Pain is a multidimensional experience involving far more than mere sensation [1]. It has primarily two domains: the sensory aspect (intensity, location and duration) and the affective-motivational (emotional and unpleasantness). Its assessment in cats has been investigated using a variety of methods, such as behavioural and physiological scales, provoked tests or natural observations,[2–4] in a range of clinical contexts such as following different surgical procedures or in relation to orthopaedic disease, etc. [5] Interest in this subject is not only important from an academic perspective, but also and perhaps primarily for its practical value to veterinarians and owners who need to recognise the signs of pain in this species in order to reduce suffering [6].

To assess pain, a tool based on natural observation seems preferable to minimise suffering, although interacting with the painful animal can be important when detecting pain (e.g. palpating the affected area) [7]. Observation of behaviour is a non-invasive and effective way by which pain can be easily investigated by different people [8], in different contexts (e.g. at home, or in the clinic) with none of the risks (for either the cat or observer) implicit from closer interaction. There is a need for a well-validated cat pain behavioural assessment tool that could be potentially used by both veterinary experts and owners/caregivers.

Even though individuals vary in the features they attend to when assessing pain such as which behavioural features they consider most important [9], or the ability to use specific methods, such as diagnostic tests, both owners and veterinarians are clearly able to recognise many relevant changes in cats related to pain⁴. However, owners may not always recognise the clinical relevance of all the observations that they make [9]. For example, they may view them as an inevitable part of the natural ageing of the animal [10] and not report them to the vet as a concern or at least not until they become quite severe. The ability to recognise behavioural indicators of pain may depend on familiarity with and knowledge of the species by the assessor [11], and may be subjective and biased if objective criteria are not used to define and evaluate these observations [12]. More objective criteria that relate to specific signs of pain might improve the ability of both owners and vets to recognise it. Furthermore, although single behaviours might be suitable for simple presence/absence observations, the use of a combination of behaviours can result in greater accuracy [11].

A recent systematic review [13] of instruments for assessing feline pain concluded that, at present, only one tool (the UNESP-Botucatu) has a reasonable degree of validity and reliability (see [13] for an explanation of these terms), but this was only established within the context of post-ovariohysterectomy. In addition to natural observation, this scale involves behavioural observation after a provoked reaction and the evaluation of physiological parameters [5]. Other feline pain assessment tools are undergoing a validation process [14,15], but until a tool is fully validated, the outputs arising from the use of this tool may only reflect preconceived ideas of what a painful cat may look like.

Even though no tool based on natural observation has been validated, three studies have focused on creating a pool of naturally observable behaviours, which may be a reliable expression of pain in cats [6,16,17]. Both Cloutier et al. [16] and Waran et al. [6] looked at the frequencies of certain behaviours shown by cats when in pain (in a randomised controlled trial with negative control group post-ovariohysterectomy or tenectomy/onychectomy). These authors highlighted that some behaviours, such as crouching or shaking of the forepaws, are expressed more often in “painful” cats than in control subjects. Furthermore, Holden et al. [17] compared pictures of the facial expressions of cats in pain (for a wide range of painful conditions) with a different group of cats not in pain. Analysing the distances between landmarks on the faces, the authors found that cats in pain have a greater distance between the ears and a shorter nose/muzzle distance compared to the control group. However, although picture angles were similar, they were not exactly the same and different subjects were observed for the two conditions (in pain and not in pain). Either or both of these factors might result in morphometric error accounting for the differences observed between the two groups. Other behavioural signs have also been reported in the literature with some evidence to support them (see Merola and Mills [13] for a review and also [18,19]) such as lameness, abnormal gait, difficulty to jump, modification in human-cat interaction, increased or decreased grooming and changes in overall activity, appetite/food intake as well as alteration in the general mood of the subject. As noted previously, these signs need to be clearly and unambiguously defined and may need to be used in combination with both other behaviours and the wider context to be accurate indicators of pain. However, there could be specific behaviours, which are reliable indicators of pain on their own whenever they occur, i.e. they are sufficient for making the inference of pain. However, that is not to say that such signs must occur when an animal is in pain, i.e. they are not necessary signs of it. In the absence of good scientific evidence about the value of specific signs as markers of pain [20,21], there is a danger that their value is based solely on the subjective opinion of the observer [11]. Nonetheless there is a need to establish an initial list of candidate behavioural signs related to pain to be prioritised for future validation. In the absence of definitive objective evidence for any sign, expert opinion and judgment provides a reasonable starting point [22] for identifying the signs which should be prioritised, especially if the opinion of several experts come to the same conclusion.

Therefore, our aim was to collect and classify expert opinion on the possible behavioural signs in cats that denoted pain in general, according to whether they were sufficient (i.e. their presence indicates that the cat is in pain) and/or necessary (i.e. their presence is essential to indicate pain, but not necessarily pathognomonic for pain) signs of either low or high level pain in this species. The severity or intensity of pain in this context is difficult to define or quantify and may be influenced by one’s own experience, but that does not negate the value of identifying where a consensus can be built among veterinary experts. By creating a core set of signs, we lay the foundation for future studies aimed at creating pain scales for cats based on natural observation that minimise subjective bias in the interpretation of each sign. To do this, we listed the behavioural signs of pain highlighted previously in our systematic review of the literature [13] and contacted veterinary experts in different disciplines of feline medicine to ask their opinion about the reliability of these behavioural signs as indicators of pain.

A modified Delphi method (following the guidelines of Hsu and Sandford [23]) was used in order to try to build consensus. This technique uses a series of interactions to adjust the initial opinion of each participant, based on the feedback received from the whole group in order to establish maximal agreement on a topic [24].

The process to develop a consensus around the behavioural expression of pain in cats started in December 2014 and ended in May 2015. The systematic review of behavioural assessment of pain in cats, previously conducted by the authors, was used to provide initial signs (67 behaviours) for consideration [13].

A Delphi method involving veterinary experts in feline medicine was used in this study, in order to create a core collection of signs identified as necessary and/or sufficient for pain assessment in cats. Different specialisms were involved in order to create a wide overview of painful phenomena. Although the use of a variety of veterinary specialists (working with cats daily) may have hindered consensus on some signs, the variety increased the likelihood that where there was a consensus that these signs were universal signs of general pain in cats, that can be used by both clinicians and other observers such as owners if adequately defined. It is also worth emphasising that participants had an opportunity to add to the initial list taken from the literature based on their experience with cats in pain. These additional signs were then appraised by the other participants, creating a wider list of behaviours that included signs related to a wide range of conditions.

This consensus building exercise took over 5 months to complete, as we needed to give participants sufficient time to evaluate each sign, recognising their co-commitment to their other professional responsibilities. This evaluation involved them reflecting on the signs in light of their previous experience and knowledge as well as the other participants’ opinion.

A total of 91 signs were collated and assessed in this exercise. Despite the high number of signs and the fact that for each of them 4 different aspects had to be evaluated by participants, a high level of consensus was built since only seventeen behaviours were left with some disagreement in the final Round, with no sign failing to gain consensus on at least one aspect. It might be that the decision to limit consultation to a maximum of 4 Rounds played a role in the failure to reach agreement on some of these seventeen items, since this list included 10 of the 24 signs added by the experts during the first Round and these signs were subject to only 3 Rounds of consultation. However, we needed to define and limit the workload of the experts from the outset in order to maximise the prospects of their engagement with the project.

Only 3 signs were reliably linked to acute pain (panting, pupil dilation and blepharospasm), and no signs were specifically related to chronic conditions (although the majority of participants related blepharospam to acute conditions, one participant suggested it could occur in chronic painful conditions as well, as mentioned in Table 1). On the one hand these results might evidence the possible presence of a common suite of behavioural signs to both acute and chronic conditions, but on the other hand this might highlight the difficulty involved in reliably distinguishing between these two conditions in a clinically meaningful way, as already noted in our systematic review [13]. In fact although three “acute” signs were highlighted, a non-specific description of acute was given (a more recent (acute) or more intense (acute) situation), based on common usage, leaving open the question of the clinical usefulness and reliability of this distinction.

None of the 91 signs was considered necessary to denote pain (i.e. if this sign is absent we cannot consider the subject to be in pain), supporting the idea that evaluation of a suite of behaviours will produce greater accuracy compared to the use of single signs, especially across different contexts [12].

For pain assessment to have validity, any tool based only on behavioural expression should consider both the sensorial and affective domains of pain [13]. The 23 signs considered sufficient to infer pain (i.e. if this sign is present the subject is in pain, but its absence does not exclude the presence of pain), plus the two behaviours (“straining to urinate” and “tail flitching”) considered reliable for pain, (but with disagreement on the intensity of pain being experienced) cover both the sensorial aspects (e.g. signs such as lameness, difficulty in jumping, etc.) and the emotional aspects (e.g. changes in general mood and temperament) of pain. These therefore give a useful starting point for future validation with a view to providing a more comprehensive evaluation of subjects.

The majority of behaviours indicated by the experts as reliable indicators of pain are in accordance with those described in the WSAVA guidelines for the assessment of pain [18], but in our results (unlike the guidelines) they were not specifically linked to acute or chronic conditions. In addition, some signs described in the guidelines were not considered in our study to be reliable signs of pain (e.g. furrowed brow, sitting or lying in abnormal positions). Nevertheless, although agreement was reached, some experts (probably included in the 20% not in agreement) had further comments on these signs, such as the need to know the general behaviour, mood and temperament of the individual subject being evaluated (e.g. increased growling is reliable for pain, but strongly related to the cat’s mood). Other comments highlight that some signs may not be reliable for pain since they may be part of the expression of a specific other problem e.g. neurological condition which is not considered painful. These comments provide useful refinement to the consideration of these signs. The importance of a thorough understanding of mood and temperament in the detection of pain was also highlighted by the responses, because both were included as reliable signs of pain, but they are also linked to the expression of other signs (e.g. growling). It seems that there is potentially great value to be gained by including reference to these aspects in any evaluation. However it is important that any proposed instrument including these aspects is informed by a solid current understanding of the science related to emotional states in non-human animals. Personality, temperament and mood seem to influence the way cats show pain and specific tools to assess these specific traits would be helpful. Additional investigation is also needed to determine the ability of individuals to read the expressions of cats. Although there seems to be generally good agreement, there is evidence to suggest that untrained observers tend to greatly anthropomorphise the emotions of cats, ascribing them overly complex human emotions and motivations [26].

Finally, some signs evidenced by the literature as related to pain, e.g. by Cloutier et al. [16] (shaking feet and crouching behaviour identified in cats after tenectomy/onychectomy), were not considered by participants to be reliable signs for pain in general. They were in fact, considered to be an expression of other clinical conditions and not specific to pain, although crouching was reported to be associated with a high level of pain, when it was related to this problem. This last point emphasizes the importance of considering first the context and then intensity when assessing pain; because, although in certain conditions (e.g. after tenectomy/onychectomy) these behaviours may be expressed more frequently by subjects in pain; it seems, based on our results, that these signs are not generalizable to unspecified clinical contexts. This, once again, cautions against the use of a specific sign to denote pain in general for cats.

Given that our aim was to highlight the sufficient signs of pain that can be observed non-intrusively in cats with the ultimate goal of creating and validating a behavioural assessment tool for this species that could be useful in a range of painful conditions, the signs found in our results seem to be a good starting point, and may be of wider value not only to clinicians trying to assess pain in cats but also to owners trying to determine if their cat is in need of veterinary attention. However, further studies are necessary to evidence their validity when assessing pain in cats provoked by different conditions, and also to evaluate their reliability when used by untrained observers (e.g. owners).

Twenty-five behavioural signs were considered by experts to be reliable and sensitive for the assessment of pain in cats, across a range of different clinical conditions. Some of these signs have been highlighted in previous scientific literature, but some arose from the experience and knowledge of experts. These results improve our knowledge of this topic, but further studies are necessary in order to evaluate their validity and clinical feasibility (especially in relation to different intensities of pain) to help vets and caregivers of cats recognize pain in this species effectively and as early as possible to maximise cat welfare.

List of 67 behaviours proposed at the Round 1

List of 24 behaviours added at the Round 2