Automated echocardiographic left ventricular dimension assessment in dogs using artificial intelligence: Development and validation.

BACKGROUND: Artificial intelligence (AI) could improve accuracy and reproducibility of echocardiographic measurements in dogs. HYPOTHESIS: A neural network can be trained to measure echocardiographic left ventricular (LV) linear dimensions in dogs. ANIMALS: Training dataset: 1398 frames from 461 canine echocardiograms from a single specialist center. VALIDATION: 50 additional echocardiograms from the same center. METHODS: Training dataset: a right parasternal 4-chamber long axis frame from each study, labeled by 1 of 18 echocardiographers, marking anterior and posterior points of the septum and free wall. VALIDATION DATASET: End-diastolic and end-systolic frames from 50 studies, annotated twice (blindly) by 13 experts, producing 26 measurements of each site from each frame. The neural network also made these measurements. We quantified its accuracy as the deviation from the expert consensus, using the individual-expert deviation from consensus as context for acceptable variation. The deviation of the AI measurement away from the expert consensus was assessed on each individual frame and compared with the root-mean-square-variation of the individual expert opinions away from that consensus. RESULTS: For the septum in end-diastole, individual expert opinions deviated by 0.12 cm from the consensus, while the AI deviated by 0.11 cm (P = .61). For LVD, the corresponding values were 0.20 cm for experts and 0.13 cm for AI (P = .65); for the free wall, experts 0.20 cm, AI 0.13 cm (P < .01). In end-systole, there were no differences between individual expert and AI performances. CONCLUSIONS AND CLINICAL IMPORTANCE: An artificial intelligence network can be trained to adequately measure linear LV dimensions, with performance indistinguishable from that of experts.

Prophylactic use of a lidocaine constant rate infusion versus saline in dogs undergoing balloon valvuloplasty for management of pulmonic stenosis: A randomized control trial.

OBJECTIVE: To evaluate the effect of a prophylactic lidocaine constant rate infusion (CRI) on the incidence and malignancy of catheter-induced ventricular ectopic complexes (VECs) during balloon valvuloplasty for management of pulmonic stenosis in dogs. STUDY DESIGN: Single-centre, prospective, randomized study. ANIMALS: Client-owned dogs (n = 70) with pulmonic stenosis. METHODS: Dogs were randomly assigned to one of two anaesthetic protocols: administration of lidocaine 2 mg kg-1 bolus followed by a CRI (50 µg kg-1 minute-1; group LD) or a saline placebo (group SL) during balloon valvuloplasty. All dogs were premedicated with methadone (0.3 mg kg-1) intramuscularly and a digital three-lead Holter monitor was applied. Anaesthetic co-induction was performed with administration of alfaxalone (2 mg kg-1) and diazepam (0.4 mg kg-1), and anaesthesia was maintained with isoflurane vaporised in 100% oxygen. CRIs were started on positioning of the dog in theatre and discontinued as the last vascular catheter was removed from the heart. All dogs recovered well and were discharged 24 hours postoperatively. Blinded Holter analysis was performed by an external veterinary cardiologist using commercially available dedicated analysis software; p < 0.05. RESULTS: Of the 70 dogs enrolled in the study, 61 were included in the final analysis: 31 in group LD and 30 in group SL. There was no significant difference between sinus beats (p = 0.227) or VECs (p = 0.519) between groups. In group LD, 19/31 (61.3%) dogs had a maximum ventricular rate ≥250 units and 20/30 (66.7%) dogs in group SL (p = 0.791). CONCLUSION AND CLINICAL RELEVANCE: In this study, the use of a prophylactic lidocaine bolus followed by CRI in dogs undergoing balloon valvuloplasty for management of pulmonic stenosis did not significantly decrease the incidence nor the malignancy of VECs during right heart catheterization compared with a saline CRI.

Anaesthetic management and complications of transvascular patent ductus arteriosus occlusion in dogs.

OBJECTIVE: To retrospectively analyse the anaesthetic management, complications and haemodynamic changes in a cohort of dogs undergoing transvascular patent ductus arteriosus (PDA) occlusion in a tertiary referral centre (from January 2017 to August 2018). STUDY DESIGN: Retrospective study. ANIMALS: A total of 49 client-owned dogs. METHODS: Anaesthetic records of dogs with PDA that underwent transvascular occlusion of the ductus were reviewed. Anaesthetic complications evaluated included tachycardia [heart rate (HR) > 160 beats minute-1], bradycardia (HR < 50 beats minute-1), hypertension [systolic arterial pressure (SAP) > 150 mmHg], hypotension [mean arterial pressure (MAP) < 60 mmHg], hypothermia (<37 °C) and the presence of arrhythmias. Cardiovascular variables [HR and invasive SAP, MAP and diastolic arterial pressure (DAP)] at the time of occlusion device deployment (time 0) were compared with variables at 5 and 10 minutes after deployment. Descriptive statistics, Shapiro-Wilk test and repeated measures analysis of variance followed by a Dunnett's post hoc test were used to analyse the data (p < 0.05). RESULTS: Crossbreed dogs were the most commonly represented followed by the Cavalier King Charles Spaniel. The median age was 8 (2-108) months, and female dogs were over-represented (65.3%). The most common American Society of Anesthesiologists score was III. Mean duration of anaesthesia was 96 ± 26 minutes and mean surgery time was 58 ± 21 minutes. Acepromazine with methadone was the most commonly used premedication combination (77.6%). Propofol was the most common induction agent (73.5%). General anaesthesia was maintained with isoflurane in oxygen in all dogs. Complications included hypotension (63%), hypothermia (34%), bradycardia (28%), arrhythmias (16%), hypertension (16%) and haemorrhage (2%). MAP and DAP increased significantly 10 minutes after device deployment compared with time 0. CONCLUSIONS: and clinical relevance: Hypotension was the most common complication reported in dogs undergoing transvascular PDA occlusion. No major adverse events were documented.