Adaptive Content Tuning of Social Network Digital Health Interventions Using Control Systems Engineering for Precision Public Health: Cluster Randomized Controlled Trial.
SNI
adaptive clinical trial
digital health
organ donation
organ procurement
patient education
precision medicine
precision public health
proportional integral derivative
psychosocial intervention
public awareness
social media
social network
social network intervention
systems analysis
tissue and organ procurement
Journal
Journal of medical Internet research
ISSN: 1438-8871
Titre abrégé: J Med Internet Res
Pays: Canada
ID NLM: 100959882
Informations de publication
Date de publication:
31 05 2023
31 05 2023
Historique:
received:
03
12
2022
accepted:
14
04
2023
revised:
13
03
2023
medline:
2
6
2023
pubmed:
31
5
2023
entrez:
31
5
2023
Statut:
epublish
Résumé
Social media has emerged as an effective tool to mitigate preventable and costly health issues with social network interventions (SNIs), but a precision public health approach is still lacking to improve health equity and account for population disparities. This study aimed to (1) develop an SNI framework for precision public health using control systems engineering to improve the delivery of digital educational interventions for health behavior change and (2) validate the SNI framework to increase organ donation awareness in California, taking into account underlying population disparities. This study developed and tested an SNI framework that uses publicly available data at the ZIP Code Tabulation Area (ZCTA) level to uncover demographic environments using clustering analysis, which is then used to guide digital health interventions using the Meta business platform. The SNI delivered 5 tailored organ donation-related educational contents through Facebook to 4 distinct demographic environments uncovered in California with and without an Adaptive Content Tuning (ACT) mechanism, a novel application of the Proportional Integral Derivative (PID) method, in a cluster randomized trial (CRT) over a 3-month period. The daily number of impressions (ie, exposure to educational content) and clicks (ie, engagement) were measured as a surrogate marker of awareness. A stratified analysis per demographic environment was conducted. Four main clusters with distinctive sociodemographic characteristics were identified for the state of California. The ACT mechanism significantly increased the overall click rate per 1000 impressions (β=.2187; P<.001), with the highest effect on cluster 1 (β=.3683; P<.001) and the lowest effect on cluster 4 (β=.0936; P=.053). Cluster 1 is mainly composed of a population that is more likely to be rural, White, and have a higher rate of Medicare beneficiaries, while cluster 4 is more likely to be urban, Hispanic, and African American, with a high employment rate without high income and a higher proportion of Medicaid beneficiaries. The proposed SNI framework, with its ACT mechanism, learns and delivers, in real time, for each distinct subpopulation, the most tailored educational content and establishes a new standard for precision public health to design novel health interventions with the use of social media, automation, and machine learning in a form that is efficient and equitable. ClinicalTrials.gov NTC04850287; https://clinicaltrials.gov/ct2/show/NCT04850287.
Sections du résumé
BACKGROUND
Social media has emerged as an effective tool to mitigate preventable and costly health issues with social network interventions (SNIs), but a precision public health approach is still lacking to improve health equity and account for population disparities.
OBJECTIVE
This study aimed to (1) develop an SNI framework for precision public health using control systems engineering to improve the delivery of digital educational interventions for health behavior change and (2) validate the SNI framework to increase organ donation awareness in California, taking into account underlying population disparities.
METHODS
This study developed and tested an SNI framework that uses publicly available data at the ZIP Code Tabulation Area (ZCTA) level to uncover demographic environments using clustering analysis, which is then used to guide digital health interventions using the Meta business platform. The SNI delivered 5 tailored organ donation-related educational contents through Facebook to 4 distinct demographic environments uncovered in California with and without an Adaptive Content Tuning (ACT) mechanism, a novel application of the Proportional Integral Derivative (PID) method, in a cluster randomized trial (CRT) over a 3-month period. The daily number of impressions (ie, exposure to educational content) and clicks (ie, engagement) were measured as a surrogate marker of awareness. A stratified analysis per demographic environment was conducted.
RESULTS
Four main clusters with distinctive sociodemographic characteristics were identified for the state of California. The ACT mechanism significantly increased the overall click rate per 1000 impressions (β=.2187; P<.001), with the highest effect on cluster 1 (β=.3683; P<.001) and the lowest effect on cluster 4 (β=.0936; P=.053). Cluster 1 is mainly composed of a population that is more likely to be rural, White, and have a higher rate of Medicare beneficiaries, while cluster 4 is more likely to be urban, Hispanic, and African American, with a high employment rate without high income and a higher proportion of Medicaid beneficiaries.
CONCLUSIONS
The proposed SNI framework, with its ACT mechanism, learns and delivers, in real time, for each distinct subpopulation, the most tailored educational content and establishes a new standard for precision public health to design novel health interventions with the use of social media, automation, and machine learning in a form that is efficient and equitable.
TRIAL REGISTRATION
ClinicalTrials.gov NTC04850287; https://clinicaltrials.gov/ct2/show/NCT04850287.
Identifiants
pubmed: 37256680
pii: v25i1e43132
doi: 10.2196/43132
pmc: PMC10267788
doi:
Banques de données
ClinicalTrials.gov
['NCT04850287']
Types de publication
Randomized Controlled Trial
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e43132Informations de copyright
©Paulo Rocha, Diego Pinheiro, Rodrigo de Paula Monteiro, Ela Tubert, Erick Romero, Carmelo Bastos-Filho, Miriam Nuno, Martin Cadeiras. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 31.05.2023.
Références
IEEE Trans Pattern Anal Mach Intell. 1979 Feb;1(2):224-7
pubmed: 21868852
J Am Heart Assoc. 2018 May 30;7(11):
pubmed: 29848493
Mhealth. 2016 Nov 7;2:
pubmed: 27840816
J Med Internet Res. 2015 Jan 13;17(1):e11
pubmed: 25586711
JAMA. 2018 Mar 13;319(10):1024-1039
pubmed: 29536101
J Am Med Inform Assoc. 2015 Jan;22(1):243-56
pubmed: 25005606
J Healthc Eng. 2021 Jun 24;2021:7118711
pubmed: 34257855
J Racial Ethn Health Disparities. 2020 Feb;7(1):72-83
pubmed: 31493296
MDM Policy Pract. 2021 Dec 6;6(2):23814683211063418
pubmed: 34901442
JAMA. 2018 Nov 13;320(18):1857-1858
pubmed: 30193304
J Racial Ethn Health Disparities. 2023 Jun;10(3):1478-1491
pubmed: 35595917
J Med Internet Res. 2020 Jan 14;22(1):e14605
pubmed: 31934867
JAMA. 2020 Sep 8;324(10):933-934
pubmed: 32805001
J Med Internet Res. 2018 Feb 15;20(2):e52
pubmed: 29449199
Semin Nephrol. 2010 Jan;30(1):90-8
pubmed: 20116653
Am J Prev Med. 2016 Mar;50(3):398-401
pubmed: 26547538
Exerc Sport Sci Rev. 2020 Oct;48(4):170-179
pubmed: 32658043
JAMA. 2016 Oct 4;316(13):1357-1358
pubmed: 27541310
Nat Med. 2021 Sep;27(9):1622-1628
pubmed: 34413518
Ind Eng Chem Res. 2015 Oct 28;54(42):10311-10321
pubmed: 26538805
Am J Health Promot. 2022 Feb;36(2):296-300
pubmed: 34814765
Transl Behav Med. 2021 Mar 16;11(2):676-685
pubmed: 32421196
Am J Transplant. 2022 Feb;22(2):474-488
pubmed: 34559944
J Med Internet Res. 2022 Jan 10;24(1):e33873
pubmed: 35006086
Prev Med Rep. 2020 Jul 03;19:101158
pubmed: 32685364
J Health Commun. 2022 Jul 3;27(7):450-459
pubmed: 36062983
Kidney Int Rep. 2019 May 31;4(9):1285-1295
pubmed: 31517147