rECHOmmend: An ECG-Based Machine Learning Approach for Identifying Patients at Increased Risk of Undiagnosed Structural Heart Disease Detectable by Echocardiography.

BACKGROUND: Timely diagnosis of structural heart disease improves patient outcomes, yet many remain underdiagnosed. While population screening with echocardiography is impractical, ECG-based prediction models can help target high-risk patients. We developed a novel ECG-based machine learning approach to predict multiple structural heart conditions, hypothesizing that a composite model would yield higher prevalence and positive predictive values to facilitate meaningful recommendations for echocardiography. METHODS: Using 2 232 130 ECGs linked to electronic health records and echocardiography reports from 484 765 adults between 1984 to 2021, we trained machine learning models to predict the presence or absence of any of 7 echocardiography-confirmed diseases within 1 year. This composite label included the following: moderate or severe valvular disease (aortic/mitral stenosis or regurgitation, tricuspid regurgitation), reduced ejection fraction <50%, or interventricular septal thickness >15 mm. We tested various combinations of input features (demographics, laboratory values, structured ECG data, ECG traces) and evaluated model performance using 5-fold cross-validation, multisite validation trained on 1 site and tested on 10 independent sites, and simulated retrospective deployment trained on pre-2010 data and deployed in 2010. RESULTS: Our composite rECHOmmend model used age, sex, and ECG traces and had a 0.91 area under the receiver operating characteristic curve and a 42% positive predictive value at 90% sensitivity, with a composite label prevalence of 17.9%. Individual disease models had area under the receiver operating characteristic curves from 0.86 to 0.93 and lower positive predictive values from 1% to 31%. Area under the receiver operating characteristic curves for models using different input features ranged from 0.80 to 0.93, increasing with additional features. Multisite validation showed similar results to cross-validation, with an aggregate area under the receiver operating characteristic curve of 0.91 across our independent test set of 10 clinical sites after training on a separate site. Our simulated retrospective deployment showed that for ECGs acquired in patients without preexisting structural heart disease in the year 2010, 11% were classified as high risk and 41% (4.5% of total patients) developed true echocardiography-confirmed disease within 1 year. CONCLUSIONS: An ECG-based machine learning model using a composite end point can identify a high-risk population for having undiagnosed, clinically significant structural heart disease while outperforming single-disease models and improving practical utility with higher positive predictive values. This approach can facilitate targeted screening with echocardiography to improve underdiagnosis of structural heart disease.

An ECG-based machine learning model for predicting new-onset atrial fibrillation is superior to age and clinical features in identifying patients at high stroke risk.

BACKGROUND: Several large trials have employed age or clinical features to select patients for atrial fibrillation (AF) screening to reduce strokes. We hypothesized that a machine learning (ML) model trained to predict AF risk from 12­lead electrocardiogram (ECG) would be more efficient than criteria based on clinical variables in indicating a population for AF screening to potentially prevent AF-related stroke. METHODS: We retrospectively included all patients with clinical encounters in Geisinger without a prior history of AF. Incidence of AF within 1 year and AF-related strokes within 3 years of the encounter were identified. AF-related stroke was defined as a stroke where AF was diagnosed at the time of stroke or within a year after the stroke. The efficiency of five methods was evaluated for selecting a cohort for AF screening. The methods were selected from four clinical trials (mSToPS, GUARD-AF, SCREEN-AF and STROKESTOP) and the ECG-based ML model. We simulated patient selection for the five methods between the years 2011 and 2014 and evaluated outcomes for 1 year intervals between 2012 and 2015, resulting in a total of twenty 1-year periods. Patients were considered eligible if they met the criteria before the start of the given 1-year period or within that period. The primary outcomes were numbers needed to screen (NNS) for AF and AF-associated stroke. RESULTS: The clinical trial models indicated large proportions of the population with a prior ECG for AF screening (up to 31%), coinciding with NNS ranging from 14 to 18 for AF and 249-359 for AF-associated stroke. At comparable sensitivity, the ECG ML model indicated a modest number of patients for screening (14%) and had the highest efficiency in NNS for AF (7.3; up to 60% reduction) and AF-associated stroke (223; up to 38% reduction). CONCLUSIONS: An ECG-based ML risk prediction model is more efficient than contemporary AF-screening criteria based on age alone or age and clinical features at indicating a population for AF screening to potentially prevent AF-related strokes.

Effects of rapid maxillary expansion on anchorage alveolar bone meta-analysis.

PURPOSE: Rapid maxillary expansion (RME) is a routine method for correcting transverse maxillary deficiency. This paper investigated the effect of RME on anchorage alveolar bone and examined the differences between micro-implant-assisted RME and conventional RME. METHODS: Relevant articles were selected from the PubMed, EMBASE and Cochrane Central Register of Controlled Trials databases. Review Manager software (v.5.3) was used for the pooled analysis and Cochran Q and I2 statistic tests were used to assess the heterogeneity. RESULTS: Following conventional RME, the distal buccal alveolar bone thickness and the mesiobuccal alveolar thickness of the maxillary first molars were significantly reduced. Hyrax (standard mean difference [SMD]: -0.93, 95% confidence interval [CI]: -1.20-0.66) and Haas procedures (SMD: -0.88, 95% CI: -1.40-0.36) significantly reduced the buccal vertical alveolar height of the maxillary first molars. Similar results were obtained for the maxillary first premolars following RME. The thickness of the buccal alveolar bone decreased with conventional RME compared to when using the method assisted by micro-implants. CONCLUSIONS: Conventional RME can reduce the thickness and vertical height of maxillary alveolar bone, and there is less loss of alveolar bone when using micro-implant-assisted RME. Further research is needed to validate the findings.

Prevalence of mild behavioural impairment: a systematic review and meta-analysis.

AIM: Mild behavioural impairment (MBI) is a neurobehavioural syndrome characterized by emergent neuropsychiatric symptoms in later life. There has been no systematic review or meta-analysis on the prevalence of MBI. The main aim of the study is to calculate the pooled prevalence of MBI. METHODS: A search of the literature on MBI in mild cognitive impairment (MCI), cognitively normal (CN), and subjective cognitive impairment (SCI) and CN but at risk (CN-AR) subjects published between 1 January 2003 and 28 September 2020 was conducted. Meta-analysis using a random effects model was performed to determine the pooled estimate of the prevalence of MBI. Meta-regression was performed to identify factors contributing to the variance of prevalence rate. A systematic review was also performed to study the impact of MBI in cognitive outcomes and its correlation to the pathology and genetics of Alzheimer's disease. RESULTS: Eleven studies conducted among 15 689 subjects underwent meta-analysis, revealing the pooled prevalence of MBI to be 33.5% (95% confidence interval (CI): 22.6%-46.6%). Seven studies conducted among 1358 MCI subjects underwent meta-analysis, revealing the pooled prevalence to be 45.5% (95%CI: 36.1%-55.3%). Four studies conducted among 13 153 CN subjects underwent meta-analysis, revealing the pooled prevalence to be 17.0% (95%CI: 7.2%-34.9%). Five studies conducted among 1158 SCI or CN-AR subjects underwent meta-analysis, revealing the pooled prevalence to be 35.8% (95%CI: 21.4%-53.2%). A systematic review of 13 studies showed that MBI has a significant impact on cognitive deterioration and is associated with the pathology and genetics of Alzheimer's disease. CONCLUSIONS: In MCI, CN, and SCI and CN-AR subjects, MBI is common. Our finding is potentially useful in planning future clinical trials.

Comprehensive comparative effectiveness and safety of first-line antihypertensive drug classes: a systematic, multinational, large-scale analysis.

BACKGROUND: Uncertainty remains about the optimal monotherapy for hypertension, with current guidelines recommending any primary agent among the first-line drug classes thiazide or thiazide-like diuretics, angiotensin-converting enzyme inhibitors, angiotensin receptor blockers, dihydropyridine calcium channel blockers, and non-dihydropyridine calcium channel blockers, in the absence of comorbid indications. Randomised trials have not further refined this choice. METHODS: We developed a comprehensive framework for real-world evidence that enables comparative effectiveness and safety evaluation across many drugs and outcomes from observational data encompassing millions of patients, while minimising inherent bias. Using this framework, we did a systematic, large-scale study under a new-user cohort design to estimate the relative risks of three primary (acute myocardial infarction, hospitalisation for heart failure, and stroke) and six secondary effectiveness and 46 safety outcomes comparing all first-line classes across a global network of six administrative claims and three electronic health record databases. The framework addressed residual confounding, publication bias, and p-hacking using large-scale propensity adjustment, a large set of control outcomes, and full disclosure of hypotheses tested. FINDINGS: Using 4·9 million patients, we generated 22 000 calibrated, propensity-score-adjusted hazard ratios (HRs) comparing all classes and outcomes across databases. Most estimates revealed no effectiveness differences between classes; however, thiazide or thiazide-like diuretics showed better primary effectiveness than angiotensin-converting enzyme inhibitors: acute myocardial infarction (HR 0·84, 95% CI 0·75-0·95), hospitalisation for heart failure (0·83, 0·74-0·95), and stroke (0·83, 0·74-0·95) risk while on initial treatment. Safety profiles also favoured thiazide or thiazide-like diuretics over angiotensin-converting enzyme inhibitors. The non-dihydropyridine calcium channel blockers were significantly inferior to the other four classes. INTERPRETATION: This comprehensive framework introduces a new way of doing observational health-care science at scale. The approach supports equivalence between drug classes for initiating monotherapy for hypertension-in keeping with current guidelines, with the exception of thiazide or thiazide-like diuretics superiority to angiotensin-converting enzyme inhibitors and the inferiority of non-dihydropyridine calcium channel blockers. FUNDING: US National Science Foundation, US National Institutes of Health, Janssen Research & Development, IQVIA, South Korean Ministry of Health & Welfare, Australian National Health and Medical Research Council.

Poorly cited articles in peer-reviewed cardiovascular journals from 1997 to 2007: analysis of 5-year citation rates.

BACKGROUND: The extent to which articles are cited is a surrogate of the impact and importance of the research conducted; poorly cited articles may identify research of limited use and potential wasted investments. We assessed trends in the rates of poorly cited articles and journals in the cardiovascular literature from 1997 to 2007. METHODS AND RESULTS: We identified original articles published in cardiovascular journals and indexed in the Scopus citation database from 1997 to 2007. We defined poorly cited articles as those with ≤5 citations in the 5 years following publication and poorly cited journals as those with >75% of journal content poorly cited. We identified 164 377 articles in 222 cardiovascular journals from 1997 to 2007. From 1997 to 2007, the number of cardiovascular articles and journals increased by 56.9% and 75.2%, respectively. Of all the articles, 75 550 (46.0%) were poorly cited, of which 25 650 (15.6% overall) had no citations. From 1997 to 2007, the proportion of poorly cited articles declined slightly (52.1%-46.2%, trend P<0.001), although the absolute number of poorly cited articles increased by 2595 (trend P<0.001). At a journal level, 44% of cardiovascular journals had more than three-fourths of the journal's content poorly cited at 5 years. CONCLUSION: Nearly half of all peer-reviewed articles published in cardiovascular journals are poorly cited 5 years after publication, and many are not cited at all. The cardiovascular literature and the number of poorly cited articles both increased substantially from 1997 to 2007. The high proportion of poorly cited articles and journals suggests inefficiencies in the cardiovascular research enterprise.

Life threatening biphasic adverse reactions to desmopressin: case report and review of the literature.

Treatment with desmopressin diacetate arginine vasopressin (DDAVP) and its withdrawal are associated with side effects. We present a rare case of severe biphasic adverse reactions induced by DDAVP and its withdrawal in a 63-year-old female patient. A lump in the left axillary region was biopsied, and she received DDAVP after surgery. The following day, she lost consciousness, with foaming at the mouth and seizures. Hypotonic encephalopathy was considered. DDAVP was ceased, and she received electrolytes. On day 1, she displayed low blood pressure and increased urine output. She received DDAVP and dopamine as well as electrolytes. The patient was ambulatory on day 7 and was discharged without brain abnormalities on MRI. In conclusion, severe hyponatremia induced by DDAVP and massive polyuria and hypovolemic shock induced by DDAVP withdrawal are life-threatening conditions. This case underlines the need to be vigilant when administering DDAVP and to monitor for any side effects.

Measures of Implicit Gender Attitudes May Exaggerate Differences in Underlying Associations among Chinese Urban and Rural Women.

The oppression of women in rural China is more severe than in urban China, not only because the two areas differ in terms of social hierarchy, but also because urban women are more likely to fight against their subordination, which is endorsed by conventional social views on gender. To independently assess these relationships, we applied the Quadruple Process model to measure the processes underlying implicit gender attitudes in a sample of urban and rural females. The results indicated that the urban women had higher in-group favoritism than did the rural women. Application of the Quad model, however, showed that pro-women associations were similarly activated among urban and rural women, but that women in rural settings more effectively inhibited activated associations. Differences in inhibition, rather than in activated associations, appear to account for the less favorable attitudes among rural women. Thus, the differences in attitudinal responses among urban and rural women exaggerate the differences in underlying evaluative associations with respect to gender and conceal differences in self-regulating the expression of those associations.

Hospital variation in admission to intensive care units for patients with acute myocardial infarction.

BACKGROUND: The treatment for patients with acute myocardial infarction (AMI) was transformed by the introduction of intensive care units (ICUs), yet we know little about how contemporary hospitals use this resource-intensive setting and whether higher use is associated with better outcomes. METHODS: We identified 114,136 adult hospitalizations for AMI from 307 hospitals in the 2009 to 2010 Premier database using codes from the International Classification of Diseases, Ninth Revision, Clinical Modification. Hospitals were stratified into quartiles by rates of ICU admission for AMI patients. Across quartiles, we examined in-hospital risk-standardized mortality rates and usage rates of critical care therapies for these patients. RESULTS: Rates of ICU admission for AMI patients varied markedly among hospitals (median 48%, Q1-Q4 20%-71%, range 0%-98%), and there was no association with in-hospital risk-standardized mortality rates (6% all quartiles, P = .7). However, hospitals admitting more AMI patients to the ICU were more likely to use critical care therapies overall (mechanical ventilation [from Q1 with lowest rate of ICU use to Q4 with highest rate 13%-16%], vasopressors/inotropes [17%-21%], intra-aortic balloon pumps [4%-7%], and pulmonary artery catheters [4%-5%]; P for trend < .05 in all comparisons). CONCLUSIONS: Rates of ICU admission for patients with AMI vary substantially across hospitals and were not associated with differences in mortality, but were associated with greater use of critical care therapies. These findings suggest uncertainty about the appropriate use of this resource-intensive setting and a need to optimize ICU triage for patients who will truly benefit.

Setting the Theater for Creativity: Proposal for Integrating Temporal and Spatial Artificial Mnemonics as a Qualitative Artificial Development of the Autobiographical Naturalistic Mnemonics (AM).

Mnemonics are not only tools that empower memory but also have a significant role in qualitatively transforming mental functions and, hence, consciousness in general. A specific type of mnemonics is autobiographical mnemonics (AM) constructed of spatial, temporal, and semantic dimensions used in a naturalist form by individuals about their own experiences. This paper proposes a spatial-temporal mnemonic that transforms AM from a naturalist level into an artificial one. We consider allowing the intellect and consciousness to grasp the abstract flow of time in the global context of geography will contribute to setting the stage for creativity. By explicitly representing the abstract time-space theater, the intellect (the world view) is more able to reflect the abstract laws of reality (the world), hence, to make the intellect sphere objectively equipped to externalize the emerged meanings (the internalized reality) that reflect the internal content of experience and, hence, make sense of them as a crucial function in creative activity. The paper is a theoretical and methodological step for the empirical part of the proposal when the mnemonic should be used as a training tool to empower creativity factors.

Near-peer teaching in a required third-year clerkship.

Students who teach less experienced students within the same educational program are known as near-peer teachers. A number of studies have shown that near-peers are effective teachers in preclinical courses such as anatomy and physical examination. We hypothesized that near-peers could also be effective teachers in a clinical clerkship. We report on a pilot study in which near-peers participated in a training session and then taught a brief problem-focused skills curriculum to third-year students during a required ambulatory medicine rotation. The clerkship students assigned high ratings to the near-peer teachers, both on an absolute scale and relative to faculty. The results suggest that including near-peers as teachers in a clinical clerkship may be appropriate and that this concept deserves further investigation.

Ginsenoside Rg1 ameliorates Alzheimer's disease pathology via restoring mitophagy.

Background: Alzheimer's disease (AD) is a common form of dementia, and impaired mitophagy is a hallmark of AD. Mitophagy is mitochondrial-specific autophagy. Ginsenosides from Ginseng involve in autophagy in cancer. Ginsenoside Rg1 (Rg1 hereafter), a single compound of Ginseng, has neuroprotective effects on AD. However, few studies have reported whether Rg1 can ameliorate AD pathology by regulating mitophagy. Methods: Human SH-SY5Y cell and a 5XFAD mouse model were used to investigate the effects of Rg1. Rg1 (1µM) was added to ß-amyloid oligomer (AßO)-induced or APPswe-overexpressed cell models for 24 hours. 5XFAD mouse models were intraperitoneally injected with Rg1 (10 mg/kg/d) for 30 days. Expression levels of mitophagy-related markers were analyzed by western blot and immunofluorescent staining. Cognitive function was assessed by Morris water maze. Mitophagic events were observed using transmission electron microscopy, western blot, and immunofluorescent staining from mouse hippocampus. The activation of the PINK1/Parkin pathway was examined using an immunoprecipitation assay. Results: Rg1 could restore mitophagy and ameliorate memory deficits in the AD cellular and/or mouse model through the PINK1-Parkin pathway. Moreover, Rg1 might induce microglial phagocytosis to reduce ß-amyloid (Aß) deposits in the hippocampus of AD mice. Conclusion: Our studies demonstrate the neuroprotective mechanism of ginsenoside Rg1 in AD models. Rg1 induces PINK-Parkin mediated mitophagy and ameliorates memory deficits in 5XFAD mouse models.

Treatment effects of low-frequency repetitive transcranial magnetic stimulation combined with motor relearning procedure on spasticity and limb motor function in stroke patients.

Objective: Limb paralysis, which is a sequela of stroke, limits patients' activities of daily living and lowers their quality of life. The purpose of this study was to investigate the effects of repetitive transcranial magnetic stimulation (rTMS) combined with a motor relearning procedure (MRP) on motor function and limb spasticity in stroke patients. Methods: Stroke patients were randomly divided into a combined treatment group (rTMS + MRP) and a control group (MRP) (n = 30 per group). The control group was given MRP in addition to conventional rehabilitation, and the combined treatment group was given 1 Hz rTMS combined with MRP. The treatment efficacy was assessed by the modified Ashworth scale (MAS), Fugl-Meyer motor function scale, and motor evoked potential (MEP) testing. Results: After 4 weeks of treatment, the Brunnstrom score, Fugl-Meyer lower extremity motor function, and Fugl-Meyer balance function were significantly higher in the combination treatment group compared to the control group, while the MAS score was lower in the combination treatment group compared to the control group. The MEP extraction rate was higher in the combined treatment group compared to the control group, while the threshold and central motor conduction time (CMCT) were lower in the combined treatment group compared to the control group. Conclusion: Low-frequency rTMS combined with MRP had better efficacy on spasticity and motor function in stroke patients with hemiparesis than MRP alone.

Modulation of perovskite degradation with multiple-barrier for light-heat stable perovskite solar cells.

The long-term stability of perovskite solar cells remains one of the most important challenges for the commercialization of this emerging photovoltaic technology. Here, we adopt a non-noble metal/metal oxide/polymer multiple-barrier to suppress the halide consumption and gaseous perovskite decomposition products release with the chemically inert bismuth electrode and Al2O3/parylene thin-film encapsulation, as well as the tightly closed system created by the multiple-barrier to jointly suppress the degradation of perovskite solar cells, allowing the corresponding decomposition reactions to reach benign equilibria. The resulting encapsulated formamidinium cesium-based perovskite solar cells with multiple-barrier maintain 90% of their initial efficiencies after continuous operation at 45 °C for 5200 h and 93% of their initial efficiency after continuous operation at 75 °C for 1000 h under 1 sun equivalent white-light LED illumination.

MicroRNA-128 suppresses tau phosphorylation and reduces amyloid-beta accumulation by inhibiting the expression of GSK3ß, APPBP2, and mTOR in Alzheimer's disease.

INTRODUCTION AND AIMS: Alzheimer's disease (AD) is characterized by the abnormal accumulation of hyperphosphorylated tau proteins and amyloid-beta (Aß) peptides. Recent studies have shown that many microRNAs (miRNAs) are dysregulated in AD, and modulation of these miRNAs can influence the development of tau and Aß pathology. The brain-specific miRNA miR-128, encoded by MIR128-1 and MIR128-2, is important for brain development and dysregulated in AD. In this study, the role of miR-128 in tau and Aß pathology as well as the regulatory mechanism underlying its dysregulation were investigated. METHODS: The effect of miR-128 on tau phosphorylation and Aß accumulation was examined in AD cellular models through miR-128 overexpression and inhibition. The therapeutic potential of miR-128 in AD mouse model was assessed by comparing phenotypes of 5XFAD mice administered with miR-128-expressing AAVs with 5XFAD mice administered with control AAVs. Phenotypes examined included behavior, plaque load, and protein expression. The regulatory factor of miR-128 transcription was identified through luciferase reporter assay and validated by siRNA knockdown and ChIP analysis. RESULTS: Both gain-of-function and loss-of-function studies in AD cellular models reveal that miR-128 represses tau phosphorylation and Aß secretion. Subsequent investigations show that miR-128 directly inhibits the expression of tau phosphorylation kinase GSK3ß and Aß modulators APPBP2 and mTOR. Upregulation of miR-128 in the hippocampus of 5XFAD mice ameliorates learning and memory impairments, decreases plaque deposition, and enhances autophagic flux. We further demonstrated that C/EBPα transactivates MIR128-1 transcription, while both C/EBPα and miR-128 expression are inhibited by Aß. CONCLUSION: Our findings suggest that miR-128 suppresses AD pathogenesis, and could be a promising therapeutic target for AD. We also find a possible mechanism underlying the dysregulation of miR-128 in AD, in which Aß reduces miR-128 expression by inhibiting C/EBPα.

PVT1 promotes resistance to 5-FU in colon cancer via the miR-486-5p/CDK4 axis.

Drug resistance in tumors is a major issue, limiting the curative efficacy of currently available cancer chemotherapeutics. 5-Fluorouracil (5-FU) is a commonly applied therapeutic drug in colon cancer patient regimens; however, the majority of patients develop resistance to 5-FU in the later stages of the disease, rendering this chemotherapy ineffective. Drug resistance is the main factor underlying the poor prognosis of patients with colon cancer. In recent years, a number of studies have confirmed that long non-coding (lnc)RNAs may play vital roles in tumor resistance. In the present study, the Gene Expression Omnibus (GEO) and lncRNADisease2 databases were screened for colon cancer-associated expression patterns of lncRNA plasmacytoma variant translocation 1 (PVT1). Subsequently, reverse transcription-quantitative polymerase chain reaction (RT-qPCR) was used to detect changes in PVT1 expression in resistant cell lines, and a Cell Counting Kit-8 (CCK-8) assay kit was used to assess the effects of PVT1 knockdown on the half maximal inhibitory concentrations of parental and 5-FU-resistant HCT116 cells. Subsequently, CCK-8, clone formation, and flow cytometric assays were performed to investigate the effects of PVT1 knockdown on the sensitivity of HCT116-5FU-resistant cells to 5-FU. Dual-luciferase assay, RNA pull-down and RNA immunoprecipitation assays verified the interactive regulation of PVT1, miR-486-5p and cyclin dependent kinase 4 (CDK4). PVT1 was highly expressed in HCT116-5FU-resistant cells, as compared to its expression in HCT116 parental cells. PVT1 knockdown significantly reduced the resistance of HCT116-5FU-resistant cells to 5-FU. In addition, PVT1 upregulated CDK4 expression by adsorbing miR-486-5p; however, CDK4 overexpression restored the effects of miR-486-5p inhibition on HCT116-5-FU-resistant cells. Additionally, PVT1 knockdown partially rescued CDK4 overexpression in HCT116-5-FU-resistant cells. On the whole, the findings of the present study suggest that PVT1 promotes the resistance of colon cancer cells to 5-FU by regulating the miR-486-5p/CDK4 axis. Therefore, PVT1 may prove to be a potential target for counteracting resistance to 5-FU in colon cancer therapy.

Large-scale evidence generation and evaluation across a network of databases for type 2 diabetes mellitus (LEGEND-T2DM): a protocol for a series of multinational, real-world comparative cardiovascular effectiveness and safety studies.

INTRODUCTION: Therapeutic options for type 2 diabetes mellitus (T2DM) have expanded over the last decade with the emergence of cardioprotective novel agents, but without such data for older drugs, leaving a critical gap in our understanding of the relative effects of T2DM agents on cardiovascular risk. METHODS AND ANALYSIS: The large-scale evidence generations across a network of databases for T2DM (LEGEND-T2DM) initiative is a series of systematic, large-scale, multinational, real-world comparative cardiovascular effectiveness and safety studies of all four major second-line anti-hyperglycaemic agents, including sodium-glucose co-transporter-2 inhibitor, glucagon-like peptide-1 receptor agonist, dipeptidyl peptidase-4 inhibitor and sulfonylureas. LEGEND-T2DM will leverage the Observational Health Data Sciences and Informatics (OHDSI) community that provides access to a global network of administrative claims and electronic health record data sources, representing 190 million patients in the USA and about 50 million internationally. LEGEND-T2DM will identify all adult, patients with T2DM who newly initiate a traditionally second-line T2DM agent. Using an active comparator, new-user cohort design, LEGEND-T2DM will execute all pairwise class-versus-class and drug-versus-drug comparisons in each data source, producing extensive study diagnostics that assess reliability and generalisability through cohort balance and equipoise to examine the relative risk of cardiovascular and safety outcomes. The primary cardiovascular outcomes include a composite of major adverse cardiovascular events and a series of safety outcomes. The study will pursue data-driven, large-scale propensity adjustment for measured confounding, a large set of negative control outcome experiments to address unmeasured and systematic bias. ETHICS AND DISSEMINATION: The study ensures data safety through a federated analytic approach and follows research best practices, including prespecification and full disclosure of results. LEGEND-T2DM is dedicated to open science and transparency and will publicly share all analytic code from reproducible cohort definitions through turn-key software, enabling other research groups to leverage our methods, data and results to verify and extend our findings.