Glaucoma Prediction Models Based on Ocular and Systemic Findings.

INTRODUCTION: Our aim was to explore the impact of various systemic and ocular findings on predicting the development of glaucoma. METHODS: Medical records of 37,692 consecutive patients examined at a single medical center between 2001 and 2020 were analyzed using machine learning algorithms. Systemic and ocular features were included. Univariate and multivariate analyses followed by CatBoost and Light gradient-boosting machine prediction models were performed. Main outcome measures were systemic and ocular features associated with progression to glaucoma. RESULTS: A total of 7,880 patients (mean age 54.7 ± 12.6 years, 5,520 males [70.1%]) were included in a 3-year prediction model, and 314 patients (3.98%) had a final diagnosis of glaucoma. The combined model included 185 systemic and 42 ocular findings, and reached an ROC AUC of 0.84. The associated features were intraocular pressure (48.6%), cup-to-disk ratio (22.7%), age (8.6%), mean corpuscular volume (MCV) of red blood cell trend (5.2%), urinary system disease (3.3%), MCV (2.6%), creatinine level trend (2.1%), monocyte count trend (1.7%), ergometry metabolic equivalent task score (1.7%), dyslipidemia duration (1.6%), prostate-specific antigen level (1.2%), and musculoskeletal disease duration (0.5%). The ocular prediction model reached an ROC AUC of 0.86. Additional features included were age-related macular degeneration (10.0%), anterior capsular cataract (3.3%), visual acuity (2.0%), and peripapillary atrophy (1.3%). CONCLUSIONS: Ocular and combined systemic-ocular models can strongly predict the development of glaucoma in the forthcoming 3 years. Novel progression indicators may include anterior subcapsular cataracts, urinary disorders, and complete blood test results (mainly increased MCV and monocyte count).

Prevalence of common and rare ophthalmic findings in adults attending a medical survey institute.

PURPOSE: To examine the ophthalmic data from a large database of people attending a general medical survey institute, and to investigate ophthalmic findings of the eye and its adnexa, including differences in age and sex. METHODS: Retrospective analysis including medical data of all consecutive individuals whose ophthalmic data and the prevalences of ocular pathologies were extracted from a very large database of subjects examined at a single general medical survey institute. RESULTS: Data were derived from 184,589 visits of 3676 patients (mean age 52 years, 68% males). The prevalence of the following eye pathologies were extracted. Eyelids: blepharitis (n = 4885, 13.3%), dermatochalasis (n = 4666, 12.7%), ptosis (n = 677, 1.8%), ectropion (n = 73, 0.2%), and xanthelasma (n = 160, 0.4%). Anterior segment: pinguecula (n = 3368, 9.2%), pterygium (n = 852, 2.3%), and cataract or pseudophakia (n = 9381, 27.1%). Cataract type (percentage of all phakic patients): nuclear sclerosis (n = 8908, 24.2%), posterior subcapsular (n = 846, 2.3%), and capsular anterior (n = 781, 2.1%). Pseudophakia was recorded for 697 patients (4.6%), and posterior subcapsular opacification for 229 (0.6%) patients. Optic nerve head (ONH): peripapillary atrophy (n = 4947, 13.5%), tilted disc (n = 3344, 9.1%), temporal slope (n = 410, 1.1%), ONH notch (n = 61, 0.2%), myelinated nerve fiber layer (n = 94, 0.3%), ONH drusen (n = 37, 0.1%), optic pit (n = 3, 0.0%), and ON coloboma (n = 4, 0.0%). Most pathologies were more common in males except for ONH, and most pathologies demonstrated a higher prevalence with increasing age. CONCLUSIONS: Normal ophthalmic data and the prevalences of ocular pathologies were extracted from a very large database of subjects seen at a single medical survey institute.

Combination of machine learning algorithms with natural language processing may increase the probability of bacteremia detection in the emergency department: A retrospective, big-data analysis of 94,482 patients.

Background: Prompt diagnosis of bacteremia in the emergency department (ED) is of utmost importance. Nevertheless, the average time to first clinical laboratory finding range from 1 to 3 days. Alongside a myriad of scoring systems for occult bacteremia prediction, efforts for applying artificial intelligence (AI) in this realm are still preliminary. In the current study we combined an AI algorithm with a Natural Language Processing (NLP) algorithm that would potentially increase the yield extracted from clinical ED data. Methods: This study involved adult patients who visited our emergency department and at least one blood culture was taken to rule out bacteremia. Using both tabular and free text data, we built an ensemble model that leverages XGBoost for structured data, and logistic regression (LR) on a word-analysis technique called bag-of-words (BOW) Term Frequency-Inverse Document Frequency (TF-IDF), for textual data. All algorithms were designed in order to predict the risk for bacteremia with ED patients whose blood cultures were sent to the laboratory. Results: The study cohort comprised 94,482 individuals, of whom 52% were males. The prevalence of bacteremia in the entire cohort was 9.7%. The model trained on the tabular data yielded an area under the curve (AUC) of 73.7% for XGBoost, while the LR that was trained on the free text achieved an AUC of 71.3%. After checking a range of weights, the best combination was for 55% weight on the XGBoost prediction and 45% weight on the LR prediction. The final model prediction yielded an AUC of 75.6%. Conclusion: Harnessing artificial intelligence to the task of bacteremia surveillance in the ED settings by a combination of both free text and tabular data analysis improved predictive performance compared to using tabular data alone. We recommend that future AI applications based on our findings should be assimilated into the clinical routines of ED physicians.

Big Data Analysis of Glaucoma Prevalence in Israel.

PRCIS: The prevalence of glaucoma in the adult population included in this study was 2.3%. Normal values of routine eye examinations are provided including age and sex variations. PURPOSE: The purpose of this study was to analyze the prevalence of glaucoma in a very large database. METHODS: Retrospective analysis of medical records of patients examined at the Medical Survey Institute of a tertiary care university referral center between 2001 and 2020. A natural language process (NLP) algorithm identified patients with a diagnosis of glaucoma. The main outcome measures included the prevalence and age distribution of glaucoma. The secondary outcome measures included the prevalence and distribution of visual acuity (VA), intraocular pressure (IOP), and cup-to-disc ratio (CDR). RESULTS: Data were derived from 184,589 visits of 36,762 patients (mean age: 52 y, 68% males). The NLP model was highly sensitive in identifying glaucoma, achieving an accuracy of 94.98% (area under the curve=93.85%), and 633 of 27,517 patients (2.3%) were diagnosed as having glaucoma with increasing prevalence in older age. The mean VA was 20/21, IOP 14.4±2.84 mm Hg, and CDR 0.28±0.16, higher in males. The VA decreased with age, while the IOP and CDR increased with age. CONCLUSIONS: The prevalence of glaucoma in the adult population included in this study was 2.3%. Normal values of routine eye examinations are provided including age and sex variations. We proved the validity and accuracy of the NLP model in identifying glaucoma.

A Novel Prediction Tool for Endoscopic Intervention in Patients with Acute Upper Gastro-Intestinal Bleeding.

(1) Background: Predicting which patients with upper gastro-intestinal bleeding (UGIB) will receive intervention during urgent endoscopy can allow for better triaging and resource utilization but remains sub-optimal. Using machine learning modelling we aimed to devise an improved endoscopic intervention predicting tool. (2) Methods: A retrospective cohort study of adult patients diagnosed with UGIB between 2012−2018 who underwent esophagogastroduodenoscopy (EGD) during hospitalization. We assessed the correlation between various parameters with endoscopic intervention and examined the prediction performance of the Glasgow-Blatchford score (GBS) and the pre-endoscopic Rockall score for endoscopic intervention. We also trained and tested a new machine learning-based model for the prediction of endoscopic intervention. (3) Results: A total of 883 patients were included. Risk factors for endoscopic intervention included cirrhosis (9.0% vs. 3.8%, p = 0.01), syncope at presentation (19.3% vs. 5.4%, p < 0.01), early EGD (6.8 h vs. 17.0 h, p < 0.01), pre-endoscopic administration of tranexamic acid (TXA) (43.4% vs. 31.0%, p < 0.01) and erythromycin (17.2% vs. 5.6%, p < 0.01). Higher GBS (11 vs. 9, p < 0.01) and pre-endoscopy Rockall score (4.7 vs. 4.1, p < 0.01) were significantly associated with endoscopic intervention; however, the predictive performance of the scores was low (AUC of 0.54, and 0.56, respectively). A combined machine learning-developed model demonstrated improved predictive ability (AUC 0.68) using parameters not included in standard GBS. (4) Conclusions: The GBS and pre-endoscopic Rockall score performed poorly in endoscopic intervention prediction. An improved predictive tool has been proposed here. Further studies are needed to examine if predicting this important triaging decision can be further optimized.