Why we need a small data paradigm
Tóm tắt
There is great interest in and excitement about the concept of personalized or precision medicine and, in particular, advancing this vision via various ‘big data’ efforts. While these methods are necessary, they are insufficient to achieve the full personalized medicine promise. A rigorous, complementary ‘small data’ paradigm that can function both autonomously from and in collaboration with big data is also needed. By ‘small data’ we build on Estrin’s formulation and refer to the rigorous use of data by and for a specific N-of-1 unit (i.e., a single person, clinic, hospital, healthcare system, community, city, etc.) to facilitate improved individual-level description, prediction and, ultimately, control for that specific unit. The purpose of this piece is to articulate why a small data paradigm is needed and is valuable in itself, and to provide initial directions for future work that can advance study designs and data analytic techniques for a small data approach to precision health. Scientifically, the central value of a small data approach is that it can uniquely manage complex, dynamic, multi-causal, idiosyncratically manifesting phenomena, such as chronic diseases, in comparison to big data. Beyond this, a small data approach better aligns the goals of science and practice, which can result in more rapid agile learning with less data. There is also, feasibly, a unique pathway towards transportable knowledge from a small data approach, which is complementary to a big data approach. Future work should (1) further refine appropriate methods for a small data approach; (2) advance strategies for better integrating a small data approach into real-world practices; and (3) advance ways of actively integrating the strengths and limitations from both small and big data approaches into a unified scientific knowledge base that is linked via a robust science of causality. Small data is valuable in its own right. That said, small and big data paradigms can and should be combined via a foundational science of causality. With these approaches combined, the vision of precision health can be achieved.
Tài liệu tham khảo
Collins FS, Varmus H. A new initiative on precision medicine. N Engl J Med. 2015;372(9):793–5.
Sackett DL, Rosenberg WM, Gray JM, Haynes RB, Richardson WS. Evidence based medicine: what it is and what it isn’t. BMJ. 1996;312(7023):71–2.
Improving Outcomes through Personalised Medicine. Working at the cutting edge of science to improve patients’ lives. 2016. https://www.england.nhs.uk/wp-content/uploads/2016/09/improving-outcomes-personalised-medicine.pdf. Accessed 10 Jun 2019.
National Research Council (US) Committee on A Framework for Developing a New taxonomy of Disease. Toward precision medicine: building a knowledge network for biomedical research and a new taxonomy of disease. Washington DC: National Academies Press; 2011.
The Precision Medicine Advisory Committee. Precision Medicine: An Action Plan for California. 2018. http://opr.ca.gov/docs/20190107-Precision_Medicine_An_Action_Plan_for_California.pdf. Accessed 10 Jun 2019.
Estrin D. Small data, where N = me. Commun ACM. 2014;57(4):32–4.
Vandenbroeck P, Goossens J, Foresight CM. Tackling obesities: future choices – obesity system atlas. London: Government Office for Science; 2010.
Alamuddin N, Wadden TA. Behavioral treatment of the patient with obesity. Endocrinol Metabol Clin. 2016;45(3):565–80.
Barte JCM, Ter Bogt NCW, Bogers RP, Teixeira PJ, Blissmer B, Mori TA, Bemelmans WJE. Maintenance of weight loss after lifestyle interventions for overweight and obesity, a systematic review. Obes Rev. 2010;11(12):899–906.
Johnson NB, Hayes LD, Brown K, Hoo EC, Ethier KA. Centers for Disease Control and Prevention (CDC). CDC National Health Report: leading causes of morbidity and mortality and associated behavioral risk and protective factors – United States, 2005–2013. MMWR Suppl. 2014;63(4):3–27.
Smedley A, Smedley BD. Race as biology is fiction, racism as a social problem is real: anthropological and historical perspectives on the social construction of race. Am Psychol. 2005;60(1):16.
Williams DR, Priest N, Anderson NB. Understanding associations among race, socioeconomic status, and health: patterns and prospects. Health Psychol. 2016;35(4):407.
Sapolsky RM. Behave: the biology of humans at our best and worst. London: Penguin; 2017.
Fisher WW, Piazza CC, Roane HS. Handbook of applied behavior analysis. New York: Guilford Press; 2011.
Staddon JE. Adaptive dynamics: the theoretical analysis of behavior. Cambridge: MIT Press; 2001.
Hekler EB, Klasnja P, Riley WT, Buman MP, Huberty JL, Rivera DE, Martin CA. Agile science: creating useful products for behavior change in the real world. Transl Behav Med. 2016;6(2):317–28.
Taleb NN. The black swan: the impact of the highly improbable, vol. 2. London: Random House; 2007.
Karkar R, Schroeder J, Epstein DA, Pina LR, Scofield J, Fogarty J, Kientz JA, Munson SA, Vilardaga R, Zia J. TummyTrials: a feasibility study of using self-experimentation to detect individualized food triggers. Proc SIGCHI Conf Hum Factor Comput Syst. 2017;2017:6850–63.
Daskalova N, Metaxa-Kakavouli D, Tran A, Nugent N, Boergers J, McGeary J, Huang J. SleepCoacher: a personalized automated self-experimentation system for sleep recommendations. UIST '16 proceedings of the 29th annual symposium on user Interface software and technology. Tokyo: Association for Computing Machinery (ACM); 2016. p. 347–58. http://uist.acm.org/uist2019/, https://www.acm.org/.
Phatak SS. Does It Work For Me? Supporting Self-Experimentation of Simple Health Behavior Interventions. Dissertation Arizona State University. Tempe: Arizona State University; 2019.
Lee J, Walker E, Burleson W, Kay M, Buman M, Hekler EB. Self-experimentation for behavior change: design and formative evaluation of two approaches. CHI '17. Proceedings of the 2017 CHI conference on human factors in computing systems, vol. 2017; 2017. p. 6837–49.
Pearl J, Mackenzie D. The book of why: the new science of cause and effect. New York: Basic Books; 2018.
Shadish WR, Cook TD, Campbell DT. Experimental and quasi-experimental designs for generalized causal inference. Boston: Wadsworth Cengage Learning; 2002.
Green LW, Ottoson JM. Community and population health. Boston: WCB/McGraw-Hill; 1999.
Chambers DA, Feero WG, Khoury MJ. Convergence of implementation science, precision medicine, and the learning health care system: a new model for biomedical researchimplementation science, precision medicine, and health care learning implementation science, precision medicine, and health care learning. JAMA. 2016;315(18):1941–2.
Riley WT, Glasgow RE, Etheredge L, Abernethy AP. Rapid, responsive, relevant (R3) research: a call for a rapid learning health research enterprise. Clin Transl Med. 2013;2(1):1–6.
Hekler EB, Rivera DE, Martin CA, Phatak SS, Freigoun MT, Korinek E, Klasnja P, Adams MA, Buman MP. Tutorial for using control systems engineering to optimize adaptive mobile health interventions. J Med Int Res. 2018;20(6):e214.
Ljung L. System identification: theory for the user. 2nd ed. Upper Saddle River: Prentice Hall; 1999.
Phatak S, Freigoun MT, Martin CA, Rivera DE, Korinek EV, Adams MA, Buman MP, Klasnja P, Hekler EB. Modeling individual differences: a case study of the application of system identification for personalizing a physical activity intervention. J Biomed Inform. 2018;79:82–97.
Freigoun MT, Martín CA, Magann AB, Rivera DE, Phatak SS, Korinek EV, Hekler EB. System identification of Just Walk: a behavioral mHealth intervention for promoting physical activity. 2017 American Control Conference. 2017. doi: https://doi.org/10.23919/ACC.2017.7962940.
Lewis D. History and perspective on DIY closed looping. J Diabet Sci Technol. 2018. https://doi.org/10.1177/1932296818808307.
Polanyi M. Personal knowledge: towards a post-critical philosophy. Chicago: University of Chicago Press; 1958.
Damasio AR. Descartes’ Error. London: Random House; 2006.
Hekler EB. Lived experience and scientific consensus. 2019. http://openingpathways.org/lived-experience-consensus. Accessed 10 Jun 2019.
Rozet A, Kronish IM, Schwartz JE, Davidson KW. Using machine learning to derive just-in-time and personalized predictors of stress: observational study bridging the gap between nomothetic and ideographic approaches. J Med Internet Res. 2019;21(4):e12910.
Hekler EB. The individual evidence pyramid. 2018. http://openingpathways.org/individual-evidence-pyramid. Accessed 10 Jun 2019.
Kravitz R, Duan N, Eslick I, Gabler N, Kaplan H, Larson E, Pace W, Schmid C, Sim I, Design VS. In: Publication A, editor. and Implementation of N-of-1 Trials: A User’s Guide, vol. 13. Rockville: Agency for Healthcare Research and Quality; 2014.
Schork NJ. Personalized medicine: time for one-person trials. Nature. 2015;520(7549):609–11.
Lillie EO, Patay B, Diamant J, Issell B, Topol EJ, Schork NJ. The N-of-1 clinical trial: the ultimate strategy for individualizing medicine? Personalized Med. 2011;8(2):161–73.
Dallery J, Raiff BR. Optimizing behavioral health interventions with single-case designs: from development to dissemination. Transl Behav Med. 2014;4(3):290–303.
Dallery J, Cassidy RN, Raiff BR. Single-case experimental designs to evaluate novel technology-based health interventions. J Med Internet Res. 2013;15(2):e22.
Barr C, Marois M, Sim I, Schmid CH, Wilsey B, Ward D, Duan N, Hays RD, Selsky J, Servadio J. The PREEMPT study-evaluating smartphone-assisted n-of-1 trials in patients with chronic pain: study protocol for a randomized controlled trial. Trials. 2015;16:67.
Kravitz RL, Schmid CH, Marois M, Wilsey B, Ward D, Hays RD, Duan N, Wang Y, MacDonald S, Jerant A, et al. Effect of mobile device-supported single-patient multi-crossover trials on treatment of chronic musculoskeletal pain: a randomized clinical trial. JAMA Inter Med. 2018;178(10):1368–77.
Miller B. When is consensus knowledge based? Distinguishing shared knowledge from mere agreement. Synthese. 2013;190(7):1293–316.
Rosenbaum PR, Rubin DB. The central role of the propensity score in observational studies for causal effects. Biometrika. 1983;70(1):41–55.
Daza EJ. Causal analysis of self-tracked time series data using a counterfactual framework for N-of-1 trials. Methods Inf Med. 2018;57(01):e10–21.
Athey S, Imbens GW. Machine learning methods for estimating heterogeneous causal effects. arXiv. 2015;1504:01132v3.