Budget impact analysis of a machine learning algorithm to predict high risk of atrial fibrillation among primary care patients

Economic benefit analysis of lithium battery recycling based on machine learning algorithm

Lithium batteries, as an important energy storage device, are widely used in the fields of renewable vehicles and renewable energy. The related lithium battery recycling industry has also ushered in a golden period of development. However, the high cost of lithium battery recycling makes it difficult to accurately evaluate its recycling value, which seriously restricts the development of the industry. To address the above issues, machine learning will be applied in the field of economic benefit analysis for lithium battery recycling, and backpropagation neural networks will be combined with stepwise regression. On the basis of considering social and commercial values, a lithium battery recycling and utilization economic benefit analysis model based on stepwise regression backpropagation neural network was designed. The experimental results show that the mean square error of the model converges between 10-6 and 10-7, and the convergence speed is improved by 33%. In addition, in practical experiments, the model predicted the actual economic benefits of recycling a batch of lithium batteries. The results show that the predictions are basically in line with the true values. Therefore, the economic benefit analysis and prediction model for lithium battery recycling proposed in the study has the advantages of high accuracy and fast operation speed, providing new ideas and tools for promoting innovation in the field of economic benefit analysis. It has certain application potential in the evaluation of the benefits of lithium battery recycling.

Risk calculator for incident atrial fibrillation across a range of prediction horizons

BACKGROUND

The increasing burden of atrial fibrillation (AF) emphasizes the need to identify high-risk individuals for enrolment in clinical trials of AF screening and primary prevention. We aimed to develop prediction models to identify individuals at high-risk of AF across prediction horizons from 6-months to 10-years.

METHODS

We used secondary-care linked primary care electronic health record data from individuals aged ≥30 years without known AF in the UK Clinical Practice Research Datalink-GOLD dataset between January 2, 1998 and November 30, 2018; randomly divided into derivation (80%) and validation (20%) datasets. Models were derived using logistic regression from known AF risk factors for incident AF in prediction periods of 6 months, 1-year, 2-years, 5-years, and 10-years. Performance was evaluated using in the validation dataset with bootstrap validation with 200 samples, and compared against the CHA2DS2-VASc and C2HEST scores.

RESULTS

Of 2,081,139 individuals in the cohort (1,664,911 in the development dataset, 416,228 in the validation dataset), the mean age was 49.9 (SD 15.4), 50.7% were women, and 86.7% were white. New cases of AF were 7,386 (0.4%) within 6 months, 15,349 (0.7%) in 1 year, 38,487 (1.8%) in 5 years, and 79,997 (3.8%) by 10 years. Valvular heart disease and heart failure were the strongest predictors, and association of hypertension with AF increased at longer prediction horizons. The optimal risk models incorporated age, sex, ethnicity, and 8 comorbidities. The models demonstrated good-to-excellent discrimination and strong calibration across prediction horizons (AUROC, 95%CI, calibration slope: 6-months, 0.803, 0.789-0.821, 0.952; 1-year, 0.807, 0.794-0.819, 0.962; 2-years, 0.815, 0.807-0.823, 0.973; 5-years, 0.807, 0.803-0.812, 1.000; 10-years 0.780, 0.777-0.784, 1.010), and superior to the CHA2DS2-VASc and C2HEST scores. The models are available as a web-based FIND-AF calculator.

CONCLUSIONS

The FIND-AF models demonstrate high discrimination and calibration across short- and long-term prediction horizons in 2 million individuals. Their utility to inform trial enrolment and clinical decisions for AF screening and primary prevention requires further study.

Fibrinaloid Microclots and Atrial Fibrillation

Atrial fibrillation (AF) is a comorbidity of a variety of other chronic, inflammatory diseases for which fibrinaloid microclots are a known accompaniment (and in some cases, a cause, with a mechanistic basis). Clots are, of course, a well-known consequence of atrial fibrillation. We here ask the question whether the fibrinaloid microclots seen in plasma or serum may in fact also be a cause of (or contributor to) the development of AF. We consider known 'risk factors' for AF, and in particular, exogenous stimuli such as infection and air pollution by particulates, both of which are known to cause AF. The external accompaniments of both bacterial (lipopolysaccharide and lipoteichoic acids) and viral (SARS-CoV-2 spike protein) infections are known to stimulate fibrinaloid microclots when added in vitro, and fibrinaloid microclots, as with other amyloid proteins, can be cytotoxic, both by inducing hypoxia/reperfusion and by other means. Strokes and thromboembolisms are also common consequences of AF. Consequently, taking a systems approach, we review the considerable evidence in detail, which leads us to suggest that it is likely that microclots may well have an aetiological role in the development of AF. This has significant mechanistic and therapeutic implications.

The added value of temporal data and the best way to handle it: A use-case for atrial fibrillation using general practitioner data

INTRODUCTION

Temporal data has numerous challenges for deep learning such as irregularity of sampling. New algorithms are being developed that can handle these temporal challenges better. However, it is unclear how the performance ranges from classical non-temporal models to newly developed algorithms. Therefore, this study compares different non-temporal and temporal algorithms for a relevant use case, the prediction of atrial fibrillation (AF) using general practitioner (GP) data.

METHODS

Three datasets with a 365-day observation window and prediction windows of 14, 180 and 360 days were used. Data consisted of medication, lab, symptom, and chronic diseases codings registered by the GP. The benchmark discarded temporality and used logistic regression, XGBoost models and neural networks on the presence of codings over the whole year. Pattern data extracted common patterns of GP codings and tested using the same algorithms. LSTM and CKConv models were trained as models incorporating temporality.

RESULTS

Algorithms which incorporated temporality (LSTM and CKConv, (max AUC 0.734 at 360 days prediction window) outperformed both benchmark and pattern algorithms (max AUC 0.723, with a significant improvement using the 360 days prediction window (p = 0.04). The difference between the benchmark and the LSTM or CKConv algorithm decreased with smaller prediction windows, indicating temporal importance for longer prediction windows. The CKConv and LSTM algorithm performed similarly, possibly due to limited sequence length.

CONCLUSION

Temporal models outperformed non-temporal models for the prediction of AF. For temporal models, CKConv is a promising algorithm to handle temporal data using GP data as it can handle irregular data.

Risk of atrial fibrillation and association with other diseases: protocol of the derivation and international external validation of a prediction model using nationwide population-based electronic health records

INTRODUCTION

Atrial fibrillation (AF) is a major public health issue and there is rationale for the early diagnosis of AF before the first complication occurs. Previous AF screening research is limited by low yields of new cases and strokes prevented in the screened populations. For AF screening to be clinically and cost-effective, the efficiency of identification of newly diagnosed AF needs to be improved and the intervention offered may have to extend beyond oral anticoagulation for stroke prophylaxis. Previous prediction models for incident AF have been limited by their data sources and methodologies.

METHODS AND ANALYSIS

We will investigate the application of random forest and multivariable logistic regression to predict incident AF within a 6-month prediction horizon, that is, a time-window consistent with conducting investigation for AF. The Clinical Practice Research Datalink (CPRD)-GOLD dataset will be used for derivation, and the Clalit Health Services (CHS) dataset will be used for international external geographical validation. Analyses will include metrics of prediction performance and clinical utility. We will create Kaplan-Meier plots for individuals identified as higher and lower predicted risk of AF and derive the cumulative incidence rate for non-AF cardio-renal-metabolic diseases and death over the longer term to establish how predicted AF risk is associated with a range of new non-AF disease states.

ETHICS AND DISSEMINATION

Permission for CPRD-GOLD was obtained from CPRD (ref no: 19_076). The CPRD ethical approval committee approved the study. CHS Helsinki committee approval 21-0169 and data usage committee approval 901. The results will be submitted as a research paper for publication to a peer-reviewed journal and presented at peer-reviewed conferences.

TRIAL REGISTRATION NUMBER

A systematic review to guide the overall project was registered on PROSPERO (registration number CRD42021245093). The study was registered on ClinicalTrials.gov (NCT05837364).

Length of hospital stay for elective electrophysiological procedures: a survey from the European Heart Rhythm Association

AIMS

Electrophysiological (EP) operations that have traditionally involved long hospital lengths of stay (LOS) are now being undertaken as day case procedures. The coronavirus disease-19 pandemic served as an impetus for many centres to shorten LOS for EP procedures. This survey explores LOS for elective EP procedures in the modern era.

METHODS AND RESULTS

An online survey consisting of 27 multiple-choice questions was completed by 245 respondents from 35 countries. With respect to de novo cardiac implantable electronic device (CIED) implantations, day case procedures were reported for 79.5% of implantable loop recorders, 13.3% of pacemakers (PMs), 10.4% of implantable cardioverter defibrillators (ICDs), and 10.2% of cardiac resynchronization therapy (CRT) devices. With respect to CIED generator replacements, day case procedures were reported for 61.7% of PMs, 49.2% of ICDs, and 48.2% of CRT devices. With regard to ablations, day case procedures were reported for 5.7% of atrial fibrillation (AF) ablations, 10.7% of left-sided ablations, and 17.5% of right-sided ablations. A LOS ≥ 2 days for CIED implantation was reported for 47.7% of PM, 54.5% of ICDs, and 56.9% of CRT devices and for 54.5% of AF ablations, 42.2% of right-sided ablations, and 46.1% of left-sided ablations. Reimbursement (43-56%) and bed availability (20-47%) were reported to have no consistent impact on the organization of elective procedures.

CONCLUSION

There is a wide variation in the LOS for elective EP procedures. The LOS for some procedures appears disproportionate to their complexity. Neither reimbursement nor bed availability consistently influenced LOS.

Prediction models for heart failure in the community: A systematic review and meta-analysis

AIMS

Multivariable prediction models can be used to estimate risk of incident heart failure (HF) in the general population. A systematic review and meta-analysis was performed to determine the performance of models.

METHODS AND RESULTS

From inception to 3 November 2022 MEDLINE and EMBASE databases were searched for studies of multivariable models derived, validated and/or augmented for HF prediction in community-based cohorts. Discrimination measures for models with c-statistic data from ≥3 cohorts were pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using PROBAST. We included 36 studies with 59 prediction models. In meta-analysis, the Atherosclerosis Risk in Communities (ARIC) risk score (summary c-statistic 0.802, 95% confidence interval [CI] 0.707-0.883), GRaph-based Attention Model (GRAM; 0.791, 95% CI 0.677-0.885), Pooled Cohort equations to Prevent Heart Failure (PCP-HF) white men model (0.820, 95% CI 0.792-0.843), PCP-HF white women model (0.852, 95% CI 0.804-0.895), and REverse Time AttentIoN model (RETAIN; 0.839, 95% CI 0.748-0.916) had a statistically significant 95% PI and excellent discrimination performance. The ARIC risk score and PCP-HF models had significant summary discrimination among cohorts with a uniform prediction window. 77% of model results were at high risk of bias, certainty of evidence was low, and no model had a clinical impact study.

CONCLUSIONS

Prediction models for estimating risk of incident HF in the community demonstrate excellent discrimination performance. Their usefulness remains uncertain due to high risk of bias, low certainty of evidence, and absence of clinical effectiveness research.

Future Innovations in Novel Detection for Atrial Fibrillation (FIND-AF): pilot study of an electronic health record machine learning algorithm-guided intervention to identify undiagnosed atrial fibrillation

INTRODUCTION

Atrial fibrillation (AF) is associated with a fivefold increased risk of stroke. Oral anticoagulation reduces the risk of stroke, but AF is elusive. A machine learning algorithm (Future Innovations in Novel Detection of Atrial Fibrillation (FIND-AF)) developed to predict incident AF within 6 months using data in primary care electronic health records (EHRs) could be used to guide AF screening. The objectives of the FIND-AF pilot study are to determine yields of AF during ECG monitoring across AF risk estimates and establish rates of recruitment and protocol adherence in a remote AF screening pathway.

METHODS AND ANALYSIS

The FIND-AF Pilot is an interventional, non-randomised, single-arm, open-label study that will recruit 1955 participants aged 30 years or older, without a history of AF and eligible for oral anticoagulation, identified as higher risk and lower risk by the FIND-AF risk score from their primary care EHRs, to a period of remote ECG monitoring with a Zenicor-ECG device. The primary outcome is AF diagnosis during ECG monitoring, and secondary outcomes include recruitment rates, withdrawal rates, adherence to ECG monitoring and prescription of oral anticoagulation to participants diagnosed with AF during ECG monitoring.

ETHICS AND DISSEMINATION

The study has ethical approval (the North West-Greater Manchester South Research Ethics Committee reference 23/NW/0180). Findings will be announced at relevant conferences and published in peer-reviewed journals in line with the Funder's open access policy.

TRIAL REGISTRATION NUMBER

NCT05898165.

Economic evaluations of artificial intelligence-based healthcare interventions: a systematic literature review of best practices in their conduct and reporting

Objectives: Health economic evaluations (HEEs) help healthcare decision makers understand the value of new technologies. Artificial intelligence (AI) is increasingly being used in healthcare interventions. We sought to review the conduct and reporting of published HEEs for AI-based health interventions. Methods: We conducted a systematic literature review with a 15-month search window (April 2021 to June 2022) on 17th June 2022 to identify HEEs of AI health interventions and update a previous review. Records were identified from 3 databases (Medline, Embase, and Cochrane Central). Two reviewers screened papers against predefined study selection criteria. Data were extracted from included studies using prespecified data extraction tables. Included studies were quality assessed using the National Institute for Health and Care Excellence (NICE) checklist. Results were synthesized narratively. Results: A total of 21 studies were included. The most common type of AI intervention was automated image analysis (9/21, 43%) mainly used for screening or diagnosis in general medicine and oncology. Nearly all were cost-utility (10/21, 48%) or cost-effectiveness analyses (8/21, 38%) that took a healthcare system or payer perspective. Decision-analytic models were used in 16/21 (76%) studies, mostly Markov models and decision trees. Three (3/16, 19%) used a short-term decision tree followed by a longer-term Markov component. Thirteen studies (13/21, 62%) reported the AI intervention to be cost effective or dominant. Limitations tended to result from the input data, authorship conflicts of interest, and a lack of transparent reporting, especially regarding the AI nature of the intervention. Conclusion: Published HEEs of AI-based health interventions are rapidly increasing in number. Despite the potentially innovative nature of AI, most have used traditional methods like Markov models or decision trees. Most attempted to assess the impact on quality of life to present the cost per QALY gained. However, studies have not been comprehensively reported. Specific reporting standards for the economic evaluation of AI interventions would help improve transparency and promote their usefulness for decision making. This is fundamental for reimbursement decisions, which in turn will generate the necessary data to develop flexible models better suited to capturing the potentially dynamic nature of AI interventions.

Feasibility of three-dimensional artificial intelligence algorithm integration with intracardiac echocardiography for left atrial imaging during atrial fibrillation catheter ablation

AIMS

Intracardiac echocardiography (ICE) is a useful but operator-dependent tool for left atrial (LA) anatomical rendering during atrial fibrillation (AF) ablation. The CARTOSOUND FAM Module, a new deep learning (DL) imaging algorithm, has the potential to overcome this limitation. This study aims to evaluate feasibility of the algorithm compared to cardiac computed tomography (CT) in patients undergoing AF ablation.

METHODS AND RESULTS

In 28 patients undergoing AF ablation, baseline patient information was recorded, and three-dimensional (3D) shells of LA body and anatomical structures [LA appendage/left superior pulmonary vein/left inferior pulmonary vein/right superior pulmonary vein/right inferior pulmonary vein (RIPV)] were reconstructed using the DL algorithm. The selected ultrasound frames were gated to end-expiration and max LA volume. Ostial diameters of these structures and carina-to-carina distance between left and right pulmonary veins were measured and compared with CT measurements. Anatomical accuracy of the DL algorithm was evaluated by three independent electrophysiologists using a three-anchor scale for LA anatomical structures and a five-anchor scale for LA body. Ablation-related characteristics were summarized. The algorithm generated 3D reconstruction of LA anatomies, and two-dimensional contours overlaid on ultrasound input frames. Average calculation time for LA reconstruction was 65 s. Mean ostial diameters and carina-to-carina distance were all comparable to CT without statistical significance. Ostial diameters and carina-to-carina distance also showed moderate to high correlation (r = 0.52-0.75) except for RIPV (r = 0.20). Qualitative ratings showed good agreement without between-rater differences. Average procedure time was 143.7 ± 43.7 min, with average radiofrequency time 31.6 ± 10.2 min. All patients achieved ablation success, and no immediate complications were observed.

CONCLUSION

DL algorithm integration with ICE demonstrated considerable accuracy compared to CT and qualitative physician assessment. The feasibility of ICE with this algorithm can potentially further streamline AF ablation workflow.

Cardiovascular disease (CVD) outcomes and associated risk factors in a medicare population without prior CVD history: an analysis using statistical and machine learning algorithms

There is limited information on predicting incident cardiovascular outcomes among high- to very high-risk populations such as the elderly (≥ 65 years) in the absence of prior cardiovascular disease and the presence of non-cardiovascular multi-morbidity. We hypothesized that statistical/machine learning modeling can improve risk prediction, thus helping inform care management strategies. We defined a population from the Medicare health plan, a US government-funded program mostly for the elderly and varied levels of non-cardiovascular multi-morbidity. Participants were screened for cardiovascular disease (CVD), coronary or peripheral artery disease (CAD or PAD), heart failure (HF), atrial fibrillation (AF), ischemic stroke (IS), transient ischemic attack (TIA), and myocardial infarction (MI) for a 3-yr period in the comorbid history. They were followed up for up to 45.2 months. Analyses included descriptive approaches in terms of incidence rates and density ratios, and inferential in terms of main effect statistical/complex machine learning modeling. The contemporary risk factors of interest spanned across the domains of comorbidity, lifestyle, and healthcare utilization history. The cohort consisted of 154,551 individuals (mean age 68.8 years; 62.2% female). The overall crude incidence rate of CVD events was 9.9 new cases per 100 person-years. The highest rates among its component outcomes were obtained for CAD or PAD (3.6 for each), followed by HF (2.2) and AF (1.8), then IS (1.3), and finally TIA (1.0) and MI (0.9).Model performance was modest in terms of discriminatory power (C index: 0.67, 95%CI 0.667-0.674 for training; and 0.668, 95%CI 0.663-0.673 for validation data), equal agreement between predicted and observed events for calibration purposes, and good clinical utility in terms of a net benefit of 15 true positives per 100 patients relative to the All-patient treatment strategy. Complex models based on machine learning algorithms yielded incrementally better discriminatory power and much improved goodness-of-fitness tests from those based on main effect statistical modeling. This Medicare population represents a highly vulnerable group for incident CVD events. This population would benefit from an integrated approach to their care and management, including attention to their comorbidities and lifestyle factors, as well as medication adherence.

Prediction of short-term atrial fibrillation risk using primary care electronic health records

OBJECTIVE

Atrial fibrillation (AF) screening by age achieves a low yield and misses younger individuals. We aimed to develop an algorithm in nationwide routinely collected primary care data to predict the risk of incident AF within 6 months (Future Innovations in Novel Detection of Atrial Fibrillation (FIND-AF)).

METHODS

We used primary care electronic health record data from individuals aged ≥30 years without known AF in the UK Clinical Practice Research Datalink-GOLD dataset between 2 January 1998 and 30 November 2018, randomly divided into training (80%) and testing (20%) datasets. We trained a random forest classifier using age, sex, ethnicity and comorbidities. Prediction performance was evaluated in the testing dataset with internal bootstrap validation with 200 samples, and compared against the CHA2DS2-VASc (Congestive heart failure, Hypertension, Age >75 (2 points), Stroke/transient ischaemic attack/thromboembolism (2 points), Vascular disease, Age 65-74, Sex category) and C2HEST (Coronary artery disease/Chronic obstructive pulmonary disease (1 point each), Hypertension, Elderly (age ≥75, 2 points), Systolic heart failure, Thyroid disease (hyperthyroidism)) scores. Cox proportional hazard models with competing risk of death were fit for incident longer-term AF between higher and lower FIND-AF-predicted risk.

RESULTS

Of 2 081 139 individuals in the cohort, 7386 developed AF within 6 months. FIND-AF could be applied to all records. In the testing dataset (n=416 228), discrimination performance was strongest for FIND-AF (area under the receiver operating characteristic curve 0.824, 95% CI 0.814 to 0.834) compared with CHA2DS2-VASc (0.784, 0.773 to 0.794) and C2HEST (0.757, 0.744 to 0.770), and robust by sex and ethnic group. The higher predicted risk cohort, compared with lower predicted risk, had a 20-fold higher 6-month incidence rate for AF and higher long-term hazard for AF (HR 8.75, 95% CI 8.44 to 9.06).

CONCLUSIONS

FIND-AF, a machine learning algorithm applicable at scale in routinely collected primary care data, identifies people at higher risk of short-term AF.

Cost-effectiveness of targeted screening for non-valvular atrial fibrillation in the United Kingdom in older patients using digital approaches

AIM

Screening for non-valvular atrial fibrillation (NVAF) is key in identifying patients with undiagnosed disease who may be eligible for anticoagulation therapy. Understanding the economic value of screening is necessary to assess optimal strategies for payers and healthcare systems. We evaluated the cost effectiveness of opportunistic screening with handheld digital devices and pulse palpation, as well as targeted screening predictive algorithms for UK patients ≥75 years of age.

METHODS

A previously developed Markov cohort model was adapted to evaluate clinical and economic outcomes of opportunistic screening including pulse palpation, Zenicor (extended 14 days), KardiaMobile (extended), and two algorithms compared to no screening. Key model inputs including epidemiology estimates, screening effectiveness, and risks for medical events were derived from the STROKESTOP, ARISTOTLE studies, and published literature, and cost inputs were obtained from a UK national cost database. Health and cost outcomes, annually discounted at 3.5%, were reported for a cohort of 10,000 patients vs. no screening over a time horizon equivalent to a patient's lifetime, Analyses were performed from a UK National Health Services and personal social services perspective.

RESULTS

Zenicor, pulse palpation, and KardiaMobile were dominant (providing better health outcomes at lower costs) vs. no screening; both algorithms were cost-effective vs. no screening, with incremental cost-effectiveness ratios per quality-adjusted life-year (QALY) of £1,040 and £1,166. Zenicor, pulse palpation, and KardiaMobile remained dominant options vs. no screening in all scenarios explored. Deterministic sensitivity analyses indicated long-term stroke care costs, prevalence of undiagnosed NVAF in patients 75-79 years of age, and clinical efficacy of anticoagulant on stroke prevention were the main drivers of the cost-effectiveness results.

CONCLUSIONS

Screening for NVAF at ≥75 years of age could result in fewer NVAF-related strokes. NVAF screening is cost-effective and may be cost-saving depending on the program chosen.

Identification of undiagnosed atrial fibrillation using a machine learning risk prediction algorithm and diagnostic testing (PULsE-AI) in primary care: cost-effectiveness of a screening strategy evaluated in a randomized controlled trial in England

OBJECTIVE

The PULsE-AI trial sought to determine the effectiveness of a screening strategy that included a machine learning risk prediction algorithm in conjunction with diagnostic testing for identification of undiagnosed atrial fibrillation (AF) in primary care. This study aimed to evaluate the cost-effectiveness of implementing the screening strategy in a real-world setting.

METHODS

Data from the PULsE-AI trial - a prospective, randomized, controlled trial conducted across six general practices in England from June 2019 to February 2021 - were used to inform a cost-effectiveness analysis that included a hybrid screening decision tree and Markov AF disease progression model. Model outcomes were reported at both individual- and population-level (estimated UK population ≥30 years of age at high-risk of undiagnosed AF) and included number of patients screened, number of AF cases identified, mean total and incremental costs (screening, events, treatment), quality-adjusted-life-years (QALYs), and incremental cost-effectiveness ratio (ICER).

RESULTS

The screening strategy was estimated to result in 45,493 new diagnoses of AF across the high-risk population in the UK (3.3 million), and an estimated additional 14,004 lifetime diagnoses compared with routine care only. Per-patient costs for high-risk individuals who underwent the screening strategy were estimated at £1,985 (vs £1,888 for individuals receiving routine care only). At a population-level, the screening strategy was associated with a cost increase of approximately £322 million and an increase of 81,000 QALYs. The screening strategy demonstrated cost-effectiveness versus routine care only at an accepted ICER threshold of £20,000 per QALY-gained, with an ICER of £3,994/QALY.

CONCLUSIONS

Compared with routine care only, it is cost-effective to target individuals at high risk of undiagnosed AF, through an AF risk prediction algorithm, who should then undergo diagnostic testing. This AF risk prediction algorithm can reduce the number of patients needed to be screened to identify undiagnosed AF, thus alleviating primary care burden.