You can deploy this model and start earning money today!

julia-pfarr/
HarmoniCA_anxiety

Name: HarmoniCA_anxiety
Availability: InStock

sentence-transformers

safetensors

questionnaire-harmonization

contrastive-learning

anxiety

text-classification

sentence-transformers/gtr-t5-large

finetune

cc-by-4.0

Views

No views yet

HarmoniCA — Anxiety Model

Part of the HarmoniCA collection for harmonising psychiatric questionnaire items across studies. This model assigns items from anxiety questionnaires to one of two theoretically motivated symptom dimensions.

Dimensions

ID	Label	Description
1	Somatic Anxiety	physiological manifestations of anxiety: racing heart, sweating, trembling, shortness of breath, autonomic symptoms
2	Cognitive Anxiety	worry, fear, apprehension, panic, distressing thoughts, anticipation of negative events

Items rated as not belonging to the anxiety construct are assigned dimension -1 (Does not fit).

Model Architecture

Type: ContrastiveModel (contrastive fine-tuning of a sentence transformer)
Base encoder: sentence-transformers/gtr-t5-large

Training Data

Training items: 159 expert-labeled questionnaire items (144 original + 10 augmented + 5 expert-reviewed)
Questionnaires: ASensI, BAI, GAD-7, HADS, HAMA, MDS-UPDRS, NMSQuest, NPI, PAS, PSWQ, SCL-90, SMGAD, STAI, plus data augmentation
Labels: Expert consensus from two rounds of surveys (psychiatrists/neurologists)

Evaluation

Evaluated on 66 held-out items from unseen questionnaires against expert labels.

Cohen's κ	Accuracy
0.877	93.9%

Cross-validation (leave-one-questionnaire-out, 13 folds): mean accuracy 93.7% ± 10.7%.

Limitations

Trained and validated on Parkinson's disease cohort questionnaires; performance may differ in other populations.
Dimension structure reflects theoretical consensus among a specific expert panel and may not match all theoretical frameworks.

Citation

in preparation

julia-pfarr/HarmoniCA_anxiety