This website is intended for healthcare professionals only.
Take a look at a selection of our recent media coverage:
24th November 2022
Use of baxdrostat in patients with treatment-resistant hypertension, concurrently taking three other anti-hypertensives, led to significant reductions in systolic blood pressure compared to placebo according to the findings of a trial by UK and US researchers.
Hypertension is the leading preventable cause of premature death worldwide with one analysis of 90 countries estimated that globally, in 2010, 31.1% of the world’s adults had hypertension and which equated to 1.39 billion people. Despite the availability of a range of effective anti-hypertensive therapies, treatment-resistant hypertension, defined as above-goal elevated blood pressure in a patient despite the concurrent use of 3 antihypertensive drug classes, can be as high as 10.3%. One therapeutic target in hypertension is aldosterone synthase and a new class of drugs, the aldosterone synthase inhibitors, are currently under development. One such agent is baxdrostat and which has been shown in preclinical studies to completely suppress aldosterone production in humans without affecting cortisol production. Nevertheless, whether reducing aldosterone would also lower blood pressure was unclear and the subject of the current study.
Researchers focused on patients with treatment-resistant hypertension with a mean blood pressure of at least 130/80 mmHg, despite the use of three different anti-hypertensives. Participants were then randomised equally to 0.5, 1 or 2 mg of baxdrostat or matching placebo and were assessed for a period of 12 weeks. The primary efficacy endpoint was the change in the mean seated systolic blood pressure from baseline to the end of the study period. The change in diastolic pressure was then set as the secondary outcome measure.
Baxdrostat and changes in systolic blood pressure
A total of 248 patients with a mean age of 62.3 (55.8% male) were included and randomised to either placebo, 0.5, 1 and 2 mg of baxdrostat. The mean baseline systolic blood pressure ranged from 147.7 to 148.9 mmHg and the mean diastolic from 87.6 to 88.2 mmHg.
The change in systolic blood pressure at 12 weeks was significantly greater than placebo for the 2 mg dose (-20.3) and the mean difference compared to placebo was significant (p < 0.001). Similarly, the 1 mg dose achieved -17.5 reduction in systolic pressure and again the mean difference compared to placebo was significant (p = 0.003). There was no significant difference for the 0.5 mg dose.
The highest reduction in diastolic pressure occurred with the 2 mg dose (-14.3) and the 1 mg dose (-11.8) although no statistical significance data were reported.
The authors that there were reported no serious adverse events attributable to baxdrostat, and no instances of adrenocortical insufficiency.
They concluded that in patients with treatment-resistant hypertension, baxdrostat provided a dose-related reduction in blood pressure.
Citation
Freeman MW et al. Phase 2 Trial of Baxdrostat for Treatment-Resistant Hypertension. N Eng J Med 2022
Research by a Spanish team has revealed how symptoms of post-COVID-19 condition (i.e., long covid) persist in both hospitalised and non-hospitalised patients for at least 2 years following their acute infection with the virus.
It has become increasingly recognised that approximately 10% – 20% of people infected with COVID-19 continue to experience a variety of mid- and long-term effects after they recover from their initial illness. The World Health Organisation uses the term ‘post-COVID-19 condition’ and which refers to the constellation of long-term symptoms that some people experience after they have been infected with COVID-19. A wide range of symptoms have been reported affecting various systems in the body, some of which leading to both cognitive and sensory impairment. In fact, a 2021 scoping review identified more than 100 symptoms and whose prevalence varied significantly and were not explained by data collection approaches, study design or other methodological approaches. To date several reviews have examined post-COVID-19 condition symptoms but have only been able to report on the prevalence up to 1 year following an acute infection. In the present study, the Spanish team set out to explore and compare the presence of symptoms in both hospitalised and non-hospitalised patients after a follow-up period of two years.
Hospitalised and non-hospitalised patient data was collected and a random sample from both cohorts who were infected during the first wave of the pandemic and had not been subsequently re-infected were included. Demographic and clinical data were collected from medical records and invited participants agreed to have a scheduled telephone interview 2 years after their infection and which enquired about the presence of a range of symptoms.
Post-COVID-19 condition symptoms after 2 years
A total of 360 hospitalised patients with a mean age of 60.7 years (45% female) and 308 non-hospitalised patients (mean age = 56.7, 59.4% female) were included in the study. The hospitalised and non-hospitalised groups were assessed after a mean of 23.8 and 23.4 months respectively.
Overall, 59.7% of hospitalised and 67.5% of non-hospitalised patients reported having at least 1 post-COVID-19 condition symptom at their follow-up interview. Dyspnoea was more prevalent at the onset of illness among hospitalised compared to non-hospitalised patients (31.1% vs 11.7%, p < 0.001). In contrast, anosmia was more common among non-hospitalised individuals (21.4% vs 10.0%, p = .003).
Th most frequent condition in both cohorts was fatigue (44.7% vs 47.7%, hospitalised vs non-hospitalised), with a similar level of pain symptoms including headaches (35.8% vs 29.9%), memory loss (20% vs 15.9%) and dyspnoea at rest (3.9% both groups).
In multivariate regression analysis, among hospitalised patients, the number of pre-existing co-morbidities was significantly associated with fatigue (odds ratio, OR = 1.93, 95% CI 1.09 – 3.42, p = 0.02) and dyspnoea (OR = 1.91, 95% CI 1.04 – 3.48, p = 0.03). Among non-hospitalised patients, the number of pre-existing co-morbidities (OR = 3.75) and the number of symptoms at infection onset (OR = 3.84) were both associated with the presence of fatigue.
The authors concluded that their cross-sectional study suggested the presence of at least 1 post-COVID-19 symptom in a large proportion of infected patients and which appeared to be irrespective of disease severity.
Citation
Fernández-de-las-Peñas C et al. Post-COVID-19 Symptoms 2 Years After SARS-CoV-2 Infection Among Hospitalized vs Nonhospitalized Patients. JAMA New Open 2022
23rd November 2022
Gantenerumab which is a fully human monoclonal IgG1 antibody failed to meet the primary endpoint of slowing clinical decline in people with early Alzheimer’s disease (AD) in two randomised, double-blind, placebo-controlled trials according to a release by the manufacturer Roche.
It has been estimated that currently, an estimated 6.2 million Americans aged 65 and older are living with Alzheimer’s dementia. Moreover, the World Health Organisation has estimated that there are more than 55 million people with dementia worldwide and nearly 10 million new cases every year, with Alzheimer’s disease accounting for between 60 – 70% dementia cases. The amyloid cascade hypothesis of AD proposes that deposition of the amyloid-β peptide in the brain is a central event in disease pathology and several drugs have been developed, including gantenerumab which binds with high affinity to aggregated amyloid-β species and removes amyloid-β plaques.
The potential value of gantenerumab came from a small trial in 2012, which revealed that it resulted in a dose-dependent reduction in brain amyloid levels. However, these early findings were called into question after a 2017 randomised trial with the drug in patients with prodromal AD, i.e., mild cognitive impairment, over a 2-year period, was halted early for futility. Despite this, the manufacturer Roche embarked to two global phase III trials, GRADUATE I and II designed to evaluate the safety and efficacy of gantenerumab in people with mild cognitive impairment due to Alzheimer’s and mild Alzheimer’s dementia over 27 months. The primary endpoint of both trials was the change from baseline in the Clinical Dementia Rating-Sum of Boxes (CDR-SB) at 116 weeks, a tool that measures cognitive and functional change across six areas including memory, orientation, judgement and problem solving, community affairs, home and hobbies, and personal care.
Gantenerumab and Alzheimer’s disease outcomes
According to the press release, 1,965 participants across 30 countries were randomised 1:1 to receive gantenerumab or placebo by subcutaneous injection and titrated to reach a target dose of 510 mg which was administered every two weeks. The results showed that while there was a slowing of clinical decline in GRADUATE I of -0.31 (p = 0.095) and -0.19 (p = 0.29) in GRADUATE II of -0.31 (p=0.0954) from baseline on CDR-SB, neither decrease was statistically significant. Additionally, the level of beta-amyloid removal was also lower than expected.
Commenting on the findings, Levi Garraway, Roche’s Chief Medical Officer and Head of Global Product Development said, ‘While the GRADUATE results are not what we hoped, we are proud to have delivered a high quality, clear and comprehensive Alzheimer’s dataset to the field, and we look forward to sharing our learnings with the community as we continue to search for new treatments for this complex disease.’
Nevertheless, the press release reports that Roche remains committed to Alzheimer’s disease and is continuing to develop and deliver tests to enable early and accurate Alzheimer’s diagnosis and has a pipeline of investigational medicines for different targets, types and stages of the disease.
21st November 2022
Using an MRI derived radiomics nomogram that also includes clinical patient characteristics helps to predict which patients with knee osteoarthritis are likely to see improvements in their pain over a 2-year period according to a study by Chinese researchers.
Osteoarthritis (OA) is a common condition that affects 7% of the global population which amounts to more than 500 million people. Although OA has been assessed conventionally using X-rays, an alternative is magnetic resonance imaging (MRI). In fact, it has been suggested that MRI is the best modality for imaging of osteoarthritis enabling visualisation of multiple individual tissue pathologies relating to pain and also to predict clinical outcome. When Chinese researchers undertook a randomised trial to examine the effect of vitamin D on OA knee pain, compared with placebo, there were no significant differences in MRI-measured tibial cartilage volume or knee pain score over 2 years. However, in a post-hoc analysis, 64% of vitamin D participants 57% of placebo participants achieved a 20% improvement in knee pain score over 2 years.
Give that a fifth of participants had actually seen an improvement in their knee pain, researchers wondered how it might be possible to identify those patients who were likely to benefit from vitamin D. They decided to create a radiomics nomogram based on MRI-derived features of subchondral bone together with clinical factors and which could be used to predict an improvement over 2 years in knee OA pain. The team used data from the VIDEO study of knee osteoarthritis in which participants had an MRI scan at baseline and after 24 months. The primary outcome was knee pain, and which was assessed using the WOMAC score. The team used MRI data to create a radiomics model which was trained and then validated with separate cohorts from the VIDEO trial. The data from the model was then used to produce a nomogram for predicting osteoarthritis knee pain improvement over two years. The model was assessed based on the area under the receiver characteristics operating curve (AUC).
MRI derived radiomics model and prediction of knee pain
A total of 216 patients with mean age of 68.3 years (47% female) were included and 172 were used in the training cohort, of whom, 78 had no improvement in pain and the remainder used in the validation cohort.
Only two variables, female gender and baseline total knee pain score were significant predictors of an improvement in knee pain over 2 years and were used in the clinical model, together with vitamin D supplementation. The MRI derived model included a radiomics signature and the two significant clinical variables.
In the validation cohort, the nomogram had a higher AUC than the clinical model (0.83 vs 0.71) for the prediction of knee pain improvement although this difference was not significant (p = 0.08). In addition, the use of a decision curve analysis confirmed the clinical usefulness of nomogram.
The authors concluded that their radiomics-based nomogram which comprised the MR radiomics signature and clinical variables achieved a favourable predictive efficacy and accuracy in differentiating improvement in knee pain among OA patients.
Citation
Lin T et al. Prediction of knee pain improvement over two years for knee osteoarthritis using a dynamic nomogram based on MRI-derived radiomics: a proof-of-concept study. Osteoarthritis Cartilage 2022
An AI read chest radiograph can be used to predict the presence of severe coronary artery disease and is superior to accepted risk scores.
An AI read chest radiograph can be used to identify patients with severe coronary artery disease who have been referred with suspected angina according to the results of a study by German researchers.
Globally, cardiovascular diseases are the leading cause of death resulting in an estimated 17.9 million lives lost every year. The first step in assessing a patient with suspected stable coronary artery disease (CAD) is to determine the pre-test probability and there are several risk scores available including the Diamond-Forrester score, the CAD Consortium clinical score and CONFIRM risk score.
However, the development of artificial intelligence (AI) systems and their use with cardiovascular imaging, is likely to better characterise disease and personalise therapy. This potential made the German researchers re-think about how simple first-line diagnostic tools such as a radiograph might benefit from incorporation of an AI system.
They set out to explore whether an AI read chest radiograph might be of value for the detection of significant coronary artery disease (CAD).
The researchers retrospectively considered patients referred to hospital with suspected angina and who underwent coronary angiography and had a chest radiograph. They included only those patients who had posteroanterior (with the patient standing) and anteroposterior (patient sitting) chest radiographs simply because lateral radiographs were not used in all patients.
The team used a deep convolutional neural network (DCNN) which was trained to detect significant CAD based on invasive coronary angiography reports. They DCNN had a binary classification, i.e., severe CAD was either absent or present and the model was trained and validated on patients referred for angiography.
The performance of the model was assessed based on the area under the receiver operating characteristics curve (AUC) and the associated sensitivity and specificity.
A total of 7728 participants with a mean age of 74 years (70.3% male) were included in the retrospective analysis and of whom, 53% had severe CAD confirmed by invasive angiography.
The AI chest read model had an AUC of 0.73 (95% CI 0.69 – 0.76) and a sensitivity of 90% and a specificity of 31%. Adding the patient’s angina status improved the predictive power of the model for the detection of severe CAD (AUC = 0.77). Moreover, addition of the Diamond Forrester score also improved the predictive power to a similar level (AUC = 0.76).
Using logistic regression, the DCNN prediction was the strongest and independent determinant of severe CAD (odds ratio, OR = 1.04, 95% CI 1.03 – 1.04, p < 0.001).
The authors concluded that an AI-read chest radiograph could be used to determine the pre-test probability of significant CAD in patients referred for suspected angina and called for future studies to externally validate the algorithm to develop a clinically applicable tool, that could support CAD screening in broader settings.
Citation
D’Ancona G et al. Deep learning to detect significant coronary artery disease from plain chest radiographs AI4CAD. Int J Cardiol 2022.
The use of mindfulness-based stress reduction (MBSR) techniques decreases anxiety levels to a similar extent as treatment with the antidepressant escitalopram according to the findings of a randomised, controlled trial by US researchers.
Anxiety is a common mental health disorder, and it has been estimated that globally, in 2017 there were 284 million individuals affected by an anxiety disorder. Antidepressant drugs are effective for generalised anxiety disorders as highlighted in a 2019 network meta-analysis and which found that duloxetine and escitalopram showed better efficacy than other agents.
Alternatives to pharmacotherapy include mindfulness-based stress reduction and cognitive behavioural therapy, with a 2021 systematic review concluding that mindfulness-based interventions produced short-term anxiolytic effects. Whilst both pharmacological and non-pharmacological interventions appear to be effective, the relative efficacy of these interventions has not been directly compared. Consequently, for the present study, the US team undertook a randomised trial of MBSR versus escitalopram and which is currently approved for the management of social and generalised anxiety disorder.
The researchers enrolled adults aged 18 to 75 with a current diagnosis of generalised anxiety, social anxiety or panic disorder and randomised them 1:1 to either 8 weeks of MBSR or escitalopram 10 to 20 mg daily. The primary outcome was the change in anxiety levels as measured on the Clinical Global Impression of Severity Scale (CGI-S) which assesses symptoms on a 7-point scale, with higher scores indicative of more severe illness.
This was assessed at baseline and then after 4 and 8 weeks. The MBSR included a weekly 2.5-hour class, and a 45-minute daily home practice exercise and escitalopram was dosed at 10 mg daily but could be increased to 20 mg daily if tolerated. The researchers set a non-inferiority margin of -0.495 for the difference in CGI-S score between the two groups, i.e., if this were to be exceeded then one of the interventions would be deemed more effective.
Mindfullness-based stress reduction and change in anxiety score
A total of 276 participants with a mean age of 33 (75% female) were included and randomised to escitalopram (140) or MBSR and the mean baseline CGI-S scores were similar (4.44 vs 4.51).
After 8 weeks of therapy, the CGI-S scores reduced by 1.35 and 1.43 in the MBSR and escitalopram groups respectively. The difference -0.07 (95% CI -0.38 to 0.23, p = 0.65) was not significant and with the lower bound of the 95% confidence interval below the pre-defined margin for non-inferiority (i.e., -0.495) not reached, the two interventions were essentially not different.
The authors concluded that given how both interventions were non-inferior, the study provided evidence to support the use of mindfulness meditation as an evidence-based treatment option for patients with anxiety disorder.
Citation
Hoge EA et al. Mindfulness-Based Stress Reduction vs Escitalopram for the Treatment of Adults With Anxiety Disorders: A Randomized Clinical Trial. JAMA Psychiatry 2022.
Serum vitamin D levels might offer some protection against infection from COVID-19 but there is a lack of positive evidence for other outcomes such as reducing disease severity or mortality, according to the conclusion of a systematic review (available as a preprint) by researchers from the Philadelphia College of Osteopathic Medicine, US.
Much has been made of the potential protective role of higher serum vitamin D levels and COVID-19. This arises from studies showing how vitamin D affects multiple immune system mechanisms including a dampening of the entry and replication of the virus, reducing concentrations of pro-inflammatory cytokines, raising levels of anti-inflammatory cytokines, enhances the production of natural antimicrobial peptide and activation of defensive cells such as macrophages. Much of the hope for the vitamin comes from a 2017 systematic review in which the vitamin was given as a supplement, concluding that it protected against acute respiratory tract infections and how those who had a deficiency of vitamin D or who did not receive bolus doses, experienced the most benefit. Moreover, throughout the COVID-19 pandemic, emerging data has demonstrated an association between deficiency of vitamin D and the severity of infection and subsequent post-infection mortality.
In the present review, the US researchers looked at studies assessing vitamin D levels and how this impacted on the level of infection, levels of inflammatory markers, disease severity and mortality. The team compared the effects of sufficient vitamin D (serum 25(OH) D levels > 30 ng/ml, insufficient (21 – 29 ng/ml) and deficient levels (< 20 ng/ml).
Serum vitamin D levels and COVID-19 outcomes
A total of 19 studies were included. Among those who tested positive for COVID-19, the median vitamin D levels were 27.08 nmol/L and 48.67 nmol/L in those who were negative. The authors termed this difference to be ‘near significant’ (p = 0.059).
In some of the included studies, elevated levels of C-Reactive Protein (which is a marker for inflammation) and therefore disease severity, were found to be significantly associated with low levels of vitamin D. In one such study, inpatients with a median serum vitamin D levels < 12 ng/ml had more severe disease compared to those with median values > 12 ng/ml (p = 0.004). However, this was not a consistent finding.
In relation to length of hospital stay (used as a measure of disease severity), studies were mixed, with some highlighting a significant association and others no difference. In fact, median vitamin D levels were 45.02 nmol/L in those categorised as having moderate severity disease and 38.08 nmol/L in those with severe disease and this difference was not significant (p = 0.22). Finally, the differences in serum levels between those who survived and died of COVID-19 were also not significantly different.
The authors concluded that there seemed to be a correlation between vitamin D deficiency and the likelihood of developing severe illness from COVID-19 when observing studies individually but that when comparing studies on a larger scale, the significant difference seemed to fade.
Citation
Kersh L et al. What is the Impact of Vitamin D Levels on COVID-19 Severity?: A Systematic Review. Research Square 2022
A prostate cancer screening strategy that involves an MRI scan following a prostate specific antigen (PSA) test with subsequent targeted biopsies, is a more cost-effective strategy than using just a PSA and standard biopsy according to a cost-effectiveness analysis by Swedish researchers.
Prostate cancer (PCa) screening based on PSA, has been shown in a 16-year follow-up study, to reduce prostate cancer mortality. A biopsy is normally used to confirm the diagnosis of PCa though in recent years there has been an increase in the role of magnetic resonance imaging (MRI) as an alternative means for the identification of PCa. In fact, data suggests that the use of multi-parametric magnetic resonance imaging (MP-MRI) might allow 27% of patients to avoid a primary biopsy. In a 2021 study which compared MRI-targeted or standard biopsy for the purposes of screening for PCa, it was found that in men with a PSA level > 3 ng/ml, an MRI result suggestive of prostate cancer was non-inferior to standard biopsy for detecting clinically significant prostate cancer. In the trial, men were randomised to either a 10 to 12-core standard biopsy or to undergo a triage MRI and then a standard biopsy if the MRI results suggested prostate cancer. Given the non-inferior findings of this study, the Swedish team set out to determine the cost-effectiveness of the MRI-based screening approach in men aged 55 to 69 years of age.
The researchers modelled three scenarios: no screening (strategy 1); PSA and standard biopsy every four years (strategy 2) and finally, MRI following an elevated PSA and then a standard biopsy if the men had a PI-RADS value of between 3 and 5, i.e., which is suggestive of PCa. For each of the three strategies, the team modelled several different outcomes including the mean lifetime number of screening tests, MRIs, over-diagnosis (where screening was positive but would not have presented with symptoms before death due to other causes) and deaths. The incremental cost-effectiveness ratio (ICER), which represents the additional cost of one unit of outcome gained by one strategy compared with another, was calculated for each scenario. The ICER was calculated by dividing the difference in costs by the difference in quality-adjusted life-years (QALYs) for the no screening and the two alternative strategies.
Prostate cancer screening and cost-effectiveness
A total of 603 men were randomised to the standard arm and 929 to the MRI arm and of whom, 11.9% underwent MRI or any biopsy.
When compared against a strategy of no screening, the ICER for the MRI and combined biopsies was $53,736 per QALY gained compared to $69,254 for the PSA and standard biopsy strategy and which the authors designated as a moderate cost per QALY gain. Furthermore, MRI-based screening reduced the number of lifetime biopsies and over-diagnosis by approximately 50% and had a high probability of being cost-effective compared to the alternative strategies.
The authors concluded that a strategy for prostate cancer screening based on PSA followed by MRI with subsequent combined targeted and standard biopsies, had a high probability to be more cost-effective compared with the traditional screening pathway using PSA and a standard biopsy.
Citation
Hao S et al. Cost-effectiveness of Prostate Cancer Screening Using Magnetic Resonance Imaging or Standard Biopsy Based on the STHLM3-MRI Study. JAMA Oncol 2022
The use of a single dose of psilocybin leads to a significant improvement in symptoms among patients with treatment-resistant major depression according to the findings of a study by an international team of researchers.
Treatment-resistant depression (TRD) is a subset of major depressive disorder which does not respond to traditional and first-line therapeutic options. The estimate of TRD varies although according to a 2021 US study, among 8.9 million adults treated for major depression, 2.8 million (30.9%) had TRD. Psilocybin is the major psychoactive alkaloid of some species of mushrooms distributed worldwide and a known hallucinogen.
Interest in the use of psilocybin to help with the depression and anxiety associated with advanced stage cancer, revealed a positive trend toward improved mood and anxiety. More recently, two doses of the hallucinogen given to patients with major depression in the context of supportive psychotherapy, suggested that psilocybin combined with therapy is efficacious in the treatment of major depressive disorder.
Consequently, in the present study, researchers recruited adults with TRD across 22 sites in 10 countries randomised them 1:1:1 to a single dose of psilocybin (10 mg, 25 mg) or 1 mg which served as a control. The treatment was given with a support session lasting6 to 8 hours and participants followed up for 12 weeks.
The primary endpoint was the change from baseline in the Montgomery-Asberg Depression Rating Scale (MADRS) total score which ranges from 0 to 60 with higher scores reflecting more severe depression. The researchers examined the change in scores for the 10 and 25 mg doses compared to the 1 mg dose. Secondary outcomes included a response, defined as a > 50% decrease from baseline to week 3 in the MADRS score and a sustained response, i.e., continuing from week 3 to 12.
Psilocybin and treatment response
A total of 233 individuals with a mean age of 39.8 years (52% female) were included and randomised to each arm of the study (ranging from 75 to 79 participants). At baseline, 68% of the entire cohort had a MADRS score indicating severe depression.
The reduction in MADRS scores were -6.6 (95% CI -10.2 to -2.9) for the 25 mg dose (p < 0.001 vs 1 mg dose) and -2.5 (95% CI -6.2 to 1.2) for the 10 mg dose (p = 0.18 vs 1 mg dose).
At 3 weeks, a response was also more likely in those given 25 mg compared to 1 mg (Odds ratio, OR = 2.9, 95% CI 1.2 – 6.6) but this was not significant for the 10 mg dose (OR = 1.2, 95% CI 0.5 – 3.01). However, the response to treatment was not sustained at 12 weeks for either dose.
Adverse effects included headaches (24%) and nausea (22%) and were much more common in the 25 mg dose group, although suicidal ideation or behaviour or self-injury was seen in each of the groups.
The authors concluded that psilocybin given as a single dose of 25 mg, but not 10 mg, reduced depression scores significantly more than a 1-mg dose over a period of 3 weeks but was associated with adverse effects, prompting the need for further studies of the treatment.
Citation
Goodwin GM et al. Single-Dose Psilocybin for a Treatment-Resistant Episode of Major Depression. N Eng J Med 2022.
18th November 2022
A model combining features of an ECG and radiomics data derived from cardiovascular magnetic resonance imaging improved the detection of atrial fibrillation (AF) in women to a greater extent than either model alone according to the findings of a study by Spanish and UK researchers.
Atrial fibrillation is the most common cardiac arrhythmia, characterised by an irregular heart rhythm and an often abnormally rapid heart rate and globally has been estimated to affect 0.51% of the population. AF is diagnosed from an ECG in which typically, P-waves are absent and there is both a chaotic baseline and an irregular ventricular rate. Cardiac magnetic resonance (CMR) is the reference imaging modality for assessment of cardiac structure and function and CMR radiomics has the potential to improve diagnostic accuracy. Moreover, Cardiac MRI of the atrial substrate is not only a tool for management and treatment of arrhythmia, but also to individualise the prevention of stroke and major cardiovascular events. But what remains unclear is whether the use of a CMR-based radiomics model can identify patients with AF and more importantly, if addition of a model that uses ECG-derived data, would further enhance the potential to detect AF.
In the present study, researchers examined the feasibility of combining a CMR-derived radiomics model and one based on ECG data. The team used information from the UK Biobank and identified patients who had both an ECG and CMR scan and compared their findings with healthy controls. Models were assessed using the area under the receiver operating characteristics curve (AUC) and associated sensitivity and specificity.
ECG and radiomics model and atrial fibrillation detection
A total of 32,121 participants with a mean age of 63 years (51% female) were included and of whom, 495 (63% male) had AF.
Overall, the AUC for the combined model was similar to the ECG-model (0.87 vs 0.86), i.e., adding the radiomics model did not significantly improve predictive power. In fact, when comparing the predictive power of models between the sexes, the AUC for the ECG-model was less predictive for women than men (0.77 vs 0.88, p < 0.05). However, although accuracy improved for women when combined with the CMR-model, but this only improved to the level of the ECG-model for men (0.87 vs 0.88, women vs men). Finally, when considering AF patients who had a normal ECG, the combined model had an AUC of 0.61.
The authors concluded that their integrative radiomics-ECG model presents a potential novel approach for earlier detection of AF.
Citation
Pujadas ER et al. Atrial fibrillation prediction by combining ECG markers and CMR radiomics. Sci Rep 2022
IMPORTANT LINKS
MORE FROM COGORA
© Cogora 2025
Cogora Limited. 1 Giltspur Street, London EC1A 9DD
Registered in the United Kingdom. Reg. No. 2147432
