Outcome of individuals with alcoholic cirrhosis hospitalized with first decompensation and their predictors.

BACKGROUND OBJECTIVES: Alcohol is one of most common aetiologies of cirrhosis and decompensated cirrhosis is linked to higher morbidity and death rates. This study looked at the outcomes and mortality associated risk variables of individuals with alcoholic cirrhosis who had hospitalization with their first episode of decompensation. METHODS: Individuals with alcoholic cirrhosis who were hospitalized with the first episode of decompensation [acute decompensation (AD) or acute-on-chronic liver failure (ACLF)] were included in the study and were prospectively followed up until death or 90 days, whichever was earlier. RESULTS: Of the 227 study participants analyzed, 167 (73.56%) and 60 (26.43%) participants presented as AD and ACLF, respectively. In the ACLF group, the mortality rate at 90 days was higher than in the AD group (48.3 vs 32.3%, P=0.02). In the AD group, participants who initially presented with ascites as opposed to variceal haemorrhage had a greater mortality rate at 90 days (36.4 vs 17.1%, P=0.041). The chronic liver failure-consortium AD score and the lactate-free Asian Pacific Association for the study of the Liver-ACLF research consortium score best-predicted mortality in individuals with AD and ACLF. INTERPRETATION CONCLUSIONS: There is significant heterogeneity in the type of decompensation in individuals with alcoholic cirrhosis. We observed significantly high mortality rate among alcoholic participants hospitalized with initial decompensation; deaths occurring in more than one-third of study participants within 90 days.

Adverse events with EUS-guided biliary drainage: a systematic review and meta-analysis.

BACKGROUND AND AIMS: Multiple meta-analyses have evaluated the technical and clinical success of EUS-guided biliary drainage (BD), but meta-analyses concerning adverse events (AEs) are limited. The present meta-analysis analyzed AEs associated with various types of EUS-BD. METHODS: A literature search of MEDLINE, Embase, and Scopus was conducted from 2005 to September 2022 for studies analyzing the outcome of EUS-BD. The primary outcomes were incidence of overall AEs, major AEs, procedure-related mortality, and reintervention. The event rates were pooled using a random-effects model. RESULTS: One hundred fifty-five studies (7887 patients) were included in the final analysis. The pooled clinical success rates and incidence of AEs with EUS-BD were 95% (95% confidence interval [CI], 94.1-95.9) and 13.7% (95% CI, 12.3-15.0), respectively. Among early AEs, bile leak was the most common followed by cholangitis with pooled incidences of 2.2% (95% CI, 1.8-2.7) and 1.0% (95% CI, .8-1.3), respectively. The pooled incidences of major AEs and procedure-related mortality with EUS-BD were .6% (95% CI, .3-.9) and .1% (95% CI, .0-.4), respectively. The pooled incidences of delayed migration and stent occlusion were 1.7% (95% CI, 1.1-2.3) and 11.0% (95% CI, 9.3-12.8), respectively. The pooled event rate for reintervention (for stent migration or occlusion) after EUS-BD was 16.2% (95% CI, 14.0-18.3; I2 = 77.5%). CONCLUSIONS: Despite a high clinical success rate, EUS-BD may be associated with AEs in one-seventh of the cases. However, major AEs and mortality incidence remain less than 1%, which is reassuring.

Natural history of portal vein thrombosis in cirrhosis: A systematic review with meta-analysis.

BACKGROUND AND AIM: Progression of liver disease in cirrhosis is associated with an increased incidence of portal vein thrombosis (PVT) in cirrhosis. However, evidence suggests that spontaneous recanalization of PVT may occur even without anti-thrombotic therapy. Thus, the present meta-analysis was conducted to study the natural history of PVT in cirrhosis, facilitating decisions regarding anticoagulation. METHODS: Three electronic databases were searched from 2000 to August 2022 for studies reporting the outcome of PVT in cirrhotics without anticoagulation. The pooled proportions with their 95% confidence intervals (CIs) were calculated using a random-effect model. RESULTS: A total of 26 studies (n = 1441) were included in the final analysis. Progression of PVT on follow-up was seen in 22.2% (95% CI 16.1-28.4), while 77.7% (95% CI 71.6-83.9) remained non-progressive (improved or stable). The most common outcome was a stable PVT with a pooled event rate of 44.6% (95% CI 34.4-54.7). The pooled rates of regression and complete recanalization of PVT in cirrhotics were 29.3% (95% CI 20.9-37.7) and 10.4% (95% CI 5.0-15.8), respectively. On follow-up after improvement, pooled recurrence rate of PVT was 24.0% (95% CI 14.7-33.4). MELD score, and presence of ascites had a negative association, while a longer follow-up duration had positive association with PVT regression. CONCLUSION: Approximately 25% of the cases of PVT in cirrhosis are progressive, 30% cases improve, and 45% remain stable. Future studies are needed to analyze the predictors of spontaneous regression.

The impact of artificial intelligence on retinal disease management: Vision Academy retinal expert consensus.

PURPOSE OF REVIEW: The aim of this review is to define the "state-of-the-art" in artificial intelligence (AI)-enabled devices that support the management of retinal conditions and to provide Vision Academy recommendations on the topic. RECENT FINDINGS: Most of the AI models described in the literature have not been approved for disease management purposes by regulatory authorities. These new technologies are promising as they may be able to provide personalized treatments as well as a personalized risk score for various retinal diseases. However, several issues still need to be addressed, such as the lack of a common regulatory pathway and a lack of clarity regarding the applicability of AI-enabled medical devices in different populations. SUMMARY: It is likely that current clinical practice will need to change following the application of AI-enabled medical devices. These devices are likely to have an impact on the management of retinal disease. However, a consensus needs to be reached to ensure they are safe and effective for the overall population.

Current status and practical considerations of artificial intelligence use in screening and diagnosing retinal diseases: Vision Academy retinal expert consensus.

PURPOSE OF REVIEW: The application of artificial intelligence (AI) technologies in screening and diagnosing retinal diseases may play an important role in telemedicine and has potential to shape modern healthcare ecosystems, including within ophthalmology. RECENT FINDINGS: In this article, we examine the latest publications relevant to AI in retinal disease and discuss the currently available algorithms. We summarize four key requirements underlining the successful application of AI algorithms in real-world practice: processing massive data; practicability of an AI model in ophthalmology; policy compliance and the regulatory environment; and balancing profit and cost when developing and maintaining AI models. SUMMARY: The Vision Academy recognizes the advantages and disadvantages of AI-based technologies and gives insightful recommendations for future directions.

New Horizons in artificial intelligence in the healthcare of older people.

Artificial intelligence (AI) in healthcare describes algorithm-based computational techniques which manage and analyse large datasets to make inferences and predictions. There are many potential applications of AI in the care of older people, from clinical decision support systems that can support identification of delirium from clinical records to wearable devices that can predict the risk of a fall. We held four meetings of older people, clinicians and AI researchers. Three priority areas were identified for AI application in the care of older people. These included: monitoring and early diagnosis of disease, stratified care and care coordination between healthcare providers. However, the meetings also highlighted concerns that AI may exacerbate health inequity for older people through bias within AI models, lack of external validation amongst older people, infringements on privacy and autonomy, insufficient transparency of AI models and lack of safeguarding for errors. Creating effective interventions for older people requires a person-centred approach to account for the needs of older people, as well as sufficient clinical and technological governance to meet standards of generalisability, transparency and effectiveness. Education of clinicians and patients is also needed to ensure appropriate use of AI technologies, with investment in technological infrastructure required to ensure equity of access.

Efficacy and Safety of Transjugular Intrahepatic Portosystemic Shunt Creation for Budd-Chiari Syndrome: A Systematic Review and Meta-Analysis.

PURPOSE: To assess the critical role of transjugular intrahepatic portosystemic shunt (TIPS) in the management of Budd-Chiari syndrome (BCS), as the data with respect to the safety and outcome of TIPS in patients with BCS are scarce because of the rarity of the disease. MATERIALS AND METHODS: A comprehensive search of literature of various databases from 2000 to October 2021 was conducted for studies evaluating the outcome of TIPS in patients with BCS. The primary outcomes of the analysis were technical and clinical success, adverse events and mortality associated with TIPS, dysfunction of TIPS, need for TIPS revision, need for liver transplantation (LT), and 1-year survival. RESULTS: A total of 33 studies (1,395 patients) were included in this meta-analysis. The pooled rates and 95% confidence intervals of various outcomes were 98.6% (97.6-99.7) for technical success, 90.3% (86.0-94.6) for clinical success, 10.0% (6.5-13.6) for major adverse events, 0.5% (0.2-1.0) for TIPS-related mortality, 11.6% (7.8-15.4) for post-TIPS hepatic encephalopathy (HE), 40.1% (32.5-47.7) for TIPS dysfunction, 8.6% (4.9-12.4) for the need for TIPS revision, 4.5% (2.8-6.2) for the need for LT, and 94.6% (93.1-96.1) for 1-year survival. Publication bias was seen with all outcomes except for post-TIPS HE, TIPS dysfunction, and the need for LT. CONCLUSIONS: The existing literature supports the feasibility, safety, and efficacy of TIPS in the treatment of BCS. Deciding the optimal timing of TIPS in BCS needs further studies.

Building trust in real-world data: lessons from INSIGHT, the UK's health data research hub for eye health and oculomics.

PURPOSE OF REVIEW: In this review, we consider the challenges of creating a trusted resource for real-world data in ophthalmology, based on our experience of establishing INSIGHT, the UK's Health Data Research Hub for Eye Health and Oculomics. RECENT FINDINGS: The INSIGHT Health Data Research Hub maximizes the benefits and impact of historical, patient-level UK National Health Service (NHS) electronic health record data, including images, through making it research-ready including curation and anonymisation. It is built around a shared 'north star' of enabling research for patient benefit. INSIGHT has worked to establish patient and public trust in the concept and delivery of INSIGHT, with efficient and robust governance processes that support safe and secure access to data for researchers. By linking to systemic data, there is an opportunity for discovery of novel ophthalmic biomarkers of systemic diseases ('oculomics'). Datasets that provide a representation of the whole population are an important tool to address the increasingly recognized threat of health data poverty. SUMMARY: Enabling efficient, safe access to routinely collected clinical data is a substantial undertaking, especially when this includes imaging modalities, but provides an exceptional resource for research. Research and innovation built on inclusive real-world data is an important tool in ensuring that discoveries and technologies of the future may not only favour selected groups, but also work for all patients.

Hepatocellular Carcinoma Evaluation and Management for Physicians: Joint Gastroenterology Research Society and Association of Physicians of India Guidelines.

Hepatocellular carcinoma (HCC) is the most common cause of, and accounts for almost 90% of all liver cancers. Data from India is limited especially due to cancer not being a reportable disease and in view of wide variation in diagnostic modalities. This document is a result of a consensus meeting comprising Hepatologists, Interventional Radiologists, Hepatobiliary surgeons, medical and surgical Oncologists nominated by the Association of Physicians of India and Gastroenterology Research Society of Mumbai. The following Clinical Practice Guidelines for practicing physicians is intended to act as an up to date protocol for clinical management of patients with hepatocellular carcinoma. The document comprises seven sections with statements and sub-statements with strength of evidence and recommendation.

Primary Amoebic Meningoencephalitis.

Primary amoebic meningoencephalitis due to free living amoeba, also called 'brain eating amoeba', Naegleria fowleri, was detected in retroviral disease patient of 40 years who has history of using well water. Patient was admitted with severe headache, fever intermittent, nausea, vomiting and slurring of speech. CT scan and MRI scan findings were normal. CSF examination showed increased protein, low sugar and predominant lymphocytes. CSF was negative for cryptococcal antigen but wet mount preparation showed highly motile free living amoeba Naegleria fowleri. Patient was put on Amphotericin B, Metronidazole, Rifampicin in addition to ART and ATT and other supportive medications. His headache was relieved and patient improved and was discharged on request. Earlier eight cases have been reported from India of which four cases survived the acute episode.

Current paradigm of endoscopic ultrasound in biliary and pancreatic duct drainage: an update.

Endoscopic retrograde cholangiopancreatography (ERCP) is the workhorse for biliary and pancreatic ductal interventions. Despite advances in both endoscopes and accessories for ERCP, it still has limitations in the presence of altered anatomy, luminal obstruction hindering access to the papilla, and proximal duct obstructions by tight stricture, calculi or intraductal growth. Endoscopic ultrasound-guided biliary drainage (EUS-BD) and EUS-guided pancreatic duct drainage (EUS-PDD) have expanded the rescue procedures after failed ERCP. This review discusses the techniques and results of various EUS-BD procedures, as well as EUS-PDD.

Adverse events with endoscopic ultrasound-guided gastroenterostomy for gastric outlet obstruction-A systematic review and meta-analysis.

BACKGROUND: The technical and clinical effectiveness of endoscopic ultrasonography (EUS)-guided gastroenterostomy (GE) has been reported by several meta-analyses, but few of them have addressed the adverse events (AE). The goal of the current meta-analysis was to analyze the AEs associated with various types of EUS-GE. METHODS: All relevant studies reporting the AEs with EUS-GE were searched from 2000 to 31st March 2023 in MEDLINE, Embase, and Scopus. The event rates were pooled using a random effects model. RESULTS: A total of 36 studies (n = 1846) were included in the meta-analysis. The present meta-analysis reports a pooled technical success rate of 96.9% (95.9-98.0; I2 = 29.3%) with a pooled clinical success rate of 90.6% (88.5-92.7; I2 = 60.9%). The pooled incidence of overall AEs with EUS-GE was 13.0% (10.3-15.7; I2 = 69.7%), with the commonest being maldeployment of the stent, seen in 4.6% (3.2-6.0; I2 = 50.6%). The pooled incidences of serious AE and procedure-related mortality were 1.2% (0.7-1.8; I2 = 1.9%) and 0.3% (0.0-0.7; I2 = 0.0%), respectively. Subgroup analysis of studies using only the free-hand technique showed a significantly lower overall AE and maldeployment but not serious AE and other individual AEs. The pooled incidences of delayed stent migration and stent occlusion were 0.5% (0.0-1.1; I2 = 0.0%) and 0.8% (0.2-1.3; I2 = 0.0%), respectively. CONCLUSION: Despite a technical and clinical success rate of >90%, AEs are seen in around one-seventh of the cases of EUS-GE, maldeployment being the commonest. However, the pooled incidence of serious AE and mortality remains low, which is reassuring.

Clinical profile of adult and pediatric patients with hepatic Wilson's disease.

BACKGROUND: The clinical profile varies in patients with Wilson's disease (WD). There is paucity of data regarding adult and pediatric patients with hepatic WD. METHODS: As many as 140 consecutive patients diagnosed with hepatic WD between December 2006 and January 2021 were included in the study. Data was collected regarding the demographic parameters, clinical presentation, extrahepatic organ involvement, liver histology and laboratory investigations. Adult and children (0-14 years) with hepatic WD were compared regarding these features. RESULT: Eighty-eight adults and 52 children were included in the study. The median age of presentation was 17 years (range: 1.1-42 years). Male preponderance was seen (adult 68/88, 69%; children 40/52, 77%). Adults as compared to children presented more commonly as cirrhosis (52/88 vs. 15/52, p = 0.0005) and with hepatic decompensation (35/88 vs. 9/52, p = 0.005). Presentation with acute-on-chronic liver failure (ACLF) was more common in children (10/52 vs. 2/88, p = 0.0005). Twenty-eight-day mortality was 50% (5/10) in children and none in adults presenting with ACLF. Nazer's Prognostic Index (≥ 7) and New Wilson Index were more accurate in predicting mortality among children with ACLF with AUROC 1, while AARC (APASL ACLF Research Consortium) was less accurate with AUROC 0.45. Liver histology findings were similar in adults and children. Extrahepatic involvement was also similar. (8/88 in adults vs. 3/52 children, p value 0.48). CONCLUSION: Most patients with WD present as cirrhosis in adulthood. ACLF is more common in children. Nazer's prognostic index and new Wilson Index score are accurate in predicting mortality in children with ACLF.

Risk of tuberculosis with anti-TNF therapy in Indian patients with inflammatory bowel disease despite negative screening.

BACKGROUND AND STUDY AIMS: Tuberculosis (TB) is a well-recognized adverse effect associated with using biological therapy to manage various autoimmune conditions. There is a dearth of information about the development of TB after using anti-TNF agents in patients with inflammatory bowel disease (IBD) from TB-endemic countries like India. This study aimed to estimate the risk of TB and its predictors after treatment with anti-TNF agents in patients with IBD. PATIENTS AND METHODS: The present study is a retrospective analysis of data of patients with IBD from two tertiary care centers in India receiving anti-TNF therapy. Patients who had undergone chest X-ray, high-resolution computed tomography of the chest, and tuberculin skin test, with a follow-up duration of at least 6 months, were included in the analysis. RESULTS: In this multi-center study, 95 patients on anti-TNF agents for IBD (Median age of onset: 27 years, 62.1 % males) were followed up for a median duration of 9 (6-142) months. Among patients with IBD, 79 (83.2 %) had Crohn's disease, and 16 (16.8 %) had ulcerative colitis. Infliximab was the commonest biological, used in 82.1 % of cases, followed by adalimumab (17.9 %). On follow-up, 8.4 % (8/95) of the patients developed TB, among which the majority had extrapulmonary tuberculosis (5/8). On multivariate analysis, the duration of biological (Odds ratio: 1.047, 95 % confidence interval 1.020-1.075; p = 0.001) use was the only independent predictor of the development of TB with biologicals. CONCLUSION: Among Indian patients with IBD, there is a high risk of TB with anti-TNF agents, which increases with the duration of therapy. The current methods for latent TB screening in Indians are ineffective, and predicting TB after initiating biological therapy is difficult.

Safety and efficacy of endoscopic retrograde cholangiopancreatography in pediatric pancreatic and biliary disorders.

INTRODUCTION: There is sparse data from India on indications, technical success, safety and outcomes of endoscopic retrograde cholangiopancreatography (ERCP) using standard adult duodenoscope in the pediatric population. METHODS: Retrospective analysis of prospectively maintained electronic endoscopy and clinical database was performed to identify pediatric patients (age ≤ 18 years) who underwent ERCP between January 2017 and December 2022. Demographics and procedural details including indications, cholangio-pancreatogram findings, endotherapy type performed, technical and clinical success and complications were noted. RESULTS: As many as 150 pediatric patients were included of whom 88 had pancreatic (mean age-13.7 years) and 62 had biliary disease (mean age- 14.9 years). Common pancreatic ERCP indications were chronic pancreatitis (n = 45 [51.1%]), pancreatic duct disruption fistula (n = 21 [23.9%]) and recurrent acute pancreatitis (n = 16 [18.2%]). Among biliary indications were choledocholithiasis (n = 29 [46.8%]), benign bile duct strictures (n = 13 [21%]), bile duct injury/leak and biliary stent removal (n = 7 [11.3%]) , choledochal cyst (n = 5  [8.1%]) and pancreatic mass causing biliary compression (n = 1 [1.6%]). Technical success in pancreatic and biliary ERCP was 94.3% and 95.2%, respectively, and clinical success was 84.1% and 93.5%, respectively. Most common complications following pancreatic ERCPs were acute pancreatitis (n = 9 [10.2%]) (mild = 5, moderate = 4) patients and post sphincterotomy bleed in one (1.1%). Among biliary ERCPs, post ERCP pancreatitis was seen in (n = 3 [4.8%]) (mild = 2, moderate = 1). CONCLUSION: ERCP can be safely and effectively performed in children using standard duodenoscope. Chronic pancreatitis, choledocholithiasis and pancreatic divisum are common pediatric ERCP indications.

Detecting Algorithmic Errors and Patient Harms for AI-Enabled Medical Devices in Randomized Controlled Trials: Protocol for a Systematic Review.

BACKGROUND: Artificial intelligence (AI) medical devices have the potential to transform existing clinical workflows and ultimately improve patient outcomes. AI medical devices have shown potential for a range of clinical tasks such as diagnostics, prognostics, and therapeutic decision-making such as drug dosing. There is, however, an urgent need to ensure that these technologies remain safe for all populations. Recent literature demonstrates the need for rigorous performance error analysis to identify issues such as algorithmic encoding of spurious correlations (eg, protected characteristics) or specific failure modes that may lead to patient harm. Guidelines for reporting on studies that evaluate AI medical devices require the mention of performance error analysis; however, there is still a lack of understanding around how performance errors should be analyzed in clinical studies, and what harms authors should aim to detect and report. OBJECTIVE: This systematic review will assess the frequency and severity of AI errors and adverse events (AEs) in randomized controlled trials (RCTs) investigating AI medical devices as interventions in clinical settings. The review will also explore how performance errors are analyzed including whether the analysis includes the investigation of subgroup-level outcomes. METHODS: This systematic review will identify and select RCTs assessing AI medical devices. Search strategies will be deployed in MEDLINE (Ovid), Embase (Ovid), Cochrane CENTRAL, and clinical trial registries to identify relevant papers. RCTs identified in bibliographic databases will be cross-referenced with clinical trial registries. The primary outcomes of interest are the frequency and severity of AI errors, patient harms, and reported AEs. Quality assessment of RCTs will be based on version 2 of the Cochrane risk-of-bias tool (RoB2). Data analysis will include a comparison of error rates and patient harms between study arms, and a meta-analysis of the rates of patient harm in control versus intervention arms will be conducted if appropriate. RESULTS: The project was registered on PROSPERO in February 2023. Preliminary searches have been completed and the search strategy has been designed in consultation with an information specialist and methodologist. Title and abstract screening started in September 2023. Full-text screening is ongoing and data collection and analysis began in April 2024. CONCLUSIONS: Evaluations of AI medical devices have shown promising results; however, reporting of studies has been variable. Detection, analysis, and reporting of performance errors and patient harms is vital to robustly assess the safety of AI medical devices in RCTs. Scoping searches have illustrated that the reporting of harms is variable, often with no mention of AEs. The findings of this systematic review will identify the frequency and severity of AI performance errors and patient harms and generate insights into how errors should be analyzed to account for both overall and subgroup performance. TRIAL REGISTRATION: PROSPERO CRD42023387747; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=387747. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/51614.

Upfront tofacitinib in patients with biological-naïve ulcerative colitis - An Indian multicentric experience.

OBJECTIVES: Tofacitinib is a Janus Kinase inhibitor used for treating moderate to severe ulcerative colitis (UC), mainly after the failure of biological therapy. There is a paucity of data on the outcome of tofacitinib in biological-naïve UC patients. The present study was aimed at analyzing the safety and efficacy of tofacitinib in biological-naïve Indian patients with UC. METHODS: The present study retrospectively evaluated consecutive patients with biological-naïve moderate-to-severe active UC from six tertiary care centers in India receiving tofacitinib from September 2020 to September 2022. Clinical remission or response assessment was based on partial Mayo score (PMS) calculated at baseline and weeks eight, 16 and 24. RESULTS: Total 47 cases (57.4% male, median age: 32 years) were included. After eight weeks of therapy, 33 (70.2%) achieved clinical remission and eight (17.0%) had a primary failure. The baseline serum albumin at treatment initiation was the only independent predictor of remission at eight weeks (Odds ratio: 11.560, 95% CI: 1.478 - 90.404), but not at 16 weeks. By 24 weeks, 59.6% (28/47) of the patients were in remission and 29.8% (14/47) had stopped tofacitinib either due to failure (27.6%) or adverse events (AEs) (2.1%). Among the 47 patients, 10 (21.2%) cases developed AEs during follow-up, including two tuberculosis (4.2%), one cytomegalovirus (CMV) colitis (2.1%) and one herpes zoster (2.1%). Four patients with infection required temporary drug discontinuations. One required permanent discontinuation (mania). CONCLUSION: Upfront tofacitinib is effective in biologic-naïve Indian patients with moderate-severe UC. Further randomized studies are required to validate the study findings.

AI as a Medical Device for Ophthalmic Imaging in Europe, Australia, and the United States: Protocol for a Systematic Scoping Review of Regulated Devices.

BACKGROUND: Artificial intelligence as a medical device (AIaMD) has the potential to transform many aspects of ophthalmic care, such as improving accuracy and speed of diagnosis, addressing capacity issues in high-volume areas such as screening, and detecting novel biomarkers of systemic disease in the eye (oculomics). In order to ensure that such tools are safe for the target population and achieve their intended purpose, it is important that these AIaMD have adequate clinical evaluation to support any regulatory decision. Currently, the evidential requirements for regulatory approval are less clear for AIaMD compared to more established interventions such as drugs or medical devices. There is therefore value in understanding the level of evidence that underpins AIaMD currently on the market, as a step toward identifying what the best practices might be in this area. In this systematic scoping review, we will focus on AIaMD that contributes to clinical decision-making (relating to screening, diagnosis, prognosis, and treatment) in the context of ophthalmic imaging. OBJECTIVE: This study aims to identify regulator-approved AIaMD for ophthalmic imaging in Europe, Australia, and the United States; report the characteristics of these devices and their regulatory approvals; and report the available evidence underpinning these AIaMD. METHODS: The Food and Drug Administration (United States), the Australian Register of Therapeutic Goods (Australia), the Medicines and Healthcare products Regulatory Agency (United Kingdom), and the European Database on Medical Devices (European Union) regulatory databases will be searched for ophthalmic imaging AIaMD through a snowballing approach. PubMed and clinical trial registries will be systematically searched, and manufacturers will be directly contacted for studies investigating the effectiveness of eligible AIaMD. Preliminary regulatory database searches, evidence searches, screening, data extraction, and methodological quality assessment will be undertaken by 2 independent review authors and arbitrated by a third at each stage of the process. RESULTS: Preliminary searches were conducted in February 2023. Data extraction, data synthesis, and assessment of methodological quality commenced in October 2023. The review is on track to be completed and submitted for peer review by April 2024. CONCLUSIONS: This systematic review will provide greater clarity on ophthalmic imaging AIaMD that have achieved regulatory approval as well as the evidence that underpins them. This should help adopters understand the range of tools available and whether they can be safely incorporated into their clinical workflow, and it should also support developers in navigating regulatory approval more efficiently. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/52602.