A non-invasive method to analyze spontaneous blink using high-speed camera and machine learning approach

Status

Recruiting

Phases

Phase 1Phase 2

Study type

Observational

Source

TCTR

Registry ID

TCTR20190817003

Enrollment

Unknown

Registered

2019-08-17

Start date

2019-08-22

Completion date

Unknown

Last updated

2026-08-03

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Normal healthy volunteers Dry eye syndrome Facial Paralysis Blepharospasm Parkinson&#39

Interventions

90 subjects without eye diseases that affect blinks 1.1) Age 18&#45

39 y&#44

30 subjects 1.2) Age 40&#45

59 y&#44

30 subjects 1.3) Age 60&#45

80 y&#44

30 subjects,e.g. Parkinson&#39

s disease&#44

blepharospasm 30 subjects,30 subjects with clinical diagnosis of facial paralysis,30 subjects with clinical diagnosis of dry eyes

Other,Other,Other,Other

Normal healthy volunteers,Other neurological disorders that affect blink,Facial Paralysis,Dry eye syndrome

Eligibility

Sex/Gender

All

Age

18 Years to 80 Years

Inclusion criteria

Inclusion criteria: Normal healthy volunteers (90) Dry eye syndrome (30) Facial Paralysis (30) Other neurologic disorders that affect blink (30)

Exclusion criteria

Exclusion criteria: Prior eyelid surgery Prior eyelid trauma Vision worse than 20/200 Inconclusive clinical diagnosis

Design outcomes

Primary

Measure	Time frame
Spontaneous blink At the time of measurement à¸ºBlink rate per minute, blink speed, amplitude/ High-speed camera and machine learning,Mahidol Blink Analyzer 3 years N/A	—

Secondary

Measure	Time frame
Accuracy and Validity of Mahidol Blink Analyzer 3 years N/A	—

Countries

Thailand

Contacts

Public ContactPimkwan Jaru-ampornpan

Faculty of Medicine Siriraj Hospital, Mahidol University

pimkwan.jar@mahidol.edu0944199164

Outcome results

None listed

Source: TCTR (via WHO ICTRP) · Data processed: Aug 9, 2026

A non&#45;invasive method to analyze spontaneous blink using high&#45;speed camera and machine learning approach