Training method for animal-based measures in dairy cattle welfare assessments
Bibliographic record
Abstract
Quantitative assessments of animal welfare are increasingly being used in the dairy industry. It is important to have good precision and accuracy within and among assessors. This study explored the effectiveness of a 3-d training workshop for animal-based measures (ABM) of welfare in dairy cows, in which 14 people were trained to evaluate 6 ABM, specifically hock injuries (HI), lameness (LM), body condition score (BCS), and udder, flank, and leg cleanliness (collectively CLN). All scoring systems were modified to a dichotomous outcome, acceptable or unacceptable. Acceptable HI included no swelling or hair loss, unacceptable HI included swelling or scab; acceptable BCS was >2 on a 5-point scale, unacceptable BCS was ≤2. Acceptable CLN was up to minor splashing, unacceptable CLN was distinct plaques to a solid manure plaque. Lameness was evaluated using locomotion score or in-stall lameness score (SLS) in tiestalls; unacceptable LM was ≥3 (lameness score) on a 5-point scale, where 3 equals mild lameness or ≥2 of 4 behavioral in-stall lameness score indicators were detected. Classroom instruction took place on d 1 of training. Day 2 consisted of group assessment of LM (n = 25 cows), and HI, CLN, and BCS (n = 30 cows), and individual assessment of HI, CLN, and BCS (n = 20 cows) were performed. Day 3 included individual assessments of HI, CLN, and BCS (n = 33 cows), and individual video assessment of LM (n = 27 cows). An additional training video for LM was sent to trainees 3 wk after the workshop, and another follow-up assessment of LM took place via video (n = 37 cows). Repeatability and accuracy of the trainees was assessed using Fleiss's κ (FK) and Byrt's κ (BK) to examine group-level inter-rater agreement and expert-trainee agreement, respectively. The kappa systems use a scale of poor (<0), slight (0.01 to 0.20), fair (0.21 to 0.40), moderate (0.41 to 0.61), substantial (0.61 to 0.80), or almost perfect (0.81 to 1.00). At the conclusion of the workshop, FK was 0.66 for HI and 0.43 for LM, and BK mean (and range) was 0.85 (0.63 to 1.00) for HI and 0.66 (0.56 to 0.85) for LM. Each trainee achieved perfect agreement for BCS [BK mean = 1.00 (1.00 to 1.00)] and each trainee achieved almost perfect agreement for CLN [BK mean 0.90 (0.82 to 0.94)]. After the follow-up video and 3 wk of experience, trainees achieved a FK of 0.66 and a BK mean of 0.74 (0.62 to 0.89) for LM. In conclusion, multiple assessors can achieve substantial agreement for ABM with adequate training.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.008 | 0.003 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".