Significance: Health care systems around the world are increasingly utilizing the large amount of routinely collected digital health data for biomedical research. Critical care medicine is a data-rich environment and has been at the forefront of these efforts to utilize data science to improve health care. Although such activities are urgently needed, opportunities in health care data science are often not realized and questions persist about how it can be ethically implemented. Innovation: High-income countries have so far dominated the discussion over data science and AI. However, in an era of increasing global collaborative health research efforts, this imbalance is problematic and there is a need to better understand the attitudes and unique challenges LMICs have in relation to health care data science and AI. This project will make an important contribution toward this in critical care medicine. Furthermore, although there has been a rush to consider how AI applications can be developed and implemented in an ethical manner, most of the existing ethical guidance consists of a range of high-level ethical principles that are often not health care specific and published mainly by organizations in high-income countries. To ensure the ethical implementation of data science and AI in critical care, there is a need to understand the value stakeholders? place in data science and AI, their awareness and use of existing ethical guidance for AI, the their needs around receiving practical ethical guidance. Approach: Using the interdisciplinary approach of empirical bioethics, this project will seek to examine how the ethical implementation of data science in critical care for biomedical research can be best achieved. It will first conduct an online survey with critical care centers and relevant professional societies from a sample of high-income countries and from a sample of LMICs, to inform and contextualize the ethical analysis. Using the analytic method of wide reflective equilibrium, it will then develop normative conclusions regarding how the implementation of data science in critical care for biomedical research can be improved. A road map for the ethical implementation of data science in critical care for biomedical research will be developed, and then discussed and refined at a workshop held at MIT.
Our project seeks to better understand how critical care stakeholders in high-income and low- and middle-income countries currently value and use health care data science for biomedical research, their awareness and use of ethical principles, and their needs around practical ethical guidance. We hope to develop a concrete roadmap for the ethical implementation of data science in critical care for biomedical research that will make a significant contribution to realizing the opportunities in health care data science.
| Rush, Barret; Wiskar, Katie; Celi, Leo Anthony et al. (2018) Association of Household Income Level and In-Hospital Mortality in Patients With Sepsis: A Nationwide Retrospective Cohort Analysis. J Intensive Care Med 33:551-556 |
| Lehman, Li-Wei H; Mark, Roger G; Nemati, Shamim (2018) A Model-Based Machine Learning Approach to Probing Autonomic Regulation From Nonstationary Vital-Sign Time Series. IEEE J Biomed Health Inform 22:56-66 |
| Piza, Felipe Maia de Toledo; Celi, Leo Anthony; Deliberato, Rodrigo Octavio et al. (2018) Assessing team effectiveness and affective learning in a datathon. Int J Med Inform 112:40-44 |
| Rush, Barret; Celi, Leo Anthony; Stone, David J (2018) Applying machine learning to continuously monitored physiological data. J Clin Monit Comput : |
| Deliberato, Rodrigo Octavio; Serpa Neto, Ary; Komorowski, Matthieu et al. (2018) An Evaluation of the Influence of Body Mass Index on Severity Scoring. Crit Care Med : |
| Rush, Barret; Tyler, Patrick D; Stone, David J et al. (2018) Outcomes of Ventilated Patients With Sepsis Who Undergo Interhospital Transfer: A Nationwide Linked Analysis. Crit Care Med 46:e81-e86 |
| Pollard, Tom J; Johnson, Alistair E W; Raffa, Jesse D et al. (2018) The eICU Collaborative Research Database, a freely available multi-center database for critical care research. Sci Data 5:180178 |
| Feng, Mengling; McSparron, Jakob I; Kien, Dang Trung et al. (2018) Transthoracic echocardiography and mortality in sepsis: analysis of the MIMIC-III database. Intensive Care Med 44:884-892 |
| Boag, Willie; Doss, Dustin; Naumann, Tristan et al. (2018) What's in a Note? Unpacking Predictive Value in Clinical Note Representations. AMIA Jt Summits Transl Sci Proc 2017:26-34 |
| Tyler, Patrick D; Stone, David J; Geisler, Benjamin P et al. (2018) Racial and Geographic Disparities in Interhospital ICU Transfers. Crit Care Med 46:e76-e80 |
Showing the most recent 10 out of 106 publications
