• Users Online: 288
  • Home
  • Print this page
  • Email this page
Home About us Editorial board Search Ahead of print Current issue Archives Instructions to authors Subscribe Contacts Login 

 Table of Contents  
Year : 2022  |  Volume : 9  |  Issue : 3  |  Page : 157-162

Assessment of knowledge, attitude, and practice regarding artificial intelligence in histopathology: A cross-sectional study among oral pathologists in India

1 Department of Oral Pathology, Government Dental College, Kottayam, Kerala, India
2 Department of Public Health, Texila American University, Georgetown, Guyana

Date of Submission09-Jun-2022
Date of Decision10-Aug-2022
Date of Acceptance21-Aug-2022
Date of Web Publication31-Dec-2022

Correspondence Address:
Dr. M Indu
Department of Oral Pathology, Government Dental College, Kottayam - 686 008, Kerala
Login to access the Email id

Source of Support: None, Conflict of Interest: None

DOI: 10.4103/sjoralsci.sjoralsci_19_22

Rights and Permissions

Introduction: The era of artificial intelligence (AI) has dawned, and its influence on different aspects of our lives is now tremendously evident. The introduction of whole slide imaging in digital pathology has changed the face of histopathology (HP) and is in the process of paving a smooth platform towards the far-reaching telepathology.
Aim: The present study was aimed to evaluate the knowledge, attitude, and practice (KAP) of Oral Pathologists (OPs) in India regarding the incorporation of AI in diagnostic HP.
Materials and Methods: This cross-sectional study was conducted among OPs across India. A structured online questionnaire comprising 27 questions was sent to each participant through email and social media platforms and responses were collected and analyzed. The relationship between demographic variables and good KAP was analyzed using Chi-square and Fisher's exact test.
Results and Discussion: One hundred and seventy-one OPs participated in the study, with 8.8% having good knowledge, 70.2% having a positive attitude, and only 4.1% using AI in diagnostic HP. Knowledge regarding AI in pathology increased in a statistically significant way (P = 0.001) with respect to years of experience. 43.9% of OPs expect AI to be integrated into HP in India over the next ten years.
Conclusion: OPs in India have a positive attitude towards the incorporation of AI in their pathology practice. Vital measures to enable the integration of AI into diagnostic HP and to improve its awareness are an absolute requisite in our scenario.

Keywords: Artificial intelligence, digital pathology, KAP survey, oral pathology, telepathology, whole slide imaging

How to cite this article:
Indu M, Shankar VG, Cherian LM, Krishna R, Paul S, Sathyan P. Assessment of knowledge, attitude, and practice regarding artificial intelligence in histopathology: A cross-sectional study among oral pathologists in India. Saudi J Oral Sci 2022;9:157-62

How to cite this URL:
Indu M, Shankar VG, Cherian LM, Krishna R, Paul S, Sathyan P. Assessment of knowledge, attitude, and practice regarding artificial intelligence in histopathology: A cross-sectional study among oral pathologists in India. Saudi J Oral Sci [serial online] 2022 [cited 2023 Feb 6];9:157-62. Available from: https://www.saudijos.org/text.asp?2022/9/3/157/366526

  Introduction Top

Artificial intelligence (AI), a revolutionary term coined in the early 1950s and embodied in the medical industry from its inception, has witnessed a steadfast journey over the years. It has sailed through time and obstacles by constantly revising its definition from “creation of computers capable of engaging in human-like mental processes” to “imitating intelligent human behavior.”[1],[2],[3] In general, AI is used in healthcare to analyze medical images and electronic health records, assist in diagnosis and treatment design, monitor treatment plans, assist in drug discovery and extract information on potential drug interactions. Thus, incorporation of AI in the medical field facilitates better understanding of disease mechanisms, which in turn improves health care quality and so on. In the field of dentistry, AI promises to reduce diagnostic and treatment costs by overcoming subjective variability, integrating curated and structured data management, and dental imaging.[4],[5],[6],[7],[8]

Salto et al. refers to AI as the third revolution in the field of histopathology (HP), following the footsteps of immunohistochemistry and genomic medicine.[9] Diagnostic pathology around the world is centered on microscopic examination of glass slides, which is considered the gold standard. Recent years have seen a drastic shift in conventional slide examination from developing digitally scanned whole slide images (WSI), enabling speedy and hassle-free diagnosis.[10],[12],[13],[14] The pattern recognition capabilities of AI on whole slide image databases are impressive and have added value to digital pathology.[11],[15],[16],[17],[18] In quantitative HP, AI can be easily coupled to count the percentage of a particular cell or to measure the positivity of an IHC marker. Hence, digitization in HP creates a platform for telepathology, allowing for faster and easier expert opinion delivery and reduction of errors.[19],[20] Supervised AI algorithms can be used for classification and segmentation in HP.[21] In numerous research areas, like colorectal cancer diagnosis, prediction of microsatellite instability in gastrointestinal cancer, detection of mitosis in breast cancer, and differentiation of lung cancer from normal tissues, AI has fostered positive results. Therefore, AI supports the pathologists to identify novel insights into the condition as well as to assess the diagnostic features.[15],[22],[23],[24],[25],[26],[27],[28],[29],[30]

Though AI is setting the pace in our day-to-day lives, it is yet to be fully integrated into diagnostic pathology in developing countries. Some possible reasons include lack of integration of WSI with information technology, validation and regulation requirements, technical concerns such as processing and storage of large database sets, personnel-based requirements such as training, adaptability to computational technology, financial resources, etc.[13],[22] There is also a lack of translation of results obtained in research settings into the clinical arena. It is critical to identify and overcome the obstacles to its implementation in a timely and orderly manner. The sheer interest of researchers in the field of AI will be the guiding force for its implementation. Though the field of HP has been witnessing remarkable outcomes, the level of awareness and implementation among the concerned population needs to be evaluated. As a result, the purpose of this study was to assess oral pathologists' (OPs) knowledge, attitude, and practice (KAP) regarding the incorporation of AI in diagnostic HP in India.

  Materials and Methods Top

This online cross-sectional study was conducted among OPs including postgraduates, faculties, and consultant OPs in India. Approval to conduct this study was obtained from the Institutional Ethics Committee and Review Board of Govt. Dental College Kottayam (IEC/M/19/2020/DCK). The minimum sample size was calculated as 120 participants with confidence level (1-α) as 99%, absolute precision as 10%. An online structured questionnaire was developed in the English language using Google Forms. This questionnaire based on information from the previous KAP surveys about AI in the health sector.[31] The content validity of the questionnaire was assessed by two experts, and their suggestions were incorporated into the final version of the questionnaire.

The study was carried out based on the convenience sampling method, and the link to the questionnaire was shared through e-mails, WhatsApp, and other social media platforms of OPs. The participants were requested to forward the questionnaire to their contacts in order to achieve maximum participation. In order to avoid skipping of questions by participants, it was made mandatory to answer all questions, without which it was impossible to submit.

The questionnaire began with an introduction, followed by 27 survey questions divided into four sections: (1) demographic characteristics of participants, (2) awareness of AI in pathology, (3) attitude toward incorporating AI in routine diagnostic oral pathology, and (4) practice with AI in routine HP. The introductory part contained information about the study. The identity of participants was kept anonymous. Respondents were asked to choose the most appropriate answer from the set of options tailored for each question. The survey was open for a duration of 3 months. The responses of the participants were collected, tabulated, and analyzed. Statistical analysis was done using the IBM SPSS Statistics for Windows, Version 25 (IBM Corp., Armonk, NY, USA). The relationship between demographic variables and good knowledge, attitude, and practice was analyzed using Chi-square and Fisher's exact tests. P ≤ 0.05 was considered to establish statistical significance.

  Results Top

The study gathered replies from 171 OPs from various Indian states, most of which were from South India (77.2%). Most of the participants belonged to the age group of 31–45 years (51.4%). Senior residents and postgraduates made up 30.4% of the participants, followed by Professors, Assistant Professors/Senior Lecturers, Associate Professors, and consultant OPs. Demographic details of the study population are summarized in [Table 1].
Table 1: Demographic characteristics of study participants

Click here to view

Knowledge level of OPs' about artificial intelligence in routine histopathology practice

77.8% (n = 133) of OPs had awareness about the application of AI in day-to-day life. 8.8% (n = 15) of OPs had good understanding and knowledge about the application of AI in Oral Pathology practice, and only 2.3% claimed to have very good knowledge. The level of understanding of OPs about AI in pathology practice is summarized in [Graph 1]. Sixty-two percent (n = 106) of all participants were aware that AI algorithms can be better applied to HP in WSI platform. It was also noted that as the age and experience of OPs increased, knowledge regarding AI in pathology increased in a statistically significant way (P = 0.01 and 0.001, respectively). [Table 2] explains the association of experience and the level of understanding of AI.

Table 2: Experience (in the field of oral pathology) and level of understanding about artificial intelligence in pathology practice

Click here to view

Attitude of OPs' toward artificial intelligence in diagnostic histopathology practice

70.2% (n = 120) of respondents thought AI could increase the accuracy of HP diagnosis. The majority of OPs opined that AI is capable of making accurate diagnoses in certain areas of pathology. [Graph 2] summarizes the opinion of OPs regarding the diagnostic ability of AI in pathology.

According to 33.3% (n = 57) of OPs, AI will not be a realistic alternative in pathology labs in India. However, 43.9% of OPs expect AI to be integrated into routine diagnostic pathology in India over the next ten years. [Graph 3] summarizes the opinions of OPs regarding the time duration needed to incorporate AI into routine HP practice in the Indian scenario.

Twenty-eight percent (n = 48) of OPs thought that AI might replace OPs in the field of HP, while 53.8% (n = 92) of OPs disagreed with this and 18.1% (n = 31) had a neutral opinion. 40.9% (n = 70) of the participants were anxious that the incorporation of AI would have a negative impact on the residents' HP training and traditional diagnostic skills. According to 90.0% (n = 154) of the participants, OPs should be equipped/trained with technical knowledge regarding AI.

63.8% (n = 109) of them said they were technologically savvy and could adapt to AI, and the majority of OPs were willing to adapt to AI in the future. [Graph 4] summarizes the attitude of OPs toward the incorporation of AI in routine HP in the future.

Most of the OPs (53.8%) thought that incorporating AI into histopathologic diagnosis would be well accepted by patients, whereas 10.0% (17) disagreed and 36.3% (n = 62) were unsure about it.


Most of the OPs relied on internet/web-based resources to update their knowledge about AI. Majority of the participants still rely on glass slides rather than digital slides. Only a small number of OPs got opportunities to try AI as a diagnostic tool at any point in their practice. [Graph 5] shows the percentage of OPs who use AI as a diagnostic tool.

  Discussion Top

The field of dentistry has embraced artificial intelligence owing to its effective contribution toward diagnosing, treatment planning, predicting prognosis, and data management. Studies on the application of AI to diagnosis and treatment planning in many branches of dentistry and forensic odontology have yielded promising results.[4],[5],[6],[7],[8]

The work done in the field of HP remains monotonous, with the exception of immunohistochemistry and molecular testing. Apart from assisting in routine activities and reporting, digital pathology and the integration of AI aid in the study of newer depths in cellular and molecular investigation, thereby revolutionizing the field of HP.[18] As a result, a proper understanding, a positive attitude, and extensive practice of AI breakthroughs in their respective disciplines are equally crucial for OPs. Therefore, this cross-sectional survey was aimed to assess the knowledge, attitude, and practice of OPs in India regarding the incorporation of AI in diagnostic HP.

The study was aimed at gathering responses from OPs across India, but the maximum responses were obtained from South India. We discovered that a large number of OPs were not only aware of AI but also mindful of its applications in the field of histology. However, 8.8% of OPs had a good understanding and knowledge of the application of AI. 62% of OPs were aware that AI algorithms could be better applied with the help of a WSI platform. Another notable point is that as the age and experience of OPs increased, knowledge regarding AI in pathology practice increased. According to the study conducted among dermatologists by Polesie et al. regarding AI in dermatology, 85.1% of them were aware of AI as a new technology. However, only 23.8% had good knowledge.[31] In a survey regarding the perspectives of medical students in the United Kingdom (UK) on AI by Sit et al., 78% of them believed that students should receive training in AI as a part of their medical degree.[32] A large proportion of students in the taught group reported a lack of confidence and understanding required for the critical use of healthcare AI tools.[32] These studies show that there is a lack of knowledge about AI among medical professionals. More educational programs are to be conducted in this regard.

The attitude of the OPs on assessment of diagnostic accuracy and proficiency was encouraging. 63.7% of them believed that AI applications will be useful to differentiate benign and malignant lesions and 70.8% of them thought that AI can be used for IHC analysis. In a survey by Sarwar et al., 75% of them voiced that AI as a diagnostic tool to facilitate improvements in workflow efficiency.[33] According to Polesie et al., 77.3% of participants agreed that AI will improve dermatology practice.[31] However, there was a mixed response when it came to the timescale for implementing AI to the conventional HP across India. 43.9% of OPs expect AI to be integrated into histopathological practice in India over the next ten years. Sarwar et al., stated that around 80% of respondents predicted the introduction of AI technology in the pathology laboratory within the coming decade.[33]

Though there was collective appreciation for tuning toward AI, the OPs' across the country did not believe AI to replace them in the coming future. However,in the study conducted by Sarwar et al, pathologist-respondents from 54 countries raised their concerns regarding the possibility of job displacement and replacement.[33] Furthermore, in this study, OPs voiced their conviction that patients will welcome the adoption of AI in HP owing to the growing awareness of public to numerous applications harboring AI in one's daily life.

For the majority of OPs here, digital slides are not a practical option which makes incorporation of AI difficult. This situation has to be reformed for better outcomes.

Studies of KAP on OPs though limited, literature did present with a few studies on the acceptance of AI in various fields of medicine. While comparing the result with other studies, it is evident that OPs in India have the same positive attitude as others towards the incorporation of AI in diagnostic pathology. However, a slight gap in knowledge level and lack of facilities create a hindrance to embrace this new technology into the diagnostic field. The study population was slightly skewed towards the South Indian population, which can be considered as a limitation of the present study.

  Conclusion Top

The application of AI in the field of medicine, and more so in the field of HP, is an obligatory change in the near future. The OPs are aware of AI, its applications in their field, but still there are lacunae to be addressed. A large-scale study with more respondents' coverage regions is needed to improve the generalizability of findings. Lack of widespread availability of WSI and other supporting facilities make incorporation of AI in diagnostic pathology difficult in India. Enhancement of facilities wills definitely speedup integration of AI in pathology. All of the aforementioned, as well as the findings of the present study, point to the incorporation of AI in the area of medicine as the next major switch, one that will undoubtedly result in a revolution, not just in practice but also in academics. As a result, practitioners in all domains of medicine and dentistry must be aware of, adapt to, and absorb the inevitable change of AI application in the field of medicine.

Financial support and sponsorship


Conflicts of interest

There are no conflicts of interest.

  References Top

Kok JN, Boers EJ, Kosters WA, Van der Putten P, Poel M. Artificial intelligence: Definition, trends, techniques, and cases. Artif intell 2009;1:270-99.  Back to cited text no. 1
Helm JM, Swiergosz AM, Haeberle HS, Karnuta JM, Schaffer JL, Krebs VE, et al. Machine learning and artificial intelligence: Definitions, applications, and future directions. Curr Rev Musculoskelet Med 2020;13:69-76.  Back to cited text no. 2
Altman RB. AI in medicine: The spectrum of challenges from managed care to molecular medicine. AI Magazine 1999;20:67.  Back to cited text no. 3
Hung M, Park J, Hon ES, Bounsanga J, Moazzami S, Ruiz-Negrón B, et al. Artificial intelligence in dentistry: Harnessing big data to predict oral cancer survival. World J Clin Oncol 2020;11:918-34.  Back to cited text no. 4
Chen YW, Stanley K, Att W. Artificial intelligence in dentistry: current applications and future perspectives. Quintessence Int 2020;51:248-57.  Back to cited text no. 5
Deshmukh SV. Artificial intelligence in dentistry. J Int Clin Dent Res Organ 2018;10:47.  Back to cited text no. 6
  [Full text]  
Khanagar SB, Al-Ehaideb A, Maganur PC, Vishwanathaiah S, Patil S, Baeshen HA, et al. Developments, application, and performance of artificial intelligence in dentistry – A systematic review. J Dent Sci 2021;16:508-22.  Back to cited text no. 7
Schwendicke F, Samek W, Krois J. Artificial intelligence in dentistry: Chances and challenges. J Dent Res 2020;99:769-74.  Back to cited text no. 8
Salto-Tellez M, Maxwell P, Hamilton P. Artificial intelligence-the third revolution in pathology. Histopathology 2019;74:372-6.  Back to cited text no. 9
Komura D, Ishikawa S. Machine learning methods for histopathological image analysis. Comput Struct Biotechnol J 2018;16:34-42.  Back to cited text no. 10
Niazi MK, Parwani AV, Gurcan MN. Digital pathology and artificial intelligence. Lancet Oncol 2019;20:e253-61.  Back to cited text no. 11
Pantanowitz L. Digital images and the future of digital pathology. J Pathol Inform 2010;1:15.  Back to cited text no. 12
[PUBMED]  [Full text]  
Tizhoosh HR, Pantanowitz L. Artificial intelligence and digital pathology: Challenges and opportunities. J Pathol Inform 2018;9:38.  Back to cited text no. 13
[PUBMED]  [Full text]  
Indu M, Rathy R, Binu MP. “Slide less pathology”: Fairy tale or reality? J Oral Maxillofac Pathol 2016;20:284-8.  Back to cited text no. 14
[PUBMED]  [Full text]  
Acs B, Rantalainen M, Hartman J. Artificial intelligence as the next step towards precision pathology. J Intern Med 2020;288:62-81.  Back to cited text no. 15
Krishna AB, Tanveer A, Bhagirath PV, Gannepalli A. Role of artificial intelligence in diagnostic oral pathology-A modern approach. J Oral Maxillofac Pathol 2020;24:152-6.  Back to cited text no. 16
  [Full text]  
Campanella G, Hanna MG, Geneslaw L, Miraflor A, Werneck Krauss Silva V, Busam KJ, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat Med 2019;25:1301-9.  Back to cited text no. 17
Colling R, Pitman H, Oien K, Rajpoot N, Macklin P, CM-Path AI in Histopathology Working Group, et al. Artificial intelligence in digital pathology: A roadmap to routine use in clinical practice. J Pathol 2019;249:143-50.  Back to cited text no. 18
Chang HY, Jung CK, Woo JI, Lee S, Cho J, Kim SW, et al. Artificial intelligence in pathology. J Pathol Transl Med 2019;53:1-12.  Back to cited text no. 19
Gurcan MN, Boucheron LE, Can A, Madabhushi A, Rajpoot NM, Yener B. Histopathological image analysis: A review. IEEE Rev Biomed Eng 2009;2:147-71.  Back to cited text no. 20
Kalra S, Tizhoosh HR, Shah S, Choi C, Damaskinos S, Safarpoor A, et al. Pan-cancer diagnostic consensus through searching archival histopathology images using artificial intelligence. NPJ Digit Med 2020;3:31.  Back to cited text no. 21
Acs B, Hartman J. Next generation pathology: Artificial intelligence enhances histopathology practice. J Pathol 2020;250:7-8.  Back to cited text no. 22
Cruz JA, Wishart DS. Applications of machine learning in cancer prediction and prognosis. Cancer Inform 2006;2:59-77.  Back to cited text no. 23
Das DK, Chakraborty C, Sawaimoon S, Maiti AK, Chatterjee S. Automated identification of keratinization and keratin pearl area from in situ oral histological images. Tissue Cell 2015;47:349-58.  Back to cited text no. 24
Saks MJ, Albright T, Bohan TL, Bierer BE, Bowers CM, Bush MA, et al. Forensic bitemark identification: Weak foundations, exaggerated claims. J Law Biosci 2016;3:538-75.  Back to cited text no. 25
Jha S, Topol EJ. Adapting to artificial intelligence: Radiologists and pathologists as information specialists. JAMA 2016;316:2353-4.  Back to cited text no. 26
Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI. Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J 2015;13:8-17.  Back to cited text no. 27
Krishnan MM, Venkatraghavan V, Acharya UR, Pal M, Paul RR, Min LC, et al. Automated oral cancer identification using histopathological images: A hybrid feature extraction paradigm. Micron 2012;43:352-64.  Back to cited text no. 28
Yu KH, Zhang C, Berry GJ, Altman RB, Ré C, Rubin DL, et al. Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features. Nat Commun 2016;7:12474.  Back to cited text no. 29
Ehteshami Bejnordi B, Veta M, Johannes van Diest P, van Ginneken B, Karssemeijer N, Litjens G, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 2017;318:2199-210.  Back to cited text no. 30
Polesie S, Gillstedt M, Kittler H, Lallas A, Tschandl P, Zalaudek I, et al. Attitudes towards artificial intelligence within dermatology: an international online survey. Br J Dermatol 2020;183:159-61.  Back to cited text no. 31
Sit C, Srinivasan R, Amlani A, Muthuswamy K, Azam A, Monzon L, et al. Attitudes and perceptions of UK medical students towards artificial intelligence and radiology: A multicentre survey. Insights Imaging 2020;11:14.  Back to cited text no. 32
Sarwar S, Dent A, Faust K, Richer M, Djuric U, Van Ommeren R, et al. Physician perspectives on integration of artificial intelligence into diagnostic pathology. NPJ Digit Med 2019;2:28.  Back to cited text no. 33


  [Table 1], [Table 2]


Similar in PUBMED
   Search Pubmed for
   Search in Google Scholar for
 Related articles
Access Statistics
Email Alert *
Add to My List *
* Registration required (free)

  Materials and Me...
  In this article
Article Tables

 Article Access Statistics
    PDF Downloaded78    
    Comments [Add]    

Recommend this journal