1.A Case of Oculomotor Nerve Palsy and Choroidal Tuberculous Granuloma Associated with Tuberculous Meningoencephalitis.
Sunghyuk MOON ; Junhyuk SON ; Woohyok CHANG
Korean Journal of Ophthalmology 2008;22(3):201-204
We report a rare case of oculomotor nerve palsy and choroidal tuberculous granuloma associated with tuberculous meningoencephalitis. A 15-year-old male visited our hospital for an acute drop of the left eyelid and diplopia. He has been on anti-tuberculous drugs (isoniazid, rifampin) for 1 year for his tuberculous encephalitis. A neurological examination revealed a conscious clear patient with isolated left oculomotor nerve palsy, which manifested as ptosis, and a fundus examination revealed choroidal tuberculoma. Other anti-tuberculous drugs (pyrazinamide, ethambutol) and a steroid (dexamethasone) were added. After 3 months on this medication, ptosis of the left upper eyelid improved and the choroidal tuberculoma decreasedin size, but a right homonymous visual field defect remained. When a patient with tuberculous meningitis presents with abrupt onset oculomotor nerve palsy, rapid re-diagnosis should be undertaken and proper treatment initiated, because the prognosis is critically dependent on the timing of adequate treatment.
Adolescent
;
Antitubercular Agents/therapeutic use
;
Blepharoptosis/diagnosis/drug therapy/microbiology
;
Choroid Diseases/diagnosis/drug therapy/*microbiology
;
Dexamethasone/therapeutic use
;
Drug Therapy, Combination
;
Ethambutol/therapeutic use
;
Glucocorticoids/therapeutic use
;
Humans
;
Magnetic Resonance Imaging
;
Male
;
Meningoencephalitis/diagnosis/drug therapy/*microbiology
;
Mycobacterium tuberculosis/*isolation & purification
;
Oculomotor Nerve Diseases/diagnosis/drug therapy/*microbiology
;
Perimetry
;
Pyrazinamide/therapeutic use
;
Radiography, Thoracic
;
Tuberculoma/diagnosis/drug therapy/*microbiology
;
Tuberculosis, Meningeal/diagnosis/drug therapy/*microbiology
;
Tuberculosis, Ocular/diagnosis/drug therapy/microbiology
;
Visual Fields
2.Strabismus Screening Using Eyetracker Combined with Machine Learning
Sun Myung SON ; Ju Hyeon KIM ; Sunghyuk MOON
Journal of the Korean Ophthalmological Society 2024;65(10):675-682
Purpose:
To assess the effectiveness of an automated screening program that diagnoses horizontal strabismus using machine learning based on ocular deviation data captured by the wearable eyetracker, Tobii pro glasses 2 (TPG2).
Methods:
The TPG2 which locates the pupil center to measure ocular movement was used. In normal adults wearing TPG2, horizontal ocular deviation was induced by covering the left eye and applying prisms of varying strengths (2, 3, 4, 5, 6, 8, 10, 12, 15, 20, 25, 30, 35, and 40 PD base-in and out) to the right eye. TPG2 automatically recorded ocular deviation before and after prism induction generating 28 types of ocular deviation sets. From each set, 20 X-axis values before and after ocular deviation were randomly extracted using an oversampling technique creating a total of 61,600 ocular deviation sets. For training, 56,000 sets were used and 5,600 were evaluated for sensitivity, specificity, and area under the curve (AUC).
Results:
Eleven normal adults (5 males) participated with a mean age of 34.8 ± 7.37 years. Based on an 8 PD threshold, deviations of 8 PD or less demonstrated a sensitivity of 1.0, a specificity of 0.95, and an AUC of 0.97. When categorized into three groups based on 8 PD and 20 PD thresholds, the results were: sensitivity of 0.90 and specificity of 0.95 for ≤ 8 PD; sensitivity of 0.60 and specificity of 1.00 for 8-20 PD; sensitivity of 1.00 and specificity of 0.88 for > 20 PD.
Conclusions
The machine learning program developed using induced ocular deviations measured with prisms and TPG2 shows promise for use in future strabismus screening tests.
3.Strabismus Screening Using Eyetracker Combined with Machine Learning
Sun Myung SON ; Ju Hyeon KIM ; Sunghyuk MOON
Journal of the Korean Ophthalmological Society 2024;65(10):675-682
Purpose:
To assess the effectiveness of an automated screening program that diagnoses horizontal strabismus using machine learning based on ocular deviation data captured by the wearable eyetracker, Tobii pro glasses 2 (TPG2).
Methods:
The TPG2 which locates the pupil center to measure ocular movement was used. In normal adults wearing TPG2, horizontal ocular deviation was induced by covering the left eye and applying prisms of varying strengths (2, 3, 4, 5, 6, 8, 10, 12, 15, 20, 25, 30, 35, and 40 PD base-in and out) to the right eye. TPG2 automatically recorded ocular deviation before and after prism induction generating 28 types of ocular deviation sets. From each set, 20 X-axis values before and after ocular deviation were randomly extracted using an oversampling technique creating a total of 61,600 ocular deviation sets. For training, 56,000 sets were used and 5,600 were evaluated for sensitivity, specificity, and area under the curve (AUC).
Results:
Eleven normal adults (5 males) participated with a mean age of 34.8 ± 7.37 years. Based on an 8 PD threshold, deviations of 8 PD or less demonstrated a sensitivity of 1.0, a specificity of 0.95, and an AUC of 0.97. When categorized into three groups based on 8 PD and 20 PD thresholds, the results were: sensitivity of 0.90 and specificity of 0.95 for ≤ 8 PD; sensitivity of 0.60 and specificity of 1.00 for 8-20 PD; sensitivity of 1.00 and specificity of 0.88 for > 20 PD.
Conclusions
The machine learning program developed using induced ocular deviations measured with prisms and TPG2 shows promise for use in future strabismus screening tests.
4.Strabismus Screening Using Eyetracker Combined with Machine Learning
Sun Myung SON ; Ju Hyeon KIM ; Sunghyuk MOON
Journal of the Korean Ophthalmological Society 2024;65(10):675-682
Purpose:
To assess the effectiveness of an automated screening program that diagnoses horizontal strabismus using machine learning based on ocular deviation data captured by the wearable eyetracker, Tobii pro glasses 2 (TPG2).
Methods:
The TPG2 which locates the pupil center to measure ocular movement was used. In normal adults wearing TPG2, horizontal ocular deviation was induced by covering the left eye and applying prisms of varying strengths (2, 3, 4, 5, 6, 8, 10, 12, 15, 20, 25, 30, 35, and 40 PD base-in and out) to the right eye. TPG2 automatically recorded ocular deviation before and after prism induction generating 28 types of ocular deviation sets. From each set, 20 X-axis values before and after ocular deviation were randomly extracted using an oversampling technique creating a total of 61,600 ocular deviation sets. For training, 56,000 sets were used and 5,600 were evaluated for sensitivity, specificity, and area under the curve (AUC).
Results:
Eleven normal adults (5 males) participated with a mean age of 34.8 ± 7.37 years. Based on an 8 PD threshold, deviations of 8 PD or less demonstrated a sensitivity of 1.0, a specificity of 0.95, and an AUC of 0.97. When categorized into three groups based on 8 PD and 20 PD thresholds, the results were: sensitivity of 0.90 and specificity of 0.95 for ≤ 8 PD; sensitivity of 0.60 and specificity of 1.00 for 8-20 PD; sensitivity of 1.00 and specificity of 0.88 for > 20 PD.
Conclusions
The machine learning program developed using induced ocular deviations measured with prisms and TPG2 shows promise for use in future strabismus screening tests.
5.Strabismus Screening Using Eyetracker Combined with Machine Learning
Sun Myung SON ; Ju Hyeon KIM ; Sunghyuk MOON
Journal of the Korean Ophthalmological Society 2024;65(10):675-682
Purpose:
To assess the effectiveness of an automated screening program that diagnoses horizontal strabismus using machine learning based on ocular deviation data captured by the wearable eyetracker, Tobii pro glasses 2 (TPG2).
Methods:
The TPG2 which locates the pupil center to measure ocular movement was used. In normal adults wearing TPG2, horizontal ocular deviation was induced by covering the left eye and applying prisms of varying strengths (2, 3, 4, 5, 6, 8, 10, 12, 15, 20, 25, 30, 35, and 40 PD base-in and out) to the right eye. TPG2 automatically recorded ocular deviation before and after prism induction generating 28 types of ocular deviation sets. From each set, 20 X-axis values before and after ocular deviation were randomly extracted using an oversampling technique creating a total of 61,600 ocular deviation sets. For training, 56,000 sets were used and 5,600 were evaluated for sensitivity, specificity, and area under the curve (AUC).
Results:
Eleven normal adults (5 males) participated with a mean age of 34.8 ± 7.37 years. Based on an 8 PD threshold, deviations of 8 PD or less demonstrated a sensitivity of 1.0, a specificity of 0.95, and an AUC of 0.97. When categorized into three groups based on 8 PD and 20 PD thresholds, the results were: sensitivity of 0.90 and specificity of 0.95 for ≤ 8 PD; sensitivity of 0.60 and specificity of 1.00 for 8-20 PD; sensitivity of 1.00 and specificity of 0.88 for > 20 PD.
Conclusions
The machine learning program developed using induced ocular deviations measured with prisms and TPG2 shows promise for use in future strabismus screening tests.
6.Self-assessment of Visual Acuity Using a Smartphone Application
Sejung KIM ; Yuhyun KIM ; Minkyung OH ; Sunghyuk MOON
Journal of the Korean Ophthalmological Society 2024;65(6):378-385
Purpose:
We evaluated the accuracy and usefulness of self-assessment of visual acuity (VA) using a smartphone application for Korean users and explored its potential application in screening eye diseases.
Methods:
In total, 52 participants aged ≥ 20 years were included in the study. Of these participants, 31 used Jin Yong-Han’s VA chart and the smartphone application to measure their distant visual acuity (DVA), whereas 21 used Han Chun-Seok’s near visual acuity chart and the application to measure their near visual acuity (NVA). The results and time required for VA measurement using both methods were compared. VA was converted to logarithm of the minimum angle of resolution (logMAR) for analysis. The voice recognition rate of the application for numbers 2-9 was assessed.
Results:
The mean NVA was 0.29 ± 0.28 using Han’s chart and 0.30 ± 0.43 using the application with no significant difference (p = 1.00). The mean DVA was 0.19 ± 5.89 using Jin's chart and 0.20 ± 0.27 using the application with no significant difference (p = 0.19). The average time spent for measuring NVA and DVA was 19 seconds (s) using Han’s and Jin's charts, whereas it was 42 and 38 s for measuring NVA and DVA using the application. The voice recognition rate of the application was 87% on average for numbers 2-9, with the highest rate for number 7 (79%) and the lowest rate for number 4 (91%).
Conclusions
Self-assessment of VA using a smartphone application exhibited similar results to conventional VA measurement methods. Although the measurement time varied, DVA and NVA could be measured at home using a smartphone, and would be particularly useful for those who have difficulty visiting a hospital.