Why we need a small data paradigm.

Why we need a small data paradigm.

Publication date: Jul 17, 2019

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.

Open Access PDF

Hekler, E.B., Klasnja, P., Chevance, G., Golaszewski, N.M., Lewis, D., and , Sim. Why we need a small data paradigm. 05017. 2019 BMC Med (17):1.

Concepts Keywords
Analytic Data management
Big Data Big data
BMC Technology forecasting
Causality Transaction processing
Chronic Diseases Small data
Healthcare Causality
Hospital Computing
Paradigm Physics
Artificial intelligence

Semantics

Type Source Name
gene UNIPROT CBLIF
disease MESH musculoskeletal pain
disease MESH chronic pain
gene UNIPROT SIM2
gene UNIPROT RASA1
gene UNIPROT RGS6
gene UNIPROT SLC35G1
gene UNIPROT ACACA
gene UNIPROT BMS1
gene UNIPROT INTU
gene UNIPROT CHL1
gene UNIPROT F11R
gene UNIPROT PROC
gene UNIPROT RBM12
disease MESH lifestyle
gene UNIPROT TECR
gene UNIPROT JUN
gene UNIPROT PFDN1
gene UNIPROT PDF
gene UNIPROT GDF15
gene UNIPROT NHS
gene UNIPROT COL9A3
gene UNIPROT COMP
gene UNIPROT COL9A1
gene UNIPROT COL9A2
gene UNIPROT SCN8A
gene UNIPROT EXOG
gene UNIPROT TNFSF13
gene UNIPROT ANP32B
gene UNIPROT SMIM10L2A
gene UNIPROT SMIM10L2B
gene UNIPROT SRPX
gene UNIPROT PNN
disease MESH multiple
gene UNIPROT APEX1
gene UNIPROT CLU
gene UNIPROT DGCR2
gene UNIPROT ABCB6
gene UNIPROT SON
gene UNIPROT SSRP1
disease MESH delusion
gene UNIPROT MICAL1
drug DRUGBANK Human vaccinia virus immune globulin
gene UNIPROT FURIN
gene UNIPROT TNFSF14
gene UNIPROT ADA2
gene UNIPROT DEPP1
gene UNIPROT GOPC
gene UNIPROT EFS
gene UNIPROT POLR3E
gene UNIPROT ITGBL1
disease MESH confusion
disease DOID irritable bowel syndrome
disease MESH irritable bowel syndrome
drug DRUGBANK Spinosad
pathway BSID Aging
disease MESH aging
gene UNIPROT NR1H4
gene UNIPROT ADRB2
gene UNIPROT BFAR
gene UNIPROT MCL1
gene UNIPROT TNMD
gene UNIPROT CYLD
drug DRUGBANK Tretamine
gene UNIPROT KCNK3
drug DRUGBANK Hexocyclium
gene UNIPROT AMACR
disease MESH comorbidities
disease MESH growth
gene UNIPROT FANCE
gene UNIPROT ELOVL6
disease DOID face
gene UNIPROT SULT1E1
gene UNIPROT MAP3K8
disease MESH weight loss
drug DRUGBANK Isoxaflutole
disease DOID lems
gene UNIPROT LEXM
gene UNIPROT LITAF
gene UNIPROT NT5E
gene UNIPROT LARGE1
gene UNIPROT SOD1
gene UNIPROT IGFALS
disease DOID als
drug DRUGBANK Coenzyme M
gene UNIPROT BTG3
gene UNIPROT PLEKHG5
disease DOID obesity
disease MESH obesity
gene UNIPROT NAA50
gene UNIPROT LAT2
gene UNIPROT ENG
gene UNIPROT TNF
disease MESH dif
gene UNIPROT IDUA
drug DRUGBANK Tropicamide
disease MESH chronic diseases
disease MESH multi
disease MESH community
disease MESH single person
gene UNIPROT RXFP2

Similar

Original Article

Leave a Comment

Your email address will not be published. Required fields are marked *