Corneal Opacity in the United States: An American Academy of Ophthalmology IRIS® Registry (Intelligent Research in Sight) Study.

PURPOSE: Vision loss associated with opacification of the cornea is one of the leading causes of blindness globally. However, the epidemiological data pertaining to the demographics, associated etiological causes and reduced vision in corneal opacity patients continue to be sparse. This study assesses the case frequencies, underlying etiologies, and vision outcomes in patients diagnosed with corneal opacity, in the United States. DESIGN: Retrospective cohort study PARTICIPANTS: Patients in the IRIS® Registry (Intelligent Research in Sight) who were diagnosed with corneal opacity between January 1st, 2013, and November 30th, 2020. METHODS: The IRIS Registry contains demographic and clinical data of 79,887,324 patients who presented to eye clinics during the study period. We identified patients with corneal opacity using International Classification of Disease (ICD) codes (ICD-9, and -10) of "371" (corneal scar) and "H17" (corneal opacity), respectively. The analyzed data included demographic parameters included age, sex, race, ethnicity, and geographical location. We evaluated clinical data including laterality, etiology, disease descriptors, and best-corrected visual acuity (VA) up to 1 year before the onset (± 30 days), at the time of diagnosis, and at one year following diagnosis (± 30 days). MAIN OUTCOME MEASURES: Case frequencies, etiology, and vision outcomes in patients diagnosed with corneal opacity. RESULTS: We identified 5,220,382 patients who were diagnosed with corneal opacity and scars using H17 (ICD-10) and 371.0 (ICD-9) codes over seven years. The case frequency of corneal opacity during the study period was 6,535 cases per 100,000 patients (6.5%). The mean age of the patients was 63.36±18.14 years and the majority were female (57.6%). In the cohort, 38.39% and 30.00% of patients had bilateral and unilateral corneal opacity, respectively. Most of the patients were White (69.13%), followed by Black or African American (6.84%), Asian (2.45%), American Indian or Alaska Native(0.34%), Native Hawaii or other Pacific Islander(0.19%). Among the patients with corneal opacity, 7.34% had Hispanic or Latino ethnicity. The primary etiologies associated with corneal opacity included corneal dystrophies (64.66%) followed by edema (18.25%), ulcer (7.78%), keratoconjunctivitis (7.18%), degeneration (5.62%), neovascularization (6.27%), and trauma (5.28%). Visual acuity of the patients significantly worsened due to corneal opacity (0.46±0.74 logMAR; ∼20/58 in Snellen) and did not improve to the baseline (0.37±0.68 logMAR, ∼20/46 in Snellen) post-management (0.43±0.77 logMAR, ∼20/54 in Snellen). The multiple linear regression analysis showed worse vision outcomes in females (compared to males), and Asian, Black or African American, and American Indian or Alaska Native (compared to White) patients. Additionally, worse vision outcomes were observed in patients with opacity associated with corneal malformation, degenerative disorders, edema, injury, and ulcer compared to those with hereditary corneal dystrophy. CONCLUSIONS: Our study shows that the corneal opacity was diagnosed in 6.5% of the patients in the IRIS Registry and it was primarily associated with corneal dystrophies. The final vision outcomes in corneal opacity patients were significantly worse compared to baseline. The worse vision outcomes were associated with sociodemographic differences that might be associated with disparities in access, utilization, and care patterns.

A two-stream deep model for automated ICD-9 code prediction in an intensive care unit.

Assigning medical codes for patients is essential for healthcare organizations, not only for billing purposes but also for maintaining accurate records of patients' medical histories and analyzing the outputs of certain procedures. Due to the abundance of disease codes, it can be laborious and time-consuming for medical specialists to manually assign these codes to each procedure. To address this problem, we discuss the automatic prediction of ICD-9 codes, the most popular and widely accepted system of medical coding. We introduce a two-stream deep learning framework specifically designed to analyze multi-modal data. This framework is applied to the extensive and publicly available MIMIC-III dataset, enabling us to leverage both numerical and text-based data for improved ICD-9 code prediction. Our system uses text representation models to understand the text-based medical records; the Gated Recurrent Unit (GRU) to model the numerical health records; and fuses these two streams to automatically predict the ICD-9 codes used in the intensive care unit. We discuss the preprocessing and classification methods and demonstrate that our proposed two-stream model outperforms other state-of-the-art studies in the literature.

Excimer laser phototherapeutic keratectomy in conjunction with mitomycin C in corneal macular and granular dystrophies / Ceratectomia fototerapêutica com excimer laser em conjunto com mitomicina C em distrofias granular e macular da córnea

ABSTRACT Purpose: To evaluate the visual outcomes, recurrence patterns, safety, and efficacy of excimer laser phototherapeutic keratectomy (PTK) in conjunction with mitomycin C (MMC) for corneal macular and granular diystrophies. Methods: The patients were divided into two groups. Group 1 included patients with macular corneal dystrophy (MCD) that caused superficial corneal plaque opacities, and Group 2 included patients with granular corneal dystrophy (GCD). Patients in both groups were pre-, peri-, and postoperatively evaluated. The groups were compared in terms of uncorrected visual acuity (VA), best spectacle-corrected VA, presence of mild or significant recurrence, and time of recurrence. Results: Eighteen eyes (nine with MCD and nine with GCD) of 18 patients (10 men and eight women) were included. PTK was performed for each eye that was included in this study. The mean ablation amount was 117.8 ± 24.4 µm and 83.5 ± 45.7 µm in MCD and GCD, respectively, (p=0.18). The postoperative improvement of the mean VA was similar between the two groups before recurrences (p>0.43) and after recurrences (p>0.71). There were no statistically significant differences in the recurrence rate and the recurrence-free period for any recurrence type. Conclusion: PTK was an effective, safe, and minimally invasive procedure for patients with MCD and GCD. PTK in conjunction with MMC was similarly effective for both groups in terms of recurrence and visual outcomes.

RESUMO Objetivo: Avaliar os resultados visuais, padrões de recorrência, segurança e eficácia da ceratectomia fototerapêutica (PTK) por excimer laser em conjunto com mitomicina C (MMC) em distrofias macular e granular da córnea. Métodos: Os pacientes foram divididos em dois grupos. Grupo 1 incluiu pacientes com distrofia macular de córnea (MCD) que causaram opacidades superficiais corneanas em placa e o grupo 2 incluiu pacientes com distrofia corneana granular (GCD). Todos os pacientes em ambos os grupos foram avaliados no pré, per e pós-operatório. Os grupos foram comparados em termos de acuidade visual (VA) não corrigida, VA melhor corrigida por óculos, presença de recorrência leve ou significativa e o tempo de recorrência. Resultados: Dezoito olhos de 18 pacientes (10 homens e 8 mulheres) foram incluídos no estudo, 9 olhos com MCD e 9 olhos com GCD. Um procedimento de PTK foi realizado em cada olho incluídos neste estudo. A quantidade média de ablação foi 117,8 ± 24,4, 83,5 ± 45,7 µm de MCD e GCD, respectivamente, (p=0,18). A melhora pós-operatória da acuidade visual média foi semelhante entre os dois grupos antes de as recidivas (p>0,43) e após as recidivas (p>0,71). Não houve diferença estatisticamente significativa na taxa de recorrência ou do período livre de recorrência para qualquer tipo de recorrência. Conclusão: PTK foi um procedimento eficaz, seguro e minimamente invasivo para pacientes MCD e GCD. PTK em conjunto com MMC é igualmente eficaz para ambos os grupos em termos de recorrência e resultados visuais.

Measurement and clinical implications of choroidal thickness in patients with inflammatory bowel disease / Determinação da espessura da coróide suas implicações clínicas em pacientes com doença inflamatória intestinal

ABSTRACTPurpose:Ocular inflammation is a frequent extraintestinal manifestation of inflammatory bowel disease (IBD) and may parallel disease activity. In this study, we evaluated the utility of a choroidal thickness measurement in assessing IBD activity.Methods:A total of 62 eyes of 31 patients with IBD [Crohn's disease (CD), n=10 and ulcerative colitis (UC), n=21] and 104 eyes of 52 healthy blood donors were included in this study. Choroidal thickness was measured using enhanced depth imaging optical coherence tomography. The Crohn's disease activity index (CDAI) and the modified Truelove Witts score were used to assess disease activity in CD and UC, respectively.Results:No significant differences in mean subfoveal, nasal 3000 μm, or temporal 3000 μm choroidal thickness measurements (P>0.05 for all) were observed between IBD patients and healthy controls. Age, smoking, CD site of involvement (ileal and ileocolonic involvement), CDAI, CD activity, and UC endoscopic activity index were all found to be significantly correlated with choroidal thickness by univariate analysis (P<0.05). Smoking (P<0.05) and the CD site of involvement (P<0.01) were the only independent parameters associated with increased choroidal thickness at all measurement locations.Conclusions:Choroidal thickness is not a useful marker of disease activity in patients with IBD but may be an indicator of ileal involvement in patients with CD.

RESUMOObjetivos:Inflamação ocular é uma manifestação extra-intestinal comum de doença inflamatória do intestino (IBD) e pode ser paralela a atividade da doença. Neste estudo, investigamos se a espessura da coroideia pode ser útil para avaliar a atividade da IBD.Método:Um total de 62 olhos de 31 pacientes com IBD [10 com doença de Crohn (CD) e 21 colite ulcerosa (UC)] além de 104 olhos de 52 doadores de sangue saudáveis foram incluídos neste estudo. A espessura da coróide foi medida utilizando-se imagens de tomografia de coerência óptica com profundidade aprimorada. O índice de atividade da doença Crohn (CDAI) e o índice de Truelove Witts modificado foram usados para avaliar atividade da doença em CD e UC, respectivamente.Resultados:Não houve diferença significativa entre os pacientes com IBD e controles saudáveis em termos de medições da espessura da coróide subfoveal média em região 3000 μm nasal e 3000 μm temporal (p>0,05). Com base na análise univariada; idade, tabagismo, local do envolvimento em CD (ileal ou íleo-cecal), CDAI, atividade CD e índice de atividade endoscópica da UC foram significativamente correlacionados com a espessura da coróide (p<0,05). No entanto, fumar (p<0,05) e o local de envolvimento em CD (p<0,01) foram os únicos parâmetros independentes associados com um aumento na espessura da coroideia em todos os pontos de medida.Conclusões:A espessura da coroide não é um marcador útil para refletir a atividade da doença em pacientes com IBD, mas pode ser um indicador de envolvimento ileal em pacientes com CD.