Applications of artificial intelligence and bioinformatics methodologies in the analysis of ocular biofluid markers: a scoping review.

PURPOSE: This scoping review summarizes the applications of artificial intelligence (AI) and bioinformatics methodologies in analysis of ocular biofluid markers. The secondary objective was to explore supervised and unsupervised AI techniques and their predictive accuracies. We also evaluate the integration of bioinformatics with AI tools. METHODS: This scoping review was conducted across five electronic databases including EMBASE, Medline, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics were included. RESULTS: A total of 10,262 articles were retrieved from all databases and 177 studies met the inclusion criteria. The most commonly studied ocular diseases were diabetic eye diseases, with 50 papers (28%), while glaucoma was explored in 25 studies (14%), age-related macular degeneration in 20 (11%), dry eye disease in 10 (6%), and uveitis in 9 (5%). Supervised learning was used in 91 papers (51%), unsupervised AI in 83 (46%), and bioinformatics in 85 (48%). Ninety-eight papers (55%) used more than one class of AI (e.g. > 1 of supervised, unsupervised, bioinformatics, or statistical techniques), while 79 (45%) used only one. Supervised learning techniques were often used to predict disease status or prognosis, and demonstrated strong accuracy. Unsupervised AI algorithms were used to bolster the accuracy of other algorithms, identify molecularly distinct subgroups, or cluster cases into distinct subgroups that are useful for prediction of the disease course. Finally, bioinformatic tools were used to translate complex biomarker profiles or findings into interpretable data. CONCLUSION: AI analysis of biofluid markers displayed diagnostic accuracy, provided insight into mechanisms of molecular etiologies, and had the ability to provide individualized targeted therapeutic treatment for patients. Given the progression of AI towards use in both research and the clinic, ophthalmologists should be broadly aware of the commonly used algorithms and their applications. Future research may be aimed at validating algorithms and integrating them in clinical practice.

Severe rhabdomyolysis secondary to COVID-19 mRNA vaccine in a teenager.

BACKGROUND: Rhabdomyolysis, the breakdown of skeletal muscles following an insult or injury, has been established as a possible complication of SARS-CoV-2 infection. Despite being highly effective in preventing COVID-19-related morbidity and mortality, several cases of COVID-19 mRNA vaccination-induced rhabdomyolysis have been identified. We provide the second description of a pediatric case of severe rhabdomyolysis presenting after COVID-19 mRNA vaccination. CASE: DIAGNOSIS/TREATMENT: A 16-year-old male reported to the emergency department with a 2-day history of bilateral upper extremity myalgias and dark urine 2 days after his first dose of COVID-19 vaccine (Pfizer-BioNtech). The initial blood work showed an elevated creatinine kinase (CK) of 141,300 units/L and a normal creatinine of 69 umol/L. The urinalysis was suggestive of myoglobinuria, with the microscopy revealing blood but no red blood cells. Rhabdomyolysis was diagnosed, and the patient was admitted for intravenous hydration, alkalinization of urine, and monitoring of kidney function. CK levels declined with supportive care, while his kidney function remained normal, and no electrolyte abnormalities developed. The patient was discharged 5 days after admission as his symptoms resolved. CONCLUSION: While vaccination is the safest and most effective way to prevent morbidity from COVID-19, clinicians should be aware that rhabdomyolysis could be a rare but treatable adverse event of COVID-19 mRNA vaccination. With early recognition and diagnosis and supportive management, rhabdomyolysis has an excellent prognosis.

Emerging applications of bioinformatics and artificial intelligence in the analysis of biofluid markers involved in retinal occlusive diseases: a systematic review.

PURPOSE: To review the literature on the application of bioinformatics and artificial intelligence (AI) for analysis of biofluid biomarkers in retinal vein occlusion (RVO) and their potential utility in clinical decision-making. METHODS: We systematically searched MEDLINE, Embase, Cochrane, and Web of Science databases for articles reporting on AI or bioinformatics in RVO involving biofluids from inception to August 2021. Simple AI was categorized as logistics regressions of any type. Risk of bias was assessed using the Joanna Briggs Institute Critical Appraisal Tools. RESULTS: Among 10,264 studies screened, 14 eligible articles, encompassing 578 RVO patients, met the inclusion criteria. The use and reporting of AI and bioinformatics was heterogenous. Four articles performed proteomic analyses, two of which integrated AI tools such as discriminant analysis, probabilistic clustering, and string pathway analysis. A metabolomic study used AI tools for clustering, classification, and predictive modeling such as orthogonal partial least squares discriminant analysis. However, most studies used simple AI (n = 9). Vitreous humor sample levels of interleukin-6 (IL-6), vascular endothelial growth factor (VEGF), and aqueous humor levels of intercellular adhesion molecule-1 and IL-8 were implicated in the pathogenesis of branch RVO with macular edema. IL-6 and VEGF may predict visual acuity after intravitreal injections or vitrectomy, respectively. Metabolomics and Kyoto Encyclopedia of Genes and Genomes enrichment analysis identified the metabolic signature of central RVO to be related to lower aqueous humor concentration of carbohydrates and amino acids. Risk of bias was low or moderate for included studies. CONCLUSION: Bioinformatics has applications for analysis of proteomics and metabolomics present in biofluids in RVO with AI for clinical decision-making and advancing the future of RVO precision medicine. However, multiple limitations such as simple AI use, small sample volume, inconsistent feasibility of office-based sampling, lack of longitudinal follow-up, lack of sampling before and after RVO, and lack of healthy controls must be addressed in future studies.

Anesthesia for ophthalmic surgery: an educational review.

PURPOSE: Selecting an anesthetic agent for ophthalmic surgery has crucial implications for the surgeon, anesthesiologist, and patient. This educational review explores the common classes of anesthesia used in ophthalmology. Additionally, we discuss the considerations unique to cataract, glaucoma, strabismus, orbital, oculoplastic, and ocular trauma surgeries. METHODS: A comprehensive Embase search was performed using combinations of the subject headings "anesthesia", "eye surgery", "ophthalmology" and "cataract extraction", "glaucoma", "strabismus", "vitreoretinal surgery", "retina surgery", "eye injury", and "eyelid reconstruction". RESULTS: Topical anesthetics are the most commonly used form of ocular anesthesia, used in both an office and surgical setting, and carry a minimal side effect profile. Notably, topical anesthetics offer analgesia, but do not provide akinesia or amnesia. Regional blocks, such as are sub-Tenon's, peribulbar, and retrobulbar blocks, are used when akinesia is required in addition to analgesia. Recently, sub-Tenon's blocks have recently gained popularity due to their improved safety profile compared to other regional blocks. General anesthesia is considered for long, complex surgery, surgery in patients with multiple comorbidities, surgery in young pediatric patients, or surgery in patients intolerant to local or regional anesthetic. CONCLUSION: Anesthetizing the eye has rapidly evolved in recent years, supporting the safety, efficacy and comfort of ocular surgery. Since there are many viable options of anesthetics available for ophthalmic surgery, a robust understanding of the patients needs, the skill of the surgical team, and surgery-specific factors ought to be considered when creating an anesthetic plan for surgery.

Exploration of exposure to artificial intelligence in undergraduate medical education: a Canadian cross-sectional mixed-methods study.

BACKGROUND: Emerging artificial intelligence (AI) technologies have diverse applications in medicine. As AI tools advance towards clinical implementation, skills in how to use and interpret AI in a healthcare setting could become integral for physicians. This study examines undergraduate medical students' perceptions of AI, educational opportunities about of AI in medicine, and the desired medium for AI curriculum delivery. METHODS: A 32 question survey for undergraduate medical students was distributed from May-October 2021 to students to all 17 Canadian medical schools. The survey assessed the currently available learning opportunities about AI, the perceived need for learning opportunities about AI, and barriers to educating about AI in medicine. Interviews were conducted with participants to provide narrative context to survey responses. Likert scale survey questions were scored from 1 (disagree) to 5 (agree). Interview transcripts were analyzed using qualitative thematic analysis. RESULTS: We received 486 responses from 17 of 17 medical schools (roughly 5% of Canadian undergraduate medical students). The mean age of respondents was 25.34, with 45% being in their first year of medical school, 27% in their 2nd year, 15% in their 3rd year, and 10% in their 4th year. Respondents agreed that AI applications in medicine would become common in the future (94% agree) and would improve medicine (84% agree Further, respondents agreed that they would need to use and understand AI during their medical careers (73% agree; 68% agree), and that AI should be formally taught in medical education (67% agree). In contrast, a significant number of participants indicated that they did not have any formal educational opportunities about AI (85% disagree) and that AI-related learning opportunities were inadequate (74% disagree). Interviews with 18 students were conducted. Emerging themes from the interviews were a lack of formal education opportunities and non-AI content taking priority in the curriculum. CONCLUSION: A lack of educational opportunities about AI in medicine were identified across Canada in the participating students. As AI tools are currently progressing towards clinical implementation and there is currently a lack of educational opportunities about AI in medicine, AI should be considered for inclusion in formal medical curriculum.

Maternal obesity reduces placental autophagy marker expression in uncomplicated pregnancies.

AIM: Obesity has been associated with changes in autophagy and its increasing prevalence among pregnant women is implicated in higher rates of placental-mediated complications of pregnancy such as pre-eclampsia and intrauterine growth restriction. Autophagy is involved in normal placentation, thus changes in autophagy may lead to impaired placental function and development. The aim of this study was to investigate the connection between obesity and autophagy in the placenta in otherwise uncomplicated pregnancies. METHODS: Immunohistochemistry and western blot analysis were done on placental and omental samples from obese (body mass index [BMI] ≥30 kg/m2 ) and normal weight (BMI <25 kg/m2 ) pregnant women with singleton pregnancies undergoing planned Caesarean delivery without labor at term. Samples were analyzed for autophagic markers LC3B and p62 in the peripheral, middle and central regions of the placenta and in omental adipocytes, milky spots and vasculature. RESULTS: As pre-pregnancy BMI increased, there was an increase in both placental and fetal weight as well as decreased levels of LC3B in the central region of the placenta (P = 0.0046). Within the obese patient group, LC3B levels were significantly decreased in the placentas of male fetuses compared to females (P < 0.0001). Adipocytes, compared to milky spots and vasculature, had lower levels of p62 (P = 0.0127) and LC3B (P = 0.003) in obese omenta and lower levels of LC3B in control omenta (P = 0.0071). CONCLUSION: Obesity leads to reduced placental autophagy in uncomplicated pregnancies; thus, changes in autophagy may be involved in the underlying mechanisms of obesity-related placental diseases of pregnancy.

Development of a standardized Canadian undergraduate medical education ophthalmology curriculum.

OBJECTIVE: To create a standardized undergraduate medicine ophthalmology curriculum for Canadian medical schools. DESIGN: Two-stage modified Delphi technique. PARTICIPANTS: Undergraduate ophthalmology leads at all the medical schools in Canada and 6 nonophthalmologist physicians with medical education expertise. METHODS: In stage 1, a preliminary list of curricular objectives was developed using the 2018 Association of University Professors in Ophthalmology's list of curricular objectives as a foundation. Subsequently, an online survey was sent to 24 individuals (18 ophthalmology undergraduate curriculum leads and 6 non-ophthalmology medical educators) at 17 institutions to evaluate the objectives using a 5-point Likert-type scale. In stage 2, the ophthalmology curriculum leads were invited to participate in a virtual meeting during which the list of curricular objectives was discussed and finalized by consensus. RESULTS: In stage 1, a preliminary list of 76 learning objectives organized into 10 overarching topics was developed. A total of 21 survey responses were received (87.5% response rate), allowing for the creation of a revised list. In stage 2, five participants from four schools met, achieving consensus following one round of feedback. The final undergraduate ophthalmology curriculum contained 10 topics and 75 objectives; it covered common presentations of a variety of acute and chronic eye diseases that were felt to be relevant to a wide medical audience. CONCLUSIONS: The consensus obtained on a comprehensive list of undergraduate medicine ophthalmology curricular objectives identified in this study is the first of its kind in Canada. These objectives can be used by medical schools across Canada to standardize undergraduate ophthalmology teaching.

High-Cost Drug Policies in Canadian Children's Hospitals: An Exploratory Study.

OBJECTIVE: Over the past decade a number of effective but costly drugs have entered the therapeutic arena. Ethical and logistical challenges associated with including children in research and policy have produced variability in public policy on funding pediatric drugs, with inconsistent coverage across Canada. The purpose of this study was to explore the processes for funding high-cost pediatric drugs in Canadian children's hospitals. METHODS: We conducted a cross-sectional, text-based survey of all 19 chairs of Canadian departments of pediatrics about the funding and accessibility of high-cost drugs. Thematic qualitative analysis was performed to organize, sort, and code verbatim written responses and follow-up correspondence. RESULTS: Responses were received from all 19 Canadian departments of pediatrics surveyed (100% response rate). Three major themes emerged about pediatric high-cost drug policies: inconsistency between funding processes, variability in funding sources, and frustration with the current system. In aggregate, a clear concern emerged that current funding options were heterogenous and inadequate to meet patient needs. CONCLUSIONS: There was widespread consensus from respondents that current options for funding pediatric high-cost drugs were inadequate and that there was need for urgent action to address this problem. Policy changes are needed to sustain and improve access to high-cost drugs for Canadian children. We propose 3 solutions, including the creation of a national framework for funding high-cost pediatric drugs, increased incorporation of pediatric considerations in drug research and development, and a multidisciplinary drug summit on pediatric therapeutics.

Cardiac implications of upper-arm arteriovenous fistulas: A case series.

BACKGROUND: Cardiovascular disease is a major cause of morbidity and mortality in patients with end-stage kidney disease. Arterio-venous fistulas (AVF), the gold standard for hemodialysis vascular access, are known to alter cardiac morphology and circulatory hemodynamics. We present a prospective case series of patients after creation of an AVF, explore the timeline for changes in their cardiac morphology, and detail considerations for clinicians. METHODS: Patients were recruited in 2010 at multiple centers immediately prior to the creation of an upper-arm AVF and the initiation of hemodialysis. Cardiovascular magnetic resonance images were taken at intake before the creation of the AVF, 6-month follow-up, and 12-month follow-up. Image segmentation was used to measure left ventricular volume and mass, left atrial volume, and ejection fraction. RESULTS: Eight patients met eligibility criteria. All eight patients had a net increase in left ventricular mass over enrollment, with a mean increase of 9.16 g (+2.96 to +42.66 g). Five participants had a net decrease in ejection fraction, with a mean change in ejection fraction of -5.4% (-21% to +5%). Upon visual inspection the patients with the largest ejection fraction decrease had noticeably hypertrophic and dilated ventricles. Left atrial volume change was varied, decreasing in five participants, while increasing in three participants. Changes in morphology were present at 6-month follow-up, even in patients who did not maintain AVF patency for the entirety of the 6-month period. CONCLUSION: All patients included in this prospective case series had increases in left ventricular mass, with variability in the effects on the ejection fraction and left atrial volume. As left ventricular mass is an independent predictor of morbidity and mortality, further research to determine appropriate vascular access management in both end-stage kidney disease and kidney transplant populations is warranted.

SPONTANEOUS RESOLUTION OF RETINOSCHISIS IN THE SETTING OF NARROW-ANGLE GLAUCOMA: A CASE REPORT.

PURPOSE: To present a rare case of retinoschisis in the setting of narrow-angle glaucoma that demonstrated spontaneous resolution with conservative management. METHODS: Case report presentation from the Vitreous Retina Macula Specialists of Toronto in December 2020. RESULTS: A 65-year-old woman with previous bilateral laser peripheral iridotomies for narrow-angle glaucoma was referred to a tertiary retina clinic for the assessment of query macular edema in the left eye. The patient presented with a blunted foveal reflex in the left eye, and optical coherence tomography imaging demonstrated diffuse retinoschisis of outer retinal layers in the peripapillary region and nasal macula. The patient elected for conservative management, and by 10-month follow-up, her retinoschisis resolved spontaneously. CONCLUSION: Only seven cases of retinoschisis in the setting of narrow-angle glaucoma have been identified in the literature. This is the first case in this setting to demonstrate spontaneous resolution with conservative management. Although laser peripheral iridotomies have been shown to resolve retinoschisis in narrow-angle glaucoma patients, clinicians should be aware of a conservative management approach to yield a positive improvement in retinal integrity.

Current uses of artificial intelligence in the analysis of biofluid markers involved in corneal and ocular surface diseases: a systematic review.

Corneal and ocular surface diseases (OSDs) carry significant psychosocial and economic burden worldwide. We set out to review the literature on the application of artificial intelligence (AI) and bioinformatics for analysis of biofluid biomarkers in corneal and OSDs and evaluate their utility in clinical decision making. MEDLINE, EMBASE, Cochrane and Web of Science were systematically queried for articles using AI or bioinformatics methodology in corneal and OSDs and examining biofluids from inception to August 2021. In total, 10,264 articles were screened, and 23 articles consisting of 1058 individuals were included. Using various AI/bioinformatics tools, changes in certain tear film cytokines that are proinflammatory such as increased expression of apolipoprotein, haptoglobin, annexin 1, S100A8, S100A9, Glutathione S-transferase, and decreased expression of supportive tear film components such as lipocalin-1, prolactin inducible protein, lysozyme C, lactotransferrin, cystatin S, and mammaglobin-b, proline rich protein, were found to be correlated with pathogenesis and/or treatment outcomes of dry eye, keratoconus, meibomian gland dysfunction, and Sjögren's. Overall, most AI/bioinformatics tools were used to classify biofluids into diseases subgroups, distinguish between OSD, identify risk factors, or make predictions about treatment response, and/or prognosis. To conclude, AI models such as artificial neural networks, hierarchical clustering, random forest, etc., in conjunction with proteomic or metabolomic profiling using bioinformatics tools such as Gene Ontology or Kyoto Encylopedia of Genes and Genomes pathway analysis, were found to inform biomarker discovery, distinguish between OSDs, help define subgroups with OSDs and make predictions about treatment response in a clinical setting.

The role of artificial intelligence in analysis of biofluid markers for diagnosis and management of glaucoma: A systematic review.

PURPOSE: This review focuses on utility of artificial intelligence (AI) in analysis of biofluid markers in glaucoma. We detail the accuracy and validity of AI in the exploration of biomarkers to provide insight into glaucoma pathogenesis. METHODS: A comprehensive search was conducted across five electronic databases including Embase, Medline, Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, and Web of Science. Studies pertaining to biofluid marker analysis using AI or bioinformatics in glaucoma were included. Identified studies were critically appraised and assessed for risk of bias using the Joanna Briggs Institute Critical Appraisal tools. RESULTS: A total of 10,258 studies were screened and 39 studies met the inclusion criteria, including 23 cross-sectional studies (59%), nine prospective cohort studies (23%), six retrospective cohort studies (15%), and one case-control study (3%). Primary open angle glaucoma (POAG) was the most commonly studied subtype (55% of included studies). Twenty-four studies examined disease characteristics, 10 explored treatment decisions, and 5 provided diagnostic clarification. While studies examined at entire metabolomic or proteomic profiles to determine changes in POAG, there was heterogeneity in the data with over 175 unique, differentially expressed biomarkers reported. Discriminant analysis and artificial neural network predictive models displayed strong differentiating ability between glaucoma patients and controls, although these tools were untested in a clinical context. CONCLUSION: The use of AI models could inform glaucoma diagnosis with high sensitivity and specificity. While insight into differentially expressed biomarkers is valuable in pathogenic exploration, no clear pathogenic mechanism in glaucoma has emerged.

Artificial Intelligence Analysis of Biofluid Markers in Age-Related Macular Degeneration: A Systematic Review.

This systematic review explores the use of artificial intelligence (AI) in the analysis of biofluid markers in age-related macular degeneration (AMD). We detail the accuracy and validity of AI in diagnostic and prognostic models and biofluid markers that provide insight into AMD pathogenesis and progression. This review was conducted in accordance with the Preferred Reporting Items for a Systematic Review and Meta-analysis guidelines. A comprehensive search was conducted across 5 electronic databases including Cochrane Central Register of Controlled Trials, Cochrane Database of Systematic Reviews, EMBASE, Medline, and Web of Science from inception to July 14, 2021. Studies pertaining to biofluid marker analysis using AI or bioinformatics in AMD were included. Identified studies were assessed for risk of bias and critically appraised using the Joanna Briggs Institute Critical Appraisal tools. A total of 10,264 articles were retrieved from all databases and 37 studies met the inclusion criteria, including 15 cross-sectional studies, 15 prospective cohort studies, five retrospective cohort studies, one randomized controlled trial, and one case-control study. The majority of studies had a general focus on AMD (58%), while neovascular AMD (nAMD) was the focus in 11 studies (30%), and geographic atrophy (GA) was highlighted by three studies. Fifteen studies examined disease characteristics, 15 studied risk factors, and seven guided treatment decisions. Altered lipid metabolism (HDL-cholesterol, total serum triglycerides), inflammation (c-reactive protein), oxidative stress, and protein digestion were implicated in AMD development and progression. AI tools were able to both accurately differentiate controls and AMD patients with accuracies as high as 87% and predict responsiveness to anti-VEGF therapy in nAMD patients. Use of AI models such as discriminant analysis could inform prognostic and diagnostic decision-making in a clinical setting. The identified pathways provide opportunity for future studies of AMD development and could be valuable in the advancement of novel treatments.

The Application of Artificial Intelligence in the Analysis of Biomarkers for Diagnosis and Management of Uveitis and Uveal Melanoma: A Systematic Review.

Purpose: This study aims to identify the available literature describing the utilization of artificial intelligence (AI) as a clinical tool in uveal diseases. Methods: A comprehensive literature search was conducted in 5 electronic databases, finding studies relating to AI and uveal diseases. Results: After screening 10,258 studies,18 studies met the inclusion criteria. Uveal melanoma (44%) and uveitis (56%) were the two uveal diseases examined. Ten studies (56%) used complex AI, while 13 studies (72%) used regression methods. Lactate dehydrogenase (LDH), found in 50% of studies concerning uveal melanoma, was the only biomarker that overlapped in multiple studies. However, 94% of studies highlighted that the biomarkers of interest were significant. Conclusion: This study highlights the value of using complex and simple AI tools as a clinical tool in uveal diseases. Particularly, complex AI methods can be used to weigh the merit of significant biomarkers, such as LDH, in order to create staging tools and predict treatment outcomes.