ABOUT THE RESEARCHER

OVERVIEW

Dr. Ben Reis is Director of the Predictive Medicine Group at Harvard Medical School and the Children’s Hospital Informatics Program. His research focuses on understanding the essential patterns of human disease, and on developing novel approaches for predicting disease. He has created systems that allow doctors to predict dangerous clinical conditions years in advance, as well as predictive pharmacology systems that allow public health officials to identify life-threatening adverse drug effects years in advance. Dr. Reis has designed predictive health monitoring systems for regional and national settings, and has advised governments worldwide on establishing biodefense and biosurveillance infrastructures. He has been recognized by the White House for his work on harnessing social networks to promote health, and by the US State Department, USAID and NASA for his work in global health innovation.

Dr. Reis’s main research areas include:

  • Intelligent HistoriesDeveloping advanced predictive methods that allow doctors to identify important clinical risks, from diabetes to domestic abuse, years in advance.
  • Predictive Pharmacology: Developing predictive network-based approaches to pharmacovigilance, capable of identifying dangerous drug side effects and interactions years in advance.
  • Social Networks and Health: The HealthySocial project explores how emerging social networks can be used to promote and spread positive health behaviors, such as blood donation and influenza vaccination. HealthySocial apps have been used by tens of thousands of people worldwide.
  • Public Health Surveillance: Designing adaptive public health monitoring systems that allow public health officials to maintain situational awareness during times of increased risk and uncertainty, including pandemics and major public events.
  • Computational Linguistics: The SpeechWars project combines history, politics and language to study and visualize hundreds of years of history. SpeechWars was selected by the United States Library of Congress for inclusion in its official historic collections.

PUBLICATIONS

Publications powered by Harvard Catalyst Profiles

  1. Accuracy Requirements for Cost-effective Suicide Risk Prediction Among Primary Care Patients in the US. JAMA Psychiatry. 2021 Mar 17. View abstract
  2. BNT162b2 mRNA Covid-19 Vaccine in a Nationwide Mass Vaccination Setting. N Engl J Med. 2021 Feb 24. View abstract
  3. Association of Genetic Variants With Migraine Subclassified by Clinical Symptoms in Adult Females. Front Neurol. 2020; 11:617472. View abstract
  4. Internet search patterns reveal clinical course of COVID-19 disease progression and pandemic spread across 32 countries. NPJ Digit Med. 2021 Feb 11; 4(1):22. View abstract
  5. Internet search patterns reveal firearm sales, policies, and deaths. NPJ Digit Med. 2020 Nov 20; 3(1):152. View abstract
  6. Do Professionalism Lapses in Medical School Predict Problems in Residency and Clinical Practice? Acad Med. 2020 06; 95(6):888-895. View abstract
  7. Constructing data-derived family histories using electronic health records from a single healthcare delivery system. Eur J Public Health. 2020 04 01; 30(2):212-218. View abstract
  8. Validation of an Electronic Health Record-Based Suicide Risk Prediction Modeling Approach Across Multiple Health Care Systems. JAMA Netw Open. 2020 03 02; 3(3):e201262. View abstract
  9. Internet search query data improve forecasts of daily emergency department volume. J Am Med Inform Assoc. 2019 12 01; 26(12):1574-1583. View abstract
  10. Early Prediction Model of Patient Hospitalization From the Pediatric Emergency Department. Pediatrics. 2017 May; 139(5). View abstract
  11. Sexual Assault Victimization and Mental Health Treatment, Suicide Attempts, and Career Outcomes Among Women in the US Army. Am J Public Health. 2017 05; 107(5):732-739. View abstract
  12. Progressive prediction of hospitalisation in the emergency department: uncovering hidden patterns to improve patient flow. Emerg Med J. 2017 May; 34(5):308-314. View abstract
  13. Using administrative data to identify U.S. Army soldiers at high-risk of perpetrating minor violent crimes. J Psychiatr Res. 2017 01; 84:128-136. View abstract
  14. Predicting Suicidal Behavior From Longitudinal Electronic Health Records. Am J Psychiatry. 2017 Feb 01; 174(2):154-162. View abstract
  15. Developing a Risk Model to Target High-risk Preventive Interventions for Sexual Assault Victimization among Female U.S. Army Soldiers. Clin Psychol Sci. 2016; 4(6):939-956. View abstract
  16. Predicting suicides after outpatient mental health visits in the Army Study to Assess Risk and Resilience in Servicemembers (Army STARRS). Mol Psychiatry. 2017 04; 22(4):544-551. View abstract
  17. Feasibility of Prioritizing Drug-Drug-Event Associations Found in Electronic Health Records. Drug Saf. 2016 Jan; 39(1):45-57. View abstract
  18. Predicting non-familial major physical violent crime perpetration in the US Army from administrative data. Psychol Med. 2016 Jan; 46(2):303-16. View abstract
  19. Effects of Social Network Exposure on Nutritional Learning: Development of an Online Educational Platform. JMIR Serious Games. 2015 Oct 05; 3(2):e7. View abstract
  20. Internet activity as a proxy for vaccination compliance. Vaccine. 2015 May 15; 33(21):2395-8. View abstract
  21. Concordance and predictive value of two adverse drug event data sets. BMC Med Inform Decis Mak. 2014 Aug 22; 14:74. View abstract
  22. Improved de-identification of physician notes through integrative modeling of both public and private medical text. BMC Med Inform Decis Mak. 2013 Oct 02; 13:112. View abstract
  23. Developing software to "track and catch" missed follow-up of abnormal test results in a complex sociotechnical environment. Appl Clin Inform. 2013; 4(3):359-75. View abstract
  24. Pharmacointeraction network models predict unknown drug-drug interactions. PLoS One. 2013; 8(4):e61468. View abstract
  25. A pharmacoepidemiological network model for drug safety surveillance: statins and rhabdomyolysis. Drug Saf. 2012 May 01; 35(5):395-406. View abstract
  26. Predicting adverse drug events using pharmacological network models. Sci Transl Med. 2011 Dec 21; 3(114):114ra127. View abstract
  27. Area disease estimation based on sentinel hospital records. PLoS One. 2011; 6(8):e23428. View abstract
  28. Measuring the impact of health policies using Internet search patterns: the case of abortion. BMC Public Health. 2010 Aug 25; 10:514. View abstract
  29. Use of population health data to refine diagnostic decision-making for pertussis. J Am Med Inform Assoc. 2010 Jan-Feb; 17(1):85-90. View abstract
  30. Longitudinal histories as predictors of future diagnoses of domestic abuse: modelling study. BMJ. 2009 Sep 29; 339:b3677. View abstract
  31. Effect of environmental factors on the spatio-temporal patterns of influenza spread. Epidemiol Infect. 2009 Oct; 137(10):1377-87. View abstract
  32. Surveillance Sans Frontières: Internet-based emerging infectious disease intelligence and the HealthMap project. PLoS Med. 2008 Jul 08; 5(7):e151. View abstract
  33. HealthMap: global infectious disease monitoring through automated classification and visualization of Internet media reports. J Am Med Inform Assoc. 2008 Mar-Apr; 15(2):150-7. View abstract
  34. AEGIS: a robust and scalable real-time public health surveillance system. J Am Med Inform Assoc. 2007 Sep-Oct; 14(5):581-8. View abstract
  35. An epidemiological network model for disease outbreak detection. PLoS Med. 2007 Jun; 4(6):e210. View abstract
  36. A self-scaling, distributed information architecture for public health, research, and clinical care. J Am Med Inform Assoc. 2007 Jul-Aug; 14(4):527-33. View abstract
  37. Linking surveillance to action: incorporation of real-time regional data into a medical decision rule. J Am Med Inform Assoc. 2007 Mar-Apr; 14(2):206-11. View abstract
  38. Running outside the baseline: impact of the 2004 Major League Baseball postseason on emergency department use. Ann Emerg Med. 2005 Oct; 46(4):386-7. View abstract
  39. Measuring outbreak-detection performance by using controlled feature set simulations. MMWR Suppl. 2004 Sep 24; 53:130-6. View abstract
  40. Syndromic surveillance: the effects of syndrome grouping on model accuracy and outbreak detection. Ann Emerg Med. 2004 Sep; 44(3):235-41. View abstract
  41. Use of emergency department chief complaint and diagnostic codes for identifying respiratory illness in a pediatric population. Pediatr Emerg Care. 2004 Jun; 20(6):355-60. View abstract
  42. Using temporal context to improve biosurveillance. Proc Natl Acad Sci U S A. 2003 Feb 18; 100(4):1961-5. View abstract
  43. Time series modeling for syndromic surveillance. BMC Med Inform Decis Mak. 2003 Jan 23; 3:2. View abstract
  44. Integrating syndromic surveillance data across multiple locations: effects on outbreak detection performance. AMIA Annu Symp Proc. 2003; 549-53. View abstract
  45. Comparing the similarity of time-series gene expression using signal processing metrics. J Biomed Inform. 2001 Dec; 34(6):396-405. View abstract
  46. Extracting knowledge from dynamics in gene expression. J Biomed Inform. 2001 Feb; 34(1):15-27. View abstract
  47. The autapse: a simple illustration of short-term analog memory storage by tuned synaptic feedback. J Comput Neurosci. 2000 Sep-Oct; 9(2):171-85. View abstract
  48. Stability of the memory of eye position in a recurrent network of conductance-based model neurons. Neuron. 2000 Apr; 26(1):259-71. View abstract