Veterinary Medical Informatics

From Clinfowiki
Jump to: navigation, search

Veterinary Medical Informatics

Veterinary medical informatics can be defined as the intersection of computer science, data science, veterinary medicine, information technology, and social and behavioral science to improve diagnosis, treatment, clinical workflow and disease prevention in veterinary medicine[1][2].

Biomedical informatics in veterinary medical research and public health is very similar to bioinformatics in human medicine. Advances in machine learning disease surveillance, antibiotic resistance studies and maps, the use of big data to gain clinical insights, genomics (e.g., the Dog Genome Project[3]) have been made, although they are slowed by challenges pertaining to access to good data[2][4]. While biomedical informatics in animal sciences has mirrored progress in human medicine, clinical health informatics in the companion animal space has lagged behind human medical practices in terms of both availability and adoption by practitioners. Some of the challenges in veterinary medical informatics include the lack of interoperability, absence of diagnosis codes, medication codes, LOINC or SNOMED for data standardization (with certain exceptions), and the wide range of practice information management systems (PIMS) available.


Practice Information Management Systems:

Practice information management systems are veterinary medicine’s equivalent to the Electronic Health Record (EHR). Early PIMS models focused primarily on transaction billing, reminders, and appointment scheduling, but have since evolved into a full electronic medical record system, replacing the paper patient medical record[5][6]. Adoption of the PIMS for full patient medical records has only become prevalent in the late 2010’s to early 2020’s, with many practices still using a combination of PIMS for billing and scheduling in combination with a paper medical record[7]. Unlike in human medicine where there are one or two EHRs that dominate the field, there are many PIMS, all with their own billing codes and different data structures. Although the AVMA has recommended the use of more standardized systems that would set the stage for sharing of data and interoperability, the use of these is usually restricted to academic or government systems and are not found in most PIMS commonly used by veterinarians in private practice[2].

Although PIMS have evolved in recent years to more closely mimic human EHRs, there remain some differences between PIMS and human medical EHRs[2]. Most PIMS record medical notes in a free text field, rather than using structured medical notes. Clinical decision support within the PIMS is not generally seen. Only selected PIMS have integration with picture archiving and communication systems (PACs) or radiological information systems (RIS). Computerized physician order entry, decision support systems, and adverse event detection are not currently available in veterinary PIMS, although this is likely to change soon.


Artificial Intelligence & Clinical Decision Support

Clinical Decision Support is still relatively new in the context of clinical practice in veterinary medicine[8][9]. The two largest commercial laboratories in North America offer clinical decision support features. In 2019, Antech Diagnostics introduced RenalTech®, a machine-learning predictive model which predicts chronic kidney disease two years earlier than the onset of clinical signs[10]. IDEXX Reference Laboratories, Inc. offers a suite of decision support tools via IDEXX DecisionIQ™ alongside patient results11. These include features such as machine learning predictive models for feline hyperthyroidism and canine hypoadrenocorticism and expert rules-based patient-specific and results specific interpretations of various endocrine tests, guidance for positive vector-borne results, and disease staging of chronic kidney disease in alignment with International Renal Interest Society (IRIS) guidelines[11]. Multiple machine-learning predictive tools have also been developed in academia including hypoadrenocorticism, Cushing’s syndrome, atopic dermatitis, epilepsy, and congestive heart failure, to name just a few[8][9][12][13][14][15].

Artificial intelligence has been in use for much longer in the realm of image classification, particularly in diagnostic imaging where it is used for identification of abnormalities in the canine thorax or for calculation of vertebral heart scores[8][9][16][17][18]. Image classification is also used on a microscopic scale as well such as reading urine sediment or cellular analysis of whole blood or other specimens[16][19].

During the SARS-CoV-2 (COVID-19) pandemic in the early 2020s, many veterinarian offices operated in a no human-contact mode where only the pet was brought into the clinic. During this time period, telemedicine was used as the primary means of communication with pet owners. It was also during this time period that chatGPT entered the playing field. ChatGPT apps could be used by pet owners as a standalone feature to get advice about their pets (excluding the veterinarian from the conversation)[20]. However, in many cases, chatGPT AI chatbots could also be used to serve as Triage nurses to answer pet owners' questions and to help determine which pets needed to be seen sooner rather than later. Many of these could be loosely integrated with PIMS. While telemedicine is no longer standard care, the chatbots have persisted.

Beyond chatbots, natural language processing is making its way into the veterinary field in the form of workflow efficiencies. Similar to human medicine, these include voice-to-SOAP tools and clinical history summarization[9]. Many of the tools available are standalone products that do not directly integrate with the PIMS, requiring veterinarians to copy/paste the results into the medical notes. Despite the inconvenience, these tools still provide great cognitive and time savings. One area of concern in this field is lack of peer-reviewed validation studies on these new technologies in veterinary medicine.


Regulatory Landscape

The regulatory landscape is rapidly evolving. At the time of this writing (March 2025) artificial intelligence tools in veterinary medicine are currently not subject to premarket FDA approval regulations pertaining to Software as a Medical Device (SaMD)[21]. In fact, the majority of AI based features available have not gone through sufficient validation to meet FDA requirements[22]. However, that does not imply that there are no regulations regarding the use of AI by veterinarians. Instead, the responsibility lies with the practitioner whose decisions and actions are regulated under the bounds of their license. In March 2025, the American Association of Veterinary State Boards (AASVB) released an official position statement regarding the use of artificial intelligence in practice21:

“The American Association of Veterinary State Boards (AAVSB) supports innovation. We recognize the potential benefits that Artificial Intelligence (AI) and other emerging technologies may offer the veterinary profession. However, Licensees must understand the risks and limitations of AI to protect the standard of patient care and prevent unlicensed practices. They must also maintain full transparency regarding AI use, safeguard Client data privacy, and, when appropriate, obtain Informed Consent for the use of AI.

The AASVB encourages Member Boards to educate Licensees on the regulatory considerations of AI use in veterinary medicine. Licensees and Facilities must comply with their jurisdiction’s Veterinary Practice Act and other applicable federal and jurisdictional laws.” (AASVB 2025, p.1)

State Boards are encouraged by the AASVB to develop specific guidelines for AI use as pertains to Informed Consent, data security and storage, transparency, and client confidentiality.

Interestingly, while the FDA does not currently regulate AI tools, the US FDA’s Center for Veterinary Medicine (CVM) has integrated AI into its regulatory framework and scientific initiatives. [23]The CVM utilizes machine learning AI in antimicrobial resistance research, genome editing safety and in modernization of information technology for operational efficiency in their regulatory work.


Education

The American Association of Veterinary Medical Colleges (AAVMC) developed a Competency-Based Veterinary Education (CBVE) framework to define the core competencies that a graduating veterinarian would need on day one of entering practice[24]. These have been utilized to plan and develop veterinary school curriculums and for evaluation and accreditation of veterinary schools. Until recently, veterinary students had minimal education or exposure to health informatics beyond entering notes into the PIMS during their clinical rotations. As health information technology has become increasingly pervasive in clinical practice, there is a need to prepare future veterinarians to utilize these technologies wisely and effectively. In 2021, a Core Competencies Framework in Health informatics was created to augment the existing core competency framework[25].

Eight core competency statements were identified as follows:

  1. “The graduate actively seeks engagement and leadership within emerging technology in the non-veterinary animal health market.
  2. The graduate advocates for effective use of current communication technology while respecting the privacy and regulatory implications on quality medical practice.
  3. The graduate advocates for the use of technology and innovation to facilitate quality practice management and improve work-life balance.
  4. The graduate seeks opportunities to further their knowledge in data management, informatics, and communication technology.
  5. The graduate selects appropriate communication technologies and manages their virtual footprint in a way that reflects well on the profession The graduate navigates online controversies involving veterinary medicine in a professional manner and supports wellness of the profession,
  6. The graduate uses medical and production software systems and maintains records in a format that allows analysis and sharing.
  7. The graduate utilizes technology to advance the surveillance and management of public health risks.
  8. The new graduate utilizes data within an evidence-based process to better promote animal health and welfare.”

(Ouyang et al. 2021, p. 6)

In response to this rapidly changing landscape, many veterinary schools have hired faculty in the field of veterinary informatics, support research involving informatics, and have added curriculum specific to the topic.


Associations and Conferences (North America):

Opportunities for continuing education in clinical health informatics are available that are specific to the veterinary field.

  • The Association for Veterinary Informatics (AVI) was founded in 1981[1]. The AVI is a non-profit organization of people involved in biomedical informatics within veterinary medicine.
  • The Talbot Symposium, sponsored by the AVI, provides the opportunity for researchers and industry alike to share new innovations in the field of veterinary informatics[26].
  • The annual Symposium on Artificial intelligence in VeterinarY medicine (SAVY) hosted by Cornell University, College of Veterinary Medicine, held its inaugural session in April 2024. This symposium focuses on bridging the gap between academic theory and practical application in the field of artificial intelligence in the context of veterinary medicine[27].
  • The Veterinary Innovation Summit is an exploration of a variety of emerging innovations and technologies in veterinary medicine[28]. The summit is held annually in St, Louis, MO. Artificial intelligence and other informatics topics are frequently highlighted at the summit.


References:

  1. ↑ 1.0 1.1 Association for Veterinary Informatics. Accessed online April 26, 2025 at [1]
  2. ↑ 2.0 2.1 2.2 2.3 Lustgarten JL, Zehnder A, Shipman W, Gancher E, Webb TL. Veterinary informatics: forging the future between veterinary medicine, human medicine, and One Health initiatives - a joint paper by the Association for Veterinary Informatics (AVI) and the CSTA One Health Alliance (COHA). JAMIA Open 2020; 3(2): 306-307. [2]
  3. ↑ The NHGRI Dog Genome Project. Accessed online April 25, 2025 at [3]
  4. ↑ Albergante L, O’Flynn C, De Meyer G. Artificial intelligence is beginning to create value for selected small animal veterinary applications while remaining immature for others. J Am Vet Med Assoc. March 2025; 263(3):388-394. [4]
  5. ↑ Meredith T. Practice software and technology, part 1. Today’s Veterinary Practice November/December 2014: 57-61. [5]
  6. ↑ Meredith T. Practice software and technology, part 2. Today's Veterinary Practice January/February 2015. Accessed online April 25, 2025 at [6]
  7. ↑ Krone LM, Brown CM, Lindenmayer JM. Survey of electronic veterinary medical record adoption and use by independent small animal veterinary medical practices in Massachusetts. J Am Vet Med Assoc 2014; 245 (3): 324-332. [7]
  8. ↑ 8.0 8.1 8.2 Appleby RB, Basran PS. Artificial intelligence in veterinary medicine. J Am Vet Med Assoc 2022; 260(8): 1-6. [8]
  9. ↑ 9.0 9.1 9.2 9.3 Danylenko G. A guide to AI tools for veterinary medicine. Full Slice. Accessed online April 28, 2025 at https://fullslice.agency/blog/a-guide-to-ai-tools-for-veterinary-medicine/
  10. ↑ Antech Diagnostics Press Release. New AI-driven diagnostic tool can predict chronic kidney disease in cats two years before onset. October 1, 2020. Accessed online April 28, 2025 at [9]
  11. ↑ IDEXX Reference Laboratories, Inc. IDEXX DecisionIQ makes the connections. You make the call. December 2021. Accessed online April 28, 2025 at [10]
  12. ↑ Schofield I, Brodbelt DC, Niessen SJM, et al. Development and internal validation of a prediction tool to aid the diagnosis of Cushing’s syndrome in dogs attending primary-care practice. J Vet Intern Med. 2020;34(6):2306–2318. [11]
  13. ↑ Fraser MA, McNeil PE, Girling SJ. Prediction of future development of canine atopic dermatitis based on examination of clinical history. J Small Anim Pract. 2008;49(3):128–132. [12]
  14. ↑ Flegel T, Neumann A, Holst AL, et al. Machine learning algorithms predict canine structural epilepsy with high accuracy. Front Vet Sci. 2024;11:1406107. [13]
  15. ↑ Reynolds CA, Brown DC, Rush JE, et al. Prediction of first onset of congestive heart failure in dogs with degenerative mitral valve disease: the PREDICT cohort study. J Vet Cardiol. 2012;14(1):193–202. [14]
  16. ↑ 16.0 16.1 IDEXX Reference Laboratories, Inc. Press Release. Latest IDEXX innovations designed to enhance patient care and drive veterinary productivity. January 17, 2020. Accessed online April 28, 2025 at [15]
  17. ↑ Antech Diagnostics Press Release. Antech’s breakthrough AI powered radiology and targeted cancer screening tools now available, unleashing new chapter for veterinary diagnostics. April 11, 2024. Accessed online April 28, 2025 at [16]
  18. ↑ SignalPet. Instant point-of-care radiology results. Accessed online April 28, 2025 at [17]
  19. ↑ IDEXX Reference Laboratories, Inc. Press Release. IDEXX announces revolutionary slide-free cellular analyzer, IDEXX inVue Dx™ transforming in-clinic workflows. January 12, 2024. Accessed online April 28, 2025 at [18]
  20. ↑ Jokar M, Abdous A, Rahmanian V. AI chatbots in pet health care: Opportunities and challenges for owners. Vet Med Sci. May 2024;10(3):e1464.[19]
  21. ↑ American Association of Veterinary State Boards. Regulatory considerations of the use of artificial intelligence in veterinary medicine. AAVSB Position Statement. March 2025.
  22. ↑ Bellamy JEC. Artificial intelligence in veterinary medicine requires regulation. The Canadian Veterinary Journal. 2023; 64(10): 968-970. [20]
  23. ↑ Duggirala HJ, Johnson JL, Tadesse DA, et al. Artificial intelligence and machine learning in veterinary medicine: a regulatory perspective on current initiatives and future prospects. Am J Vet Res March 2025; 86(S1): S16-S21. [21]
  24. ↑ Molgaard LK, Hodgson JK, Bok HGJ, Chaney KP, Ilkiw JE, Matthew SM, et al. Competency-Based Veterinary Education: Part 1-CBVE Framework. Washington DC: Association of American Veterinary Medical Colleges (2018). Accessed online April 26, 2025 at: [22]
  25. ↑ Ouyang ZB, Hodgson JL, Robson E, et al. Day-1 competencies for veterinarians specific to health informatics. Front Vet Sci 2021; 8;651238. [23]
  26. ↑ Association of Veterinary Informatics. The Annual Talbot Veterinary Informatics Symposium. Accessed online April 28, 2025 at [24]
  27. ↑ Cornell University College of Veterinary Medicine. Symposium of Artificial Intelligence in Veterinary Medicine (SAVY 2.0) Accessed online April 28, 2025 at [25]
  28. ↑ Veterinary Innovation Council. Innovation, Collaboration, Transformation. Accessed online April 28, 2025 at [26]


Submitted by M. Alexis Seguin

Retrieved from "https://clinfowiki.org/wiki/index.php?title=Veterinary_Medical_Informatics&oldid=33813"