Automated extraction of clinical measures from videos of oculofacial disorders using machine learning: feasibility, validity and reliability.

OBJECTIVES: To determine the feasibility, validity and reliability of automatically extracting clinically meaningful eyelid measurements from consumer-grade videos of individuals with oculofacial disorders. METHODS: A custom computer program was designed to automatically extract clinical measures from consumer-grade videos. This program was applied to publicly available videos of individuals with oculofacial disorders, and age-matched controls. The primary outcomes were margin reflex distance 1 (MRD1) and 2 (MRD2), blink lagophthalmos, and ocular surface area exposure. Test-retest reliability was evaluated using Bland-Altman analysis to compare the agreement in obtained measures between separate videos of the same individual taken within 48 h of each other. RESULTS: MRD1 was reduced in individuals with ptosis versus controls (2.2 mm versus 3.4 mm, p < 0.001), and increased in individuals with facial nerve palsy (FNP) (3.9 mm, p = 0.049) and thyroid eye disease (TED) (4.1 mm; p = 0.038). Blink lagophthalmos was increased in individuals with FNP (3.7 mm); p < 0.001) and those with TED (0.1 mm, p = 0.003) versus controls (0.0 mm). Ocular surface exposure was reduced in individuals with ptosis compared with controls (12.2 mm2 versus 13.1 mm2; p < 0.001) and increased in TED (13.7 mm2; p 0.002). Bland-Altmann analysis demonstrated 95% limits of agreement for video-derived measures: median MRD1: -1.1 to 1.1 mm; median MRD2: -0.9 to 1.0 mm; blink lagophthalmos: -3.5 to 3.7 mm; and average ocular surface area exposure: -1.6 to 1.6 mm2. CONCLUSIONS: The presented program is capable of taking consumer grade videos of patients with oculofacial disease and providing clinically meaningful and reliable eyelid measurements that show promising validity.

Novel use of an autologous scleral button graft to close the anterior defect in evisceration surgery.

PURPOSE: To present an alternative evisceration technique with long-term follow-up data. This technique involves the insertion of an acrylic implant into a modified scleral shell which is closed using an autologous scleral graft. METHODS: This was a retrospective analysis of eviscerations performed in a district-general hospital in the UK. All patients underwent conventional ocular evisceration after total keratectomy. A full thickness scleral graft is harvested from the posterior sclera, using an internal approach, with an 8 mm dermatological punch. An 18-20 mm acrylic implant is placed into the shell, and the scleral graft is used to close the anterior defect. Demographic characteristics, implant size and type, and cosmetic results from pictures of all patients were recorded. All patients were invited for a review to measure motility, eyelid height, patient recorded satisfaction and complications. RESULTS: Of the five patients identified, one had since died. The remaining four attended a review in person. The mean time between surgery and review was 48 months. The mean implant size was 19 mm. There were no cases of implant extrusion or infection. All four had a <1 mm asymmetry in measured eyelid height and ≥5 mm horizontal gaze motility. All patients self-reported "good" cosmesis. An independent assessment identified "mild asymmetry" in two cases and "moderate" in the other two. CONCLUSION: Evisceration with this novel autologous scleral graft technique restores volume in the anterior orbit with good cosmetic results, and with no cases of implant exposure reported in this small case series. This technique should be compared prospectively to established techniques.