Latent classes associated with the intention to use a symptom checker for self-triage.

It is currently unknown which attitude-based profiles are associated with symptom checker use for self-triage. We sought to identify, among university students, attitude-based latent classes (population profiles) and the association between latent classes with the future use of symptom checkers for self-triage. Informed by the Technology Acceptance Model and a larger mixed methods study, a cross-sectional survey was developed and administered to students (aged between 18 and 34 years of age) at a University in Ontario. Latent class analysis (LCA) was used to identify attitude-based profiles that exist among the sample while general linear modeling was applied to identify the association between latent classes and future symptom checker use for self-triage. Of the 1,547 students who opened the survey link, 1,365 did not use a symptom checker in the past year and were thus identified as "non-users". After removing missing data (remaining sample = n = 1,305), LCA revealed five attitude-based profiles: tech acceptors, tech rejectors, skeptics, tech seekers, and unsure acceptors. Tech acceptors and tech rejectors were the most and least prevalent classes, respectively. As compared to tech rejectors, tech seekers and unsure acceptors were the latent classes with the highest and lowest odds of future symptom checker use, respectively. After controlling for confounders, the effect of latent classes on symptom checker use remains significant (p-value < .0001) with the odds of future use in tech acceptors being 5.6 times higher than the odds of future symptom checker use in tech rejectors [CI: (3.458, 9.078); p-value < .0001]. Attitudes towards AI and symptom checker functionality result in different population profiles that have different odds of using symptom checkers for self-triage. Identifying a person's or group's membership to a population profile could help in developing and delivering tailored interventions aimed at maximizing use of validated symptom checkers.

Introduction

Unnecessary care and delaying seeking care are two factors that contribute to higher system costs [1-3]. One way to economize the healthcare system is to provide patients with reliable tools to inform better decisions on when to seek care [1, 4]. Symptom checkers, especially those involving artificial intelligence, have provided a means for users to self-triage (self-assess whether or not they should seek medical care) [5, 6]. Examples of these platforms include Babylon Health, the Ada health app, and the K Health app. Although there are hundreds of symptom checkers available for public use, the literature surrounding the use of this technology remains scarce [7, 8]. It is unclear, for example, whether population groups accept or use this technology as well as the group profiles more likely to accept such a technology.

Research on individual acceptance and use of information technology is one of the most established streams of research in information systems [9]. Stemming from theories in social-psychological and behavioural literature, mainly the Theory of Planned Behavior [10], the Technology Acceptance Model (TAM) outlines various factors to explain an individual’s decision to adopt and use a technology [11]. TAM states that behavioural intention, the most proximal santecedent to actual technology use, is influenced by individuals’ attitude, which in turn, is influenced by two key constructs: perceived usefulness (PU) and perceived ease of use (PEOU) of the technology [11]. Over time, researchers have applied the TAM to identify factors associated with the use of various types of technologies, in different settings, while targeting diverse population groups. The growing body of knowledge in the field contributed to the development of a refined model, the Unified Theory of Acceptance and Use of Technology (UTAUT) [12].

Most studies applying the TAM and UTAUT frameworks, however, have studied the effect of individual factors on technology use, none of which focused on symptom checkers [8, 12]. For example, higher trust in technology has been shown to be associated with increased technology use, but it is unclear if the co-occurrence of high trust with other attitude-based variables may affect this association. As such it is unclear how a group of variables co-exist and in turn, explain acceptance and use of such symptom checkers. To address this gap, latent Class Analysis (LCA), a statistical and probabilistic method introduced in the 1950s [13], can be used to classify individuals from a heterogeneous group into smaller more homogenous unobserved subgroups [14]. Examples of LCA applications include identifying classes based on Internet searching behaviours among older adults [15], an attitude-based segmentation of mobile phone users [16], and identifying patterns of technology and interactive social media use among adolescents [17]. While there are various possible bases to use in segmentation analysis (e.g., ranging from demographic data to lifestyle-related bases), attitudes have been suggested as a useful basis as they take into account a more affective dimension of consumers’ choices and have a better ability to describe behaviour [18, 19].

Little is known about the types of attitude-based population profiles that exist as well as how they are associated with the use of symptom checkers. Addressing this gap has key practical implications for health systems and population health interventions which seek to increased adoption and use of such platforms by the population. The target population in this study were university students as they are typically young adults–a group known to be eager adopters of technology; as such, they are the ideal target for such digital platforms and may contribute to maximizing symptom checker use [20]. The objective of this study was to identify attitude-based latent classes (population profiles) and the association of each of these latent classes with the future use of symptom checkers for self-triage.

Materials and methods

We conducted a cross-sectional survey-based study that targeted young adults (between the ages of 18 and 34 years of age) enrolled at the university of Waterloo, a public research university with six faculties. Prior to participant recruitment, ethics clearance was granted from the Research Ethics Board at the University of Waterloo (#41366). Participant recruitment occurred through an email invitation sent by the University Registrar’s office and a link posted on the Graduate news webpage. In addition to being approved by the Ethics board, the survey email invitation was also submitted to and approved by the Institute of Analysis and Planning. Consent was obtained from participants through the survey. Data collected cannot be shared for confidentiality purposes.

The survey used in this study (S1 Appendix) was developed and reviewed in collaboration with a Survey Research Center (SRC) at the affiliated University. The SRC is comprised of experts in survey design and methodology who work in developing expertise in rigorous and specialized research. Survey development began in August and was finalized the same year, in December 2020. Survey questions were informed by the literature and adapted for the target population and technology of interest (S2 Appendix). Moreover, to reduce respondent burden, not all factors included in the UTAUT were measured in the survey. A shortlist of factors was developed based on the UTAUT model and a ranking exercise conducted with 22 participants from the same target population (i.e., university students) as part of semi-structured interviews–this list is included in S3 Appendix and findings from this work can be found elsewhere [21].

LCA was used on survey data to identify underlying latent variables based on observed measured categorical variables (i.e., trust, usefulness, credibility, demonstrability, output quality, perspectives about AI, ease of use, and accessibility). The selection of the best fitted latent class model(s) for attitudes towards symptom checker functionality and AI in health was based on key fit statistics and interpretability. For models assessing association between latent classes and future use, our General Linear Logit models considered various types of latent classes, and the best regression model was chosen based on model fits statistics and model interpretability.

Data set

A total of 35,643 undergraduate university students received an email invitation for the survey through the Registrar’s office. A total of 1,547 students complete the survey which was available online on January 11, 2021 and closed the following day. Respondents who clicked on the web survey link and did not complete the survey were classified as either screened out or a drop out. Respondents who were screened out were those not meeting the eligibility criterion of being between the ages of 18 and 34. There were 12 and 2 respondents who indicated they were under 18 or over the age of 34, respectively–they were deemed ineligible and screened out of the survey. Drop-outs were defined as respondents who clicked on the web survey link but did not complete the survey. There was a total of 558 dropouts with just over half (57%) having occurred at the introduction page with the rest of the dropouts occurred throughout the survey with most occurring within the first several questions. Given that the outcome of interest is the future use of symptom checkers, 180 respondents who had used symptom checkers in the past 12 months and were thus categorized as “users” were excluded from the analysis. The remaining sample (n = 1,365) who had not used the platform were identified as “non-users” and are the focus of this study.

Data analysis

All analyses were performed using SAS 9.4. Descriptive statistics and bivariate analyses were conducted to provide an overview of the sample. Items used to determine latent classes were coded with binary variables such that 1 denoted “no or neutral” and 2 denoted “yes”. PROC LCA was used to identify response patterns that define latent classes. In order to identify an optimal baseline model, the procedure was repeated for different numbers of latent classes [22]. Once latent class models were identified, relative model fit statistics were used to select the model that best describes the data. Model selection for best latent class model was based on goodness of fit measures such as Bayes Information Criterion (BIC) and entropy [23]. A low BIC value, a high entropy value, and interpretability of the classes informed our model selection [22]. General Logit Models were used for our nominal outcome of interest since the three categories do not have a natural order. Future use of symptom checkers was the outcome of interest with it having three categories and “neutral” as the referent categories and the two other categories (i.e., “yes” and “no”) compared with this referent. The “neutral” category was used as the referent as the interest was to understand the odds-like of using or not using symptom checkers in the future.

Results

Sample

Participants with missing data on key variables of interest were removed (n = 62). The sample (n = 1,305) of non-users is somewhat evenly split across men and women, non-white, enrolled in an undergraduate program, and often have access to the Internet. An overview of this sample in terms of demographics (gender, age, race), academic/professional environment (education level, faculty, employment status), self-perceived health, health literacy, healthcare access, healthcare use, healthcare use frequency, wait time, and healthcare need are shown in Table 1. The counts and percentages of the outcome variable and items used to determine latent classes are presented in Table 2.

Table 1

Sample characteristics.

Characteristics	Count (%)
Gender
• Women	710 (54)
• Men	556 (43)
• Other	39 (3)
Age group
• 18–24 years	1256 (96)
• 25–29 years	37 (3)
• 30–34 years	12 (1)
Racial group a
• White	370 (28)
• Non-white	935 (72)
Current education level b
• Undergraduate	1272 (97)
• Other	33 (3)
Faculty
• Engineering	358 (27)
• Sciences	247 (19)
• Applied Health Sciences	112 (8)
• Environment	77 (7)
• Arts	212 (16)
• Mathematics	299 (23)
Employment status
• Employed	469 (36)
• Not employed	785 (60)
• Prefer not to disclose	51 (4)
Self-perceived health c
• Good	1156 (89)
• Poor or do not know	149 (11)
Health literacy d
• High	1140 (87)
• Average or low	165 (13)
Healthcare access
• Same day to 2 weeks	948 (73)
• 2 weeks to 1 month	85 (7)
• One month or more	24 (2)
• Do not know	248 (19)
Healthcare use e
• Yes	664 (51)
• No or do not know	641 (49)
Healthcare use frequency f
• None to few	501 (75)
• Sometimes	120 (18)
• Often	43 (7)
Wait time g
• Short	982 (75)
• Medium or long	323 (25)
Healthcare need h
• Low	1289 (99)
• Medium or high	16 (1)

Notes: all percentage values are rounded to the nearest integer.

a Race captures the self-perceived racial or cultural group of participants. Prevalent racial groups include South Asian and Chinese. The response options were collapsed into two categories (white and non-white) for data analysis.

b Most participants are currently enrolled in an undergraduate program. Masters and PhD programs were grouped into “other”.

c There were five categories for self-perceived health (i.e., excellent, very good, good, fair, poor) which were grouped into two categories (i.e., good and poor) for data analysis. Eight participants indicated “don’t know”; they were grouped with the “poor” self-perceived health group for analysis purposes.

d Four questions with five-response option Likert scale were used for measuring health literacy. The mean of the responses was calculated and grouped into three options (i.e., high, average, and low).

e Healthcare use was measured by asking whether participants saw a family doctor or nurse in the past year (before COVID-19).

f Healthcare use frequency was answered by 664 participants who had utilised healthcare in the past year. Zero to 2 visits were categorized as “none to few”; 3–5 categorized as “sometimes”; and more than 5 visits categorized as “often”.

g Wait time was measured as the amount of time participants had to wait between the time of their appointment and the time seen by the primary care provider. Less than 15 minutes to 2 hours was categorized as low; 1 to 2 hours was categorized as medium; and 3 hours or more was categorized as long. Eighty-two participants reported long wait times.

h Healthcare need was measured by the number of health conditions reported with “no chronic health conditions” and 1–2 health conditions categorized as “low”; 3–5 health conditions categorized as medium; and 6 or more conditions categorized as “high”. Four participants were identified to have “high” healthcare need and were grouped with those with medium healthcare need.

Table 2

Descriptive statistics on the intent to use symptom checkers.

Characteristics	Count (%)
Future SC use (outcome variable)
• No	215 (16)
• Neutral	391 (30)
• Yes	699 (54)
Perspective on the use of AI
• Negative or neutral	480 (37)
• Positive	825 (63)
Perceived SC ease of use
• Low or neutral	469 (36)
• Yes	836 (64)
Perceived access to SC
• Low or neutral	397 (30)
• High	908 (70)
Demonstrability
• Low or neutral	644 (49)
• High	661 (51)
Trust
• Low or neutral	827 (63)
• High	478 (37)
Usefulness
• Low or neutral	318 (24)
• High	987 (76)
Output quality
• Low or neutral	442 (34)
• High	863 (66)
Credibility
• Low or neutral	161 (12)
• High	1144 (88)

Notes: all percentage values are rounded to the nearest integer; variables in the table were measured using Likert scale response options.

Latent classes

Eight items (i.e., trust, usefulness, credibility, demonstrability, output quality, perspectives about AI, ease of use, and accessibility) were used for latent class modelling; as such, the number of latent class considered were K = 2, 3, … 7. Table 3 displays the fit statistics for the LCA for the top three models arising from K = 3,4, and 5 based on fit statistics and interpretability. These models had relatively lower BIC values and higher entropy as shown in Table 3.

Table 3

Fit statistics for the latent class analysis.

	Number of latent classes
	2	3	4	5	6	7
Fixed effects model
Degrees of freedom	238	229	220	211	202	193
Log likelihood	-5882.62	-5837.06	-5802.22	-5786.55	-5776.10	-5768.13
G-squared	392.99	301.87	232.19	200.85	179.96	164.01
AIC	426.99	353.87	302.19	288.85	285.96	288.01
BIC	514.95	488.40	483.28	516.51	560.18	608.80
Adjusted BIC	460.95	405.81	372.10	376.74	391.83	411.85
Entropy	0.74	0.65	0.61	0.63	0.63	0.66

Note: The bolded text represents models (3, 4, and 5 latent classes) that have been interpreted further for their potential in being selected as the preferred model. An interpretation of these models are in a S4 Appendix.

Based on the fit statistic and interpretability, the five-class model was chosen. While the BIC and adjusted BIC were slightly higher for the five-class model as compared to the three- and four-class models, the entropy was higher as compared to the 4-class model. Importantly, the five-class model provides more detailed information regarding the classes that exist in the population with tech seekers being an important class that is in line with findings from the qualitative phase of this work which highlights the key barrier related to lack of perceived access to symptom checkers. An overview of the five classes are provided in Table 4.

Table 4

Five-latent-class model: Probability of positive perceptions for each subgroup.

	Latent Class (count; %)
	Tech acceptors (621, 48%)	Tech rejectors (137, 11%)	Skeptics (190, 14%)	Unsure acceptors (185, 14%)	Tech seekers (172, 13%)
Trust	0.5428	0.0675	0.1217	0.1887	0.5521
Credibility	0.9927	0.3112	0.7544	0.9744	0.9724
Output quality	0.8824	0.0924	0.3572	0.5811	0.8679
Usefulness	0.9671	0.0989	0.5600	0.7480	0.8479
Demonstrability	0.7195	0.1102	0.2649	0.1678	0.8359
Accessibility	0.9939	0.1905	0.8921	0.5369	0.1311
Ease of use	0.8036	0.2076	0.8729	0.3697	0.5082
Perspectives about AI	0.7557	0.3517	0.5774	0.4656	0.7249

Note: Item-response probabilities >.5 are bolded to facilitate interpretation.

Similarly to the three- and four-latent class models, the first profile describes a group with positive attitudes towards various aspects of symptom checkers and were thusly labeled tech acceptors. The second group were the opposite, having a low probability of answering positively on any of the items assessed, and were labeled as tech rejectors. The third group had a mixed response pattern showcasing some negative perceptions, particularly related to trust, demonstrability, and output quality–this group was labeled as skeptics. The fourth subgroup (tech seekers) has positive perceptions related to all aspects of symptom checkers but do not find the platform to be accessible whereas the fifth group (unsure acceptors) does not perceive access to be an issue but rather have some negative perceptions about AI and other aspects of symptom checkers.

In terms of prevalence, tech acceptors and tech rejectors make up the biggest and smallest proportion across models, respectively. Skeptics are the second most prevalent group with additional granularity provided in models with additional classes.

Regression analysis

The GLM procedure in SAS was used to the fit the above General Logit Regression where the five attitude-based latent profiles serve as a predictor variable in regression models. We additionally ran the above models without confounders (i.e., gender, race, healthcare use, wait time, health literacy, and self-perceived health) for the purpose to assess whether the relationship between the main predictor and the outcome changes. Detailed outputs of these model are provided in S5 Appendix. As seen in Tables 5 and 6, it is noteworthy that the effect of latent classes on the future use of symptom checkers remained significant even after controlling for confounders; this highlights the strength of the association between latent classes and symptom checker use.

Table 5

Output for the five-class model without confounders.

Type 3 Analysis of Effects
Effect	DF	Wald Chi-Square	Pr > ChiSq
Latent Class	8	142.8164	< .0001

Table 6

Output for the five-class model with confounders.

Type 3 Analysis of Effects
Effect		DF		Wald Chi-Square		Pr > ChiSq
Latent Class		8		143.3710		< .0001
GenHealth1		2		2.7162		0.2572
HL2		2		0.6488		0.7230
HC Use3		2		5.6047		0.0607
Wait time4		2		5.0084		0.0817
Gender5		4		5.8547		0.2103
Race6		2		12.3150		0.0021
Odds Ratio Estimates
Effect	Future Use		Point Estimate		95% Wald Confidence Limits
Tech acceptors vs. tech rejectors	Yes		5.603		3.458		9.078
Tech acceptors vs. tech rejectors	No		0.565		0.346		0.922
Skeptics vs. tech rejectors	Yes		2.615		1.491		4.586
Skeptics vs. tech rejectors	No		1.384		0.808		2.371
Tech seekers vs. tech rejectors	Yes		7.669		4.276		13.752
Tech seekers vs. tech rejectors	No		0.662		0.325		1.352
Unsure acceptors vs. tech rejectors	Yes		2.080		1.207		3.584
Unsure acceptors vs. tech rejectors	No		0.538		0.302		0.958

1 Self-perceived health

2 Health literacy

3 Healthcare use.

After controlling for confounders, the effect of latent classes on symptom checker use remains significant (p-value < .0001) with the odds of future use in tech acceptors being 5.6 times higher than the odds of future symptom checker use in tech rejectors [CI: (3.458, 9.078); p-value < .0001]. The odds of future use are 2.6 times higher in skeptics than the odds of future use in tech rejectors [CI: (1.491, 4.586); p-value = .0008]. The odds of future use are 7.6 times higher in tech seekers than the odds of future use in tech rejectors [CI: (4.276, 13.752); p-value = < .0001]. The odds of future use in unsure acceptors are 2 times higher than the odds of future use in tech rejectors [CI: (1.207, 3.584); p-value = .008]. In sum, being in a certain latent class is a significant predictor of future symptom checker use. Tech seekers and unsure acceptors were the latent classes with the highest and lowest odds of future symptom checker use, respectively.

Discussion

To our knowledge, our study is the first to merge the TAM and LCA literature to identify profiles among university students and regress these profiles on future symptom checker use. Interestingly, while young adults are perceived to be technology savvy, most of the participants recruited had not used a symptom checker in the past year–this may be due to the lack of awareness regarding the existence of these platforms [21]. Most had positive perspectives regarding the use of AI in health and symptom checkers’ functionality; however, some skepticism and issues related to perceived accessibility and functionality may hinder the future adoption and use of symptom checkers. Five distinct latent classes were identified: tech acceptors, tech rejectors, skeptics, unsure acceptors, and tech seekers. It is a noteworthy finding that the effect of latent classes remained significant even after controlling for confounders; this is not always the case since from a statistical perspective, the effect of a variable can lose its significance when controlling for other variables [24].

Previous studies have applied the TAM to identify the factors associated with the adoption and use of health apps and health technologies; for example, a study found that adolescents found wearable activity trackers to be useful, but the efforts required to use these technologies may influence overall engagement and technology acceptance [25]. In our study perceived ease of use was also found to play a role in defining latent classes and in turn, the latent class association with future use of symptom checkers. For example, tech rejectors and unsure acceptors did not perceive the use of symptom checkers to be easy which was evident by their lower odds of using symptom checkers in the future. While age was not explored in our study due to the young age of our sample, another study found that younger populations displayed more confidence with the use of mHealth apps and were less concerned about compromising the confidentiality of their health records [26]. Answers to TAM-related questions among mHealth apps users were significantly more positive compared with non-users [26]. Interestingly, as found in our study, the endorsement of health apps by health organizations can play an influential role in technology acceptance and utilization as well as support efforts in shaping regulation [26, 27].

Tech seekers and unsure acceptors had the highest and lowest odds of future symptom checker use, respectively. Interestingly, it was found that tech seekers (those who have positive perspectives related to symptom checker functionality and AI but do not perceive to have access to the technology) had the highest odds of future symptom checker use, even more so than tech acceptors (those who have positive perspectives related to all aspects and perceive to have access to the technology). This nuance was highlighted through five latent classes but lost when approaching the same objective with three or four latent classes. These classes could serve as a starting point in similar studies targeting other population groups.

This study has several strengths that relate to the technology studied, choice of target population, theoretical framework and methodological approach used, tools developed, and practical implications for key stakeholders in the public health arena. Firstly, the development and use of an interview protocol and survey will enable other researchers in the field to adapt and use these tools. This study also contributed to developing the literature on an understudied technology that has real potential in addressing key healthcare challenges. Symptom checkers, along with other digital platforms that allow for self-care, have been named as one of the top 10 emerging technologies in 2020 [28], and their importance has been accentuated during the COVID-19 pandemic [29]. Our study allowed for the identification of five latent classes that may need to be targeted differently to promote the use of promising symptom checkers.

Some limitations warrant mention. First, findings stem from a bounded case which is categorized by a sample that is highly educated and perceived to have a good health status thus limiting the transferability of findings to other populations with a wide range of age groups, education levels, self-perceived health, and health literacy. As such, additional studies targeting other population groups are needed. Moreover, selection bias may be present as those included in the study may be different than those who did not opt to participate; however, findings from this work could help reduce selection bias in future studies as it provides an overview of the profiles that may exist and thus, should be represented in the sample. While the study targeted adults between the ages of 18 and 34, most participants were between 18 and 24 suggesting that latent classes identified may differ if the sample was comprised of individuals in the higher age range. This study focused specifically on non-users with the intention to use a symptom checker being the outcome of interest; while data on “users” were collected, the sample size was too small highlighting that a higher sample size will be required to avoid underextraction of classes. Survey questions were not assessed for two psychometric measures (i.e., reliability and validity); however, questions were developed based on published studies and adapted for the target population and technology. Moreover, the survey was developed with assistance from the Survey Research Center; as such, best available practices were applied in survey design, administration, collection and curation.

Conclusion

Symptom checkers may not be as widely known by the population, even those considered to be eager adopters of technology. Within the university student population, profiles–characterized by their attitudes toward symptom checkers and AI–exist. Perceived ease of use and accessibility are key factors that explain some of the nuances across identified profiles. To maximize the use of validated symptom checkers and therefore, reduce unnecessary healthcare visits, targeted interventions could be developed and delivered depending on an individual’s or group’s identification to a certain profile. Future research is warranted to assess whether similar profiles exist among other population groups as well as which interventions (both at the health system and population health levels) would be best suited based on existing attitude-based variables.

Survey.

(DOCX)

Click here for additional data file.

Construct definitions and source of survey questions.

(DOCX)

Click here for additional data file.

Number of participants choosing factors that are important for using a symptom checker for self-triage.

(DOCX)

Click here for additional data file.

Interpretation of the three- and four-latent class models.

(DOCX)

Click here for additional data file.

Detailed GLM output.

(DOCX)

Click here for additional data file.

18 Aug 2021

PONE-D-21-24082

Latent Classes Associated with the Future Use of a Symptom Checker for Self-Triage by Young Adults

PLOS ONE

Dear Dr. Aboueid,

Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process.

==============================

ACADEMIC EDITOR: Please see comments below

==============================

Please submit your revised manuscript by 18.9.2021. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file.

Please include the following items when submitting your revised manuscript:

A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'.

A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'.

An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'.

If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter.

If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: http://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols.

We look forward to receiving your revised manuscript.

Kind regards,

Dejan Dragan, PhD

Academic Editor

PLOS ONE

Journal Requirements:

When submitting your revision, we need you to address these additional requirements.

1. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at

https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and

https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf

2. In the Methods section of the manuscript, please provide additional information regarding the steps taken to validate the questionnaire used in the study.

3. We note that the figure in your supporting information contain copyrighted images. All PLOS content is published under the Creative Commons Attribution License (CC BY 4.0), which means that the manuscript, images, and Supporting Information files will be freely available online, and any third party is permitted to access, download, copy, distribute, and use these materials in any way, even commercially, with proper attribution. For more information, see our copyright guidelines: http://journals.plos.org/plosone/s/licenses-and-copyright.

We require you to either (1) present written permission from the copyright holder to publish these figures specifically under the CC BY 4.0 license, or (2) remove the figures from your submission:

a. You may seek permission from the original copyright holder of Figure to publish the content specifically under the CC BY 4.0 license.

We recommend that you contact the original copyright holder with the Content Permission Form (http://journals.plos.org/plosone/s/file?id=7c09/content-permission-form.pdf) and the following text:

“I request permission for the open-access journal PLOS ONE to publish XXX under the Creative Commons Attribution License (CCAL) CC BY 4.0 (http://creativecommons.org/licenses/by/4.0/). Please be aware that this license allows unrestricted use and distribution, even commercially, by third parties. Please reply and provide explicit written permission to publish XXX under a CC BY license and complete the attached form.”

Please upload the completed Content Permission Form or other proof of granted permissions as an "Other" file with your submission.

In the figure caption of the copyrighted figure, please include the following text: “Reprinted from [ref] under a CC BY license, with permission from [name of publisher], original copyright [original copyright year].”

b. If you are unable to obtain permission from the original copyright holder to publish these figures under the CC BY 4.0 license or if the copyright holder’s requirements are incompatible with the CC BY 4.0 license, please either i) remove the figure or ii) supply a replacement figure that complies with the CC BY 4.0 license. Please check copyright information on all replacement figures and update the figure caption with source information. If applicable, please specify in the figure caption text when a figure is similar but not identical to the original image and is therefore for illustrative purposes only.

Additional Editor Comments:

The reviewers have completed their reviews. Three of them require a minor revision, while the fourth insists on the major revision. My decision is: A major revision. Please, follow all comments carefully and fix them. AE DD

[Note: HTML markup is below. Please do not edit.]

Reviewers' comments:

Reviewer's Responses to Questions

Comments to the Author

1. Is the manuscript technically sound, and do the data support the conclusions?

The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

**********

2. Has the statistical analysis been performed appropriately and rigorously?

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

**********

3. Have the authors made all data underlying the findings in their manuscript fully available?

The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified.

Reviewer #1: Yes

Reviewer #2: No

Reviewer #3: No

Reviewer #4: No

**********

4. Is the manuscript presented in an intelligible fashion and written in standard English?

PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here.

Reviewer #1: Yes

Reviewer #2: Yes

Reviewer #3: Yes

Reviewer #4: Yes

**********

5. Review Comments to the Author

Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters)

Reviewer #1: This manuscript analyzed the hidden factors for future use of a AI-based symptom checker for self-triage. Though this manuscript is well-written, I have sever comments.

Major comments:

1) Why the authors focus on young adults? Is there any specific reason without comparison on older adults?

2) Why the authors choose only "non-users" for their analysis? It should be comparison results between users and non-users.

3) Why five latent classes are chosen for future analysis? It seems too arbitrary.

4) How the authors control the confounders? There is no explanation on controlling confounders. Please describe it.

5) What are the exact number of samples? It is confusing.

A total of 1,547 students. 12 (under 18) and 2 (over 34) are removed. This means 1533 (1547 - 14). And 180 respondents are users. This derives 1533-180=1353.

But the manuscript mentioned 1,365 samples and after removing missing data, 1,305. Which one is correct?

Minor comments:

6) The legends of Table 1 and Table 2 are the same. Please revise it.

Reviewer #2: In their manuscript, Aboueid et al. present results from a survey among university students aged 18-34 years regarding their attitude towards, and use of, symptom checkers used for self-triage. They identify 5 latent classes representing attitude profiles - tech acceptors, tech rejectors, skeptics, tech seekers, and unsure acceptors. According to their analysis, tech seekers are the most likely and tech rejectors are the least likely to use symptom checkers in the future. While their results provide interesting and novel insights into attitudes that may promote or hinder the acceptance of symptom checkers in different population subgroups, several shortcomings need to be addressed before publication of this manuscript.

1. The study likely suffers from self-selection bias because it only includes participants who opened a link in an email. This should at least be discussed.

2. How were the items on the questionnaire chosen?

3. The latent classes are inferred from “non-users”, and the authors give transparent reasons for this choice. However, they should retrospectively determine in which latent class the “users” fall - are they e.g. tech acceptors or seekers?

4. The fit statistics are not substantially worse for the cases of fewer latent classes. If a smaller number of latent classes (2, 3 or 4) is chosen, do the 5 classes end up in separate classes? This would validate their separation; it is hinted at in the manuscript but should be demonstrated explicitly.

5. A major shortcoming of this study is that it was only conducted in one defined population. It would substantially increase the impact of the study if the authors could confirm whether equivalent latent classes are also observed in other populations. At the very least, this shortcoming should be discussed in the manuscript.

6. Why do tech seekers have higher odds of symptom checker use than tech acceptors, despite finding them less accessible? This is counter-intuitive and should be discussed in detail.

7. The authors mention the significance of their work for public health, but the immediate impact of their results is not clear. They argue that members of the different latent classes may need to be targeted differently in public health interventions, but apart from ease of use or access to symptom checkers, their results suggest that a more general lack of trust in AI is also shown by some participants. It would be very helpful if the authors could expand on this point, suggesting explicitly in what way their results could be taken into account for public health interventions.

Reviewer #3: The manuscript provides an interesting insight into the attitudes of unversity students towards symptom checker applications. It is well written and even more details are presented in the supplement. However, the raw data are not published.

I have some minor questions/comments to the manuscript:

1. Page 5, row 115: the participants of the interviews were from the same population as the study targets, i.e. university students? please indicate this in the text

2. Page 9, row 173: why is "gender" mentioned in the footnote for race? please review and correct if necessary

3. Page 9, row 178: "fair" was also categorized into "good health", and only "poor" (and "don't know") were grouped into the main category "poor"?

4. Page 13, Table 6: footnotes 4-6 only repeat the content of the table cell, I think they are not necessary and can be removed

Reviewer #4: I overall enjoyed reading the work, also, due to its high relevance and real life applicability. I only have some minor questions about details.

Introduction:

- In the introduction the purpose, the necessity and the real life application of the study is clearly stated and explained

- It is also clear which models are used and why these models are chosen

Materials and methods:

- Overall this chapter is also described really clearly

- There is only one thing, which I do not really understand. How are the eight categorical variables chosen? In the bottom of page fife is written: “LCA was used on survey data to identify underlying latent variables based on observed measured categorical variables (…).”

Please specify the process, in which the categorical variables were observed and measured

Data set:

The data set is very clearly and precisely described.

Data Analysis:

The data analysis part is clearly and precisely described.

Results (Sample):

- Tabel1:

- Even though the purpose of table 1 is clear, it is not part of the main result and rather a clarification of the sample group. Thus, it is part of the supportive material

- There are some highly unbalanced classes in the table. In some cases, you could even argue to remove the underrepresented class and give a statement about a narrower sample group (for example a separation into 1256, 37 and 12 (age group) data points is problematic, since the outcome basically represents an age group of 18-24). Since the goal of the study is to find latent classes and not comparing the demographic groups, one option is to keep the data as it is. But then a disclaimer in the discussion mentioning the distribution / group imbalance is necessary to outline this issue and the limitation to the study

- Table2:

- As already mentioned in materials and methods I do not understand where the eight parameters are based on. If I compare the parameters from table 2 to the supporting material 2, I can identify the following:

o Trust

o Credibility

o Perceived accessibility

o tangibility of the result(s) = Demonstrability ?

o healthcare need = Usefulness ?

o Perspective on the use of AI (from TAM ? )

o Perceived SC ease of use (from TAM ? )

o Output quality (from TAM ? )

- Please clarify in chapter materials and methods or in results

- Table 1 and table 2 have both the same title. Please use titles which supply supporting information about the data show in the table

Results (Latent Classes):

- In the discussion is written why the 5 class model is better interpretable than the 3 or 4 class model. Please enter a similar explanation here. Otherwise, it seems like an unsubstantial comment

- Sentence: “While the BIC and adjusted BIC were slightly higher for the five-class model as compared to the three- and four-class models.”

If I compare that statement to table 3 it is not entirely correct. Adjusted BIC is for the 3 class model higher than for the 5 class model.

Results (Regression Analysis):

Is well explained

Discussion:

- Overall it is a good discussion outlining the strengths and limitations of the study

- Please add the disclaimer about the sample group distribution

- there are two "most" in the discussion. Please add specific numbers

**********

6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files.

If you choose “no”, your identity will remain anonymous but your review may still be made public.

Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy.

Reviewer #1: No

Reviewer #2: No

Reviewer #3: Yes: Tamas Toth

Reviewer #4: No

[NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.]

While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step.

23 Sep 2021

RESPONSE TO REVIEWERS

Dear editorial board and reviewers,

We first want to thank you for the time you have taken to review our work.

We sought to address journal requirements. Below is a record of responses from the previous revision.

Previous submission:

We are responding to your comments regarding the manuscript entitled “Latent Classes Associated with the Intention to Use a Symptom Checker for Self-Triage”. We hope that the changes and clarifications made to the manuscript address your comments.

Journal requirements

• We have adapted the manuscript to adhere to journal requirements.

Method for validating the questionnaire

• We added supporting information to highlight the definition of constructs measured as well as the sources of questions used. These questions were adapted for the target population and technology of interest in collaboration with the Survey Research Center at the University of Waterloo. This is also now explained in the methods section.

Figure in the survey

• This figure has been removed and replaced with a description of the image.

Data availability

• Three reviewers have noted that data were not made publicly available. For confidentiality purposes, these data cannot be shared. As part of the data collection process and ethics clearance, participants were told that data will not be shared or used for purposes other than for this study. As per PlosOne data privacy instructions, this has been indicated in the “materials and methods” section.

Reviewer 1:

Major comments:

1. Why the authors focus on young adults? Is there any specific reason without comparison on older adults?

To limit the scope of work, we focused on young adults because they are typically eager adopters of technology and tend to be technology savvy. As such, they could be considered the “ideal target” for such platforms. If this population has negative attitudes towards symptom checkers, then it may be likely that older adults (typically less eager to adopt new technologies) will also have this attitude. Moreover, young adults are undergoing a transition period in which they have to start making decisions regarding their own health and more likely to engage in risky behaviours. It was an interest for myself and my co-authors to explore how symptom checkers could help address health needs of this population.

We acknowledge the importance of conducting other similar studies in other age groups. The profiles identified in this work could inform future work with older adults and would thus help with replication.

2. Why the authors choose only "non-users" for their analysis? It should be comparison results between users and non-users.

The focus of this study was to identify profiles within a population rather than compare two populations. The survey collected information on both “users” and “non-users”; however, the “users” sample was only 180 which was not sufficient for us to conduct LCA (Dziak et al., 2014). While the researchers initially thought that symptom checkers was widely adopted by university students, both our qualitative and quantitative work found that symptom checkers were not as known.

3. Why five latent classes are chosen for future analysis? It seems too arbitrary.

Given that we have eight items, the minimum and maximum number of classes is 2 and 7 (respectively), within which lies the most optimal number of classes. The choice of the optimal number of classes was based on three criteria: model fit statistics, nature of the determined classes (based on the 8 items), and their interpretability. Once the nature of latent classes was determined for each of the number of classes (from 2 to 7), the optimal model was selected based in the aforementioned criteria. This process of model selection in LCA is guided/recommended by the original authors of LCA methodology Lanza’s (2007). Hence, the model selection for best latent class model was not arbitrary. Additionally, the choice of the five class model elucidated a fifth distinct class (in terms of the behaviour profile in the 8 items), which is the sole purpose of LCA methodology – determine distinct classes/patterns formed by the responses in the eight items. While the BIC and adjusted BIC were slightly higher for the five-class model as compared to the three- and four-class models, the entropy was higher as compared to the 4-class model. More importantly, the five-class model provides insight into existence of the (new) class/profile described as tech seekers. This finding is in line with findings from the qualitative phase (Aboueid et al., 2021) which highlighted perceived access to symptom checkers as one of the key barriers. Models with 6 or 7 classes did not provide optimal fit statistics or meaningful class descriptors/interpretations and hence did not serve as top candidate models for the data.

4. How the authors control the confounders? There is no explanation on controlling confounders. Please describe it.

Variables that were used as confounders in our study were based on literature pertaining to technology acceptance model. Our model(s) controlled for the confounding effects of (i) health literacy, (ii) perceived health, and other variables highlighted in the supporting document. The key takeaway from these models is that a subject’s latent class is significant predictor of intention of future even after controlling for effects of confounders the influence intention of future use. This finding elucidates that profile of subjects based on their attitudes towards SC, is an important factor when determining intention of future use of SC, even after controlling for subject’s confounding effects.

5. What are the exact number of samples? It is confusing.

A total of 1,547 students. 12 (under 18) and 2 (over 34) are removed. This means 1533 (1547 - 14). And 180 respondents are users. This derives 1533-180=1353.

But the manuscript mentioned 1,365 samples and after removing missing data, 1,305. Which one is correct?

The 1,547 does not include those that were screened out and drop-outs. The 1,547 are the number of surveys that were completed. So the calculation is as such: 1,547 – 180 = 1,367 (non-users).

1,367 – 62 (participants with missing data) = 1,305. The numbers have been adjusted to reflect this.

Minor comments:

6. Thank you – this has been revised.

Reviewer 2:

1. The study likely suffers from self-selection bias because it only includes participants who opened a link in an email. This should at least be discussed.

We agree about this point and we have made this more explicit in the limitations.

2. How were the items on the questionnaire chosen?

This study was part of a larger mixed methods study in which the first phase of the work entailed conducting interviews with participants of the same target population. Based on our literature review of the technology acceptance model, there is a total of over 15 variables/factors that could potentially be important. To reduce respondent burden, 22 participants were asked to choose the top five factors from the 15 potential factors they believed to be most important when deciding to use symptom checkers. Factors the at were chosen most often in addition the factors identified by Davies et al. were then selected as the varaibles to be measured in the survey. This information is now incorportated in the methods section.

3. The latent classes are inferred from “non-users”, and the authors give transparent reasons for this choice. However, they should retrospectively determine in which latent class the “users” fall - are they e.g. tech acceptors or seekers?

Thank you for this feedback. The issue with predicting classes for “users” based on model built using “non-users” assumes subject are exchangeable between the two groups, which is not an assumption we feel comfortable making for our study. The two groups may come from different populations and extrapolation from one group to another can be misleading. We aimed to conduct the analysis for the “users” but the sample is too small (in some cases the cell size was less than 5 participants in certain matrices); as such, the findings would not be reliable. Additional participants will be required for future studies to assess the profiles among those users as well as their association with use and frequency of use.

4. The fit statistics are not substantially worse for the cases of fewer latent classes. If a smaller number of latent classes (2, 3 or 4) is chosen, do the 5 classes end up in separate classes? This would validate their separation; it is hinted at in the manuscript but should be demonstrated explicitly.

We agree that the fit statistics for the 3 and 4 classes are not much worse, but the five-class model highlighted an interesting split of the unaware acceptors which showed that “perceived accessibility” to be a key hindrance which is similar to what was found in our qualitative work. Interpretability was the key factor that guided the choice of the 5-class model.

5. A major shortcoming of this study is that it was only conducted in one defined population. It would substantially increase the impact of the study if the authors could confirm whether equivalent latent classes are also observed in other populations. At the very least, this shortcoming should be discussed in the manuscript.

We have addressed this point in length in the first comment made by reviewer 1. We are hoping that this study and approach will be leveraged by other researchers in the field who will target other population groups. This will be important for replication and generalizability. We have made this point more explicit in our limitations.

6. Why do tech seekers have higher odds of symptom checker use than tech acceptors, despite finding them less accessible? This is counter-intuitive and should be discussed in detail.

We too found this quite interesting as well but are unsure why this is the case. The reason behind such an association eludes and hence, rather the speculating reasons for such a counter-intuitive finding, our discussion leaves this as an association to be investigated in future studies with different populations.

7. The authors mention the significance of their work for public health, but the immediate impact of their results is not clear. They argue that members of the different latent classes may need to be targeted differently in public health interventions, but apart from ease of use or access to symptom checkers, their results suggest that a more general lack of trust in AI is also shown by some participants. It would be very helpful if the authors could expand on this point, suggesting explicitly in what way their results could be taken into account for public health interventions.

The items measured in this survey could also be assessed in different settings depending on data captured (e.g., in a healthcare clinic or a national survey). It would then be possible to tailor discussions and interventions based on the profile of a person or group. Trust was perceived to be quite important throughout our work, so interventions and strategies related to improving trust in symptom checkers is important; however, if a person does trust the symptom checker but does not perceive it to be accessible or easy to use, other interventions may need to be used such as referring the patient to individuals who could support in symptom checker use etc. Identifying interventions and strategies for this was not in the scope of this work but is an area of exploration for us.

Reviewer 3:

1. Page 5, row 115: the participants of the interviews were from the same population as the study targets, i.e. university students? please indicate this in the text

This has been clarified.

2. Page 9, row 173: why is "gender" mentioned in the footnote for race? please review and correct if necessary

Thanks for spotting that – it is now corrected.

3. Page 9, row 178: "fair" was also categorized into "good health", and only "poor" (and "don't know") were grouped into the main category "poor"?

The interest was to compare to those who had poor health and the variable had to be dichotomized for analysis purposes. As such, any category that was not “poor” or “don’t know” were not included in the “good” category. Given that the “good” category includes those who have excellent to fair health, the sample averages out and thus justify the label “good”. Moreover, even if the “fair” group was added into the “poor” self-perceived health category, the analysis would not change.

4. Page 13, Table 6: footnotes 4-6 only repeat the content of the table cell, I think they are not necessary and can be removed

Agreed. They have been removed.

Reviewer 4:

Introduction:

1) In the introduction the purpose, the necessity and the real-life application of the study is clearly stated and explained

Thank you.

2) It is also clear which models are used and why these models are chosen

Thank you.

Materials and methods:

3) Overall this chapter is also described really clearly

Thank you.

4) There is only one thing, which I do not really understand. How are the eight categorical variables chosen? In the bottom of page fife is written: “LCA was used on survey data to identify underlying latent variables based on observed measured categorical variables (…).”

Please specify the process, in which the categorical variables were observed and measured

The eight variables were chosen based on input from participants in the qualitative phase on this work. Prior to developing the survey, 22 participants from the same target population were asked to choose the top five factors they believed to be most important when deciding to use a symptom checker for self-triage. The ones most chosen were the ones included in the survey in addition to the factors identified as important by Davies (i.e., perceived ease of use and perceived usefulness).

Data set:

5) The data set is very clearly and precisely described.

Thank you.

Data Analysis:

6) The data analysis part is clearly and precisely described.

Thank you.

Results (Sample):

- Tabel1:

7) Even though the purpose of table 1 is clear, it is not part of the main result and rather a clarification of the sample group. Thus, it is part of the supportive material

Our reason for keeping table 1 in the main text is to gives the reader some context about the characteristics of the sample. This will allow them to read the rest of the results with sample characteristics in mind. For this reason, the revised manuscript has table 1 in the main text instead of supplementary/supportive material.

8) There are some highly unbalanced classes in the table. In some cases, you could even argue to remove the underrepresented class and give a statement about a narrower sample group (for example a separation into 1256, 37 and 12 (age group) data points is problematic, since the outcome basically represents an age group of 18-24). Since the goal of the study is to find latent classes and not comparing the demographic groups, one option is to keep the data as it is. But then a disclaimer in the discussion mentioning the distribution / group imbalance is necessary to outline this issue and the limitation to the study

We have incorporated the your comments in our limitation section.

- Table2:

9) As already mentioned in materials and methods I do not understand where the eight parameters are based on. If I compare the parameters from table 2 to the supporting material 2, I can identify the following:

o Trust

o Credibility

o Perceived accessibility

o tangibility of the result(s) = Demonstrability ?

o healthcare need = Usefulness ?

o Perspective on the use of AI (from TAM ? )

o Perceived SC ease of use (from TAM ? )

o Output quality (from TAM ? )

- Please clarify in chapter materials and methods or in results

Thank you for this feedback. This has been addressed in our responses for Reviewer 1.

10) Table 1 and table 2 have both the same title. Please use titles which supply supporting information about the data show in the table

Thanks for spotting this – we edited the titles accordingly.

Results (Latent Classes):

11) In the discussion is written why the 5-class model is better interpretable than the 3 or 4 class model. Please enter a similar explanation here. Otherwise, it seems like an unsubstantial comment

We have added this explanation in the results.

12) Sentence: “While the BIC and adjusted BIC were slightly higher for the five-class model as compared to the three- and four-class models.”

If I compare that statement to table 3 it is not entirely correct. Adjusted BIC is for the 3 class model higher than for the 5 class model.

We have corrected this. Interpretability was the main reason why we opted for the five-class model rather than the two other candidates (3- and 4- class models). Please see our response in comment #3 of Reviewer1.

Results (Regression Analysis):

13) Is well explained

Thank you.

Discussion:

14) Overall it is a good discussion outlining the strengths and limitations of the study

Thank you.

15) Please add the disclaimer about the sample group distribution

We have added this in the limitations.

16) there are two "most" in the discussion. Please add specific numbers

We have added the numbers.

Thanks again and we hope that the above addresses your comments.

Best regards,

Stephanie Aboueid, RD, MSc, PhD

School of Public Health and Health Systems

University of Waterloo

Ontario, Canada

21 Oct 2021

Latent Classes Associated with the Intention to Use a Symptom Checker for Self-Triage

PONE-D-21-24082R1

Dear Authors,

We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements.

Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication.

An invoice for payment will follow shortly after the formal acceptance. To ensure an efficient process, please log into Editorial Manager at http://www.editorialmanager.com/pone/, click the 'Update My Information' link at the top of the page, and double check that your user information is up-to-date. If you have any billing related questions, please contact our Author Billing department directly at authorbilling@plos.org.

If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org.

Kind regards,

Dejan Dragan, PhD

Academic Editor

PLOS ONE

Additional Editor Comments (optional):

The authors have completed a revision of their paper. Already an innovative advanced study has become even better after carefully processed corrections carried out by the authors. Moreover, the answers to reviewers are clear, exact, and transparent. Accordingly, I warmly recommend the acceptance of the paper. The A.E. Dejan Dragan.

Reviewers' comments:

25 Oct 2021

PONE-D-21-24082R1

Latent Classes Associated with the Intention to Use a Symptom Checker for Self-Triage

Dear Dr. Aboueid:

I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now with our production department.

If your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information please contact onepress@plos.org.

If we can help with anything else, please email us at plosone@plos.org.

Thank you for submitting your work to PLOS ONE and supporting open access.

Kind regards,

PLOS ONE Editorial Office Staff

on behalf of

Dr. Dejan Dragan

Academic Editor

PLOS ONE