Andrew Taylor, MD, MHS
Associate Professor of Emergency Medicine and of Bioinformatics & Data Science; Director of Artificial Intelligence and Data Science, Emergency Medicine
Research & Publications
Biography
News
Research Summary
Dr. Taylor’s chief interest is in applying data science to solve problems in emergency medicine. His lab is involved in a diverse set of projects including: using machine learning, particularly deep learning, for image recognition and predictive analytics; cluster analysis for novel group/phenotype discovery; decision theory for optimal therapeutic pathways; and EHR-driven, outcomes-based research. In addition, he has interests in the computational reproducibility of research and the gamification of the peer-review process.
Extensive Research Description
Richard Andrew Taylor M.D. is Assistant Professor of Emergency Medicine and Director of Clinical Informatics and Analytics. His work focuses on applying data science to various aspects of emergency care. Prior work has included developing high performance prediction algorithms for urinary tract infections, sepsis severity, and hospital admissions; cost-effective analyses for diagnostic imaging, and research in point-of-care ultrasound outcomes. He is currently the PI on several grants supporting the development of better learning systems in healthcare and is a co-investigator on a PCORTF grant creating better data infrastructure for opioid used disorder. He has methodologic expertise in machine learning, databases, and the secondary use of electronic health record (EHR) data for research.
Current areas of research:
Machine learning/Deep learning for predictive analytics– Emergency medicine is a unique and exciting field for the application of predictive analytics. Providers must make numerous decisions (admission/discharge; ordering tests, medications, etc.) in a chaotic environment within a compressed time-frame that can lead to a variety of cognitive errors. Our lab is focused on augmenting this decision process and lessening the cognitive burden of providers through integration of machine learning tools into clinical work-flows. To accomplish this task, we use a variety of methods including deep learning.
Data Mining/Unsupervised Learning– Adoption of EHRs has led to an explosion of secondary data available for research. We use of variety of data science tools to mine EHR emergency medicine data, find novel relationships, and gain better insight into care processes. Our current research is focused on finding low-dimensional representations of ED encounters and using cluster analysis for phenotype discovery.
Discovery of optimal pathways of care through the use of decision analysis– Our work in this area is primarily focused on establishing appropriate testing thresholds and cost-effective clinical pathways for emergency conditions including: aortic dissection, renal colic, trauma, and head injury.
EHR-driven, outcomes-based research– Current work in this area focuses on causal analysis of difficult to randomize interventions in emergency research using observational EHR data. For example, we are interested in examining the effect of point-of-care ultrasound on mortality and other patient-centered outcomes.
Coauthors
Research Interests
Artificial Intelligence; Decision Theory; Medical Informatics; Natural Language Processing; Neural Networks, Computer; Data Mining; Deep Learning; Data Science
Public Health Interests
Health Care Quality, Efficiency; Health Informatics
Selected Publications
- Computational phenotypes for patients with opioid-related disorders presenting to the emergency departmentTaylor R, Gilson A, Schulz W, Lopez K, Young P, Pandya S, Coppi A, Chartash D, Fiellin D, D’Onofrio G. Computational phenotypes for patients with opioid-related disorders presenting to the emergency department. PLOS ONE 2023, 18: e0291572. PMID: 37713393, PMCID: PMC10503758, DOI: 10.1371/journal.pone.0291572.
- Authors’ Reply to: Variability in Large Language Models’ Responses to Medical Licensing and Certification ExaminationsGilson A, Safranek C, Huang T, Socrates V, Chi L, Taylor R, Chartash D. Authors’ Reply to: Variability in Large Language Models’ Responses to Medical Licensing and Certification Examinations. JMIR Medical Education 2023, 9: e50336. PMID: 37440299, PMCID: PMC10375396, DOI: 10.2196/50336.
- Disparities Associated With Electronic Behavioral Alerts for Safety and Violence Concerns in the Emergency DepartmentHaimovich A, Taylor R, Chang-Sing E, Brashear T, Cramer L, Lopez K, Wong A. Disparities Associated With Electronic Behavioral Alerts for Safety and Violence Concerns in the Emergency Department. Annals Of Emergency Medicine 2023, 83: 100-107. PMID: 37269262, PMCID: PMC10689576, DOI: 10.1016/j.annemergmed.2023.04.004.
- Predicting relations between SOAP note sections: The value of incorporating a clinical information modelSocrates V, Gilson A, Lopez K, Chi L, Taylor R, Chartash D. Predicting relations between SOAP note sections: The value of incorporating a clinical information model. Journal Of Biomedical Informatics 2023, 141: 104360. PMID: 37061014, PMCID: PMC10197152, DOI: 10.1016/j.jbi.2023.104360.
- Clinical criteria to exclude acute vascular pathology on CT angiogram in patients with dizzinessTu L, Malhotra A, Venkatesh A, Taylor R, Sheth K, Yaesoubi R, Forman H, Sureshanand S, Navaratnam D. Clinical criteria to exclude acute vascular pathology on CT angiogram in patients with dizziness. PLOS ONE 2023, 18: e0280752. PMID: 36893103, PMCID: PMC9997874, DOI: 10.1371/journal.pone.0280752.
- How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge AssessmentGilson A, Safranek C, Huang T, Socrates V, Chi L, Taylor R, Chartash D. How Does ChatGPT Perform on the United States Medical Licensing Examination? The Implications of Large Language Models for Medical Education and Knowledge Assessment. JMIR Medical Education 2023, 9: e45312. PMID: 36753318, PMCID: PMC9947764, DOI: 10.2196/45312.
- Automatable end‐of‐life screening for older adults in the emergency department using electronic health recordsHaimovich A, Xu W, Wei A, Schonberg M, Hwang U, Taylor R. Automatable end‐of‐life screening for older adults in the emergency department using electronic health records. Journal Of The American Geriatrics Society 2023, 71: 1829-1839. PMID: 36744550, PMCID: PMC10258151, DOI: 10.1111/jgs.18262.
- Neural Natural Language Processing for unstructured data in electronic health records: A reviewLi I, Pan J, Goldwasser J, Verma N, Wong W, Nuzumlalı M, Rosand B, Li Y, Zhang M, Chang D, Taylor R, Krumholz H, Radev D. Neural Natural Language Processing for unstructured data in electronic health records: A review. Computer Science Review 2022, 46: 100511. DOI: 10.1016/j.cosrev.2022.100511.
- 56EMF Augmenting D-dimer Testing for Pulmonary Embolism Rule-out in the Emergency Department With Artificial IntelligenceHaimovich A, Lopez K, Forman H, Kline J, Venkatesh A, Taylor R. 56EMF Augmenting D-dimer Testing for Pulmonary Embolism Rule-out in the Emergency Department With Artificial Intelligence. Annals Of Emergency Medicine 2022, 80: s29-s30. DOI: 10.1016/j.annemergmed.2022.08.079.
- Visualization of emergency department clinical data for interpretable patient phenotypingHurley N, Haimovich A, Taylor R, Mortazavi B. Visualization of emergency department clinical data for interpretable patient phenotyping. Smart Health 2022, 25: 100285. DOI: 10.1016/j.smhl.2022.100285.
- 49156 Effects of Race and Demographics on Use of Physical Restraints in the Emergency DepartmentWong A, Whitfill T, Ohuabunwa E, Ray J, Dziura J, Bernstein S, Taylor R. 49156 Effects of Race and Demographics on Use of Physical Restraints in the Emergency Department. Journal Of Clinical And Translational Science 2021, 5: 121-122. PMCID: PMC8827920, DOI: 10.1017/cts.2021.710.
- Machine Learning in Emergency Medicine: Keys to Future SuccessTaylor RA, Haimovich AD. Machine Learning in Emergency Medicine: Keys to Future Success. Academic Emergency Medicine 2021, 28: 263-267. PMID: 33277733, DOI: 10.1111/acem.14189.
- 402 The Effect of Patient Demographics on the Odds of Restraint Use for Agitation in the Emergency DepartmentOhuabunwa E, Whitfill T, Ray J, Bernstein S, Taylor R, Wong A. 402 The Effect of Patient Demographics on the Odds of Restraint Use for Agitation in the Emergency Department. Annals Of Emergency Medicine 2020, 76: s153-s154. DOI: 10.1016/j.annemergmed.2020.09.418.
- Patient factors associated with SARS‐CoV‐2 in an admitted emergency department populationHaimovich A, Warner F, Young HP, Ravindra NG, Sehanobish A, Gong G, Wilson FP, van Dijk D, Schulz W, Taylor R. Patient factors associated with SARS‐CoV‐2 in an admitted emergency department population. Journal Of The American College Of Emergency Physicians Open 2020, 1: 569-577. PMID: 32838371, PMCID: PMC7280703, DOI: 10.1002/emp2.12145.
- 325 – Development and Validation of Machine Learning Models to Predict Outcomes in Ugib with Comparison to Clinical Risk ScoresShung D, Au B, Taylor R, Tay K, Laursen S, Stanley A, Dalton H, Ngu J, Schultz M, Laine L. 325 – Development and Validation of Machine Learning Models to Predict Outcomes in Ugib with Comparison to Clinical Risk Scores. Gastroenterology 2019, 156: s-64. DOI: 10.1016/s0016-5085(19)36945-8.
- 330 Computational Discovery and Visualization of Patient Phenotypes from Emergency Department Electronic Health RecordsHaimovich A, Hong W, Taylor R, Mortazavi B. 330 Computational Discovery and Visualization of Patient Phenotypes from Emergency Department Electronic Health Records. Annals Of Emergency Medicine 2018, 72: s130-s131. DOI: 10.1016/j.annemergmed.2018.08.335.
- Physical Restraint Use in Adult Patients Presenting to a General Emergency DepartmentWong AH, Taylor RA, Ray JM, Bernstein SL. Physical Restraint Use in Adult Patients Presenting to a General Emergency Department. Annals Of Emergency Medicine 2018, 73: 183-192. PMID: 30119940, DOI: 10.1016/j.annemergmed.2018.06.020.
- Predicting urinary tract infections in the emergency department with machine learningTaylor RA, Moore CL, Cheung KH, Brandt C. Predicting urinary tract infections in the emergency department with machine learning. PLOS ONE 2018, 13: e0194085. PMID: 29513742, PMCID: PMC5841824, DOI: 10.1371/journal.pone.0194085.
- Applying advanced analytics to guide emergency department operational decisions: A proof-of-concept study examining the effects of boardingTaylor R, Venkatesh A, Parwani V, Chekijian S, Shapiro M, Oh A, Harriman D, Tarabar A, Ulrich A. Applying advanced analytics to guide emergency department operational decisions: A proof-of-concept study examining the effects of boarding. The American Journal Of Emergency Medicine 2018, 36: 1534-1539. PMID: 29310983, DOI: 10.1016/j.ajem.2018.01.011.
- 108 Advanced Analytics: Boarding Adjustment Factors for Key Emergency Department Operational MetricsTaylor R, Ulrich A, Shapiro M, Oh A, Harriman D, Parwani V. 108 Advanced Analytics: Boarding Adjustment Factors for Key Emergency Department Operational Metrics. Annals Of Emergency Medicine 2017, 70: s44. DOI: 10.1016/j.annemergmed.2017.07.134.
- Agreement Between Serum Assays Performed in ED Point-of-Care and Hospital Central LaboratoriesDashevsky M, Bernstein SL, Barsky CL, Taylor RA. Agreement Between Serum Assays Performed in ED Point-of-Care and Hospital Central Laboratories. Western Journal Of Emergency Medicine 2017, 18: 403-409. PMID: 28435491, PMCID: PMC5391890, DOI: 10.5811/westjem.2017.1.30532.
- Determination of a Testing Threshold for Lumbar Puncture in the Diagnosis of Subarachnoid Hemorrhage after a Negative Head Computed Tomography: A Decision AnalysisTaylor RA, Gill H, Marcolini EG, Meyers HP, Faust JS, Newman DH. Determination of a Testing Threshold for Lumbar Puncture in the Diagnosis of Subarachnoid Hemorrhage after a Negative Head Computed Tomography: A Decision Analysis. Academic Emergency Medicine 2016, 23: 1119-1127. PMID: 27378053, DOI: 10.1111/acem.13042.
- Use of Point‐of‐Care Ultrasound in the Emergency DepartmentHall MK, Hall J, Gross CP, Harish NJ, Liu R, Maroongroge S, Moore CL, Raio CC, Taylor RA. Use of Point‐of‐Care Ultrasound in the Emergency Department. Journal Of Ultrasound In Medicine 2016, 35: 2467-2474. PMID: 27698180, DOI: 10.7863/ultra.16.01041.
- The Association Between Physician Empathy and Variation in Imaging UseMelnick ER, O'Brien EG, Kovalerchik O, Fleischman W, Venkatesh AK, Taylor RA. The Association Between Physician Empathy and Variation in Imaging Use. Academic Emergency Medicine 2016, 23: 895-904. PMID: 27343485, PMCID: PMC5884096, DOI: 10.1111/acem.13017.
- Cost‐effectiveness of the Cardiac Component of the Focused Assessment of Sonography in Trauma Examination in Blunt TraumaHall MK, Omer T, Moore CL, Taylor RA. Cost‐effectiveness of the Cardiac Component of the Focused Assessment of Sonography in Trauma Examination in Blunt Trauma. Academic Emergency Medicine 2016, 23: 415-423. PMID: 26857839, DOI: 10.1111/acem.12936.
- Impact of point-of-care ultrasonography on ED time to disposition for patients with nontraumatic shockHall MK, Taylor RA, Luty S, Allen IE, Moore CL. Impact of point-of-care ultrasonography on ED time to disposition for patients with nontraumatic shock. The American Journal Of Emergency Medicine 2016, 34: 1022-1030. PMID: 26988105, DOI: 10.1016/j.ajem.2016.02.059.
- Prediction of In‐hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data–Driven, Machine Learning ApproachTaylor RA, Pare JR, Venkatesh AK, Mowafi H, Melnick ER, Fleischman W, Hall MK. Prediction of In‐hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data–Driven, Machine Learning Approach. Academic Emergency Medicine 2016, 23: 269-278. PMID: 26679719, PMCID: PMC5884101, DOI: 10.1111/acem.12876.
- Emergency physician focused cardiac ultrasound improves diagnosis of ascending aortic dissectionPare JR, Liu R, Moore CL, Sherban T, Kelleher MS, Thomas S, Taylor RA. Emergency physician focused cardiac ultrasound improves diagnosis of ascending aortic dissection. The American Journal Of Emergency Medicine 2015, 34: 486-492. PMID: 26782795, DOI: 10.1016/j.ajem.2015.12.005.
- Comparative Effectiveness Research: Alternatives to “Traditional” Computed Tomography Use in the Acute Care SettingMoore CL, Broder J, Gunn ML, Bhargavan‐Chatfield M, Cody D, Cullison K, Daniels B, Gans B, Hall M, Gaines BA, Goldman S, Heil J, Liu R, Marin JR, Melnick ER, Novelline RA, Pare J, Repplinger MD, Taylor RA, Sodickson AD. Comparative Effectiveness Research: Alternatives to “Traditional” Computed Tomography Use in the Acute Care Setting. Academic Emergency Medicine 2015, 22: 1465-1473. PMID: 26576033, DOI: 10.1111/acem.12831.
- Improving emergency physician performance using audit and feedback: a systematic reviewLe Grand Rogers R, Narvaez Y, Venkatesh AK, Fleischman W, Hall MK, Taylor RA, Hersey D, Sette L, Melnick ER. Improving emergency physician performance using audit and feedback: a systematic review. The American Journal Of Emergency Medicine 2015, 33: 1505-1514. PMID: 26296903, DOI: 10.1016/j.ajem.2015.07.039.
- The Prevalence and Characteristics of Emergency Medicine Patient Use of New MediaPost LA, Vaca FE, Biroscak BJ, Dziura J, Brandt C, Bernstein SL, Taylor R, Jagminas L, D'Onofrio G. The Prevalence and Characteristics of Emergency Medicine Patient Use of New Media. JMIR MHealth And UHealth 2015, 3: e72. PMID: 26156096, PMCID: PMC4526985, DOI: 10.2196/mhealth.4438.
- Redefining Overuse to Include Costs: A Decision Analysis for Computed Tomography in Minor Head InjuryMelnick ER, Keegan J, Taylor RA. Redefining Overuse to Include Costs: A Decision Analysis for Computed Tomography in Minor Head Injury. The Joint Commission Journal On Quality And Patient Safety 2015, 41: 313-ap2. PMID: 26108124, DOI: 10.1016/s1553-7250(15)41041-4.
- The “5Es” of Emergency Physician–performed Focused Cardiac Ultrasound: A Protocol for Rapid Identification of Effusion, Ejection, Equality, Exit, and EntranceHall M, Coffey EC, Herbst M, Liu R, Pare JR, Taylor R, Thomas S, Moore CL. The “5Es” of Emergency Physician–performed Focused Cardiac Ultrasound: A Protocol for Rapid Identification of Effusion, Ejection, Equality, Exit, and Entrance. Academic Emergency Medicine 2015, 22: 583-593. PMID: 25903585, DOI: 10.1111/acem.12652.
- Accuracy of emergency physician-performed limited echocardiography for right ventricular strainTaylor RA, Moore CL. Accuracy of emergency physician-performed limited echocardiography for right ventricular strain. The American Journal Of Emergency Medicine 2013, 32: 371-374. PMID: 24559906, DOI: 10.1016/j.ajem.2013.12.043.
- Point-of-Care Focused Cardiac Ultrasound for Prediction of Pulmonary Embolism Adverse OutcomesTaylor RA, Davis J, Liu R, Gupta V, Dziura J, Moore CL. Point-of-Care Focused Cardiac Ultrasound for Prediction of Pulmonary Embolism Adverse Outcomes. Journal Of Emergency Medicine 2013, 45: 392-399. PMID: 23827166, DOI: 10.1016/j.jemermed.2013.04.014.
- A decision analysis to determine a testing threshold for computed tomographic angiography and d-dimer in the evaluation of aortic dissectionTaylor RA, Iyer NS. A decision analysis to determine a testing threshold for computed tomographic angiography and d-dimer in the evaluation of aortic dissection. The American Journal Of Emergency Medicine 2013, 31: 1047-1055. PMID: 23702073, DOI: 10.1016/j.ajem.2013.03.039.
- Point‐of‐care Focused Cardiac Ultrasound for the Assessment of Thoracic Aortic Dimensions, Dilation, and Aneurysmal DiseaseTaylor RA, Oliva I, Van Tonder R, Elefteriades J, Dziura J, Moore CL. Point‐of‐care Focused Cardiac Ultrasound for the Assessment of Thoracic Aortic Dimensions, Dilation, and Aneurysmal Disease. Academic Emergency Medicine 2012, 19: 244-247. PMID: 22288871, DOI: 10.1111/j.1553-2712.2011.01279.x.
- 56 Accuracy of Emergency Physician-Performed Transthoracic Echocardiography in the Evaluation of the Thoracic AortaTaylor R, Van Tonder R, Oliva I, Dziura J, Moore C. 56 Accuracy of Emergency Physician-Performed Transthoracic Echocardiography in the Evaluation of the Thoracic Aorta. Annals Of Emergency Medicine 2011, 58: s196. DOI: 10.1016/j.annemergmed.2011.06.082.
- Synthesis of iron-based bulk metallic glasses as nonferromagnetic amorphous steel alloysPonnambalam V, Poon S, Shiflet G, Keppens V, Taylor R, Petculescu G. Synthesis of iron-based bulk metallic glasses as nonferromagnetic amorphous steel alloys. Applied Physics Letters 2003, 83: 1131-1133. DOI: 10.1063/1.1599636.
- Extraordinary magnetoelasticity and lattice softening in bcc Fe-Ga alloysClark A, Hathaway K, Wun-Fogle M, Restorff J, Lograsso T, Keppens V, Petculescu G, Taylor R. Extraordinary magnetoelasticity and lattice softening in bcc Fe-Ga alloys. Journal Of Applied Physics 2003, 93: 8621-8623. DOI: 10.1063/1.1540130.
- Synthesis and Properties of High-Manganese Iron-Based Bulk Amorphous Metals as Non-Ferromagnetic Amorphous Steel AlloysJoseph S, Shiflet G, Ponnambalam V, Keppens V, Taylor R, Petculescu G. Synthesis and Properties of High-Manganese Iron-Based Bulk Amorphous Metals as Non-Ferromagnetic Amorphous Steel Alloys. MRS Advances 2002, 754: cc1.2. DOI: 10.1557/proc-754-cc1.2.