Received: 18 May 2018
| Revised: 16 October 2018
DOI: 10.1111/ajr.12496
ORIGINAL RESEARCH
Efficacy of a remote screening model for oral potentially
malignant disorders using a free messaging application: A
diagnostic test for accuracy study
Kalaiselvi Vinayagamoorthy MDS1 | Shruthi Acharya MDS2 | Mathangi Kumar MDS2 |
Kalyana Chakravarthy Pentapati MDS1 | Shashidhar Acharya MDS1
1
Department of Public Health Dentistry,
Manipal College of Dental Sciences,
Manipal Academy of Higher Education,
Manipal, India
2
Department of Oral Medicine and
Radiology, Manipal College of Dental
Sciences, Manipal Academy of Higher
Education, Manipal, India
Correspondence
Shashidhar Acharya, Department of Public
Health Dentistry, Manipal College of
Dental Sciences, Manipal Academy of
Higher Education, Manipal, India.
Email: sh.acharya@manipal.edu
Aust. J. Rural Health. 2019;1–7.
| Accepted: 2 December 2018
Abstract
Objective: To assess the feasibility of using a remote sensing model as a free
messaging application tool in the preventive screening of oral potentially malig-
nant disorders in a rural area of India.
Design: An observational cross‐sectional study.
Setting: Primary care setting in Udupi District, Karnataka, South India.
Participants: One‐hundred and thirty‐one individuals with a mean (SD) age of
37.34 (11.31) years, of whom 64.1% and 35.9% were men and women, respec-
tively.
Interventions: Clinical oral examination followed by photo capture of five areas
of the patients' mouth.
Main outcome measures: Reliability measures for the use of a photo messaging
service in diagnosing oral potentially malignant disorders, as compared to the
clinical examination.
Results: When lesions were categorised as normal and abnormal, the reliability
(kappa) between the diagnoses, based on photo messaging and clinical oral exam-
ination, was 0.68 and 0.67 for Examiners 1 and 2, respectively. The sensitivity
values for Examiners 1 and 2 were 98.5% and 99.04%, respectively, whereas the
specificity was 72% and 64%, respectively. When the agreement between photo
messaging and clinical oral examination for an exact diagnostic match was
assessed, the reliability (kappa) was 0.59 and 0.55 for Examiners 1 and 2, respec-
tively. The sensitivity values for Examiners 1 and 2 were 98.1% and 98.7%,
respectively, whereas the specificity was 64% and 52% respectively.
Conclusion: There was a substantial agreement between the diagnosis based on
clinical examination and WhatsApp image for both the examiners, when the
lesions were dichotomised as normal and abnormal, but slightly reduced when
assessed for the exact diagnostic match. Screening for oral potentially malignant
disorders using photo messaging can serve as an effective adjunct and a potential
cost‐effective tool in a low‐resource setting.
KEYWORDS
lesions, premalignant, reliability, teledentistry, WhatsApp
wileyonlinelibrary.com/journal/ajr © 2019 National Rural Health Alliance Ltd. | 1
2
| VINAYAGAMOORTHY
1 | INTRODUCTION
Advances in IT have reduced the distance between
individuals and health care providers with unique
prospects for remote access.1 Teledentistry is one such
technological innovation in dentistry that can serve to
bridge the gap between health care providers and indi-
viduals. Teledentistry is defined as the “diagnosis and
treatment of dental patients using electronically aided
communication technologies”.2 Also, teledentistry has
been reported to be a cost‐effective means of reaching
the less privileged.3,4 The application of teledentistry is
diverse and its efficiency has been proved in different
dental settings.
Given the increased incidence rates of oral cancer in
underprivileged populations, the fragmented health care
system and the associated higher mortality and morbidity
rates in developing countries like India, alternative cost‐
effective and readily available methods of early detection
like teledentistry need to be considered.5 Moreover, the
main challenge in the early detection of oral cancer is the
diagnostic pathway that relies on an unhindered exchange
of information between primary and secondary health care
providers.6 Teledentistry is a promising alternative to over-
come geographic distance as a barrier to seek expert con-
sultation for oral potentially malignant disorders (PMDs)
and increase the early detection of oral cancer. In recent
times, the increased usage of smartphones by health care
professionals has enhanced the role of teledentistry in
everyday practice.
Innovations in smartphone imaging technology and
instant messaging services provide better prospects for the
utilisation of teledentistry as a means for virtual consulta-
tion.7 Smartphones have the basic requirements for a tele-
dentistry system like image capture, storage and transfer
to distant location and view without change in resolution.
The ready availability and user‐friendly nature of smart-
phones make it an efficient and cost‐effective alternative
to the conventional telemedicine system.8 Studies have
proved the efficacy of photographic methods in the diag-
nosis of oral lesions.3,9 Cross‐platform mobile messaging
applications that allow exchange of text messages, images,
audio and video messages online have been found to be
useful for remote consultation by experts in dental
settings.10-12
Reduced access to and utilisation of cancer screening
services in rural and remote areas might lead to poor can-
cer outcomes.13-16 However, there is limited evidence on
the use of photo messaging as an adjunct in the screening
of individuals for oral PMDs in a community setting.
Therefore, this study was done to assess the feasibility of
using photo messaging as a tool in the preventive screening
for oral PMDs in a rural area of India.
ET AL.
What is already known on this subject:
• There are numerous applications, which are
broadening the scope of teledentistry.
• Many of these apps are proprietary, difficult to
use, require an excellent Internet connectivity
and are out of reach of the rural and remote pop-
ulations.
• There is a lack of diagnostic evidence of health
apps on Apple's and Google's app stores.
• Some studies have shown the efficiency of free
messaging apps for remote consultation by
experts in dental settings.
• Early diagnosis of oral premalignant lesions is
the most effective means of reducing the inci-
dence of malignancies and its associated morbid-
ity and mortality.
What this study adds:
• Free messaging apps are a reliable tool for the
remote screening of oral premalignant disorders.
• There was a high reliability when the oral mucosa
was dichotomised as normal and abnormal.
• The reliability reduced to moderate levels when
the accuracy requirement of the screening
increased to an “exact” lesion diagnosis.
• Screening for oral potentially malignant disor-
ders, using photo messaging, can serve as an
effective adjunct and a potential cost-effective
tool in a low-income and remote setting.
2 | METHODS
A cross‐sectional study was conducted between January
and June 2017, among a convenience sample of partici-
pants of oral screening programs in different areas of
Udupi District, Karnataka. The sample size was estimated
to be 131, considering a power of 90%, kappa of 0.9 and
an expected observed proportion of premalignant lesions of
10%.
Prior to the start of the study, information sheets and
consent forms for clinical examination and photographing
the oral cavity were provided to participants who visited
the screening programs. Photographs were focussed only
inside the oral cavity excluding the face, thus preventing
direct identification of the participants. Those who had
problems with comprehension, and limited mouth opening
restricting accessibility for the mobile phone camera to
click images, were excluded from the study.
VINAYAGAMOORTHY ET AL.
2.1 | Clinical oral examination procedures
Each participant was given an individualised code number.
Information was collected on demographic details (age,
sex), medical history and oral habits among those who ful-
filled the inclusion criteria. Following this, a screening of
the oral cavity of the participants was carried out by a
trained and calibrated examiner (Examiner 1). All examina-
tions were carried out under a natural light source using a
mouth mirror and explorer. The findings of the clinical oral
examination were recorded in the proforma.
2.2 | Image capture
In a separate room, a comprehensive set of five photographs
for each participant, covering different areas of the oral cav-
ity, was captured by a single calibrated dental student using a
standardised procedure on a mobile phone camera under nat-
ural but not direct sunlight. A Samsung Note 2 mobile phone
with an 8‐megapixel camera and a display with a resolution
of 720 × 1280 pixels with autofocus (Samsung, Seoul,
South Korea) was used for this purpose. The images were
obtained in a sequential manner: left buccal mucosa; right
buccal mucosa; then upper labial mucosa including buccal
vestibule; then upper labial mucosa including buccal vesti-
bule and tongue. The photographs were checked immedi-
ately for clarity and coverage of the desired area. Following
this, the images of each patient were sequentially numbered
and stored as separate folders in the phone storage. The
images were not modified or enhanced.
2.3 | Image transfer and evaluation
The photo messaging feature of the WhatsApp messenger
(version 2.17.190; WhatsApp, Mountain View, CA, USA)
was used in the present study. Information, regarding age,
sex, medical and habit history along with five images of
the oral cavity of each individual, were sent through the
messenger to both the examiners (1 and 2) after a washout
period of 2 months. Both the examiners separately analysed
the images in their mobile phones with the display bright-
ness at 50%. Both the examiners used Android
smartphones with a display size of 5.50″ and a display res-
olution of 1080 × 1920 pixels.
2.4 | Training and calibration
Prior to the main study, a pilot study was conducted among
patients attending the dental outpatient department of the
university hospital. The patients were examined twice by
Examiners 1 and 2, following which the images of five
areas of the oral cavity were captured by the calibrated
dental student. After a washout period of 1 month, an
| 3
assessment of the images sent through photo messaging
was conducted to determine the reliability (kappa).
2.5 | Statistical analysis
Data were analysed using Statistical Package for Social
Sciences (SPSS for Windows, version 20; SPSS, Chicago,
IL, USA). P ≤ 0.05 was considered statistically significant.
The reliability was tested at two levels. At the general level,
lesions were categorised as normal and abnormal where oral
lesions, like leukoplakia, tobacco pouch keratosis, postin-
flammatory hyperpigmentation and oral submucous fibrosis,
were coded as abnormal. Clinically, normal mucosa and nor-
mal variants, like benign migratory glossitis, linea alba buc-
calis, depapillation and hyperpigmentation, were coded as
normal. At the specific level, the reliability of an exact diag-
nostic match of lesions between the examinations was con-
sidered. The kappa statistic was calculated to test the the
inter‐examiner and intra‐examiner reliability of the clinical
oral (gold standard) examination and photographic examina-
tion (WhatsApp images) for both levels. Accuracy, sensitiv-
ity, specificity, positive predictive value and negative
predictive value were calculated for photo messaging, as
compared with a clinical oral examination (gold standard).
Further, the agreement between the two examiners for the
diagnosis based on photo messaging was calculated.
2.6 | Ethics approval
The study was approved by the Kasturba Hospital Institu-
tional Ethics Committee.
3 | RESULTS
A total of 131 individuals (655 images) were screened and
the images of five areas of the oral cavity were captured.
Out of the 655 images, five images were scored as unclear
by either of the examiners, when sent through photo mes-
saging (Figure 1).
The mean (SD) age of the screened individuals was 37.34
(11.31) years. This included 64.1% of men and 35.9% of
women. Approximately 13.1% of the screened individuals
had a history of tobacco smoking habit. Among the 131 indi-
viduals screened, 16 of them were diagnosed with PMDs
during the clinical oral examination, with a prevalence of
12.2%. The PMDs diagnosed were tobacco pouch keratosis
(n = 10), leukoplakia (n = 2), oral submucous fibrosis
(n = 3) and postinflammatory hyperpigmentation (n = 1).
All of these individuals were men and habitual tobacco users
with a mean (SD) age of 41 (13.06) years.
When lesions were categorised as normal and abnormal,
the reliability (kappa) between the diagnosis based on
4
| VINAYAGAMOORTHY ET AL.

Participants screened
n = 131

Images obtained
n = 655(131*5)

Excluded images
n=5
Diagnosed using
Reasons -
WhatsApp
image scored unclear
n = 650

Examiner 1 Examiner 2

WhatsApp WhatsApp WhatsApp WhatsApp

diagnosis normal diagnosis abnormal diagnosis normal diagnosis abnormal
n = 622 n = 27 n = 627 n = 22

Clinical oral Clinical oral Clinical oral Clinical oral

examination examination examination examination
diagnosis normal diagnosis abnormal diagnosis normal diagnosis abnormal
F I G U R E 1 Flow diagram to report the
n = 624 n = 25 n = 624 n = 25
flow of participants through the study

photo messaging and clinical oral examination was 0.68
and 0.67 for Examiners 1 and 2, respectively (Figures 2
and 3). The sensitivity values for Examiners 1 and 2, were
98.5% and 99.04%, respectively, whereas the specificity
was 72% and 64%, respectively (Table 1).
When the agreement between photo messaging and clin-
ical oral examination for an exact diagnostic match was
assessed, the reliability (kappa) was 0.59 and 0.55 for
Examiners 1 and 2, respectively. The sensitivity values for
Examiners 1 and 2 were 98.1% and 98.7%, respectively,
whereas the specificity was 64% and 52%, respectively
(Table 2). Kappa for the agreement between the two exam-
iners in the diagnosis, based on photo messaging images,
was 0.59 and the accuracy was 97 (Table 3, Figure 4).
4 | DISCUSSION
In our study, there was a substantial agreement between the
diagnosis based on clinical examination and photo messag-
ing image for both the examiners, when the lesions were
dichotomised as normal and abnormal. However, when the

F I G U R E 3 Clinical oral examination‐tobacco pouch keratosis;

F I G U R E 2 Clinical oral examination‐normal; WhatsApp WhatsApp (Examiner 1), normal; WhatsApp (Examiner 2), tobacco
(Examiner 1), normal; WhatsApp (Examiner 2), normal pouch keratosis
VINAYAGAMOORTHY ET AL. | 5

T A B L E 1 Sensitivity, specificity, reliability, positive and negative predictive values in the diagnosis based on photographic images, as
compared with clinical oral examination (normal/abnormal)

Diagnosis based on Kappa (95% CI) Accuracy (%) Sensitivity (%) Specificity (%) PPV (%) NPV (%)
Photo messaging images
Examiner 1 vs gold standard 0.68 (0.53‐0.83) 97.5 98.56 72.00 98.87 66.67
Examiner 2 vs gold standard 0.67 (0.51‐0.82) 97.6 99.04 64.00 98.57 72.73

CI, confidence interval; NPV, negative predictive value; PPV, positive predictive value.

T A B L E 2 Sensitivity, specificity, reliability, positive and negative predictive values in the definitive diagnosis based on images, as compared
with clinical oral examination (exact diagnostic match)

Diagnosis based on Kappa (95% CI) Accuracy (%) Sensitivity (%) Specificity (%) PPV (%) NPV (%)
Photo messaging images
Examiner 1 vs gold standard 0.59 (0.43‐0.75) 96.77 98.08 64.00 98.56 57.14
Examiner 2 vs gold standard 0.55 (0.37‐0.72) 96.92 98.72 52 98.09 61.90
CI, confidence interval; NPV, negative predictive value; PPV, positive predictive value.

T A B L E 3 Reliability of diagnosis based on images between the two examiners

Diagnosis based on Kappa (95% CI) Accuracy (%) Sensitivity (%) Specificity (%) PPV (%) NPV (%)
Photo messaging images
Examiner 1 vs examiner 2 0.6 (0.43‐0.76) 97.0 98.09 68.18 98.88 55.56

CI, confidence interval, NPV, negative predictive value; PPV, positive predictive value.

messaging‐based image assessment indicated a slight over-

F I G U R E 4 Clinical oral examination‐Leukoplakia; WhatsApp
(Examiner 1), leukoplakia; WhatsApp (Examiner 2), normal
reliability was assessed for an exact diagnostic match, the
kappa values for the examiners decreased to moderate levels
of agreement. Inter‐examiner agreement between the two
examiners in the diagnosis, based on photo messaging
images, was moderate. The results of the present study were
in agreement with those of earlier studies assessing
image‐based screening for oral lesions.10,17 Moreover, the
heterogeneity of oral lesions, importance of palpation and
histological examination in confirmatory diagnosis need to
be considered.10 The sensitivity and specificity of photo‐
estimation of the lesions, as compared with clinical oral
examination, which could be attributed to the wide array of
diagnoses in oral medicine, the two‐dimensional representa-
tion of the lesions and the factors, affecting the image qual-
ity, like the extent of coverage and lighting.18 This could be
further explained by the subtle nature of early lesions of oral
cancer and precancer, which lack the characteristics demon-
strated in advanced lesions.19
Drawbacks mentioned in previous studies, assessing the
feasibility of teledentistry like image quality, clinical data
and habit history, were minimised in the present study.9,17
Along with images, information on habit history and clini-
cal data for each patient was sent to the examiners through
photo messaging. In our study, images were captured using
a mobile phone with an 8 megapixel camera. Previous
studies have reported 8 megapixels as suitable for an
image‐based diagnosis.17 Five images were excluded due
to lack of diagnostic details by either of the examiners.
The images are generally compressed when transferred
using photo messaging, which might have significant effect
on the diagnosis.
Overall, the findings demonstrated a good level of
agreement between the two methods (clinical and photo-
graphic examination) and the two examiners. The results
also showed that the examiners were consistent in the way
they diagnosed premalignant lesions from photographs.
6
| VINAYAGAMOORTHY
The sensitivity scores were higher than the specificity
scores across all examiners and assessment methods. The
higher sensitivity scores were in line with the World Health
Organisation's reference standard of 0.85‐0.90 for sensitiv-
ity values.20
Recent advancements in telecommunication services and
the provision of high‐speed internet services at low cost,
covering a majority of the rural areas in countries like
India, can be leveraged in the provision of health care ser-
vices to remote areas.21 The fact that the colour gamut of
phones varies enormously and that there is considerable
inconsistency between phones, even of the same brand,
needs to be considered. As such, this is likely to have an
impact on the diagnostic yield of any proposed arrange-
ment. It has to be conceded that the use of a free messag-
ing service would be precluded in some countries due to
information governance concerns.
Distance and isolation remain the major obstacles for
providing health care in rural and remote areas. Whether
the secondary care infrastructure has the capacity to deal
with this diagnostic pathway is still unclear. Furthermore,
this capacity might be distributed unevenly and dimin-
ished in areas that require it the most. There has been an
increasing use of telemedicine in cancer care in many
countries around the world and in countries like Australia
in particular, to provide cancer care closer to homes.22
Research on these models has demonstrated feasibility,23
patient and health professional acceptance24-26 and cost
savings to the health systems.27 The teledentistry model
is very suitable in countries like India with a high preva-
lence of oral PMDs, and paucity of skilled manpower
and existing cancer screening programs. Using free mes-
saging services for screening oral lesions can help
improve the quality of care in remote areas by facilitating
better decision‐making through expert consultation. How-
ever, in countries with a lower prevalence, these diagnos-
tic aids can be used in a “PML present or absent” mode
to aid the referral pathway from primary to secondary
care.
As compared with specialised telemedicine/dentistry
apps that require some level of technological sophistica-
tion to operate, common freeware is easy to use and
requires much less training. Furthermore, these apps
require a much lesser bandwidth than other proprietary
apps and consume much less device memory. In cases
where the experts are in short supply or are unable to
cover remote areas on a regular basis, this system can be
the next best thing to the physical presence of an expert.
It has to be conceded that no matter how fine the tech-
nique, it is possible to miss a lesion in the teledentistry
mode and the patient could later develop oral cancer. But
the same can be said for clinical examination as well
where a PMD could be missed or misdiagnosed as a non‐
ET AL.
PMD. Teledentistry models can be used as an adjunct to
traditional models where they exist and as the next best
thing in areas where they are lacking.
ACKNOWLEDGEMENTS
The authors thank the non‐teaching staff who helped carry
out the screening.
CONFLICT OF INTEREST
The authors have no conflict of interest to declare and this
study has not in part or whole, been published or is under
consideration for publication elsewhere. No external fund-
ing was obtained for this study.
AUTHORS’ CONTRIBUTIONS
Kalaiselvi Vinayagamoorthy, Kalyana Chakravarthy Penta-
pati and Shashidhar Acharya conceptualised and designed
the study; Kalyana Chakravarthy Pentapati, Shruthi
Acharya and Mathangi Kumar analysed and interpreted the
data; and Kalaiselvi Vinayagamoorthy and Shashidhar
Acharya prepared the manuscript. All authors edited and
reviewed the manuscript.
ORCID
Shashidhar Acharya https://orcid.org/0000-0002-2196-
3979
REFERENCES
1. Purohit BM, Singh A, Dwivedi A. Utilization of teledentistry as a
tool to screen for dental caries among 12‐year‐old school children
in a rural region of India. J Public Health Dent. 2017;7:174‐180.
2. Ignatius E, Makela K, Happonen RP, Perala S. Teledentistry in
dental specialist education in Finland. J Telemed Telecare.
2006;12:46‐49.
3. Bradley M, Black P, Noble S, Thompson R, Lamey PJ. Applica-
tion of teledentistry in oral medicine in a Community Dental Ser-
vice, N. Ireland. Br Dent J. 2010;209:399‐404.
4. Mariño R, Hopcraft M, Tonmukayakul U. Teleconsultation/teledi-
agnosis using teledentistry technology: a pilot feasibility study.
Int J Adv Life Sci. 2014;6:291‐299.
5. Coelho KR. Challenges of the oral cancer burden in India. J Can-
cer Epidemiol. 2012;2012:17, Article ID 701932.
6. McLeod N, Saeed N, Ali E. Oral cancer: delays in referral and
diagnosis persist. Br Dent J. 2005;198:681‐684.
7. Estai M, Kanagasingam Y, Xiao D, et al. A proof‐of‐concept
evaluation of a cloud‐based store‐and‐forward telemedicine app
for screening for oral diseases. J Telemed Telecare. 2016;22:
319‐325.
8. Kopycka-Kedzierawski DT, Billings RJ. Teledentistry in inner‐
city child‐care centres. J Telemed Telecare. 2006;12:176‐181.
VINAYAGAMOORTHY ET AL.
9. Torres-Pereira C, Possebon RS, Simoes A, Bortoluzzi MC, Leao JC,
Giovanini AF. Email for distance diagnosis of oral diseases‐prelimin-
ary study of teledentistry. J Telemed Telecare. 2008;14:435‐438.
10. Petruzzi M, Benedittis MD. WhatsApp: a telemedicine platform
for facilitating remote oral medicine consultation and improving
clinical examinations. Oral Surg Oral Med Oral Pathol Oral
Radiol. 2016;121:248‐254.
11. Sarode SC, Sarode GS, Anand R, Patil S, Unadkat H. WhatsApp
is an effective tool for obtaining second opinion in oral pathology
practice. J Oral Pathol Med. 2017;46:513‐519.
12. Zotti F, Dalessandri D, Salgarello S, et al. Usefulness of an app
in improving oral hygiene compliance in adolescent orthodontic
patients. Angle Orthod. 2016;86:101‐107.
13. Underhill C, Bartel R, Goldstein D, et al. Mapping oncology ser-
vices in regional and rural Australia. Aust J Rural Health.
2009;17:321‐329.
14. Garvey G, Cunningham J, Valery PC, et al. Reducing the burden
of cancer for Aboriginal and Torres Strait Islander Australians:
time for a coordinated, collaborative, priority driven, Indigenous‐
led research program. Med J Aust. 2011;194:530‐531.
15. Roder D. Epidemiology of cancer in Indigenous Australians:
implications for service delivery. Cancer Forum. 2007;31:85‐90.
16. Australian Health Ministers’ Advisory Council. Aboriginal and
Torres Strait Islander Health Performance Framework 2014
Report. Canberra, ACT: AHMAC; 2015.
17. Haron N, Zain RB, Nabillah WM, et al. Mobile phone imaging
in low resource settings for early detection of oral cancer and
concordance with clinical oral examination. Telemed J E Health.
2017;23:192‐199.
18. Estai M, Kanagasingam Y, Huang B, et al. Comparison of a
smartphone‐based photographic method with face‐to‐face caries
assessment: a mobile teledentistry model. Telemed J E Health.
2017;23:435‐440.
19. Lingen MW, Kalmar JR, Karrison T, Speight PM. Critical evalu-
ation of diagnostic aids for the detection of oral cancer. Oral
Oncol. 2008;44:10‐22.
| 7
20. World Health Organization. Oral Health Surveys: Basic Methods
World Health Organization, 5th edn. Geneva, Switzerland: World
Health Organization; 2013.
21. Mallick R, Perwez E, Noor R, Sachdeva S, Tamrakar AK. Tele-
dentistry: proposal of an implementation model in India. Ann
Dent Spec. 2016;4:33‐37.
22. Hazin R, Qaddoumi I. Teleoncology: current and future applica-
tions for improving cancer care globally. Lancet Oncol.
2010;11:204‐210.
23. Sabesan S, Larkins S, Evans R, et al. Telemedicine for rural can-
cer care in North Queensland: bringing cancer care home. Aust J
Rural Health. 2012;20:259‐264.
24. Sabesan S, Simcox K, Marr I. Medical oncology clinics
through videoconferencing: an acceptable telehealth model for
rural patients and health workers. Intern Med J. 2012;42:780‐
785.
25. Mair F, Whitten P, May C, Doolittle GC. Patients’ perceptions of
a telemedicine specialty clinic. J Telemed Telecare. 2000;6:36‐
40.
26. Mooi JK, Whop LJ, Valery PC, Sabesan SS. Teleoncology for
indigenous patients: the responses of patients and health workers.
Aust J Rural Health. 2012;20:265‐269.
27. Thaker DA. Cost savings from a telemedicine model of care in
northern Queensland, Australia. Med J Aust. 2013;199:414‐417.
How to cite this article: Vinayagamoorthy K,
Acharya S, Kumar M, Pentapati KC, Acharya S.
Efficacy of a remote screening model for oral
potentially malignant disorders using a free
messaging application: A diagnostic test for accuracy
study. Aust. J. Rural Health. 2019;00:1–7.
https://doi.org/10.1111/ajr.12496