Trained dogs can detect the odour of Parkinson's Disease
Rooney, N. J.; Trivedi, D. K.; Sinclair, E.; Walton-Doyle, C.; Silverdale, M.; Barran, P.; Kunath, T.; Morant, S.; Somerville, M.; Smith, J.; Jones-Diette, J. J.; Corish, J.; Milne, J.; Guest, C.
Show abstract
A definitive diagnostic test for PD remains elusive, so identification of potential biomarkers may shed light on methods for diagnosis and facilitate early intervention. Excess sebum secretion and skin pathology are recognised symptoms of early PD. It is likely these result in a unique signature of volatile organic compounds that could be used to identify early stages of disease. Numerous medical conditions produce distinctive odours, and dogs have been trained to detect many of these. A single previous study, suggested that dogs can also be trained to detect Parkinsons Disease. In this study, two dogs were trained to distinguish sebum swabs obtained from drug naive, and medicated Parkinsons patients from swabs from control participants. After 38-53 weeks of training on 205 samples (90 target and 115 control), the dogs were tested in a double-blind trial using 60 control and 40 target samples from drug-naive patients. The dogs both showed high sensitivity (proportion of target samples found 70% and 80%) and specificity (proportion of control samples not alerted to 90% and 98%) of alerting response. This trial supports previous findings that dogs can be trained to reliably detect the odour of PD. We suggest there is a potential for dogs to achieve even higher accuracy with increased exposure and refined training methods and to detect early-stage PD, even prior to diagnosis, as well as hard to diagnose PD cases. Further exploration of the factors which affect dogs sensitivity and specificity and sample features which affect accuracy of discrimination are now required.
Matching journals
The top 3 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Slow Motion Analysis of Repetitive Tapping (SMART) test: measuring bradykinesia in recently diagnosed Parkinson’s disease and idiopathic anosmia 94%
- Voice of the patient: Emergence of new motor and non-motor symptoms in early Parkinsons Disease? 93%
- Quantitative Digitography Solves the Remote Measurement Problem in Parkinson’s disease 93%
Similar papers in this journal
- Amplification parameters of the alpha-synuclein seed amplification assay on CSF predict the clinical subtype of Parkinson's Disease at 10-year follow-up 93%
- Sensitivity to somatomotor conflicts links frontal subcortical dysfunction and minor hallucinations in Parkinson's disease 93%
- Parkinson’s Progression Markers Initiative: A Milestone-Based Strategy to Monitor PD Progression 92%
Similar papers in this journal
- impaired bed mobility in prediagnostic and de novo Parkinson’s disease 93%
- Timely referral for advanced therapy in Parkinson’s disease. Development of a screening tool 93%
- Online unsupervised performance-based cognitive testing: a feasible and reliable approach to scalable cognitive phenotyping of Parkinson’s patients 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.