Background: Though artificial intelligence (AI) has the potential to augment the patient-physician relationship in primary care, bias in intelligent health care systems has the potential to differentially impact vulnerable patient populations.
Objective: The purpose of this scoping review is to summarize the extent to which AI systems in primary care examine the inherent bias toward or against vulnerable populations and appraise how these systems have mitigated the impact of such biases during their development.
Methods: We will conduct a search update from an existing scoping review to identify studies on AI and primary care in the following databases: Medline-OVID, Embase, CINAHL, Cochrane Library, Web of Science, Scopus, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI, and arXiv. Two screeners will independently review all abstracts, titles, and full-text articles. The team will extract data using a structured data extraction form and synthesize the results in accordance with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines.
Results: This review will provide an assessment of the current state of health care equity within AI for primary care. Specifically, we will identify the degree to which vulnerable patients have been included, assess how bias is interpreted and documented, and understand the extent to which harmful biases are addressed. As of October 2020, the scoping review is in the title- and abstract-screening stage. The results are expected to be submitted for publication in fall 2021.
Conclusions: AI applications in primary care are becoming an increasingly common tool in health care delivery and in preventative care efforts for underserved populations. This scoping review would potentially show the extent to which studies on AI in primary care employ a health equity lens and take steps to mitigate bias.
International Registered Report Identifier (IRRID): PRR1-10.2196/27799
Artificial intelligence (AI) is a field of computer science that aims to create systems that are capable of independent reasoning [, ]. Despite tremendous gains in some industries, ranging from the perfection of recommendation systems [ ] and optimizing supply chains [ ] to self-driving cars and collaborative robotics [ ], AI has continued to marginalize minority populations. One such example involves NorthPointe’s COMPAS Core solution, an algorithm that seeks to assess the risk that recent convicts would recommit a crime [ ]. The algorithm has a demonstrated bias toward labeling Black individuals as being at a high risk for recommitting a crime when compared to their White counterparts, when in reality the former were half as likely to commit the crime. While this case represents a case of algorithm bias, the bias intrinsic to other AI applications may be more subtle and therefore more likely to stay undetected.
Vulnerable populations in health care, such as women and transgender individuals, Black and Latinx populations, and those with low socioeconomic status, represent cohorts of individuals who experience significant baseline health disparities and are at heightened risk of being affected by algorithmic bias [- ]. Pre-existing and unintended biases in the development pipeline, whether they take the form of historical, representation, or aggregation bias [ ], have the potential to perpetuate deeply rooted stigma, poor cohort representation, and ineffective treatment modalities in the end-product that may further discriminate against these groups through these AI systems. For example, Obermeyer et al [ ] showed that a popular health care risk–scoring algorithm recommended fewer health care assessments for Black patients than for White patients, likely because the algorithm was trained from a data set where the health care system itself contained unequal access to and lower levels of care for Black patients. Such studies reflect the need for research into fairness and AI within health care.
Primary care is the cornerstone of health care delivery and serves, in theory, as the entry point for most patients into the health care setting . Historically, primary care leads medicine to recognize and attend to social determinants of health, which are strong drivers of inequitable health outcomes in vulnerable populations [ , ]. Primary care includes a wide spectrum of disease and many diverse care tasks for patients, which makes augmenting clinical practice with AI tools particularly appealing and useful. Using AI for routine tasks may allow primary care clinicians to focus on complex diagnostic and therapeutic tasks and cultivate stronger patient-physician relationships [ ]. To our knowledge, only 1 other scoping review has identified current AI applications in primary care [ ]. We build on their work by focusing specifically on health equity. As such, this systematic scoping review aims to (1) assess the baseline representation of these vulnerable populations in the AI applications for primary care, (2) determine whether studies are cognizant of potential biases in their results, and (3) understand how, if at all, these studies address the manner in which these biases affect the model’s impact on vulnerable populations, either positively or negatively, in the primary care setting.
We selected a scoping review as the best method for assessing the research landscape of AI and health equity in primary care because it offers a way to systematically identify key research gaps, opportunities, evidence, and concepts in this understudied space. This type of review differs from systematic reviews and meta-analyses in that it does not narrow the parameters of the review to a specific quality assessment. Instead, it is a systematic approach to examine the landscape of a research field using broad questions to examine both empirical and conceptual aspects [, ]. This is particularly important in the fields of health equity, primary care, and AI, where much of the literature is currently focused on specific outcomes or aspects of care [ - ]. Equity considerations extend across multiple outcomes and therefore require a scoping review to draw overall conclusions. Our protocol, developed on the basis of seminal work by Arksey and O’Malley [ ], includes six stages: (1) identification of the research question; (2) identification of relevant studies; (3) study selection; (4) data extraction; (5) collation, summarization, and reporting of the results; and (6) consultation of knowledge users. We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Scoping Reviews) checklist [ ] and registered our protocol with the Open Science Framework (digital object identifier: 10.17605/OSF.IO/WGSB3). To identify articles of interest, we conducted a search update on the basis of a previous study by Kueper et al [ ], who conducted a systematic scoping review of AI and primary care research in May 2020.
Step 1: Identifying the Research Question
A committee of medical professionals at different levels (medical students and attending physicians) with multiple domain expertise (AI, primary care, and fairness in machine learning) and training in recognition of health care disparities led the scope of this study. We used the methodology of Arksey and O’Malley  and Levac et al [ ] to guide the discussions for determining the research questions we sought to investigate. We considered vulnerable populations on the basis of the PROGRESS (place of residence, race/ethnicity/culture/language, occupation, gender/sex, religion, education, socioeconomic status, and social capital) criteria [ ], which include the following variables to ascertain vulnerabilities: place of residence; race, ethnicity, and culture; occupation; gender; religion; education; socioeconomic status; and social capital. We identified three key domains for assessment: representation of vulnerable populations in the underlying data set relative to the intended target population, as assessed, for example, by subgroup prevalence; author reporting of the types of bias outlined by Suresh et al [ ]; and whether these studies attempt to mitigate these pre-existing biases in their systems upstream of, during, or downstream of model development ( ).
|Research questions||Operational definitions|
|What is the representation of vulnerable individuals in the intended target population for any study on artificial intelligence within primary care?||Vulnerable populations are defined as those with known disparities as described by the following categories:|
|How well do current studies on artificial intelligence in primary care report different types of bias that may be perpetuated as health disparities by their systems?||Data extraction elements ()|
|What interventions do current studies on artificial intelligence in primary care use to address harmful effects of pre-existing biases in their systems?||Example interventions are listed below:|
Steps 2 and 3: Identify Relevant Studies and Study Selection
To guide the search strategy for our scoping review, we have developed a number of protocols and parameters. We will use Covidence  to manage our records and data throughout the review.
To retrieve all AI and primary care literature, we will use a similar search strategy and eligibility criteria documented by Kuepfer et al , in which a team of interdisciplinary experts iteratively refined search terms for 11 databases to reliably and robustly retrieve literature spanning AI and primary care globally. This study screened over 7900 articles to amass a total of 405 eligible articles at this domain intersection ( ). Our populations of interest are vulnerable patients (who may or may not be explicitly recognized by the study of interest in our search strategy); we will include any AI intervention; the comparison will be the current standard of care without the AI intervention; and we will include any patient-level outcome of interest in primary care. Rather than combining vulnerable population search terms, we allow our search query to broadly include AI literature that addresses vulnerable populations implicitly (eg, only ensuring demographic parity for a primary clinical outcome) or, equally importantly, fails to do so at all. For example, Hannun et al [ ] used a corpus of ambulatory electrocardiograhs and trained a deep learning model to predict arrhythmias, which may have strong implications of use in primary care, but provide no context on the demographic representation and comorbidity burden in their data sets. To confirm that we applied the methodology appropriately, 2 independent reviewers (JW and SS) will extract a random sample of 4% of titles from their initial search. Then, they will apply the title and abstract screening and full-text screening process, resolving disputes with a third reviewer. Cohen κ will then be calculated between the studies we select and those selected by Kueper et al [ ]. This will be repeated until a Cohen κ of >0.80 is achieved. We will then include the 405 studies that were selected by Kueper et al [ ].
We will also apply the search strategy and screening criteria applied to any new articles since Kueper et al ’s initial search on April 6, 2018 ( ). Two independent reviewers (JW and SS) will first review all titles and abstracts on the basis of the defined eligibility criteria. Full-text versions of all identified articles will be independently reviewed by these 2 independent reviewers for inclusion after initial screening of titles and abstracts to determine whether any other further refinements to the eligibility criteria should be made. Disagreements will be resolved by an independent reviewer through discussion, and the selection process will be adjusted to reflect these subsequent changes. Articles for which no consensus can be reached will be included in the review. Based on guidelines from Cochrane Methods, the search strategy will be utilized once again if 12 months have passed since the initial search strategy and the date of publication [ ].
Once this process is complete, a final PRISMA flow diagram  will be submitted to document the number of articles at each step of identification, screening, eligibility, and inclusion. For now, a PRISMA flow diagram containing the number of queried and screened articles is available in .
In line with Kueper et al , we searched the following databases: Medline-OVID, Embase, CINAHL, Cochrane Library, Web of Science, Scopus, IEEE Xplore, ACM Digital Library, MathSciNet, AAAI, and arXiv; these will capture published studies predominantly in the fields of medicine, computer science, and the intersection of both fields.
Step 4: Extracting the Data
We built a preliminary data framework in accordance with the suggestions of Daudt et al  to align data extraction with the initial research question ( ). One category we extracted is measuring compliance with existing AI ethics guidelines developed for the European Commission. This category was chosen after examining multiple other AI ethical guidelines, including those of the House of Lords [ ] and IEEE [ ]. The European Commission's guidelines were chosen because of the comprehensible key requirements, orientation toward conceptual, higher-level evaluation (rather than technical specificities), and wide adoption across the AI community [ - ]. Two authors (JW and SS) will independently extract data from the first 10 included studies and meet to determine whether the framework is specific enough for consistency and the data are sufficient for research questions outlined initially. During this process and in prior stages, it is likely that additional categories and adjustments will be made to our data extraction framework, at which time we shall consult with the research team to guide decisions on how to appropriately modify the framework. Once the reviewers reach a consensus using the data extraction framework, it will be circulated among the research team and consultation team for final comments and suggestions. Following this, additional reviewers may be brought on, in which case they are expected to match the data extracted from these first 10 included studies in order to take part in the data collection (Cohen κ>0.8). For any disputes on data extraction, a third reviewer will be involved in settling the discussion, and appropriate adjustments to the data extraction framework will be made.
|Primary care function (adapted from Kueper et al )|
|Author-reported intended end-users|
|Target health condition (adapted from Kueper et al )|
|Compliance with “Ethics Guidelines for Trustworthy AI” : which of the 7 elements were addressed (yes/no)?|
|Model fairness and focus on health equity: is the main purpose of the study specifically outlined to improve health for a vulnerable population (yes/no)?||Must be explicitly stated in the introduction or abstract as motivation for the paper to focus on at least 1 vulnerable population (though there may be other populations studied as well) defined by any of the following categories which are largely based off of the NIMHD Research Framework :|
|Stage of the study|
Step 5: Collating, Summarizing, and Reporting the Results
Our analysis will involve both a descriptive numerical summary and an interpretive synthesis. While our approach in stage 5 will be an iterative process, we will use this section to first provide descriptive tables, frequency tables, and visual representation of the results. Further synthesis will be performed to identify current obstacles, gaps, and opportunities in the literature.
Step 6: Consultation
Our scoping review will include consultation with other AI researchers in academia, nonprofit, and industry to enhance the perspective, applicability, and purpose of our study and ultimately offer more practical recommendations. We will engage with stakeholders at three timepoints: (1) prior to the submission of this protocol, (2) during the finalization of the data collection framework, and (3) at the end of the study during the collation, summarization, and reporting of the results.
Electronic database searches were conducted in October 2020, and title and abstract screening are currently underway. We expect to complete the remaining steps of the scoping review, including publication, by fall 2021.
To our knowledge, this will be the first scoping review that applies an equity lens to the existing literature on AI in primary care. Primary care has a large potential to reduce costs and improve quality of life, especially for underserved populations . Many experts have lauded AI’s potential to affect primary care [ ] and issues in vulnerable patient care management. By understanding AI’s current place in primary care through the lens of health care equity, researchers can develop AI interventions that address the field’s existing gaps and opportunities.
After completing this scoping review, we will write a briefing paper to address the implications of the findings in a narrative. We will also develop a manuscript and PRISMA-ScR checklist to submit for publication.
Our scoping review will not incorporate a peer review process for our search strategy despite being recommended in Peer Review of Electronic Search Strategies . This is typically conducted for systematic reviews rather than for scoping reviews and is not feasible with the time and resource constraints we have to achieve this review [ ]. Additionally, we do not engage with community members or underserved populations themselves for consultation or feedback. We believe this is important for any study related to health equity as it improves the quality and applicability of studies for the populations they hope to serve [ , ]. However, identifying and consulting with these groups has been difficult and costly to incorporate into the protocol, which has been a recurring problem in this field of research. Instead, we rely on expert stakeholders to guide our critical appraisal of the existing literature. Considering the design of this study, we also will not conduct a rigorous assessment of the included articles beyond an inequity lens [ ]. Additionally, scoping reviews do not provide a clear understanding of the efficacy of current interventions in practice as systematic reviews do, which is offset by the benefit of providing breadth from a large number of studies [ ]. We also limit our work to English language articles, and no proprietary research is captured in this review.
AI has immense potential to improve the patient-physician relationship by augmenting physician capabilities. Primary care is an especially viable area for the integration of AI, given its early entry point, broad scope of vulnerable populations, the heavy toll these socioeconomic factors have on patient care, and the need to address these factors to manage disease more effectively. However, algorithms are susceptible to performance disparities across different subgroups, which may further reinforce pre-existing health inequities if not rigorously assessed before deployment. With this scoping review protocol, we aim to provide a process to assess the state of AI in primary care for vulnerable populations.
We are very grateful for Jill Barr-Walker, who served as our clinical librarian consultant in this study. Jill Barr-Walker assisted us in the process of protocol development and validating our search queries. US received funding from the National Institute of Health’s National Cancer Institute Midcareer Investigator Award (grant K24CA212294).
Conflicts of Interest
US is funded by the National Institute of Health’s National Cancer Institute, the California Healthcare Foundation, the Center for Care Innovation, the United States Food and Drug Administration, the National Library of Medicine, and the Commonwealth Fund. She is also supported by an unrestricted gift from the Doctors Company Foundation. She has received prior funding from the United States Department of Health and Human Services’ Agency for Healthcare Research and Quality, Gordon and Betty Moore Foundation, and the Blue Shield of California Foundation. She holds contract funding from AppliedVR, Inquisithealth, and Somnology. Furthermore, US serves as a scientific/expert advisor for the nonprofit organizations HealthTech 4 Medicaid and for HopeLab. She has been a clinical advisor for Omada Health and an advisory panel member for Doximity. SS is a co-founder and equity holder in Monogram Orthopedics. JHC is supported in part by the National Institutes of Health/National Library of Medicine via Award R56LM013365 and Stanford Clinical Excellence Research Center (CERC), is the co-founder of Reaction Explorer LLC, which develops and licenses organic chemistry education software, and has been paid consulting or speaker fees by the National Institute of Drug Abuse Clinical Trials Network, Tuolc Inc, Roche Inc, and Younker Hyde MacFarlane PLLC.
Search strategy and overview for Kueper et al [<xref ref-type="bibr" rid="ref15">15</xref>].PDF File (Adobe PDF File), 3605 KB
PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) flow diagram from Kueper et al [<xref ref-type="bibr" rid="ref15">15</xref>].PPT File (Microsoft PowerPoint Presentation), 184 KB
- Kok J. Artificial Intelligence. Paris: EOLSS Publications; 2009.
- Baştanlar Y, Özuysal M. Introduction to Machine Learning. In: miRNomics: MicroRNA Biology and Computational Analysis. Totowa, NJ: Humana Press; 2014:105-128.
- Covington P, Adams J, Sargin E. Deep Neural Networks for YouTube Recommendations. 2016 Presented at: RecSys '16: Tenth ACM Conference on Recommender Systems; September 15-19, 2016; Boston, MA. [CrossRef]
- Carbonneau R, Laframboise K, Vahidov R. Application of machine learning techniques for supply chain demand forecasting. Eur J Oper Res 2008 Feb;184(3):1140-1154. [CrossRef]
- Pierson HA, Gashler MS. Deep learning in robotics: a review of recent research. Adv Robot 2017 Aug 21;31(16):821-835. [CrossRef]
- Rudin C, Ustun B. Optimized Scoring Systems: Toward Trust in Machine Learning for Healthcare and Criminal Justice. Interfaces 2018 Oct;48(5):449-466. [CrossRef]
- Frohlich KL, Potvin L. Transcending the known in public health practice: the inequality paradox: the population approach and vulnerable populations. Am J Public Health 2008 Feb;98(2):216-221. [CrossRef] [Medline]
- O'Neill J, Tabish H, Welch V, Petticrew M, Pottie K, Clarke M, et al. Applying an equity lens to interventions: using PROGRESS ensures consideration of socially stratifying factors to illuminate inequities in health. J Clin Epidemiol 2014 Jan;67(1):56-64. [CrossRef] [Medline]
- Suresh H, Guttag JV. A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle. arXiv. Preprint posted online January 28, 2019. [FREE Full text]
- Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science 2019 Oct 25;366(6464):447-453. [CrossRef] [Medline]
- Donaldson MS, Yordy KD, Lohr KN, Vanselow NA. Defining Primary Care. In: Primary Care: America's Health in a New Era. Washington, DC: National Academies Press; 1996:27-51.
- Katz A, Chateau D, Enns JE, Valdivia J, Taylor C, Walld R, et al. Association of the Social Determinants of Health With Quality of Primary Care. Ann Fam Med 2018 May;16(3):217-224 [FREE Full text] [CrossRef] [Medline]
- Khanassov V, Pluye P, Descoteaux S, Haggerty JL, Russell G, Gunn J, et al. Organizational interventions improving access to community-based primary health care for vulnerable populations: a scoping review. Int J Equity Health 2016 Oct 10;15(1):168 [FREE Full text] [CrossRef] [Medline]
- Lin SY, Mahoney MR, Sinsky CA. Ten Ways Artificial Intelligence Will Transform Primary Care. J Gen Intern Med 2019 Aug;34(8):1626-1630 [FREE Full text] [CrossRef] [Medline]
- Kueper JK, Terry AL, Zwarenstein M, Lizotte DJ. Artificial Intelligence and Primary Care Research: A Scoping Review. Ann Fam Med 2020 May;18(3):250-258 [FREE Full text] [CrossRef] [Medline]
- Arksey H, O'Malley L. Scoping studies: towards a methodological framework. Int J Soc Res Methodol 2005 Feb;8(1):19-32. [CrossRef]
- Graham ID. Knowledge synthesis and the Canadian Institutes of Health Research. Syst Rev 2012 Feb 09;1:6 [FREE Full text] [CrossRef] [Medline]
- Entezarjou A, Bonamy AE, Benjaminsson S, Herman P, Midlöv P. Human- Versus Machine Learning-Based Triage Using Digitalized Patient Histories in Primary Care: Comparative Study. JMIR Med Inform 2020 Sep 03;8(9):e18930 [FREE Full text] [CrossRef] [Medline]
- Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS One 2017;12(4):e0174944 [FREE Full text] [CrossRef] [Medline]
- Zhou S, Fernandez-Gutierrez F, Kennedy J, Cooksey R, Atkinson M, Denaxas S, UK Biobank Follow-up and Outcomes Group, et al. Defining Disease Phenotypes in Primary Care Electronic Health Records by a Machine Learning Approach: A Case Study in Identifying Rheumatoid Arthritis. PLoS One 2016;11(5):e0154515 [FREE Full text] [CrossRef] [Medline]
- Abràmoff MD, Lavin PT, Birch M, Shah N, Folk JC. Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices. NPJ Digit Med 2018;1:39 [FREE Full text] [CrossRef] [Medline]
- Tricco AC, Lillie E, Zarin W, O'Brien KK, Colquhoun H, Levac D, et al. PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation. Ann Intern Med 2018 Oct 02;169(7):467-473 [FREE Full text] [CrossRef] [Medline]
- Levac D, Colquhoun H, O'Brien KK. Scoping studies: advancing the methodology. Implement Sci 2010 Sep 20;5:69 [FREE Full text] [CrossRef] [Medline]
- Better systematic review management. Covidence. URL: https://www.covidence.org/ [accessed 2020-09-10]
- Hannun AY, Rajpurkar P, Haghpanahi M, Tison GH, Bourn C, Turakhia MP, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 2019 Jan;25(1):65-69 [FREE Full text] [CrossRef] [Medline]
- Methodological Expectations of Cochrane Intervention Reviews. Cochrane Methods. URL: https://methods.cochrane.org/methodological-expectations-cochrane-intervention-reviews [accessed 2020-11-27]
- Moher D, Liberati A, Tetzlaff J, Altman DG, PRISMA Group. Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. PLoS Med 2009 Jul 21;6(7):e1000097 [FREE Full text] [CrossRef] [Medline]
- Daudt H, van Mossel C, Scott S. Enhancing the scoping study methodology: a large, inter-professional team's experience with Arksey and O'Malley's framework. BMC Med Res Methodol 2013 Mar 23;13:48 [FREE Full text] [CrossRef] [Medline]
- Artificial Intelligence Committee. AI in the UK: ready, willing and able? UK Parliament. 2017. URL: https://publications.parliament.uk/pa/ld201719/ldselect/ldai/100/10002.htm [accessed 2021-04-19]
- IEEE Ethics in Action in Autonomous and Intelligent Systems. IEEE. URL: https://ethicsinaction.ieee.org/ [accessed 2021-04-14]
- Hagendorff T. The Ethics of AI Ethics: An Evaluation of Guidelines. Minds Mach 2020 Feb 01;30(1):99-120. [CrossRef]
- Rességuier A, Rodrigues R. AI ethics should not remain toothless! A call to bring back the teeth of ethics. Big Data Soc 2020 Jul 22;7(2):205395172094254. [CrossRef]
- Jobin A, Ienca M, Vayena E. The global landscape of AI ethics guidelines. Nat Mach Intell 2019 Sep 02;1(9):389-399. [CrossRef]
- Urban and Rural. US Census Bureau. URL: https://www.census.gov/programs-surveys/geography/guidance/geo-areas/urban-rural.html [accessed 2020-10-13]
- Communication: Building Trust in Human Centric Artificial Intelligence. European Commission. URL: https://digital-strategy.ec.europa.eu/en/library/communication-building-trust-human-centric-artificial-intelligence [accessed 2020-10-13]
- Overview. National Institute of Minority Health and Health Disparities. URL: https://www.nimhd.nih.gov/about/overview/ [accessed 2021-04-09]
- Morelli V. An Introduction to Primary Care in Underserved Populations: Definitions, Scope, and Challenges. Prim Care 2017 Mar;44(1):1-9. [CrossRef] [Medline]
- McGowan J, Sampson M, Salzwedel DM, Cogo E, Foerster V, Lefebvre C. PRESS Peer Review of Electronic Search Strategies: 2015 Guideline Statement. J Clin Epidemiol 2016 Jul;75:40-46 [FREE Full text] [CrossRef] [Medline]
- Kilbourne AM, Switzer G, Hyman K, Crowley-Matoka M, Fine MJ. Advancing health disparities research within the health care system: a conceptual framework. Am J Public Health 2006 Dec;96(12):2113-2121. [CrossRef] [Medline]
|AI: artificial intelligence|
|PRISMA-ScR: Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews.|
Edited by G Eysenbach; submitted 07.02.21; peer-reviewed by N Benda, S Rahimi; comments to author 14.03.21; revised version received 09.05.21; accepted 16.06.21; published 17.09.21Copyright
©Jonathan Xin Wang, Sulaiman Somani, Jonathan H Chen, Sara Murray, Urmimala Sarkar. Originally published in JMIR Research Protocols (https://www.researchprotocols.org), 17.09.2021.
This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Research Protocols, is properly cited. The complete bibliographic information, a link to the original publication on https://www.researchprotocols.org, as well as this copyright and license information must be included.