Lameness remains a significant welfare and productivity challenge in dairy farming, often underdiagnosed due to the limitations of conventional detection methods. Unlike most previous approaches to lameness detection that rely on a single-sensor or gait-based measurement, this study integrates four complementary data domains—behavioural, physiological, biochemical, and milk composition parameters—collected from 272 dairy cows during early lactation to enhance diagnostic accuracy and biological interpretability. The main objective of this study was to evaluate and compare the diagnostic classification performance of multiple machine learning (ML) algorithms trained on multimodal data collected at the time of clinical lameness diagnosis during early lactation, and to identify the most influential physiological and biochemical traits contributing to classification accuracy. Specifically, six algorithms—random forest (RF), neural network (NN), Ensemble, support vector machine (SVM), k-nearest neighbors (KNN), and logistic regression (LR)—were assessed. The input dataset integrated physiological parameters (e.g., water intake, body temperature), behavioural indicators (rumination time, activity), blood biochemical biomarkers (non-esterified fatty acids (NEFA), aspartate aminotransferase (AST), lactate dehydrogenase (LDH), gamma-glutamyl transferase (GGT)), and milk quality traits (fat, protein, lactose, temperature). Among all models, RF achieved the highest validation accuracy (97.04%), perfect validation specificity (100%), and the highest normalized Matthews correlation coefficient (nMCC = 0.94), as determined through Monte Carlo cross-validation on independent validation sets. Lame cows showed significantly elevated NEFA and body temperatures, reflecting enhanced lipid mobilization and inflammatory stress, alongside reduced water intake, milk protein, and lactose content, indicative of systemic energy imbalance and impaired mammary function. These physiological and biochemical deviations emphasize the multifactorial nature of lameness. Linear models like LR underperformed, likely due to their inability to capture the non-linear and interactive relationships among physiological, biochemical, and milk composition features, which were better represented by tree-based and neural models. Overall, the study demonstrates that combining sensor data with blood biomarkers and milk traits using advanced ML models provides a powerful, objective tool for the clinical classification of lameness, offering practical applications for precision livestock management by supporting early, data-driven decision-making to improve welfare and productivity on dairy farms.

Epilepsy is one of the most common chronic neurological disorders in dogs, characterized by recurrent, unprovoked seizures. Epileptic seizures are typically classified as single generalized (SG), cluster seizures (CS), or status epilepticus (SE), with CS and SE representing neurological emergencies linked to high morbidity and mortality. This retrospective study analyzed 254 canine epilepsy cases from two veterinary clinics in Finland and Lithuania, aiming to evaluate the frequency and clinical associations of CS and SE. Patient data included age of seizure onset, sex, weight, neuter status, blood test results, clinical and neurological examinations, magnetic resonance imaging (MRI) findings, etiology classification and clinical outcome. Seizure type distribution was as follows: CS in 47.2%, SG in 26.8%, and SE in 26.0% of cases. SG seizures were significantly more common than CS in dogs aged 6–72 months (54.4% vs. 38.3%, p = 0.005), and more frequent in first-time cases compared to previously treated ones (p = 0.005). SE was significantly associated with inflammatory brain disease, abnormal clinical and neurological findings, and a higher rate of euthanasia (29.2%, p < 0.05). Dogs with structural epilepsy were older (median 108 months) and more likely to develop SE (35.5%). Most cases initially presented as SG (58.1%), but 44.5% progressed to CS and 24.6% to SE. MRI revealed lesions in 46.5% of cases, with SE more frequent in dogs with inflammatory changes and SG predominating in neoplastic cases. No significant associations were found between seizure type and sex, reproductive status, or body weight. These findings provide new insights into seizure presentation, progression, and underlying pathology, supporting the importance of early diagnosis and individualized clinical management in canine epilepsy.

Oxidative stress (OS) is caused by an imbalance between the production of oxygen-containing free radicals and their elimination. General anesthesia increases the production of reactive oxygen species (ROS) and therefore causes oxidative stress. Our objective was to determine the effects of medetomidine–butorphanol (MEDBUT) and medetomidine–buprenorphine (MEDBUP) on oxidative stress and cardiorespiratory parameters in dogs undergoing ovariohysterectomy (OHE). Ten healthy female dogs were randomly assigned to two groups: the MEDBUT group (n = 5) received medetomidine and butorphanol, while the MEDBUP group (n = 5) received medetomidine and buprenorphine. OS was evaluated by measuring total antioxidant status (TAS), total oxidant status (TOS), and oxidative stress index (OSI) during five different time points (from the administration of anesthetic drugs to 2 h after surgery). The observed vital cardiorespiratory parameters included heart rate (HR), respiratory rate (fR), noninvasive systolic (SAP) and diastolic (DAP) arterial blood pressures, oxygen saturation (SpO₂), end-tidal CO₂ (EtCO₂), and body temperature (BT). Cardiorespiratory parameters were altered at a significantly greater degree in animals sedated with MEDBUT (p < 0.05). The administration of medetomidine–butorphanol was more likely to increase OS parameters, while medetomidine–buprenorphine showed decreased levels of oxidative stress throughout the study.

Epilepsy is a common neurological disorder in cats, but its seizure types, etiologies, and clinical associations remain incompletely characterized compared to dogs. This retrospective study analyzed 118 feline epilepsy cases from two veterinary hospitals in Finland and Lithuania, aiming to evaluate the distribution of seizure types and their associations with demographic, clinical, neurological, diagnostic, and diagnostic test results. Seizures were classified as single generalized (SG), cluster seizures (CS), or status epilepticus (SE). SG and CS occurred with nearly equal frequency (44.9% and 45.8%, respectively), while SE was less common (9.3%). Median age at presentation was 72 months, and no significant differences were found in age, sex, reproductive status, or body weight between seizure types. Abnormal clinical findings (p = 0.009) and neurological abnormalities (p < 0.001) were significantly more frequent in cats with SE, indicating greater neurological compromise in severe seizure forms. MRI was performed in 74.6% of cases and revealed a significant difference in utilization among seizure types (p = 0.004), with lower imaging rates in SE, likely reflecting clinical instability at presentation. Etiology of seizure development was established in 89 cats: idiopathic epilepsy (IE) predominated (80.9%), followed by structural (15.7%) and metabolic/toxic (3.4%) causes. Seizure type and etiology were significantly associated (p = 0.006), with structural epilepsy most common in SE and idiopathic epilepsy prevailing in SG and CS. Among cats with known outcomes (n = 35), seizure control was achieved in 68.6%, while mortality and euthanasia were higher in SE. These findings provide new insight into feline epilepsy by linking seizure type to clinical and etiological profiles, emphasizing that severe presentations are more often associated with neurological abnormalities and structural causes, whereas demographic factors alone do not predict seizure severity.

The main distinction between open and laparoscopic ovariectomy (OVE) is pneumoperitoneum (PNP) and anesthesia management. The objective of this study was to evaluate the effect of laparoscopic and open OVE on plasma cortisol, oxidative stress (OS), and cardiorespiratory parameters in dogs under the same anesthesia protocol. Twenty healthy female dogs were assigned to laparotomy OVE (LPTOVE, n = 10) and laparoscopic OVE (LAPOVE, n = 10) groups. OS was assessed using the total oxidant status (TOS), total antioxidant status (TAS), and oxidative stress index (OSI). Blood samples were collected prior to sedation (T0); prior to surgical incision (T1); prior to surgical closure in the LPTOVE group; and prior to the deflation of CO₂ in the LAPOVE group (T2), 2 h after the surgery (T3). The monitored cardiorespiratory parameters were heart rate, respiratory rate, and end-tidal CO₂ (EtCO₂). Cortisol levels at T3 were markedly elevated in the LPTOVE group compared to the LAPOVE group. No substantial changes in TOS, TAS, or OSI between groups were detected. In the LAPOVE group, TOS diminished at T2, but TAS declined and OSI escalated at T3. EtCO₂ levels were elevated in the LAPOVE group at the end of the procedure. These findings support laparoscopic OVE as a less traumatic alternative to open surgery, with careful management of PNP and anesthesia recommended to minimize postoperative stress.

A key distinction between open and laparoscopic surgery is the use of CO₂ insufflation to create pneumoperitoneum and establish the operative field. This study compared the effects of laparoscopic and open ovariectomy (OVE) on plasma cortisol, oxidative stress (OS), systemic inflammation, and systemic CO₂ dynamics in healthy dogs anesthetized under a standardized protocol. Thirty-eight healthy female dogs were enrolled in the study and allocated to the laparotomy (LPTOVE, n = 19) or laparoscopic (LAPOVE, n = 19) OVE group. OS was assessed using total oxidant status (TOS), total antioxidant status (TAS), and oxidative stress index (OSI). Systemic inflammation was evaluated by TNF-α and IL-6 concentrations, whereas systemic CO₂ dynamics were assessed using plasma total CO₂ (TCO₂) and end-tidal CO₂ (EtCO₂). Blood samples were collected prior to sedation (T0), prior to surgical incision (T1), prior to surgical closure in the LPTOVE group or CO₂ desufflation in the LAPOVE group (T2), and 2 h postoperatively (T3). Cortisol concentrations at T2 and T3 were significantly higher in the LPTOVE group than in the LAPOVE group. No significant intergroup differences were observed in TOS, TAS, OSI, or TCO₂. In the LPTOVE group, TOS significantly decreased at T3, whereas in the LAPOVE group, TOS mildly increased at T1 and OSI significantly decreased at T2. No measurable TNF-α or IL-6 concentrations were detected at the evaluated time points. EtCO₂ levels were higher in the LAPOVE group at the end of surgery. These findings suggest that laparoscopic OVE was associated with lower perioperative cortisol concentrations, while systemic redox status, TNF-α and IL-6 concentrations, and carbon dioxide-related parameters remained largely comparable between surgical approaches.