Subject(s)
Eye Infections, Bacterial , Humans , Eye Infections, Bacterial/microbiology , Eye Infections, Bacterial/diagnosis , Prognosis , Cornea/microbiology , Cornea/pathology , Corneal Ulcer/microbiology , Corneal Ulcer/diagnosis , Keratitis/microbiology , Keratitis/diagnosis , Bacteria/isolation & purificationABSTRACT
PURPOSE: We aim to report the natural course of non-center involving diabetic macular edema (NCIDME) progression to center involving diabetic macular edema (CIDME) and associated risk factors. METHODS: This is a multicenter retrospective comparative study. Data was collected from electronic medical records from 8 centers in India covering. We included patients with type 2 diabetes above 18 years of age with treatment-naïve NCIDME on OCT and best-corrected visual acuity at baseline of 6/12 or better who were under observation for NCIDME and had 2 years follow-up data. RESULTS: Out of 72 patients with NCIDME, 26.38% patients progressed to CI DME by 2 years, and the visit wise proportion was 11.11% at 6 months, 7% at 1st year and 8.3% at 2 years. The change in CST was statistically significant at 2 years in patients who developed CIDME, the mean difference was 137.73 ± 48.56 microns p = 0.045. Duration of diabetes mellitus > 10 years was the only risk factor for conversion to CIDME. CONCLUSION: A quarter of eyes with NCIDME developed CIDME and 15% progressed from NPDR to PDR by 2 years, highlighting the disease burden in these patients with NCIDME.
Subject(s)
Diabetes Mellitus, Type 2 , Diabetic Retinopathy , Macular Edema , Humans , Child, Preschool , Macular Edema/diagnosis , Macular Edema/etiology , Macular Edema/drug therapy , Diabetic Retinopathy/complications , Diabetic Retinopathy/diagnosis , Diabetic Retinopathy/epidemiology , Diabetes Mellitus, Type 2/complications , Diabetes Mellitus, Type 2/epidemiology , Retrospective Studies , Tomography, Optical Coherence , Visual Acuity , Intravitreal InjectionsABSTRACT
PURPOSE: To analyze the influence of infiltrate size, depth, and organism on the outcome of microbial keratitis. DESIGN: Retrospective comparative study. METHODS: Medical records of patients with infective keratitis, who reported from January 2015 to December 2019 to a tertiary eye care center, were analyzed. Size and depth of ulcer at presentation were the factors used to group patients, and the influence on the outcome of the organism causing it was analyzed. Grouping was as follows: group A: ulcer size <6 mm/anterior to midstromal infiltrate, group B: ulcer < 6 mm/full-thickness infiltrate, group C: ulcer >6 mm/anterior to midstromal infiltrate, group D: ulcer > 6 mm/full-thickness infiltrate. Patients with viral keratitis or unidentified organism were excluded. Response to treatment and best-corrected visual acuity (BCVA) at the final follow-up were the outcome measures. RESULTS: In the study, 1117/6276 patients were included, with 60.8% patients in group A. A significant improvement in visual acuity was noted in groups A/B compared to groups C/D. Group A had the best response to medical management, irrespective of the organism. Higher risk for surgery was noted in group C compared to group B, with group A as the reference. Overall resolution with medical treatment was noted in 70% miscellaneous keratitis, 64.8% bacterial keratitis, 64.3% mixed keratitis, 62.5% acanthamoeba keratitis, 52.6% fungal keratitis, and 12.1% Pythium keratitis. Bacteria and acanthamoeba responded better to medical management than fungal keratitis, whereas Pythium had the highest risk for surgery. CONCLUSION: An interplay between virulence of the organism along with depth and size of the infiltrate determines the outcome of microbial keratitis.
Subject(s)
Acanthamoeba Keratitis , Corneal Ulcer , Eye Infections, Bacterial , Eye Infections, Fungal , Humans , Ulcer , Retrospective Studies , Corneal Ulcer/diagnosis , Corneal Ulcer/microbiology , Eye Infections, Bacterial/diagnosis , Eye Infections, Bacterial/microbiology , Eye Infections, Fungal/diagnosis , Eye Infections, Fungal/microbiologyABSTRACT
PURPOSE: Chronic kidney disease (CKD) may elevate susceptibility to age-related macular degeneration (AMD) because of shared risk factors, pathogenic mechanisms, and genetic polymorphisms. Given the inconclusive findings in prior studies, we investigated this association using extensive datasets in the Asian Eye Epidemiology Consortium. DESIGN: Cross-sectional study. PARTICIPANTS: Fifty-one thousand two hundred fifty-three participants from 10 distinct population-based Asian studies. METHODS: Age-related macular degeneration was defined using the Wisconsin Age-Related Maculopathy Grading System, the International Age-Related Maculopathy Epidemiological Study Group Classification, or the Beckman Clinical Classification. Chronic kidney disease was defined as estimated glomerular filtration rate (eGFR) of less than 60 ml/min per 1.73 m2. A pooled analysis using individual-level participant data was performed to examine the associations between CKD and eGFR with AMD (early and late), adjusting for age, sex, hypertension, diabetes, body mass index, smoking status, total cholesterol, and study groups. MAIN OUTCOME MEASURES: Odds ratio (OR) of early and late AMD. RESULTS: Among 51 253 participants (mean age, 54.1 ± 14.5 years), 5079 had CKD (9.9%). The prevalence of early AMD was 9.0%, and that of late AMD was 0.71%. After adjusting for confounders, individuals with CKD were associated with higher odds of late AMD (OR, 1.46; 95% confidence interval [CI], 1.11-1.93; P = 0.008). Similarly, poorer kidney function (per 10-unit eGFR decrease) was associated with late AMD (OR, 1.12; 95% CI, 1.05-1.19; P = 0.001). Nevertheless, CKD and eGFR were not associated significantly with early AMD (all P ≥ 0.149). CONCLUSIONS: Pooled analysis from 10 distinct Asian population-based studies revealed that CKD and compromised kidney function are associated significantly with late AMD. This finding further underscores the importance of ocular examinations in patients with CKD. FINANCIAL DISCLOSURE(S): Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Subject(s)
Glomerular Filtration Rate , Macular Degeneration , Renal Insufficiency, Chronic , Humans , Male , Cross-Sectional Studies , Female , Middle Aged , Renal Insufficiency, Chronic/epidemiology , Renal Insufficiency, Chronic/physiopathology , Aged , Macular Degeneration/physiopathology , Macular Degeneration/epidemiology , Risk Factors , Asian People/ethnology , Adult , Odds Ratio , Prevalence , Aged, 80 and overABSTRACT
BACKGROUND OBJECTIVES: In view of anecdotal reports of sudden unexplained deaths in India's apparently healthy young adults, linking to coronavirus disease 2019 (COVID-19) infection or vaccination, we determined the factors associated with such deaths in individuals aged 18-45 years through a multicentric matched case-control study. METHODS: This study was conducted through participation of 47 tertiary care hospitals across India. Cases were apparently healthy individuals aged 18-45 years without any known co-morbidity, who suddenly (<24 h of hospitalization or seen apparently healthy 24 h before death) died of unexplained causes during 1 st October 2021-31 st March 2023. Four controls were included per case matched for age, gender and neighborhood. We interviewed/perused records to collect data on COVID-19 vaccination/infection and post-COVID-19 conditions, family history of sudden death, smoking, recreational drug use, alcohol frequency and binge drinking and vigorous-intensity physical activity two days before death/interviews. We developed regression models considering COVID-19 vaccination ≤42 days before outcome, any vaccine received anytime and vaccine doses to compute an adjusted matched odds ratio (aOR) with 95 per cent confidence interval (CI). RESULTS: Seven hundred twenty nine cases and 2916 controls were included in the analysis. Receipt of at least one dose of COVID-19 vaccine lowered the odds [aOR (95% CI)] for unexplained sudden death [0.58 (0.37, 0.92)], whereas past COVID-19 hospitalization [3.8 (1.36, 10.61)], family history of sudden death [2.53 (1.52, 4.21)], binge drinking 48 h before death/interview [5.29 (2.57, 10.89)], use of recreational drug/substance [2.92 (1.1, 7.71)] and performing vigorous-intensity physical activity 48 h before death/interview [3.7 (1.36, 10.05)] were positively associated. Two doses lowered the odds of unexplained sudden death [0.51 (0.28, 0.91)], whereas single dose did not. INTERPRETATION CONCLUSIONS: COVID-19 vaccination did not increase the risk of unexplained sudden death among young adults in India. Past COVID-19 hospitalization, family history of sudden death and certain lifestyle behaviors increased the likelihood of unexplained sudden death.
Subject(s)
Binge Drinking , COVID-19 , Young Adult , Humans , Case-Control Studies , COVID-19 Vaccines , Binge Drinking/complications , Death, Sudden/etiology , COVID-19/epidemiology , COVID-19/complicationsABSTRACT
OBJECTIVE: This study aimed to develop a predictive risk score model based on deep learning (DL) independent of fundus photography, totally reliant on systemic data through targeted screening from a population-based study to diagnose diabetic retinopathy (DR) in the Indian population. METHODS: It involved machine learning application on datasets of a cross-sectional population-based study. A total of 1425 subjects (1175 subjects with known diabetes and 250 with newly diagnosed diabetes) were included in the study. We applied five machine learning algorithms, random forest (RF), logistic regression (LR), support vector machines (SVM), artificial neural networks (ANN), and decision trees (DT), to predict diabetic retinopathy in our datasets. We incorporated a percentage split in the first experiment and randomly divided our data set into 80% as a training set and 20% as a test set. We performed a three-way data split in the second experiment to prevent overestimating predictive performance. We randomly divided our data set into 60% as a training set, 20% as a validation set, and 20% as the test set. Furthermore, we integrated five-fold cross-validation to split the percentage to evaluate our method. We judged the predictive performance based on the receiver operating characteristic (ROC) curve, the area under the curve (AUC), accuracy (Acc), sensitivity, and specificity. RESULTS: The RF classifier achieved the best prediction performance with AUC, Acc, and sensitivity values of 0.91, 0.89, and 0.90, respectively, in the percentage split. Similarly, a three-way data split attained an outcome of 0.86 and 0.85 in AUC and Acc. Likewise, the five-fold cross-validation performed the best with results of 0.90, 0.97, 0.91, and 0.75 in AUC, Acc, sensitivity, and specificity, respectively. CONCLUSION: Since the RF classifier achieved the best performance, we propose it to identify diabetic retinopathy for targeted screening in the general population.
ABSTRACT
Purpose: To analyze the efficacy of a deep learning (DL)-based artificial intelligence (AI)-based algorithm in detecting the presence of diabetic retinopathy (DR) and glaucoma suspect as compared to the diagnosis by specialists secondarily to explore whether the use of this algorithm can reduce the cross-referral in three clinical settings: a diabetologist clinic, retina clinic, and glaucoma clinic. Methods: This is a prospective observational study. Patients between 35 and 65 years of age were recruited from glaucoma and retina clinics at a tertiary eye care hospital and a physician's clinic. Non-mydriatic fundus photography was performed according to the disease-specific protocols. These images were graded by the AI system and specialist graders and comparatively analyzed. Results: Out of 1085 patients, 362 were seen at glaucoma clinics, 341 were seen at retina clinics, and 382 were seen at physician clinics. The kappa agreement between AI and the glaucoma grader was 85% [95% confidence interval (CI): 77.55-92.45%], and retina grading had 91.90% (95% CI: 87.78-96.02%). The retina grader from the glaucoma clinic had 85% agreement, and the glaucoma grader from the retina clinic had 73% agreement. The sensitivity and specificity of AI glaucoma grading were 79.37% (95% CI: 67.30-88.53%) and 99.45 (95% CI: 98.03-99.93), respectively; DR grading had 83.33% (95 CI: 51.59-97.91) and 98.86 (95% CI: 97.35-99.63). The cross-referral accuracy of DR and glaucoma was 89.57% and 95.43%, respectively. Conclusion: DL-based AI systems showed high sensitivity and specificity in both patients with DR and glaucoma; also, there was a good agreement between the specialist graders and the AI system.
Subject(s)
Deep Learning , Diabetes Mellitus , Diabetic Retinopathy , Glaucoma , Humans , Diabetic Retinopathy/diagnosis , Artificial Intelligence , Retina , Glaucoma/diagnosis , Photography/methods , Mass Screening/methodsABSTRACT
Diabetic Retinopathy (DR) affects about 27% of patients with diabetes globally. According to the World Health Organization (WHO), DR is responsible for37 million cases of blindness worldwide. The SMART India study (October 2020-August 2021) documented the prevalence of diabetes, and DR in people40 years and above across ten Indian states and one Union Territory by conducting community screening. About 90% of people with sight threatening diabetic retinopathy (STDR) were referred from this screening study to eye hospitals for management, but failed to attend. This qualitative study, a component of the SMART India study, explored perceptions of referred patients regarding their susceptibility to eye related problems in diabetes and the benefits/barriers to seeking care. Perceived barriers from the viewpoint of ophthalmologists were also explored. Guided by the Health Beliefs Model (HBM), 20 semi structured interviews were carried out with consenting patients diagnosed with STDR. They included nine patients who had sought care recruited from eight eye hospitals across different states in India and eleven patients who did not seek care. Eleven ophthalmologists also participated. Four themes of analysis based on the HBM were, understanding of DR and its treatment, perceptions about susceptibility and severity, perceived barriers, perceived benefits and cues to action. Findings revealed poor understanding of the effects of diabetes on the eye contributing to low risk perception. Prohibitive costs of treatment, difficulties in accessing care services and poor social support were major barriers to seeking care. Ophthalmologists acknowledged that the absence of symptoms and the slow progressive nature of the disease deluded patients into thinking that they were fine. The study attests to the need for greater health literacy around diabetes, DR and STDR; for making treatment more affordable and accessible and for the development of effective patient education and communication strategies towards increasing compliance.
Subject(s)
Diabetes Mellitus, Type 2 , Diabetic Retinopathy , Humans , Diabetic Retinopathy/epidemiology , Diabetic Retinopathy/therapy , Diabetic Retinopathy/diagnosis , Physical Examination , India/epidemiology , Prevalence , Diabetes Mellitus, Type 2/epidemiologyABSTRACT
Purpose: The study was conducted to compare the compliance to intravitreal injection treatment and follow-up in patients with center-involving diabetic macular edema (CI-DME) and treatment outcomes between a tertiary eye care facility and a tertiary diabetes care center. Methods: A retrospective review was conducted on treatment naïve DME patients who had received intravitreal anti-vascular endothelial growth factor (anti-VEGF) injections in 2019. Participants were people with type 2 diabetes who were under regular care at the eye care center or the diabetes care center in Chennai. The outcome measures were noted at months 1, 2, 3, 6, and 12. Results: A review of 136 patients treated for CI-DME (72 from the eye care center and 64 from a diabetes care center) was carried out. The severity of diabetic retinopathy (DR) was similar in both centers. There was no statistically significant (P > 0.05) difference in the choice of initial intravitreal drug in the two centers. At 12-month follow-up, only 29.16% came for a follow-up in the eye center vs. 76.56% in a diabetes care center (P = 0.000). The multivariate logistic regression showed increasing age was associated with non-compliance in both the groups (eye care center: odds ratio [OR] 0.91; 95% confidence interval [CI] 0.82-1.21; P = 0.044) and diabetes care center (OR 1.15; 95% CI 1.02-1.29; P = 0.020). Conclusion: The follow-up rate between eye care and diabetic care center with DME showed a significant disparity. By providing comprehensive diabetes care for all complications under one roof, compliance with follow-up can be improved in people with DME.
Subject(s)
Diabetes Mellitus, Type 2 , Diabetic Retinopathy , Macular Edema , Humans , Angiogenesis Inhibitors , Diabetes Mellitus, Type 2/complications , Diabetes Mellitus, Type 2/epidemiology , Diabetic Retinopathy/complications , Diabetic Retinopathy/diagnosis , Diabetic Retinopathy/drug therapy , Follow-Up Studies , India/epidemiology , Macular Edema/diagnosis , Macular Edema/drug therapy , Macular Edema/etiology , Ranibizumab , Vascular Endothelial Growth Factor AABSTRACT
Purpose: Emergency delirium (ED), a common postoperative neurologic complication, causes behavioral disturbances leading to self-traumas and also has long-term adverse effects in children. Our aim was to investigate the efficacy of a single-bolus dose of dexmedetomidine in reducing the incidence of ED. Additionally, pain relief, number of patients who needed rescue analgesia, hemodynamic parameters, and adverse events were assessed. Methods: One hundred and one patients were randomly allocated into two groups: 50 patients received 15 mL of dexmedetomidine 0.4 µg/kg (group D) and 51 patients received volume-matched normal saline (group C). Hemodynamic parameters such as heart rate (HR), systolic blood pressure (SBP), and diastolic blood pressure (DBP) were monitored regularly throughout the procedure. ED was assessed with Pediatric Anesthesia Emergence Delirium Scale (PAEDS), and pain was measured using the modified Objective Pain Score (MOPS). Results: The incidences of ED and pain were higher in group C than group D (P < 0.0001 and P < 0.0001, respectively). Group D showed significant decrease in MOPS and PAEDS values at 5, 10, 15, and 20 min (P < 0.05), HR at 5 min (P < 0.0243), and SBP at 15 min (P < 0.0127). There was no significant difference in DBP between the two groups at any time point. The mean blood pressure (MBP) at 10 min was significantly less in group D than group C (P < 0.001). Conclusion: Dexmedetomidine 0.4 µg/kg as a single bolus over 10 min immediately after intubation is effective for the prevention of ED and significantly reduces the need of rescue analgesia without compromising the hemodynamic parameters in children undergoing ophthalmic surgery.
Subject(s)
Dexmedetomidine , Emergence Delirium , Child , Humans , Emergence Delirium/etiology , Emergence Delirium/prevention & control , Emergence Delirium/drug therapy , Postoperative Complications/prevention & control , Postoperative Complications/drug therapy , Pain , Blood Pressure , Double-Blind MethodABSTRACT
PURPOSE: To identify optical coherence tomography angiography (OCTA) biomarkers in patients who were treated for diabetic macular oedema (DME) with intravitreal anti-vascular endothelial growth factor (VEGF) injections and compare the OCTA parameters between responders and non-responders. METHODS: A retrospective cohort study of 61 eyes with DME who received at least one intravitreal anti-VEGF injection was included between July 2017 and October 2020. The subjects underwent a comprehensive eye examination followed by an OCTA examination before and after intravitreal anti-VEGF injection. Demographic data, visual acuity, and OCTA parameters were documented, and further analysis was performed pre- and post-intravitreal anti-VEGF injection. RESULTS: Out of 61 eyes which underwent intravitreal anti-VEGF injection for diabetic macular oedema, 30 were responders (group 1) and 31 were non-responders (group 2). We found that the responders (group 1) had a higher vessel density in the outer ring that was statistically significant (p = 0.022), and higher perfusion density was noted in the outer ring (p = 0.012) and full ring (p = 0.044) at levels of the superficial capillary plexus (SCP). We also observed a lower vessel diameter index in the deep capillary plexus (DCP) in responders when compared to non-responders (p < 0.00). CONCLUSION: The evaluation of SCP in OCTA in addition to DCP can result in a better prediction of treatment response and early management in diabetic macular oedema.
ABSTRACT
Purpose: To determine the functional and anatomical outcomes of patients with endophthalmitis with concurrent or delayed onset retinal detachment (RD), and compare the preoperative, intraoperative and postoperative features. Patients and Methods: This was a retrospective review of 121 eyes in 121 patients presenting with endophthalmitis and RD. Subjects were categorized into two groups: endophthalmitis with delayed onset RD (group 1, N=76) and endophthalmitis with concurrent RD (group 2, N=45). Results: The mean age of patients in groups 1 and 2 was 38.21±21.60 and 46.78±24.42 years, respectively (P=0.047). Exogenous endophthalmitis was common in both groups 1 and 2 (86.84% and 84.44%, respectively). No significant differences were found between the groups in the type of RD, retinal breaks, number of quadrants involved or proliferative vitreoretinopathy grade. In the overall cohort, visual acuity improved post-surgery in one-third of the patients who were in the near or total blindness category at presentation. We found good anatomical success rates of an attached retina in both groups 1 and 2 (84.3% and 77.7%, P=0.376). Conclusion: Our study presents the results of patients with endophthalmitis and delayed onset RD or concurrent RD. It shows a few differences in presentation between the groups, but the anatomical and functional outcomes were almost the same.
ABSTRACT
PURPOSE: To analyze clinical characteristics of scleritis in elderly patients and also compare the data with relatively younger patients with scleritis (<60 years). METHOD: Retrospective analysis of medical records of patients with scleritis who visited a tertiary eye care centre between 2008 and 2018. RESULT: Scleritis in ≥60 years accounted for 3% of the total scleritis cases. The mean age of the patients was 67 ± 6 years, and a female (66%) predominance was noted. Of the 44 elderly patients with scleritis, 48% were 66-70 years of age and 20% were above 70 years of age. Diffuse scleritis was the most common subtypes followed by necrotizing scleritis (35%). Overall, 32% of elderly patients with scleritis had underlying disease and the most common systemic association was granulomatous with polyangiitis. When compared with a subset of patients (<60 years of age), the elderly group showed higher rate of recurrences and complications. CONCLUSION: Scleritis in elderly patients is relatively rare but can have a higher recurrence rate with a increased complications.
Subject(s)
Scleritis , Humans , Female , Aged , Middle Aged , Scleritis/diagnosis , Scleritis/epidemiology , Scleritis/complications , Retrospective Studies , Tertiary Care CentersABSTRACT
Background: The aim of this study was to assess the performance of regional graders and artificial intelligence algorithms across retinal cameras with different specifications in classifying an image as gradable and ungradable. Methods: Study subjects were included from a community-based nationwide diabetic retinopathy screening program in Thailand. Various non-mydriatic fundus cameras were used for image acquisition, including Kowa Nonmyd, Kowa Nonmyd α-Dâ ¢, Kowa Nonmyd 7, Kowa Nonmyd WX, Kowa VX 10 α, Kowa VX 20 and Nidek AFC 210. All retinal photographs were graded by deep learning algorithms and human graders and compared with a standard reference. Results: Images were divided into two categories as gradable and ungradable images. Four thousand eight hundred fifty-two participants with 19,408 fundus images were included, of which 15,351 (79.09%) were gradable images and the remaining 4057 (20.90%) were ungradable images. Conclusions: The deep learning (DL) algorithm demonstrated better sensitivity, specificity and kappa than the human graders for all eight types of non-mydriatic fundus cameras. The deep learning system showed, more consistent diagnostic performance than the human graders across images of varying quality and camera types.
Subject(s)
Diabetes Mellitus , Diabetic Retinopathy , Macular Edema , Anti-Inflammatory Agents, Non-Steroidal/therapeutic use , Diabetic Retinopathy/complications , Diabetic Retinopathy/diagnosis , Diabetic Retinopathy/drug therapy , Humans , Intravitreal Injections , Macular Edema/diagnosis , Macular Edema/drug therapy , Macular Edema/etiology , Visual AcuityABSTRACT
AIM: To find the optimal threshold of fasting plasma glucose (FPG) and glycated hemoglobin (HbA1c) for diagnosis of diabetes mellitus (DM) and to evaluate the association with diabetic retinopathy (DR) in the South Indian population. SETTINGS AND DESIGN: A retrospective population-based study. METHODS AND MATERIALS: A total of 909 newly detected type 2 DM patients were selected from our two previously conducted studies, which include an urban and a rural population of South India. All underwent estimation of fasting, postprandial plasma glucose (PPG), and other biochemical tests. A comprehensive and detailed ophthalmic examination was carried out. The fundi of patients were photographed using 45°, four-field stereoscopic photography. Based on receiver operating characteristic (ROC) curves, sensitivity and specificity were derived. RESULTS: The optimal cut-off values determined by maximizing the sensitivity and specificity of FPG and HbA1c using the Youden index were ≥ 6.17 mmol/L and ≥ 6.3%, respectively. By distributing the cut-off points into deciles and comparing them to the WHO criteria, we found that our HbA1c level of 6.60% was more than the WHO threshold (6.5%), with higher sensitivity (81.6%) and lower specificity (48.3%). The FPG level of 6.80 mmol/L was lower to the WHO criteria (7 mmol/L) with increased sensitivity (77.0%) and lower specificity (45.7%). Prevalence of DR by HbA1c levels between 6.5% and 6.9% was 15.3%. The prevalence of DR was more in the FPG category between 6.4 and 6.9 mmol/L and ≥ 7.5 mmol/L. CONCLUSION: Our population-based data indicate that for the South Indian population HbA1c value of ≥63 % and FPG value of ≥6.17 mmol/L may be optimal for diagnosing DM with a high level of accuracy and will be useful for the identification of mild and moderate DR.
ABSTRACT
In epidemiology, a risk factor is a variable associated with increased disease risk. Understanding the role of risk factors is significant for developing a strategy to improve global health. There is strong evidence that risk factors like smoking, alcohol consumption, previous cataract surgery, age, high-density lipoprotein (HDL) cholesterol, BMI, female gender, and focal hyper-pigmentation are independently associated with age-related macular degeneration (AMD). Currently, in the literature, statistical techniques like logistic regression, multivariable logistic regression, etc., are being used to identify AMD risk factors by employing numerical/categorical data. However, artificial intelligence (AI) techniques have not been used so far in the literature for identifying risk factors for AMD. On the other hand, artificial intelligence (AI) based tools can anticipate when a person is at risk of developing chronic diseases like cancer, dementia, asthma, etc., in providing personalized care. AI-based techniques can employ numerical/categorical and/or image data thus resulting in multimodal data analysis, which provides the need for AI-based tools to be used for risk factor analysis in ophthalmology. This review summarizes the statistical techniques used to identify various risk factors and the higher benefits that AI techniques provide for AMD-related disease prediction. Additional studies are required to review different techniques for risk factor identification for other ophthalmic diseases like glaucoma, diabetic macular edema, retinopathy of prematurity, cataract, and diabetic retinopathy.
ABSTRACT
BACKGROUND: To estimate the prevalence of optical coherence tomography (OCT)-defined diabetic macular oedema (DME) in urban South Indian population and to elucidate their associated risk factors. METHODS: Of 911 participants from the Sankara Nethralaya Diabetic Retinopathy and Molecular Genetics Study-II (SN-DREAMS-), 759 who underwent OCT were analysed. The participants underwent a comprehensive examination and retinal photography following a standard protocol for diabetic retinopathy (DR) grading. The subjects were categorized into centre-involving DME (CI-DME), non-centre involving DME (NCI-DME), and No-DME based on the mean retinal thickness at the central 1 mm, inner and outer ETDRS subfields. RESULTS: The prevalence of CI-DME and NCI-DME in the Chennai population was 3.03% (95% CI: 3.01-3.05) and 10.80% (95% CI: 10.7-11.02). NCI-DME was found to be higher by 9.5% (95% CI: 0.07-0.11) in the early stages of DR. A greater number of subjects with CI DME were aged >60 years and had diabetes mellitus (DM) for >10 years. The significant risk factors for NCI-DME are diastolic blood pressure, serum total cholesterol, serum triglyceride, insulin use and neuropathy (OR (95% CI): 0.97 (0.94-100), 1.00 (1.00-1.01), 0.99 (0.98-0.99), 2.32 (1.15-4.68) and 4.24 (1.22-14.69), respectively) and for CI DME are duration of diabetes, anaemia, neuropathy and insulin use (OR (95% CI): 2.49 (0.96-6.40), 3.41 (1.34-8.65), 10.58 (1.68-66.56) and 3.51 (1.12-10.95), respectively). CONCLUSIONS: The prevalence of NCI-DME was found to be higher than that of CI-DME in patients with DR.