Evaluating the accuracy of a state-of-the-art large language model for prediction of admissions from the emergency room.

BACKGROUND: Artificial intelligence (AI) and large language models (LLMs) can play a critical role in emergency room operations by augmenting decision-making about patient admission. However, there are no studies for LLMs using real-world data and scenarios, in comparison to and being informed by traditional supervised machine learning (ML) models. We evaluated the performance of GPT-4 for predicting patient admissions from emergency department (ED) visits. We compared performance to traditional ML models both naively and when informed by few-shot examples and/or numerical probabilities. METHODS: We conducted a retrospective study using electronic health records across 7 NYC hospitals. We trained Bio-Clinical-BERT and XGBoost (XGB) models on unstructured and structured data, respectively, and created an ensemble model reflecting ML performance. We then assessed GPT-4 capabilities in many scenarios: through Zero-shot, Few-shot with and without retrieval-augmented generation (RAG), and with and without ML numerical probabilities. RESULTS: The Ensemble ML model achieved an area under the receiver operating characteristic curve (AUC) of 0.88, an area under the precision-recall curve (AUPRC) of 0.72 and an accuracy of 82.9%. The naïve GPT-4's performance (0.79 AUC, 0.48 AUPRC, and 77.5% accuracy) showed substantial improvement when given limited, relevant data to learn from (ie, RAG) and underlying ML probabilities (0.87 AUC, 0.71 AUPRC, and 83.1% accuracy). Interestingly, RAG alone boosted performance to near peak levels (0.82 AUC, 0.56 AUPRC, and 81.3% accuracy). CONCLUSIONS: The naïve LLM had limited performance but showed significant improvement in predicting ED admissions when supplemented with real-world examples to learn from, particularly through RAG, and/or numerical probabilities from traditional ML models. Its peak performance, although slightly lower than the pure ML model, is noteworthy given its potential for providing reasoning behind predictions. Further refinement of LLMs with real-world data is necessary for successful integration as decision-support tools in care settings.

Obesity Is Associated with Fatty Liver and Fat Changes in the Kidneys in Humans as Assessed by MRI.

BACKGROUND: Obesity is associated with metabolic syndrome and fat accumulation in various organs such as the liver and the kidneys. Our goal was to assess, using magnetic resonance imaging (MRI) Dual-Echo phase sequencing, the association between liver and kidney fat deposition and their relation to obesity. METHODS: We analyzed MRI scans of individuals who were referred to the Chaim Sheba Medical Center between December 2017 and May 2020 to perform a study for any indication. For each individual, we retrieved from the computerized charts data on sex, and age, weight, height, body mass index (BMI), systolic and diastolic blood pressure (BP), and comorbidities (diabetes mellitus, hypertension, dyslipidemia). RESULTS: We screened MRI studies of 399 subjects with a median age of 51 years, 52.4% of whom were women, and a median BMI 24.6 kg/m2. We diagnosed 18% of the participants with fatty liver and 18.6% with fat accumulation in the kidneys (fatty kidneys). Out of the 67 patients with fatty livers, 23 (34.3%) also had fatty kidneys, whereas among the 315 patients without fatty livers, only 48 patients (15.2%) had fatty kidneys (p < 0.01). In comparison to the patients who did not have a fatty liver or fatty kidneys (n = 267), those who had both (n = 23) were more obese, had higher systolic BP, and were more likely to have diabetes mellitus. In comparison to the patients without a fatty liver, those with fatty livers had an adjusted odds ratio of 2.91 (97.5% CI; 1.61-5.25) to have fatty kidneys. In total, 19.6% of the individuals were obese (BMI ≥ 30), and 26.1% had overweight (25 < BMI < 30). The obese and overweight individuals were older and more likely to have diabetes mellitus and hypertension and had higher rates of fatty livers and fatty kidneys. Fat deposition in both the liver and the kidneys was observed in 15.9% of the obese patients, in 8.3% of the overweight patients, and in none of those with normal weight. Obesity was the only risk factor for fatty kidneys and fatty livers, with an adjusted OR of 6.3 (97.5% CI 2.1-18.6). CONCLUSIONS: Obesity is a major risk factor for developing a fatty liver and fatty kidneys. Individuals with a fatty liver are more likely to have fatty kidneys. MRI is an accurate modality for diagnosing fatty kidneys. Reviewing MRI scans of any indication should include assessment of fat fractions in the kidneys in addition to that of the liver.

Deep learning in magnetic resonance enterography for Crohn's disease assessment: a systematic review.

Crohn's disease (CD) poses significant morbidity, underscoring the need for effective, non-invasive inflammatory assessment using magnetic resonance enterography (MRE). This literature review evaluates recent publications on the role of deep learning in improving MRE for CD assessment. We searched MEDLINE/PUBMED for studies that reported the use of deep learning algorithms for assessment of CD activity. The study was conducted according to the PRISMA guidelines. The risk of bias was evaluated using the QUADAS-2 tool. Five eligible studies, encompassing 468 subjects, were identified. Our study suggests that diverse deep learning applications, including image quality enhancement, bowel segmentation for disease burden quantification, and 3D reconstruction for surgical planning are useful and promising for CD assessment. However, most of the studies are preliminary, retrospective studies, and have a high risk of bias in at least one category. Future research is needed to assess how deep learning can impact CD patient diagnostics, particularly when considering the increasing integration of such models into hospital systems.

Navigating the vestibular maze: text-mining analysis of publication trends over five decades.

Introduction: The field of vestibular science, encompassing the study of the vestibular system and associated disorders, has experienced notable growth and evolving trends over the past five decades. Here, we explore the changing landscape in vestibular science, focusing on epidemiology, peripheral pathologies, diagnosis methods, treatment, and technological advancements. Methods: Publication data was obtained from the US National Center for Biotechnology Information (NCBI) PubMed database. The analysis included epidemiological, etiological, diagnostic, and treatment-focused studies on peripheral vestibular disorders, with a particular emphasis on changes in topics and trends of publications over time. Results: Our dataset of 39,238 publications revealed a rising trend in research across all age groups. Etiologically, benign paroxysmal positional vertigo (BPPV) and Meniere's disease were the most researched conditions, but the prevalence of studies on vestibular migraine showed a marked increase in recent years. Electronystagmography (ENG)/ Videonystagmography (VNG) and Vestibular Evoked Myogenic Potential (VEMP) were the most commonly discussed diagnostic tools, while physiotherapy stood out as the primary treatment modality. Conclusion: Our study presents a unique opportunity and point of view, exploring the evolving landscape of vestibular science publications over the past five decades. The analysis underscored the dynamic nature of the field, highlighting shifts in focus and emerging publication trends in diagnosis and treatment over time.

ChatGPT's adherence to otolaryngology clinical practice guidelines.

OBJECTIVES: Large language models, including ChatGPT, has the potential to transform the way we approach medical knowledge, yet accuracy in clinical topics is critical. Here we assessed ChatGPT's performance in adhering to the American Academy of Otolaryngology-Head and Neck Surgery guidelines. METHODS: We presented ChatGPT with 24 clinical otolaryngology questions based on the guidelines of the American Academy of Otolaryngology. This was done three times (N = 72) to test the model's consistency. Two otolaryngologists evaluated the responses for accuracy and relevance to the guidelines. Cohen's Kappa was used to measure evaluator agreement, and Cronbach's alpha assessed the consistency of ChatGPT's responses. RESULTS: The study revealed mixed results; 59.7% (43/72) of ChatGPT's responses were highly accurate, while only 2.8% (2/72) directly contradicted the guidelines. The model showed 100% accuracy in Head and Neck, but lower accuracy in Rhinology and Otology/Neurotology (66%), Laryngology (50%), and Pediatrics (8%). The model's responses were consistent in 17/24 (70.8%), with a Cronbach's alpha value of 0.87, indicating a reasonable consistency across tests. CONCLUSIONS: Using a guideline-based set of structured questions, ChatGPT demonstrates consistency but variable accuracy in otolaryngology. Its lower performance in some areas, especially Pediatrics, suggests that further rigorous evaluation is needed before considering real-world clinical use.

Utilizing natural language processing and large language models in the diagnosis and prediction of infectious diseases: A systematic review.

BACKGROUND: Natural Language Processing (NLP) and Large Language Models (LLMs) hold largely untapped potential in infectious disease management. This review explores their current use and uncovers areas needing more attention. METHODS: This analysis followed systematic review procedures, registered with the Prospective Register of Systematic Reviews. We conducted a search across major databases including PubMed, Embase, Web of Science, and Scopus, up to December 2023, using keywords related to NLP, LLM, and infectious diseases. We also employed the Quality Assessment of Diagnostic Accuracy Studies-2 tool for evaluating the quality and robustness of the included studies. RESULTS: Our review identified 15 studies with diverse applications of NLP in infectious disease management. Notable examples include GPT-4's application in detecting urinary tract infections and BERTweet's use in Lyme Disease surveillance through social media analysis. These models demonstrated effective disease monitoring and public health tracking capabilities. However, the effectiveness varied across studies. For instance, while some NLP tools showed high accuracy in pneumonia detection and high sensitivity in identifying invasive mold diseases from medical reports, others fell short in areas like bloodstream infection management. CONCLUSIONS: This review highlights the yet-to-be-fully-realized promise of NLP and LLMs in infectious disease management. It calls for more exploration to fully harness AI's capabilities, particularly in the areas of diagnosis, surveillance, predicting disease courses, and tracking epidemiological trends.

Artificial intelligence for detection of effusion and lipo-hemarthrosis in X-rays and CT of the knee.

BACKGROUND: Traumatic knee injuries are challenging to diagnose accurately through radiography and to a lesser extent, through CT, with fractures sometimes overlooked. Ancillary signs like joint effusion or lipo-hemarthrosis are indicative of fractures, suggesting the need for further imaging. Artificial Intelligence (AI) can automate image analysis, improving diagnostic accuracy and help prioritizing clinically important X-ray or CT studies. OBJECTIVE: To develop and evaluate an AI algorithm for detecting effusion of any kind in knee X-rays and selected CT images and distinguishing between simple effusion and lipo-hemarthrosis indicative of intra-articular fractures. METHODS: This retrospective study analyzed post traumatic knee imaging from January 2016 to February 2023, categorizing images into lipo-hemarthrosis, simple effusion, or normal. It utilized the FishNet-150 algorithm for image classification, with class activation maps highlighting decision-influential regions. The AI's diagnostic accuracy was validated against a gold standard, based on the evaluations made by a radiologist with at least four years of experience. RESULTS: Analysis included CT images from 515 patients and X-rays from 637 post traumatic patients, identifying lipo-hemarthrosis, simple effusion, and normal findings. The AI showed an AUC of 0.81 for detecting any effusion, 0.78 for simple effusion, and 0.83 for lipo-hemarthrosis in X-rays; and 0.89, 0.89, and 0.91, respectively, in CTs. CONCLUSION: The AI algorithm effectively detects knee effusion and differentiates between simple effusion and lipo-hemarthrosis in post-traumatic patients for both X-rays and selected CT images further studies are needed to validate these results.

AI in the ED: Assessing the efficacy of GPT models vs. physicians in medical score calculation.

BACKGROUND AND AIMS: Artificial Intelligence (AI) models like GPT-3.5 and GPT-4 have shown promise across various domains but remain underexplored in healthcare. Emergency Departments (ED) rely on established scoring systems, such as NIHSS and HEART score, to guide clinical decision-making. This study aims to evaluate the proficiency of GPT-3.5 and GPT-4 against experienced ED physicians in calculating five commonly used medical scores. METHODS: This retrospective study analyzed data from 150 patients who visited the ED over one week. Both AI models and two human physicians were tasked with calculating scores for NIH Stroke Scale, Canadian Syncope Risk Score, Alvarado Score for Acute Appendicitis, Canadian CT Head Rule, and HEART Score. Cohen's Kappa statistic and AUC values were used to assess inter-rater agreement and predictive performance, respectively. RESULTS: The highest level of agreement was observed between the human physicians (Kappa = 0.681), while GPT-4 also showed moderate to substantial agreement with them (Kappa values of 0.473 and 0.576). GPT-3.5 had the lowest agreement with human scorers. These results highlight the superior predictive performance of human expertise over the currently available automated systems for this specific medical outcome. Human physicians achieved a higher ROC-AUC on 3 of the 5 scores, but none of the differences were statistically significant. CONCLUSIONS: While AI models demonstrated some level of concordance with human expertise, they fell short in emulating the complex clinical judgments that physicians make. The study suggests that current AI models may serve as supplementary tools but are not ready to replace human expertise in high-stakes settings like the ED. Further research is needed to explore the capabilities and limitations of AI in emergency medicine.

Large language models for generating medical examinations: systematic review.

BACKGROUND: Writing multiple choice questions (MCQs) for the purpose of medical exams is challenging. It requires extensive medical knowledge, time and effort from medical educators. This systematic review focuses on the application of large language models (LLMs) in generating medical MCQs. METHODS: The authors searched for studies published up to November 2023. Search terms focused on LLMs generated MCQs for medical examinations. Non-English, out of year range and studies not focusing on AI generated multiple-choice questions were excluded. MEDLINE was used as a search database. Risk of bias was evaluated using a tailored QUADAS-2 tool. RESULTS: Overall, eight studies published between April 2023 and October 2023 were included. Six studies used Chat-GPT 3.5, while two employed GPT 4. Five studies showed that LLMs can produce competent questions valid for medical exams. Three studies used LLMs to write medical questions but did not evaluate the validity of the questions. One study conducted a comparative analysis of different models. One other study compared LLM-generated questions with those written by humans. All studies presented faulty questions that were deemed inappropriate for medical exams. Some questions required additional modifications in order to qualify. CONCLUSIONS: LLMs can be used to write MCQs for medical examinations. However, their limitations cannot be ignored. Further study in this field is essential and more conclusive evidence is needed. Until then, LLMs may serve as a supplementary tool for writing medical examinations. 2 studies were at high risk of bias. The study followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.

Utilizing large language models in breast cancer management: systematic review.

PURPOSE: Despite advanced technologies in breast cancer management, challenges remain in efficiently interpreting vast clinical data for patient-specific insights. We reviewed the literature on how large language models (LLMs) such as ChatGPT might offer solutions in this field. METHODS: We searched MEDLINE for relevant studies published before December 22, 2023. Keywords included: "large language models", "LLM", "GPT", "ChatGPT", "OpenAI", and "breast". The risk bias was evaluated using the QUADAS-2 tool. RESULTS: Six studies evaluating either ChatGPT-3.5 or GPT-4, met our inclusion criteria. They explored clinical notes analysis, guideline-based question-answering, and patient management recommendations. Accuracy varied between studies, ranging from 50 to 98%. Higher accuracy was seen in structured tasks like information retrieval. Half of the studies used real patient data, adding practical clinical value. Challenges included inconsistent accuracy, dependency on the way questions are posed (prompt-dependency), and in some cases, missing critical clinical information. CONCLUSION: LLMs hold potential in breast cancer care, especially in textual information extraction and guideline-driven clinical question-answering. Yet, their inconsistent accuracy underscores the need for careful validation of these models, and the importance of ongoing supervision.

Artificial Intelligence for Identification of Images with Active Bleeding in Mesenteric and Celiac Arteries Angiography.

PURPOSE: The purpose of this study is to evaluate the efficacy of an artificial intelligence (AI) model designed to identify active bleeding in digital subtraction angiography images for upper gastrointestinal bleeding. METHODS: Angiographic images were retrospectively collected from mesenteric and celiac artery embolization procedures performed between 2018 and 2022. This dataset included images showing both active bleeding and non-bleeding phases from the same patients. The images were labeled as normal versus images that contain active bleeding. A convolutional neural network was trained and validated to automatically classify the images. Algorithm performance was tested in terms of area under the curve, accuracy, sensitivity, specificity, F1 score, positive and negative predictive value. RESULTS: The dataset included 587 pre-labeled images from 142 patients. Of these, 302 were labeled as normal angiogram and 285 as containing active bleeding. The model's performance on the validation cohort was area under the curve 85.0 ± 10.9% (standard deviation) and average classification accuracy 77.43 ± 4.9%. For Youden's index cutoff, sensitivity and specificity were 85.4 ± 9.4% and 81.2 ± 8.6%, respectively. CONCLUSION: In this study, we explored the application of AI in mesenteric and celiac artery angiography for detecting active bleeding. The results of this study show the potential of an AI-based algorithm to accurately classify images with active bleeding. Further studies using a larger dataset are needed to improve accuracy and allow segmentation of the bleeding.

Advancing Medical Practice with Artificial Intelligence: ChatGPT in Healthcare.

BACKGROUND: Advancements in artificial intelligence (AI) and natural language processing (NLP) have led to the development of language models such as ChatGPT. These models have the potential to transform healthcare and medical research. However, understanding their applications and limitations is essential. OBJECTIVES: To present a view of ChatGPT research and to critically assess ChatGPT's role in medical writing and clinical environments. METHODS: We performed a literature review via the PubMed search engine from 20 November 2022, to 23 April 2023. The search terms included ChatGPT, OpenAI, and large language models. We included studies that focused on ChatGPT, explored its use or implications in medicine, and were original research articles. The selected studies were analyzed considering study design, NLP tasks, main findings, and limitations. RESULTS: Our study included 27 articles that examined ChatGPT's performance in various tasks and medical fields. These studies covered knowledge assessment, writing, and analysis tasks. While ChatGPT was found to be useful in tasks such as generating research ideas, aiding clinical reasoning, and streamlining workflows, limitations were also identified. These limitations included inaccuracies, inconsistencies, fictitious information, and limited knowledge, highlighting the need for further improvements. CONCLUSIONS: The review underscores ChatGPT's potential in various medical applications. Yet, it also points to limitations that require careful human oversight and responsible use to improve patient care, education, and decision-making.

Bidirectional Encoder Representations from Transformers in Radiology: A Systematic Review of Natural Language Processing Applications.

INTRODUCTION: Bidirectional Encoder Representations from Transformers (BERT), introduced in 2018, has revolutionized natural language processing. Its bidirectional understanding of word context has enabled innovative applications, notably in radiology. This study aimed to assess BERT's influence and applications within the radiologic domain. METHODS: Adhering to Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we conducted a systematic review, searching PubMed for literature on BERT-based models and natural language processing in radiology from January 1, 2018, to February 12, 2023. The search encompassed keywords related to generative models, transformer architecture, and various imaging techniques. RESULTS: Of 597 results, 30 met our inclusion criteria. The remaining were unrelated to radiology or did not use BERT-based models. The included studies were retrospective, with 14 published in 2022. The primary focus was on classification and information extraction from radiology reports, with x-rays as the prevalent imaging modality. Specific investigations included automatic CT protocol assignment and deep learning applications in chest x-ray interpretation. CONCLUSION: This review underscores the primary application of BERT in radiology for report classification. It also reveals emerging BERT applications for protocol assignment and report generation. As BERT technology advances, we foresee further innovative applications. Its implementation in radiology holds potential for enhancing diagnostic precision, expediting report generation, and optimizing patient care.

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.

Deep learning in voice analysis for diagnosing vocal cord pathologies: a systematic review.

OBJECTIVES: With smartphones and wearable devices becoming ubiquitous, they offer an opportunity for large-scale voice sampling. This systematic review explores the application of deep learning models for the automated analysis of voice samples to detect vocal cord pathologies. METHODS: We conducted a systematic literature review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) reporting guidelines. We searched MEDLINE and Embase databases for original publications on deep learning applications for diagnosing vocal cord pathologies between 2002 and 2022. Risk of bias was assessed using Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2). RESULTS: Out of the 14 studies that met the inclusion criteria, data from a total of 3037 patients were analyzed. All studies were retrospective. Deep learning applications targeted Reinke's edema, nodules, polyps, cysts, unilateral cord paralysis, and vocal fold cancer detection. Most pathologies had detection accuracy above 90%. Thirteen studies (93%) exhibited a high risk of bias and concerns about applicability. CONCLUSIONS: Technology holds promise for enhancing the screening and diagnosis of vocal cord pathologies. While current research is limited, the presented studies offer proof of concept for developing larger-scale solutions.

Elevated International Normalized Ratio and Mortality in Hospitalized Patients Treated with Direct Oral Anticoagulants.

BACKGROUND: Direct oral anticoagulants (DOACs) are associated with a prolongation of the prothrombin time and an increased international normalized ratio (INR). The clinical significance of these changes is unclear. This study aimed to examine the association between an elevated INR on admission and in-hospital death and long-term survival in patients treated with DOACs. METHODS: Data were retrospectively retrieved from records of hospitalized patients at the Sheba Medical Center between November 2008 and July 2023. Patients were selected based on DOAC treatment, coagulation profile, and INR test done within 48 hours of hospitalization. The outcomes were in-hospital mortality and mortality in the year following hospitalization. RESULTS: The study included 11,399 hospitalized patients treated with DOACs. Patients with elevated INR had a 180% higher risk of in-hospital mortality (adjusted odds ratio 2.80; 95% confidence interval, 2.30-3.39) and a 57% increased risk of death during the following year (adjusted hazard ratio 1.57; 95% confidence interval, 1.44-1.71). Similar results were observed in subgroup analyses for each DOAC. CONCLUSIONS: An elevated INR on admission is associated with a higher risk for in-hospital death and increased risk for mortality during the first year following hospitalization in hospitalized patients treated with DOACs. This highlights that elevated INR levels in patients on DOACs should not be dismissed as laboratory variations due to DOAC treatment, as they may serve as a prognostic marker.

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).

Deep Learning in Coeliac Disease: A Systematic Review on Novel Diagnostic Approaches to Disease Diagnosis.

BACKGROUND: Coeliac disease affects approximately 1% of the global population with the diagnosis often relying on invasive and time-demanding methods. Deep learning, a powerful tool in medical science, shows potential for non-invasive, accurate coeliac disease diagnosis, though challenges remain. OBJECTIVE: This systematic review aimed to evaluate the current state of deep-learning applications in coeliac disease diagnosis and identify potential areas for future research that could enhance diagnostic accuracy, sensitivity, and specificity. METHODS: A systematic review was conducted using the following databases: PubMed, Embase, Web of Science, and Scopus. PRISMA guidelines were applied. Two independent reviewers identified research articles using deep learning for coeliac disease diagnosis and severity assessment. Only original research articles with performance metrics data were included. The quality of the diagnostic accuracy studies was assessed using the QUADAS-2 tool, categorizing studies based on risk of bias and concerns about applicability. Due to heterogeneity, a narrative synthesis was conducted to describe the applications and efficacy of the deep-learning techniques (DLT) in coeliac disease diagnosis. RESULTS: The initial search across four databases yielded 417 studies with 195 being removed due to duplicity. Finally, eight studies were found to be suitable for inclusion after rigorous evaluation. They were all published between 2017 and 2023 and focused on using DLT for coeliac disease diagnosis or assessing disease severity. Different deep-learning architectures were applied. Accuracy levels ranged from 84% to 95.94% with the GoogLeNet model achieving 100% sensitivity and specificity for video capsule endoscopy images. CONCLUSIONS: DLT hold substantial potential in coeliac disease diagnosis. They offer improved accuracy and the prospect of mitigating clinician bias. However, key challenges persist, notably the requirement for more extensive and diverse datasets, especially to detect milder forms of coeliac disease. These methods are in their nascent stages, underscoring the need of integrating multiple data sources to achieve comprehensive coeliac disease diagnosis.