Medical-AI trial: classifying parkinsonian syndromes from brain imaging (DaTSCAN SPECT) with machine learning — aiding a hard diagnosis (NCT05080296)

1Parkinson's disease and DaTSCAN

Parkinson disease (PD) is a neurological disease in which loss of dopamine nerves in the brain causes tremor, slowed movement, and stiffness. Diagnosis is made mainly by a clinician observing symptoms, but early disease, and telling PD apart from look-alike atypical parkinsonian syndromes, can be hard.

A useful clue is DaTSCAN, a nuclear-medicine imaging test (SPECT) that visualizes the distribution of dopamine transporters in the brain.

2Can machine learning classify the images

This study evaluates, as an observational study, whether machine learning (ML) applied to DaTSCAN images can classify. Per the registry summary, because PD diagnosis relies mainly on clinical observation and is sometimes challenging, ML is framed as potentially helping early diagnosis and differentiating idiopathic (true) PD from atypical parkinsonian syndromes.

Prior research provided a set of imaging features extracted from DaTSCAN (ioflupane, an iodine-123-labeled radiopharmaceutical) SPECT scans, used to discern healthy participants from those with PD. The primary outcome is algorithm accuracy, and the size is 1,664, at the completed stage.

3From observation to numbers

Parkinson's disease is diagnosed largely by a physician observing symptoms, and distinguishing early disease or closely similar syndromes can be difficult. What this study seeks to change is the material on which that judgement rests.

1. 1Observe the symptomsDiagnose from tremor, slowness of movement and rigidity
2. 2Difficult cases remainEarly disease and atypical parkinsonian syndromes are hard to tell apart
3. 3Image itDaTSCAN visualises the distribution of dopamine transporters in the brain
4. 4Quantify features and classifyMorphological features extracted from the image separate healthy subjects from PD

The primary endpoint is the accuracy of the algorithm, across 1,664 cases, and the study is complete. Distinguishing true PD from atypical syndromes matters clinically because treatment response and outlook differ. The study evaluates algorithm accuracy and does not establish any replacement for imaging diagnosis or specialist judgement.