Smart decision support system for keratoconus severity staging using corneal curvature and thinnest pachymetry indices.

BACKGROUND: This study proposes a decision support system created in collaboration with machine learning experts and ophthalmologists for detecting keratoconus (KC) severity. The system employs an ensemble machine model and minimal corneal measurements. METHODS: A clinical dataset is initially obtained from Pentacam corneal tomography imaging devices, which undergoes pre-processing and addresses imbalanced sampling through the application of an oversampling technique for minority classes. Subsequently, a combination of statistical methods, visual analysis, and expert input is employed to identify Pentacam indices most correlated with severity class labels. These selected features are then utilized to develop and validate three distinct machine learning models. The model exhibiting the most effective classification performance is integrated into a real-world web-based application and deployed on a web application server. This deployment facilitates evaluation of the proposed system, incorporating new data and considering relevant human factors related to the user experience. RESULTS: The performance of the developed system is experimentally evaluated, and the results revealed an overall accuracy of 98.62%, precision of 98.70%, recall of 98.62%, F1-score of 98.66%, and F2-score of 98.64%. The application's deployment also demonstrated precise and smooth end-to-end functionality. CONCLUSION: The developed decision support system establishes a robust basis for subsequent assessment by ophthalmologists before potential deployment as a screening tool for keratoconus severity detection in a clinical setting.

Evaluating the strengths and limitations of multimodal ChatGPT-4 in detecting glaucoma using fundus images.

Overview: This study evaluates the diagnostic accuracy of a multimodal large language model (LLM), ChatGPT-4, in recognizing glaucoma using color fundus photographs (CFPs) with a benchmark dataset and without prior training or fine tuning. Methods: The publicly accessible Retinal Fundus Glaucoma Challenge "REFUGE" dataset was utilized for analyses. The input data consisted of the entire 400 image testing set. The task involved classifying fundus images into either 'Likely Glaucomatous' or 'Likely Non-Glaucomatous'. We constructed a confusion matrix to visualize the results of predictions from ChatGPT-4, focusing on accuracy of binary classifications (glaucoma vs non-glaucoma). Results: ChatGPT-4 demonstrated an accuracy of 90% with a 95% confidence interval (CI) of 87.06%-92.94%. The sensitivity was found to be 50% (95% CI: 34.51%-65.49%), while the specificity was 94.44% (95% CI: 92.08%-96.81%). The precision was recorded at 50% (95% CI: 34.51%-65.49%), and the F1 Score was 0.50. Conclusion: ChatGPT-4 achieved relatively high diagnostic accuracy without prior fine tuning on CFPs. Considering the scarcity of data in specialized medical fields, including ophthalmology, the use of advanced AI techniques, such as LLMs, might require less data for training compared to other forms of AI with potential savings in time and financial resources. It may also pave the way for the development of innovative tools to support specialized medical care, particularly those dependent on multimodal data for diagnosis and follow-up, irrespective of resource constraints.

The utilization of artificial intelligence in glaucoma: diagnosis versus screening.

With advancements in the implementation of artificial intelligence (AI) in different ophthalmology disciplines, it continues to have a significant impact on glaucoma diagnosis and screening. This article explores the distinct roles of AI in specialized ophthalmology clinics and general practice, highlighting the critical balance between sensitivity and specificity in diagnostic and screening models. Screening models prioritize sensitivity to detect potential glaucoma cases efficiently, while diagnostic models emphasize specificity to confirm disease with high accuracy. AI applications, primarily using machine learning (ML) and deep learning (DL), have been successful in detecting glaucomatous optic neuropathy from colored fundus photographs and other retinal imaging modalities. Diagnostic models integrate data extracted from various forms of modalities (including tests that assess structural optic nerve damage as well as those evaluating functional damage) to provide a more nuanced, accurate and thorough approach to diagnosing glaucoma. As AI continues to evolve, the collaboration between technology and clinical expertise should focus more on improving specificity of glaucoma diagnostic models to assess ophthalmologists to revolutionize glaucoma diagnosis and improve patients care.

Assessing the Impact of Simulated Color Vision Deficiency on Ophthalmologists' Ability to Differentiate between Choroidal Melanoma and Choroidal Nevus.

Background: Color vision deficiency (CVD) is an often-overlooked issue within the medical community, and its consequences remain insufficiently explored. We aim to evaluate how CVD affects diagnostic accuracy and distinguish between malignant choroidal melanoma and benign choroidal nevus among ophthalmologists. Methods: In this cross-sectional study, we engaged ophthalmologists through a web-based survey distributed via the professional ophthalmology society's social media channels. The survey encompassed a series of three fundus images representing normal fundus, choroidal nevus, and choroidal melanoma. Each image underwent simulation for the three primary types of CVD-protanopia, deuteranopia, and tritanopia-alongside a non-simulated version. Results: The study included 41 participants, averaging 40 years of age (±9.2), comprising 28 (68%) men and 13 (32%) women. Significantly lower rates of identifying orange pigments were observed in simulated protanopia images compared to non-simulated ones (p = 0.038). In simulated deutranopia images, the recognition of melanotic lesions was notably reduced compared to non-simulated images (p = 0.048). No such limitation was observed for tritanopia. However, participants retained their ability to identify subretinal fluid and estimate tumor thickness in simulated and non-simulated images. Concerning simulated images of choroidal nevi, participants misdiagnosed nevi as choroidal melanoma in 37% of cases in simulated protanopia nevi images and 41% in simulated deutranopia nevi images. This resulted in unnecessary referrals of benign lesions as malignant, emphasizing the potential for mistaken diagnoses. Nevertheless, almost all simulated images of malignant melanoma were correctly referred for specialized oncological treatment. Conclusions: The simulated CVD conditions of protanopia and deuteranopia affected the accuracy of identifying the melanotic nature of the choroidal tumor and the presence of orange pigments. This limitation led to challenges in correctly diagnosing choroidal melanoma and choroidal nevus, resulting in extra referrals for nevus cases. However, participants were safe and could still determine the possible risk of eyes with choroidal melanoma, so most referred melanoma cases to specialized oncologists as needed.

Assessment of a Telehealth Platform in Evaluating the Urgency of Ophthalmical Consultation in the Middle East and North Africa Region: The Red Flags of Retinal Detachment.

Background: The availability and utilization of telehealth services have been rapidly increasing in the past decade, which paved the way for ophthalmological care to be offered more easily and conveniently. However, the proficiency of telehealth in the context of ophthalmical care still requires further studies to prove its effectiveness. This study examined the proficiency of general practitioners in a telemedicine platform in identifying red flag symptoms, suggestive of retinal detachment, and devising optimal management strategies. Methods: Our cross-sectional study used chat-based consultations on Altibbi Telemedicine platform (2018-2023) to study ophthalmical patients presenting with "blurred vision" or "blindness." Those endorsing red flag symptoms were categorized as having "positive symptomatology" and those reporting none as having "negative symptomatology." Management plans were classified as referral or reassuring. Statistical analysis was performed using IBM's Statistical Package for Social Sciences to examine associations between symptomatology and other variables. p values below 0.05 were considered statistically significant. Results: Five hundred and fifty (n = 550) patients with a mean age 22.5 ± 13 years were included. Patients expressing positive symptomatology were more likely to be referred relative to those expressing negative symptomatology (81% vs. 61%, p < 0.001). No significant difference was found between genders and referral (p = 0.053) or age and referral (p = 0.231). Multivariate regression showed a significant correlation between positive symptoms and referral (adjusted odds ratio [aOR]: 2.0; 95% confidence interval [95% CI]: 1.3-3.3), none between gender (aOR: 1.5; 95% CI: 0.9-2.2) or age (aOR: 1.0; 95% CI: 0.9-1.1) and referral odds. Conclusion: The telemedicine platform studied is effective in referring cases with red flag symptoms to urgent care, regardless of age and gender.

Non-arteritic anterior ischemic optic neuropathy secondary to idiopathic intracranial hypertension.

Purpose: Patients with increased intracranial pressure and underlying hypertensive emergency may present with optic disc edema. Papilledema in this setting may be a predisposing risk factor for superimposed non-arteritic anterior ischemic optic neuropathy (NAION). We highlight the role of neuroimaging including diffusion-weighted imaging in magnetic resonance imaging that can help to differentiate visual loss from NAION versus papilledema in fulminant IIH with and without hypertension. Observations: A 46-year-old female presented with acute vision loss in the right eye and transient right hemiparesis. Neuro-ophthalmic examination revealed optic disc edema in both eyes. Magnetic resonance imaging (MRI) of the brain with diffusion-weighted imaging (DWI) sequences showed restricted diffusion in the optic nerve head of the affected eye. Lumbar puncture revealed an elevated opening pressure of 34.8 cm H2O confirming increased intracranial pressure. Additionally, literature searches were conducted in the PubMed, Google Scholar and Embase databases to uncover previous cases of patients with ischemic optic neuropathy and restricted diffusion on MRI. Conclusions and importance: We highlight the shared pathophysiology between optic disc edema related visual loss in NAION and papilledema in IIH. We review the overlapping clinical and radiographic findings in these two conditions which may occur simultaneously. The presence of restricted diffusion in the optic nerve head versus in the optic nerve parenchyma may support a diagnosis of superimposed NAION and might influence the decision to perform surgery in cases of IIH with fulminant visual loss. Although restricted diffusion on MRI DWI sequences is often used to define cytotoxic edema related to ischemic infarction in the brain, this radiographic finding alone should not be used to determine the indication for surgery for papilledema related visual loss in fulminant IIH.

Painful Eyes in Neurology Clinic: A Guide for Neurologists.

Eye pain is a common complaint among patients presenting to the neurology clinic. It can be related to neurologic diseases, but it can also be a localized eye condition. Such disorders can be misleading, as their benign appearance might mask more grave underlying conditions, potentially leading to misdiagnoses or delayed treatment. Clinicians should be aware of the specific neurologic or systemic disorders (eg, demyelinating diseases or vascular abnormalities) that might first manifest as eye pain. Formal ophthalmic consultation is recommended for patients presenting with eye pain as the predominant complaint especially when red flags for more serious pathology are present.

Global research productivity of post-transplant lymphoproliferative disorder: a bibliometric study.

Background: Post-transplant lymphoproliferative diseases (PTLD) are a heterogeneous collection of neoplasms that occur after solid organ transplants (SOT). In the past 20 years, there has been a rise in PTLD research. This study aims to investigate the global research output and interest regarding PTLD using a bibliometric approach. Material and methods: On 28 November 2022, the Web of Science Core Collection documents on PTLD published between 2000 and 2022 were collected and analyzed using bibliometric techniques. The VOSviewer application was utilized to visualize the annual number of publications, authors, organizations, countries, published journals, citations, and most occurring keywords. Results: A total of 2814 documents were retrieved, and a screening process included 1809 documents. The total number of citations was 45 239, and the average number per item was 25. Most articles (n = 747) and citations (n = 25 740) were produced in the United States. Based on citations, most of the top 10 institutions that contributed were in the United States of America. The University of Pittsburgh topped the list with 2700 citations and 64 articles. The vast majority of articles were published in Pediatric Transplantation (n = 147), Transplantation (n = 124), and the American Journal of Transplantation (n = 98). Transplantation has received the most citations, 6499, followed by the American Journal of Transplantation with 5958 citations and Blood with 4107 citations. Conclusion: With ongoing debates over optimal classification, Epstein-Bar virus involvement, and treatment, this topic has received significant interest from researchers in recent years. Our results can be used as a guide for future research in the field and as a framework for a more in-depth look at the scientific progress of PTLD.

Blood pressure difference between pre and post-menopausal women and age-matched men: A cross-sectional study at a tertiary center.

Hypertension is a prominent risk factor for cardiovascular and cerebrovascular diseases. Gender differences and menopausal status contribute to blood pressure changes across the lifespan which have not been completely characterized. Our study aims to explore the impact of multiple factors on blood pressure levels in previously healthy women and men. Factors of interest included gender, menopausal status, age, and body mass index. Healthy women and men were recruited through healthcare facility announcements. Detailed menopausal history was obtained from females. The authors measured each participant's systolic and diastolic blood pressure at our outpatient clinics twice on the same day, and two different days, one week apart, and the authors included the mean of the averaged two readings for each participant. The study sample consisted of 313 participants. Female gender was a significant predictor of lower systolic and diastolic blood pressure (p < .001), while age significantly correlated with higher systolic blood pressure readings (p = .004). Although systolic blood pressure levels were significantly higher in postmenopausal females (124 mmHg) compared to premenopausal females (116 mmHg), our multiple linear regression analysis revealed that postmenopausal status did not significantly predict changes in either systolic or diastolic blood pressure. Our study demonstrates significant associations between blood pressure levels and various factors such as gender and age. This could emphasize the intricate interplay of demographic and clinical factors in blood pressure variations among individuals, highlighting the importance of a holistic approach to diagnosing hypertension, which considers various individual factors, including gender and age.

Intrastromal corneal ring segments for keratoconus patients: up to 12 years follow up.

PURPOSE: Intrastromal corneal ring segment (ICRS) implantation is a surgical technique developed with the purpose of avoiding the progression of corneal protrusion and is considered a viable option for managing patients with keratoconus as it stabilizes or improves vision thus delaying or excluding the need of more advanced surgical intervention such as penetrating keratoplasty. However, long term follow up is still limited to determine its actual success in achieving this goal. The current project aims to provide an extended follow up reporting a mean followup of around 5 years, extending up to 12.5 years. METHODS: We recruited patients who performed their ICRS between 2008 and 2013. We contacted patients for a follow up exam with a possible corneal tomography. For each patient, we obtained baseline pre operative data and latest follow up data which included visual acuity, subjective refraction, clinical slit-lamp exam, and corneal tomography. We compared the change in best corrected visual acuity and maximum keratometry readings from clinical visits before ring implantation to the latest follow up. RESULTS: A total of 68 eyes for 53 patients were included. The mean duration of follow up was 53.87 (± 38.8) months, with a maximum duration of 153 months. We found a significant improvement in corrected and uncorrected visual acuity, keratometries and refraction during the follow up period. On correlation analysis, strong negative significant correlation was found between duration since surgery and change in uncorrected visual acuity (p = 0.03, ρ = 0.338) and mean keratometry values (p = 0.033, ρ = 0.296). At the latest follow up for majority of patients with more than 100 weeks of follow up (12 eyes), uncorrected visual acuity were equal to or worse than baseline. CONCLUSION: This study represents the largest follow up for ICRS implanted in keratoconus patients. Improvement of visual acuity following ICRS implantation can be expected in the first few years, after which, a decline occurring thereafter.

Diagnostic accuracy of artificial intelligence in detecting retinitis pigmentosa: A systematic review and meta-analysis.

Retinitis pigmentosa (RP) is often undetected in its early stages. Artificial intelligence (AI) has emerged as a promising tool in medical diagnostics. Therefore, we conducted a systematic review and meta-analysis to evaluate the diagnostic accuracy of AI in detecting RP using various ophthalmic images. We conducted a systematic search on PubMed, Scopus, and Web of Science databases on December 31, 2022. We included studies in the English language that used any ophthalmic imaging modality, such as OCT or fundus photography, used any AI technologies, had at least an expert in ophthalmology as a reference standard, and proposed an AI algorithm able to distinguish between images with and without retinitis pigmentosa features. We considered the sensitivity, specificity, and area under the curve (AUC) as the main measures of accuracy. We had a total of 14 studies in the qualitative analysis and 10 studies in the quantitative analysis. In total, the studies included in the meta-analysis dealt with 920,162 images. Overall, AI showed an excellent performance in detecting RP with pooled sensitivity and specificity of 0.985 [95%CI: 0.948-0.996], 0.993 [95%CI: 0.982-0.997] respectively. The area under the receiver operating characteristic (AUROC), using a random-effect model, was calculated to be 0.999 [95%CI: 0.998-1.000; P < 0.001]. The Zhou and Dendukuri I² test revealed a low level of heterogeneity between the studies, with [I2 = 19.94%] for sensitivity and [I2 = 21.07%] for specificity. The bivariate I² [20.33%] also suggested a low degree of heterogeneity. We found evidence supporting the accuracy of AI in the detection of RP; however, the level of heterogeneity between the studies was low.

Career Regret and Health-Related Quality of Life among Medical Students: A Nationwide Cross-Sectional Study in Jordan.

OBJECTIVES: Medical students have a lower quality of life (QoL) when compared to the general population. This lower QoL is associated with multiple factors such as burnout and depressive symptoms. QoL can be reflected in the degree of career satisfaction and career regret. We aim to study the prevalence of career regret in Jordanian medical students and its association with QoL and other related factors. METHODS: This national cross-sectional study consisted of an anonymous online survey distributed to medical students enrolled in all six Jordanian medical schools over a period of 6 weeks. A validated tool was used to assess QoL and students were asked a series of questions related to their career satisfaction and career regret. RESULTS: A total of 544 medical students completed the survey. The mean age was 21.5 ± 1.63 years (range 17-29), with 45.6% being males. The overall mean physical health score was 45.9 ± 5.17, and the overall mean mental health score (mental component summary (MCS)) was 42.04 ± 5.52. 76.3% of students have regretted studying medicine, citing stress as the main reason. There was a significant relation between the year of study and the percentage of career regret. Additionally, mean MCS was significantly lower in students who were frequently or always thinking about dropping out of medical school. DISCUSSION: The high percentage of career regret and the low mental QoL in Jordanian students are alarming findings, highlighting an underlying source of psychological distress in Jordanians. This calls for further investigations into the psychological health of medical students, as well as interventions to prevent the development of consequences that can impact both students and their future patients.

Optic Neuropathy Following Acute Decompensated Hypothyroidism (Myxedema Crisis).

Myxedema crisis (MC) refers to an unusual state of regulatory dysfunction precipitated by uncontrolled hypothyroidism. The pathogenic consequences of MC are broad and may contribute to significant bodily decompensation across multiple organ systems. However, shock-induced ischemic optic neuropathy (SION) in this setting has not been reported previously. Here, we present the case of a 76-year-old female with presumed bilateral optic neuropathy following abdominal surgery. The patient experienced a prolonged and complicated postoperative course in which she remained off supplemental levothyroxine. Subsequently, her clinical status deteriorated until she met diagnostic criteria for acute decompensated hypothyroidism (MC). Upon awakening from a comatose state, she reported significant vision loss. A neuro-ophthalmologic evaluation later confirmed significant constriction of her visual fields, optic disc pallor, and global retinal nerve fiber layer loss consistent with nonarteritic ischemic optic neuropathy.

The impact of COVID-19 on open access publishing in radiology and nuclear medicine: an in-depth analysis.

In response to the COVID-19 pandemic, numerous initiatives have been implemented to ensure open access availability of COVID-19-related articles to make published articles accessible for anyone. This study aimed to assess the impact of the COVID-19 pandemic on open-access publishing in radiology and nuclear medicine. We conducted a comprehensive analysis of articles and reviews published in these fields during the COVID-19 publishing era using the Web of Science database. We analyzed several indicators between COVID-19 and non-COVID-19 related articles, including the number and percentage of open-access articles, the top ten cited articles, and the number of reviews. In total, 67,100 articles were published in radiology and nuclear medicine between January 2020 and June 2022. Among those, more than half (51.1%) were open-access articles. Among these publications, 2,336 were COVID-19-related, and 64,764 were non-COVID-19-related. However, articles related to COVID-19 had an open access rate of 91.5%, compared to only 49.6% of the non-COVID-19-related articles. Moreover, COVID-19-related articles had a higher percentage of highly cited and hot papers compared to articles not related to COVID-19. Moreover, most highly cited studies were related to chest computerized tomography (CT) scan findings in COVID-19 patients. The findings emphasize the significant proportion of open access COVID-19-related publications in radiology and nuclear medicine, facilitating widespread and timely access to everyone.

The Leading Transplantation Journals: A Trend Analysis, 2011-2021.

Background: As the field of transplantation has expanded, so have the quantity and variety of articles published on the topic. Evaluation of publications and journals is crucial to the expansion of transplant research. This study investigated the research output and journal metrics of the leading solid organ transplant journals published between 2011 and 2021 based on estimations of the trends in the category CiteScore from the Scopus database. Materials and Methods: We obtained data on the listed journals from the Scopus Source List. We then filtered the list for "Transplantation" journals. Only the top quartiles or quartile 1 (Q1) journals were placed in this category. This study focused specifically on transplantation journals and did not include other journals related to diseases of transplanted organs such as the kidney, liver, heart, and lungs. Results: The number of transplantation journals increased by 42.8% in the last ten years, from 28 in 2011 to 40 in 2021. Between 2011 and 2021, nine transplantation journals ranked in the highest quartile (Q1). The American Journal of Transplantation was the top journal in both years, with a 150% increase in citations and an 11.2% increase in articles published. Open access (OA) transplant journals rose from 3 in 2011 to 10 in 2021. In 2021, OA journals earned 8,555 citations, a 125% increase from 2011. Despite this increase, non-OA journals received more citations than OA in 2021 (p value 0.026). Conclusion: Solid organ transplantation advances lead to more publications and citations. Regular journals and publications evaluation benefits academics and policymakers by promoting the growth of research. This study examined solid organ transplantation journals and gave a global perspective on transplant journal rankings and compared their status in 2011 and 2021.

ChatGPT and Artificial Intelligence in Transplantation Research: Is It Always Correct?

INTRODUCTION: ChatGPT (OpenAI, San Francisco, California, United States) is a chatbot powered by language-based artificial intelligence (AI). It generates text based on the information provided by users. It is currently being evaluated in medical research, publishing, and healthcare. However, there has been no prior study on the evaluation of its ability to help in kidney transplant research. This feasibility study aimed to evaluate the application and accuracy of ChatGPT in the field of kidney transplantation. METHODS: On two separate dates, February 21 and March 2, 2023, ChatGPT 3.5 was questioned regarding the medical treatment of kidney transplants and related scientific facts. The responses provided by the chatbot were compiled, and a panel of two specialists reviewed the correctness of each answer. RESULTS: We demonstrated that ChatGPT possessed substantial general knowledge of kidney transplantation; however, they lacked sufficient information and had inaccurate information that necessitates a deeper understanding of the topic. Moreover, ChatGPT failed to provide references for any of the scientific data it provided regarding kidney transplants, and when requested for references, it provided inaccurate ones. CONCLUSION: The results of this short feasibility study indicate that ChatGPT may have the ability to assist in data collecting when a particular query is posed. However, caution should be exercised and it should not be used in isolation as a supplement to research or decisions regarding healthcare because there are still challenges with data accuracy and missing information.