Machine learning algorithms estimating prognosis and guiding therapy in adult congenital heart disease: data from a single tertiary centre including 10 019 patients

Diller, Gerhard‐Paul; Kempny, Aleksander; Babu‐Narayan, Sonya V.; Henrichs, Marthe; Brida, Margarita; Uebing, Anselm; Lammers, Astrid E.; Baumgartner, Helmut; Wei, Li; Wort, Stephen J.; Dimopoulos, Konstantinos; Gatzoulis, Michael Α.

doi:10.1093/eurheartj/ehy915

Cited by 151 publications

(104 citation statements)

References 15 publications

Supporting

Mentioning

102

Contrasting

Unclassified

Order By: Relevance

“…Health model restructuring should go through a reasoned resources reallocation, 11 promotion of international collaborations, and use of new technologies such as remote monitoring, remote counselling, and artificial intelligence to allow early detection of disease-modifying events. 12 Moreover, further investment on patient education to social distancing is paramount, 13,14 particularly moving forward to the next stage of the pandemic, during which more patients with CHD will inevitably be exposed to coronavirus disease 2019.…”

Section: Discussionmentioning

confidence: 99%

Caring for adults with CHD in the era of coronavirus disease 2019 pandemic: early experience in an Italian tertiary centre

et al. 2020

View full text Add to dashboard Cite

Abstract Background Adults with CHD are known to greatly benefit from a prompt access to continuous expert care. On the other hand, Covid-19 pandemic has determined a dramatic worldwide reconfiguration of the healthcare systems, with rapid redeployment of resources towards this emergency. Italy was the first western country affected by a large-scale spread of Covid-19. The aim of our study is to analyse the impact of the Covid-19 outbreak on in-hospital care of patients with CHD in an Italian tertiary centre. Methods and Results We retrospectively reviewed data on CHD hospital admissions in our centre since March 1st 2020, when the adoption of a strict infection containment policy throughout the country resulted in limited access of patients to routine hospital care and resources reallocation to the care of COVID-19 patients. Comparison with data from the previous year was performed in order to identify any relevant differences attributable to the outbreak. Despite cancellation of all elective procedures, the overall number of urgent hospital admission remained stable throughout the period of study. Patients admitted during the pandemic had greater disease complexity (p=0.001) with longer length on in-hospital stay (p=0.01). No adverse events or positive swabs were reported among CHD patients who were admitted to hospital or medical personnel caring for these patients. Conclusion Data from our early experience suggest that Covid-19 pandemic did not impact significantly on the provision of urgent care to adult patients with CHD.

show abstract

Section: Discussionmentioning

confidence: 99%

Caring for adults with CHD in the era of coronavirus disease 2019 pandemic: early experience in an Italian tertiary centre

et al. 2020

View full text Add to dashboard Cite

show abstract

“…A personalised CHD follow‐up can be subsequently prescribed: patients with simple CHD or at the good end of the spectrum of moderate CHD can be followed up at more local, non‐tertiary centres, and at less frequent intervals. Their progress should be monitored remotely utilising current technologies, including artificial intelligence, so that outliers are identified and return to the hub if needed. The remainder of patients with moderate and complex CHD should remain under periodic surveillance at the tertiary centre (hub) (Figure ).…”

Section: How Can We Do Better?mentioning

confidence: 99%

“…For the ACHD profession collaborative work is paramount given the heterogeneity of CHD and prospective, controlled data are now due. Stem cell therapy, new immunosuppressive therapies for heart transplantation, mechanical pumps and artificial hearts, machine‐learning algorithms represent some of the exciting new research in the field of cardiology and CHD . The future is now.…”

Section: How Can We Do Better?mentioning

confidence: 99%

Adult congenital heart disease: Past, present and future

Brida

Gatzoulis

2019

Acta Paediatrica

Self Cite

View full text Add to dashboard Cite

The challenge is great; the rewards are enormous. For me there have been few things in life which have been more satisfying than to face a small child, struggling for his very existence, to perform some corrective surgical maneuver, and later to see the youngster, thriving and healthy, starting out in life, sound in body and mind.Robert Edward Gross 'father of cardiac surgery' | INTRODUC TI ONThe diagnosis and management of congenital heart disease (CHD), the most common inborn and global defect, has been a tremendous success story of modern medicine. Back in the 1950s, survival of children born with CHD was only approximately 15%. Thanks to remarkable advances in paediatric cardiology, cardiac surgery and catheter interventions, including radical and innovative procedures such as atrial/arterial switch for transposition of great arteries (TGA), the Fontan operation for "single ventricle", percutaneous pulmonary valve implantation and others, more than 90% of children survive now well into adulthood ( Figure 1). 1 Residual and progressive haemodynamic lesions, exercise intolerance, arrhythmias, heart failure (HF) and premature death, however, afflict many patients. 2 Beyond CHD, adult patients face additional opportunities and/or challenges such as pregnancy, acquired heart disease, non-cardiac pathology, necessitating integrated care and most if not all medical disciplines. Furthermore, there is a pressing need to understand better the late pathophysiology of CHD and provide evidence regarding drug therapy, devices and transplantation. 3 We are truly faced with a "tsunami" in terms of adult CHD numbers, disease heterogeneity and complexity of work and intervention/s needed. We must work together, beyond age and geographic boundaries to provide

show abstract

“…Machine learning algorithms were deployed to train a large data set of adults with CHD to prognosticate outcomes and facilitate management. 31,32 These tools may help combat the big challenges in paediatric cardiology of navigating the diagnosis, prognosis and management in individuals with minor different manifestations of the same disease. Ruiz-Fernández et al developed four artificial intelligence-based neural networks to classify the risk of various paediatric cardiac surgeries.…”

Section: Clinical Decision Support Systemsmentioning

confidence: 99%

“…Deep-learning algorithms applied to cardiac magnetic resonance proved superior in the detection of pulmonary hypertension to clinicians' assessment. 31 Advancements in the intersection of artificial intelligence and echocardiography include algorithms capable of differentiating constrictive from restrictive pericarditis 62 and hypertrophic cardiomyopathy from physiologic cardiomyopathy seen in athletes. 63 Additional trained algorithms now autonomously detect hypertrophic cardiomyopathy, cardiac amyloidosis, and pulmonary arterial hypertension from echocardiograms.…”

Section: Medical Imagingmentioning

confidence: 99%

A primer on artificial intelligence for the paediatric cardiologist

2020

View full text Add to dashboard Cite

AbstractThe combination of pediatric cardiology being both a perceptual and a cognitive subspecialty demands a complex decision-making model which makes artificial intelligence a particularly attractive technology with great potential. The prototypical artificial intelligence system would autonomously impute patient data into a collaborative database that stores, syncs, interprets and ultimately classifies the patient’s profile to specific disease phenotypes to compare against a large aggregate of shared peer health data and outcomes, the current medical body of literature and ongoing trials to offer morbidity and mortality prediction, drug therapy options targeted to each patient’s genetic profile, tailored surgical plans and recommendations for timing of sequential imaging. The focus of this review paper is to offer a primer on artificial intelligence and paediatric cardiology by briefly discussing the history of artificial intelligence in medicine, modern and future applications in adult and paediatric cardiology across selected concentrations, and current barriers to implementation of these technologies.

show abstract

Machine learning algorithms estimating prognosis and guiding therapy in adult congenital heart disease: data from a single tertiary centre including 10 019 patients

Cited by 151 publications

References 15 publications

Caring for adults with CHD in the era of coronavirus disease 2019 pandemic: early experience in an Italian tertiary centre

Caring for adults with CHD in the era of coronavirus disease 2019 pandemic: early experience in an Italian tertiary centre

Adult congenital heart disease: Past, present and future

A primer on artificial intelligence for the paediatric cardiologist

Contact Info

Product

Resources

About