In accordance with the Dipartimento di Science Veterinarie of Università degli Studi di Torino policy, this research does not require the approval of the ethical committee, for the utilization of our assessment tool does not modify the clinical process designed for each patient and rabbits were manipulated for routine diagnostic purposes only. Proper informed consent was collected from the owner prior to each clinical evaluation.

One hundred and sixteen client-owned rabbits admitted to the C.A.N.C. (the exotics and wild animals Veterinary Teaching Hospital of the Veterinary Science DPT. of University of Torino), were considered for inclusion, between the years 2016 and 2018. No restrictions were placed on the breed, sex, age or weight of the rabbits.

Patients were both healthy rabbits admitted for vaccination, checkups or neutering surgery and animals suffering from assorted conditions, such as dental diseases, traumatic injuries, dermatitis, gastric stasis, endoparasites infestation, urinary diseases, and abscesses.

Critically ill patients with respiratory distress syndrome in need of oxygen administration, were excluded from the study in order to avoid further stress to the animals. In some patients, facial expression was not evaluable (e.g. rabbits requiring nasogastric tube or Elizabethan collar), therefore they were excluded from the study as well. Stuporous and comatose states also represented exclusion criteria, considering stupor as a state of lethargy and immobility with diminished responsiveness to stimulation and coma as a deep state of prolonged unconsciousness and unresponsiveness to external stimuli [21].

Pain was always scored at admission, during the patient’s first clinical examination, prior to any potential analgesia administration or surgery. Since clinical examination always happened in the same room, environmental conditions, including noise and light conditions, where similar. When facial action units belonging to the RbtGS were assessed, rabbits were kept in a carrier; the patients were then taken out from the carrier and handled for clinical assessment.

A multidimensional composite pain scale (CANCRS) was developed for rabbits, merging the RbtGS with a Clinical Parameters Scale (CPS), which includes some physiologic parameters (pupil dilation, respiratory rate, respiratory pattern, heart rate) and behavioral responses (response to palpation, mental status and vocalization). The choice of the CPS parameters were based on other pain scales developed for other species of mammals [14,22], bearing in mind that dealing with rabbits allows the clinician to monitor parameters that are less stressful for the patient. Furthermore, respiratory pattern was included, in order to have a more accurate overview of the respiratory response to pain, since polypnea is not pain specific. Finally, pupil dilation can occur in painful situations [23,24].

The RbtGS considers five facial action units (FAU): orbital tightening, cheek flattening, nostril shape, whisker position, and ear position. Each FAU was scored according to whether it was not present (score 0), moderately present (score 1) and obviously present (score 2). Lop eared rabbits’ ear morphology does not permit for evaluation of ear position properly, therefore this parameter was not considered when assessing pain in such breeds.

For the CPS, the scores were given as follow. In response to noxious stimulation, pupillary dilation reflex occurs [24]. No pupillometer was available and raters were asked to make a subjective assessment of whether the rabbits’ pupils were dilated (score 1) or not (score 0).

Since heart rate is extremely variable and difficult to assess in rabbits [7], raters were asked to score percentage increases of the maximum physiological value (250 bpm) [25]. Increases greater than 20% (score 1) and 50% (score 2) were considered, for increases smaller than 20% the score assigned was 0. Heart rate was measured by both raters with a stethoscope for 15 seconds and the result was multiplied by four, in order to obtain beats per minute.

The average respiratory rate for a healthy subject was considered in a values range from 30 to 60 bpm [25]; four possible scores assigned: rates of 60 bpm or less (score 0), rates between 61 and 72 (score 1), rates between 73 and 90 (score 2) and rates higher than 90 bpm (score 3).

Respiratory pattern was considered as eupneic (score 0) or dyspneic (score 1). Dyspnea is associated with a number of pulmonary and cardiac diseases, as well as diseases of the chest wall and anxiety. Respiratory pattern was included to provide a more complete description of the changes which the respiratory rate goes through during pain, as in human medicine, association between pain and dyspnea has been reported [26].

When the suspected painful area was delicately palpated by each rater, the reaction was recorded and classified as no reaction (score 0), reaction during the palpation (score 1) and reaction before the palpation (score 2).

For vocalizations, the possibilities were absence of vocalization (score 0), vocalization when touched (score 1), intermittent vocalization without any contact with the operator (score 2) or continuous vocalization (score 3).

The mental status was classified as ‘normal’ (score 0), ‘depression’ (score 1) and ‘obtundation’ (score 2); the state in which the patient has a reduced interest in the environment, but still responds to external stimuli, was described as ‘depression’; obtundation occurs when responsiveness to visual and auditory stimuli (e.g. hand clapping and fingers snapping) decreases and the patient tends to sleep more than normal with drowsiness in between sleep states [27].

The medical history of the patient was reported on each clinical form in order to establish a presumptive pain (PP) class according to literature [2], since it is plausible that pain is directly proportional to the damage extent, as occurs in humans [2]; No pain (NP), discomfort (D), moderate pain (MP) and severe pain (SP) were the four pain classes created. Table 1 summarizes presumptive levels of pain associated with illness or injuries [2,28] adjusted for rabbit medicine.

Raters were asked to report the time they spent on the evaluation of each rabbit on the printed copy of the scale, in order to establish the average time needed to use the assessment tool. Parameters of the three scales are summarized in Table 2.

Each of the 116 rabbits included in the study was evaluated independently by two raters during the veterinary clinical examination; therefore, the total number of assessments was 232. The raters could be either veterinarians (V) or a veterinarian and a veterinary medicine student (S). Two veterinarians and four students took part in the study.

Raters were familiar with using the scale and provided with a printed copy for each rabbit. To ensure consistency, each rater also received clear instructions on how to use the scale and they were supported by the presence of images explaining how to evaluate the FAU considered by the RbtGS. Rabbits were scored during the first clinical examination and raters were instructed to first fill in the RbtGS part, assessing the rabbit visually from a distance, prior to opening the same carrier in which the rabbit was admitted to the hospital, in order to avoid further stress. Afterwards, raters had to interact with the patient and fill in the second part (CPS) of the scale, which included physiologic and behavioral data.

Each patient was assigned a score for the RbtGS, the CPS and, consequently, for the composite pain scale. Score ranges were adjusted when evaluating Lop eared rabbit, since ear position was not assessable. Pain scores ranged from 0 to 24 for the CANCRS or from 0 to 22 for the Lop eared rabbit version of the CANCRS, from 0 to 14 for the CPS and from 0 to 10 for the RbtGS or from 0 to 8 for the Lop eared rabbit version of the RbtGS. In order to make the comparison between scales possible, for each scale, the scores were divided into four classes: no pain (NP), discomfort (D), moderate pain (MP), severe pain (SP); this allowed comparison with the four classes belonging to the PP (presumptive pain). Score ranges for the aforementioned classes are shown in Table 3.

Raters were asked to measure the time spent on each assessment, in order to define an average time needed to evaluate pain with the CANCRS, verifying if it would fit a clinical environment, where the clinician must identify pain as fast as possible.

The ICC was 0.88 (p ≤ 0.001; 95% CI 0.81–0.92) between veterinarians (V) and students (S) and 0.94 (p ≤ 0.001; 95% CI 0.88–0.97) between V and V for the CANCRS, indicating very good inter-rater reliability.

The ICC was 0.97 (p ≤ 0.001; 95% CI 0.96–0.98) between V and S and 0.91 (p ≤ 0.001; 95% CI 0.83–0.95) between V and V for the CPS, indicating very good inter-rater reliability.

Finally, the ICC was 0.77 (p ≤ 0.001; 95% CI 0.66–0.85) between V and S and 0.88 (p ≤ 0.001; 95% CI 0.78–0.94) between V and V for the RbtGS, indicating good and very good inter-rater reliability respectively.

For the weighted Cohen’s kappa values, moderate agreement was obtained for cheek flattening (0.48; 95% CI 0.25–0.68), nostril shape (0.58; 95% CI 0.39–0.73) and whisker position (0.56; 95% CI 0.32–070). Good agreement was obtained for orbital tightening (0.68; 95% CI 0.43–0.76).

Ear position (0.78; 95% CI 0.68–0.97), pupil dilation (0.87; 95% CI 0.75–0.99), respiratory rate (0.97; 95% CI 0.90–1), respiratory pattern (0.89; 95% CI 0.74–1), heart rate (0.93; 95% CI 0.83–1), response to palpation (0.87; 95% 0.71–1), mental status (0.92; 95% 0.80–1) and vocalization (0.88; 95% CI 0.65–1) had very good inter-rater agreement. Cohen’s kappa coefficients are summarized in Table 4.

The four possible results matched PP classes: No Pain (NP), Discomfort (D), Moderate Pain (MP), and Severe Pain (SP).

The chi-squared test indicated that the CANCRS-scale and the RbtGS scores are distributed as expected according to P (P ≤ 0.05). Patients in a presumptive condition of pain absence (PP = NP) and rabbits in discomfort (PP = D) are mostly classified as NP or D; rabbits in a moderately pain condition (PP = MP) are mostly classified as D. None of the presumed cases of several pain (PP = SP) was detected by the CANCRS, although some cases were detected using the RbtGS. Otherwise, the test indicated that the CPS score frequencies are statistically different from the expected results based on PP (P > 0.05).

Results for each scale are shown in Table 5 and Fig 1 summarizes how the results obtained with the three scales matched PP classes.