian Genkins, MD 2018. (Internal Medicine Resident, UCSF))
Sharidan Parr, (MD), MS 2018. (Assistant Professor, Vanderbilt Biomedical Informatics)
Mara Kim, PhD 2018. (Machine Learning Engineer, S&P Global Market Intelligence)
Lina Sulieman, PhD 2018. (Postdoc, Vanderbilt Biomedical Informatics)
Shikha Chaganti, PhD 2018. (Siemens Healthineers)
Ling Chen, PhD 2019. (Senior Data Scientist, Illumina, Inc.)
Sharon Davis, PhD 2019. (Assistant Professor, Vanderbilt Biomedical Informatics)
Code repository for my Computational Medicine Lab.
Shaganti S, Mawn LA, Noguera CB, Lasko TA, Landman BA. Contextual Deep Regression Network for Volume Estimation in Orbital CT. Med Image Comput Comput Assist Interv (MICCAI). 2019.
Shi Y, Graves J, Garbett S, Zhou Z, Marathi R, Wang X, Harrell F, Lasko TA, Denny J, Roden D, Peterson J,; Schildcrout J. A Decision Theoretic Approach to Panel-Based, Preemptive Genotyping. MDM Policy Pract. 2019 [to appear].
Wei Q, Chen Y, Salimi M, Denny JC, Mei Q, Lasko TA, Chen Q, Wu S, Franklin A, Cohen T, Xu H. Cost-aware Active Learning for Named Entity Recognition in Clinical Text. J Am Med Inform Assoc. 2019 [to appear].
Chaganti S, Mawn LA, Kang H, Egan J, Resnick SM, Beason-Held LL, Landman BA, Lasko TA. Electronic Medical Record Context Signatures Improve Diagnostic Classification using Medical Image Computing. IEEE J Biomed Health Inform. 2018 Dec 28.
Parr SK, Shotwell MS, Jeffrey AD, Lasko TA, Matheny ME. Automated Mapping of Laboratory Tests to LOINC Codes using Noisy Labels in a National Electronic Health Record System Database. J Am Med Inform Assoc. 2018 Aug 17. doi:10.1093/jamia/ocy110.
Ye C, Coco J, Epishova A, Hajaj C, Bogardus H, Novak L, Denny J, Vorobeychik Y, Lasko TA, Malin B, Fabbri, D. A Crowdsourcing Framework for Medical Data Sets. AMIA Joint Summits on Translational Science. 2018;2017:273–80.
Zhang L, Fabbri D, Lasko TA, Ehrenfeld JM, Wanderer JP. A System for Automated Determination of Perioperative Patient Acuity. Journal of Medical Systems. 2018 May;42(7):123.
Davis SE, Lasko TA, Chen G, Matheny ME. Calibration Drift Among Regression and Machine Learning Models for Hospital Mortality. AMIA Annu Symp Proc. 2018 Apr 16;2017:625-634 (1st place, Best Student Papers in Knowledge Discovery and Data Mining).
Lasko TA, Walsh CG, Malin B. Benefits and Risks of Machine Learning Decision Support Systems. JAMA. 2017 Dec 19;318(23):2355.
Chaganti S, Robinson JR, Bermudez C, Lasko TA, Mawn LA, Landman BA. EMR-Radiological Phenotypes in Diseases of the Optic Nerve and their Association with Visual Function. Deep Learn Med Image Anal Multimodal Learn Clin Decis Support (2017). 2017:373-381.
Davis SE, Lasko TA, Chen G, Siew ED, Matheny ME. Calibration Drift in Regression and Machine Learning Models for Acute Kidney Injury. J Am Med Inform Assoc. 2017 Nov 1;24(6):1052-1061.
Bajor JM, Lasko TA. Predicting Medications from Diagnostic Codes with Recurrent Neural Networks. International Conference on Learning Representations (ICLR), 2017.
Teixeira PL, Wei WQ, Cronin RM, Mo H, VanHouten JP, Carroll RJ, LaRose E, Bastarache LA, Rosenbloom ST, Edwards TL, Roden DM, Lasko TA, Dart RA, Nikolai AM, Peissig PL, Denny JC. Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals. J Am Med Inform Assoc. 2017 Jan;24(1):162-17
Chen Y, Lasko TA, Mei Q, Denny JC, Xu H. A Study of Active Learning Methods for Named Entity Recognition in Clinical Text. J Biomed Inform, 2015 Dec;58: 11-8.
Lasko TA. Nonstationary Gaussian Process Regression for Evaluating Clinical Laboratory Test Sampling Strategies. AAAI 2015.
VanHouten JP, Starmer J, Lorenzi N, Maron DJ, Lasko TA. Machine Learning for Risk Prediction of Acute Coronary Syndrome. AMIA 2014.
Chen Y, Zhang Y, Mei Q, Lasko TA, Denny JC. A Preliminary Study of Coupling Transfer Learning with Active Learning for Clinical Named Entity Recognition Between Two Institutions. AMIA 2014.
Lasko TA. Efficient Inference of Gaussian Process Modulated Renewal Processes with Application to Medical Event Data. UAI 2014.
Wei WQ, Cronin RM, Xu H, Lasko TA, Bastarache L, Denny JC. Development of an ensemble resource linking MEDications to their Indications (MEDI). AMIA TBI 2013.
Lasko TA, Denny JC, Levy MA. Scalable Data-driven Phenotypes via Unsupervised Feature Learning. AMIA TBI 2013.
Cowan J, Basford, M, Carroll R, Harris P, Lasko TA, Malin B, Denny JC. Big data in medical research: using a big data appliance to manage genomic and EHR data. AMIA TBI 2013.
Atreya RV, Lasko TA, Levy MA. Role of ICD Granularity in Phenotyping Hematologic Malignancies for Tumor Registries. AMIA 2013.
Chen Y, Lasko TA, Mei Q, Denny J, Xu, H. A Study of Active Learning Methods for Clinical Entities Recognition. AMIA 2013.
VanHouten J, Starmer J, Lorenzi N, Lasko TA. Random Forest Classification of Acute Coronary Syndromes. AMIA 2013.
Lasko TA. Inferring the Latent Intensity of Clinical Events Using Modulated Renewal Processes. NIPS 2013 Workshop on Machine Learning for Clinical Data Analysis and Healthcare.
Sun J, McNaughton CD, Zhang P, Perer A, Gkoulalas-Divanis A, Denny JC, Kirby J, Lasko T, Saip A, Malin BA. Predicting changes in hypertension control using electronic health records from a chronic disease management program. J Am Med Inform Assoc. 2014 Mar-Apr;21(2):337-44. doi: 10.1136/amiajnl-2013-002033.
Lasko TA, Denny JC, Levy MA. Computational phenotype discovery using unsupervised feature learning over noisy, sparse, and irregular clinical data. PLoS One. 2013 Jun 24;8(6):e66341. doi: 10.1371/journal.pone.0066341.
Wei WQ, Cronin RM, Xu H, Lasko TA, Bastarache L, Denny JC. Development and evaluation of an ensemble resource linking medications to their indications. J Am Med Inform Assoc. 2013 Sep-Oct;20(5):954-61. doi: 10.1136/amiajnl-2012-001431.
Carroll RJ, Thompson WK, Eyler AE, Mandelin AM, Cai T, Zink RM, Pacheco JA, Boomershine CS, Lasko TA, Xu H, Karlson EW, Perez RG, Gainer VS, Murphy SN, Ruderman EM, Pope RM, Plenge RM, Kho AN, Liao KP, Denny JC. Portability of an algorithm to identify rheumatoid arthritis in electronic health records. J Am Med Inform Assoc. 2012 Jun;19(e1):e162-9.
Lasko TA, Vinterbo SA. Spectral Anonymization of Data. IEEE Trans Knowl Data Eng. 2010 Mar 1;22(3):437-446.
Atlas SJ, Chang Y, Lasko TA, Chueh HC, Grant RW, Barry MJ. Is this "my" patient? Development and validation of a predictive model to link patients to primary care providers. J Gen Intern Med. 2006 Sep;21(9):973-8.
Lasko TA, Atlas SJ, Barry MJ, Chueh HC. Automated identification of a physician's primary patients. J Am Med Inform Assoc. 2006 Jan-Feb;13(1):74-9.
Lasko TA, Bhagwat JG, Zou KH, Ohno-Machado L. The use of receiver operating characteristic curves in biomedical informatics. J Biomed Inform. 2005 Oct;38(5):404-15.
Lasko TA, Feldman MJ, Barnett GO. DXplain Evoking Strength – clinician interpretation and consistency. AMIA 2002.
Lasko TA, Hauser, SE. Approximate string matching algorithms for limited-vocabulary OCR output correction. Proc SPIE, Document Recognition and Retrieval VIII, 2000 Dec;4307:232-40. doi:10.1117/12.410841.
Lasko TA, Kripke DF, Elliot JA. Melatonin suppression by illumination of upper and lower visual fields. J Biol Rhythms. 1999 Apr;14(2):122-5.
Mathis RF, May BA, Lasko TA. Polarization coupling in unpolarized interferometric fiber optic gyros (IFOGS): effect of imperfect components. Proc SPIE, Fiber Optic and Laser Sensors XII, 1994 Nov;2292:283-91. doi:10.1117/12.191842.
US Patent 5,323,229. May BA, Lasko TA, Everett DH. Science Applications International Corporation, assignee. Measurement system using optical coherence shifting interferometry, 1992.
US Patent 8,473,489. Lasko TA, Tomkins A, Angelo M, Gray MK, Ryan R, Godbole NU, Zeiger RF. Google, Inc, assignee. Identifying Entities Using Search Results, 2013. (This and the next three are Google Symptom Search Patents).
US Patent 8,775,439. Lasko TA, Tomkins A, Angelo M, Gray MK, Ryan R, Godbole NU, Zeiger RF. Google, Inc, assignee. Identifying Entities Using Search Results, 2014.
US Patent 8,843,466. Zeiger RF, Lasko TA, Tomkins A, Angelo M, Gray MK, Ryan R, Godbole NU. Google, Inc, assignee. Identifying Entities Using Search Results, 2014.
US Patent 8,856,099. Lasko TA, Tomkins A, Angelo M, Gray MK, Ryan R, Godbole NU, Zeiger RF. Google, Inc, assignee. Identifying Entities Using Search Results, 2014.