Glaucoma monitoring,
from home.
Three gaps in glaucoma care.
A quarterly clinic model cannot see what determines outcomes.
Continuous monitoring,
between visits.
Glaucosim is a browser-and-phone layer that runs a longitudinal home cadence of clinically grounded tests, captures medication adherence, and surfaces a trend to the eye-care professional before the next appointment.
- Visual function — VF 24-2, visual acuity, contrast sensitivity
- Anatomy — anterior-segment video, voice-guided
- Pressure — acoustic IOP screen (β, research)
- Patient-reported — NEI VFQ-25, symptom diary
- Adherence — drop diary, reminders, missed-dose log
What already exists.
Most home tools cover one test and depend on dedicated hardware. Glaucosim runs a multi-modality session on the devices the patient already owns.
Continuous IOP needs an implant or a contact lens (Eyemate, Triggerfish). Home perimetry needs a VR headset or a tablet kiosk (Olleyes, Heru, RadiusXR, Imo Vifa). Home anterior-segment imaging needs a clip-on lens. Home tools that ship without dedicated hardware cover a single test — refraction (EyeQue, Easee), VF (MRF, iPad ZEST), or screening (Peek Vision).
Glaucosim is the only point in the top-right quadrant covering visual function + anterior segment + IOP screen (β) + adherence in one home session, on devices the patient already owns. Peek Vision is the closest conceptual peer but is built for community-screening triage, not longitudinal glaucoma monitoring.
Per-measurement precision is lower than instrument-bound counterparts. The trade is an order-of-magnitude increase in sampling cadence, and slope-estimate variance falls as 1/n³ when test occasions are added.5
A home test without integrity
checks is a screenshot of a screen.
How do we run clinical-grade tests remotely, without dedicated devices, and still trust the data?
Is the room within spec?
Visual acuity, contrast and perimetry each assume a different luminance window. A test outside its window is not interpretable.
Is the patient where the test assumes?
Stimulus angle, optotype size, and pixel pitch all depend on the patient-to-screen distance — and on which eye is actually being tested.
Is the patient actually fixating?
Peripheral perimetry assumes central fixation. A 4° saccade away from target makes the stimulus land at the wrong location.
Five models guard every trial.
No additional hardware. No data leaves the device until results are signed and synced.
Screen distance
Iris-pinhole projection from MediaPipe FaceMesh.
Eye cover
EAR + hand-landmark + iris occlusion fusion.
Gaze fixation
Iris-relative-to-canthi, Kalman-filtered.
Ambient light
Calibrated webcam-mean luminance proxy + glare.
Capture quality
Anterior-segment focus, exposure, framing scorer.
Each module reads all five channels before allowing a trial. Out-of-band readings prompt re-positioning or invalidate the affected stimulus. Every event is logged for retrospective audit.
Distance from a single RGB frame.
Principle
We use the interpupillary distance (IPD) as the real-world anchor — the population mean for adults is 63 mm (SD ~3.5 mm).7 MediaPipe FaceMesh returns the two iris-center landmarks (468 left, 473 right). We measure the IPD in pixels and recover patient-to-screen distance from the pinhole projection.
d patient-to-camera (mm) · fpx camera focal length (px), recovered with a one-time on-screen calibration step · IPDpx live pixel distance between iris centers (FaceMesh 468 ↔ 473).
Why IPD and not iris diameter: the iris edge is harder to segment reliably under variable lighting and lashes, while iris centers are detected by MediaPipe with sub-pixel stability and remain visible even when the lid covers part of the limbus.
What we measure to trust it
- Mean absolute error vs ruler-measured distance, 30–100 cm window
- Sample variance across head pose (±20° yaw, ±15° pitch)
- Drop-out rate under low light / glasses / blink frames
- Latency budget < 33 ms / frame (30 Hz)
SIMILAR TRIANGLES · REAL IPD FIXED AT 63 MM · PIXEL IPD INVERTS WITH DISTANCE
Per-trial verification of which eye is occluded.
Principle
Monocular tests assume the operator knows which eye is tested. At home, a left-eye trial labelled as right-eye produces a clean, plausible, incorrect record. Glaucosim verifies cover state from three independent signals — any single one of which is brittle alone.
Open eye ≈ 0.27–0.32; closed eye < 0.15. Threshold calibrated per subject over a 25-frame baseline at session start.8
- EAR — lid aperture from FaceMesh landmarks
- Hand landmarks — overlapping the orbital bounding box
- Iris occlusion — skin or fabric inside iris ROI
What we measure to trust it
- Sensitivity / specificity per channel vs ground-truth video labels
- Mis-occlusion rate (eye reported covered when it isn't)
- Robustness against glasses, dark lashes, sleeves, palms
PER-EYE STATE GATES EVERY STIMULUS · LIVE @ ~30 HZ
Drift outside 4° invalidates the stimulus.
Principle
Perimetry assumes the patient is looking at the central target. If gaze drifts, the stimulus meant to land at 21° lands at 17° or 25°, and the threshold at the labelled location is wrong without the algorithm knowing.
Gaze is computed as iris position relative to the eye corners, in a head-relative frame — so translating the head does not move the vector; only a saccade does. A 1-D Kalman filter is applied to each component, with measurement noise inflated during blinks.
Reads as: the offset of the iris center from the eye's center, normalised by the width of the eye opening.
- ciris — pixel coordinate of the iris center (FaceMesh 468 / 473).
- ccanthi — midpoint between the inner and outer canthus of the same eye (landmarks 33 ↔ 133 left, 263 ↔ 362 right). This is the eye's geometric center in a head-relative frame.
- weye — distance between the same two canthi. Used as the normaliser so g is unitless: head pose, screen distance, and resolution drop out.
After a 30-frame baseline at session start g₀, drift is Δ = g − g₀. Stimuli presented while ‖Δ‖ > 4° are flagged and excluded from the ZEST posterior update. Heijl-Krakau blind-spot catches run in parallel for the standard reliability indices.
What we measure to trust it
- Calibrated gaze accuracy at 9-point grid (mean ± SD in degrees)
- Blink-window rejection sensitivity
- Head-pose invariance across ±20° yaw / ±15° pitch
DRIFTED STIMULI ARE DROPPED FROM THE BAYESIAN POSTERIOR · FL / FP / FN COMPUTED IN PARALLEL
Reject the session if the room is off-spec.
Principle
Visual function thresholds are luminance-dependent. Acuity assumes ISO 8596 background; Pelli-Robson assumes ~85 cd/m²; perimetry assumes a dim room so stimulus contrast reaches operating range.
Glaucosim derives an operational ambient proxy from the webcam: mean greyscale intensity of the central patch, exposure-compensated, calibrated against an on-screen reference step at session start.
⟨Igrey⟩ mean intensity of central patch · ecam camera exposure from MediaStream constraints · k per-device constant from a 5 s on-screen reference.
What we measure to trust it
- Agreement (Pearson r, Bland-Altman) vs a calibrated lux meter
- Per-module operating window pass-through rate
- Off-axis glare detection: variance over the corneal reflection ROI
EACH TEST DEFINES ITS OWN WINDOW · OUT-OF-WINDOW SESSIONS ARE TAGGED ADVISORY OR REJECTED
Anterior segment frames graded in real time.
Principle
A patient's phone records a short anterior-segment clip per take. To be useful for surface review, each frame has to be in focus, well exposed, and framed on the iris. A quality scorer runs over every frame so the patient is guided in real time.
Fvar Laplacian variance (focus) · Ehist exposure flatness · Riris iris coverage from FaceMesh ROI · Mblur motion blur from optical-flow magnitude.
What we measure to trust it
- Frame-level agreement with rater quality grading (κ)
- Take re-do rate vs unguided baseline capture
- Lens-blur, light-flicker, off-axis rejection
Only takes that pass the threshold are kept. The voice avatar tells the patient to come a little closer, hold still, or retake.
ONE FRAME PER EYE · PHONE OR LAPTOP · IMAGES ENCRYPTED AT REST
Visual field 24-2.
ZEST Bayesian thresholding on the 54-location grid · same family as SITA.
- Function — earliest, most actionable damage signal
- Arcuate — RNFL anatomy maps to superior/inferior loss
- Cadence — current 6–12 mo → home enables monthly
- Posterior per location, not a single number
- Stop when SD < 1.5 dB
- Gaze-drifted stimuli are dropped from the update
- 54 locations · 6° spacing · 24-2 grid
- Calibrated display — luminance via Model 04
- Gaze, cover, distance, light gated per trial
- Fixation check via Heijl-Krakau on blind spot
Acoustic IOP.
Contactless pressure screen — laptop emits, phone listens. Research-only signal. Not a replacement for Goldmann.
- Diurnal IOP peaks escape the 6-month clinic window
- Tonometry at home needs an implant or rebound device
- Goal — contactless screen on own devices
- Eye = viscoelastic ball under pressure
- Resonance f* scales with corneal/scleral stiffness
- Iris motion in video is the read-out (no mic)
- Drive — 12→22 Hz chirp · 5 s · laptop or phone speaker
- Capture — MediaPipe iris (468/473) per frame
- Subtract head motion · ICD-normalise
- FFT on aligned iris-displacement trace
Visual acuity exam.
ETDRS / Bailey-Lovie logMAR on a physically calibrated display, at the patient's measured distance.
- Universal baseline — every clinician reads it
- Sanity gate for any session (rules out gross drops)
- Trends tighten interpretation of VF / IOP
- 20/20 letter = 5 arcminutes visual angle
- Patient ≠ 4 m from laptop → resize in real time
- Same angular subtense at any distance
- Pixel pitch from device fingerprint, not the patient
- iPad / iPhone / MacBook / common monitors in internal DB
- Distance from Model 01 · iris cross-check optional
- 2-down-1-up staircase · 0.1 logMAR · 5 reversals
core/calibration.js
Contrast sensitivity exam.
Pelli-Robson, age-normed. Background luminance gated by Model 04 before the run starts.
- CS loss precedes detectable VA loss in early glaucoma
- Correlates with daily-life function better than VA
- Sensitive to drug-induced surface change
- Letter size fixed above acuity → only contrast varies
- Triplets step down 0.15 log units
- 2/3 correct rule per triplet
- Luminance · ambient lux + display gain locked
- Pixel pitch shared with VA pipeline
- Distance from Model 01 — fixed letter size
- Voice + tap input · skip/retry per triplet
Anterior segment exam.
Four graded outputs from a single frame per eye. Phone or laptop — patient picks the device.
- PG side effects (redness, pigmentation, sulcus) develop slowly
- Visit cadence misses onset by months
- Home capture closes loop on tolerability
- 4 grades from one primary-gaze frame per eye
- ROIs anchored to FaceMesh landmarks
- Cheek-as-reference cancels lighting + skin tone
- Phone or laptop · 32 cm ± 10 cm
- 2-sensor gate · distance + luminance
- 3-still burst · Laplacian-variance pick
- FaceMesh must lock or capture rejected
Active-learning loop.
V0 ships day one (classical CV) · V1+ replaces it per grade once labels accumulate · IQ stays deterministic.
Hy = ⟨R/(R+G+B)⟩ vs cheek
PO = arctan((L*−50)/b*) vs cheek
PAP = (Lskin − Lsulcus) / Lskin
- Deterministic · no training data needed
- FaceMesh landmarks + per-pixel color
- Calibrated against published reference photos
- Confidence flagged low until labels validate
- Each review → 3 ordinal labels per take
- Clinician owns the label · patient never sees prediction-as-truth
- The platform IS the labelling tool
- ConvNeXt-Tiny · ImageNet-pretrained
- 3 ordinal heads · CORN loss
- Inputs = frame + (distance, lux, Q) metadata
- Active sampling · low-confidence + disagreement
- V_n replaces V0 per grade above κ threshold
- Eval = weighted κ vs 2-grader consensus
- Predictions never overwrite labels (versioned)
- UCSD-labelled corpus stays UCSD-owned
Vision-related quality of life.
The standard 25-item PRO, voice or tap, on a home cadence rather than annual.
- Objective tests can't measure perceived function
- Anchors what the patient actually cares about
- Cadence shift: annual → 90-day makes trajectory visible
- 25 items → 12 subscales → composite
- Each response rescaled 0–100
- Composite = mean of vision-targeted subscales
- Voice or tap · patient picks per item
- Adaptive branching skips irrelevant items
- ~7 min total · saved offline if unreachable
- 90-day default cadence (vs annual)
Medication adherence,
as a clinical variable.
Reminders, single-tap confirmation, structured missed-dose reason — then overlaid on visual-function trend.
- Self-report at visit overstates adherence ~31%3
- Hidden variable behind every VF / IOP slope
- Goal — adherence as a continuously logged signal
- Reminder at every scheduled dose
- Single-tap confirms
- Missed dose → structured reason (not generic apology)
- Push reminders per regimen (per drop, eye, time)
- Tap window ± 30 min vs scheduled
- Side-effect log piped into the same record
I built Glaucosim because two appointments a year can't catch a disease that damages the optic nerve silently, fiber by fiber, between visits.
References
[1] Olthoff CMG et al. Ophthalmology 2005
[2] Newman-Casey PA et al. Ophthalmology 2015
[3] Friedman DS et al. IOVS 2014
[4] Stagg BC et al. JAMA Ophthalmol 2022
[5] Chauhan BC et al. Br J Ophthalmol 2008
[6] Sakata R et al. Am J Ophthalmol 2021
[7] Caroline P, André M. Contact Lens Spectrum 2002
[8] Soukupová T, Čech J. CVWW 2016 (Eye Aspect Ratio)
[9] Turpin A et al. IOVS 2003 (ZEST validation)
[10] Schulz AM et al. JAMA Ophthalmol 2018 (iPad ZEST)
[11] Heijl A et al. Acta Ophthalmol 1989
[12] Bailey IL, Lovie JE. Am J Optom 1976
[13] Rosser DA et al. Br J Ophthalmol 2003
[14] Pelli DG et al. Clin Vis Sci 1988
[15] Mangione CM et al. Arch Ophthalmol 2001 (NEI VFQ-25)