Machine Learning in Cardiovascular Risk Prediction and Precision Preventive Approaches.

PURPOSE OF REVIEW: In this review, we sought to provide an overview of ML and focus on the contemporary applications of ML in cardiovascular risk prediction and precision preventive approaches. We end the review by highlighting the limitations of ML while projecting on the potential of ML in assimilating these multifaceted aspects of CAD in order to improve patient-level outcomes and further population health. RECENT FINDINGS: Coronary artery disease (CAD) is estimated to affect 20.5 million adults across the USA, while also impacting a significant burden at the socio-economic level. While the knowledge of the mechanistic pathways that govern the onset and progression of clinical CAD has improved over the past decade, contemporary patient-level risk models lag in accuracy and utility. Recently, there has been renewed interest in combining advanced analytic techniques that utilize artificial intelligence (AI) with a big data approach in order to improve risk prediction within the realm of CAD. By virtue of being able to combine diverse amounts of multidimensional horizontal data, machine learning has been employed to build models for improved risk prediction and personalized patient care approaches. The use of ML-based algorithms has been used to leverage individualized patient-specific data and the associated metabolic/genomic profile to improve CAD risk assessment. While the tool can be visualized to shift the paradigm toward a patient-specific care, it is crucial to acknowledge and address several challenges inherent to ML and its integration into healthcare before it can be significantly incorporated in the daily clinical practice.

Efficacy and safety of sodium-glucose cotransporter 2 inhibitors initiation in patients with acute heart failure, with and without type 2 diabetes: a systematic review and meta-analysis.

BACKGROUND: There is uncertainty and limited data regarding initiation of sodium-glucose cotransporter 2 (SGLT2) inhibitors among patients hospitalized with acute heart failure (AHF). This systematic review and meta-analysis aim to establish the efficacy and safety of SGLT2 inhibitors initiated in patients hospitalized for AHF. METHODS: PubMed/Medline, Embase, and Cochrane library were searched using the following terms: ("sglt2" and "acute heart failure") and ("sglt2" and "worsening heart failure") from inception till November 15th, 2021 for randomized controlled trials (RCTs) comparing the efficacy and safety of initiating an SGLT2 inhibitor compared with placebo in patients with AHF. Major cardiovascular and diabetes scientific meetings in 2021 were also searched for relevant studies. Prespecified efficacy outcomes were all-cause mortality, rehospitalization for heart failure, and improvement in Kansas City Cardiomyopathy Questionnaire (KCCQ) scale score. Prespecified safety outcomes were acute kidney injury (AKI), hypotension, and hypoglycemia. Random effects odds ratio (OR) and mean difference with 95% confidence intervals (CIs) were calculated. RESULTS: Three RCTs with a total of 1831 patients were included. Initiation of SGLT2 inhibitors in patients with AHF reduced the risk of rehospitalization for heart failure (OR 0.52; 95% CI [0.42, 0.65]) and improved Kansas City Cardiomyopathy Questionnaire scores (mean difference 4.12; 95% CI [0.1.89, 6.53]). There was no statistically significant effect for initiation of SGLT2 inhibitors in patients with AHF on all-cause mortality (OR 0.70; 95% CI [0.46, 1.08]). Initiation of SGLT2 inhibitors in patients with AHF did not increase the acute kidney injury (OR 0.76; 95% CI [0.50, 1.16]), hypotension (OR 1.17; 95% CI [0.80, 1.71]), or hypoglycemia (OR 1.51; 95% CI [0.86, 2.65]). CONCLUSION: Initiation of SGLT2 inhibitors in patients hospitalized for AHF during hospitalization or early post-discharge (within 3 days) reduces the risk of rehospitalization for heart failure and improves patient-reported outcomes with no excess risk of adverse effects.

Significance of indeterminate and abnormal stress electrocardiography despite normal imaging in patients with suspected coronary artery disease - An analysis of the PROMISE trial.

BACKGROUND: Abnormal and indeterminate electrocardiographic (ECG) changes during cardiac stress imaging are not uncommon. While the prognostic importance of abnormal ECG despite normal imaging has been previously studied, prognosis of indeterminate stress ECG changes is uncertain. METHODS: We studied the prognostic value of stress ECG changes in symptomatic patients without known CAD and normal stress imaging from the PROMISE trial. Patients with normal ECG (concordant), indeterminate ECG and abnormal ECG (discordant) were identified among those with negative exercise imaging stress test (EIST) and negative vasodilator nuclear stress test (PIST). Outcomes of interest were major adverse cardiovascular endpoint (MACE, including all-cause mortality, myocardial infarction, and unstable angina hospitalization) and likelihood of coronary revascularization. RESULTS: In EIST, indeterminate stress ECG [1.1% vs. 0.2% adjusted hazard ratio (aHR) 4.2, (95% CI 1.11-15.6), p = 0.034] and discordant ECG [7.2% vs. 0.2% adjusted hazard ratio (aHR) 27.6, (95% CI 9.6-79.8), p < 0.0001] were associated with increased likelihood of revascularization compared to normal stress ECG. Similar findings were observed with PIST [indeterminate vs concordant [1.7% vs. 0.5% adjusted hazard ratio (aHR) 5.9, (95% CI 1.1-31.7), p = 0.041; discordant vs concordant 15.4% vs. 0.5% adjusted hazard ratio (aHR) 24.2, (95% CI 4.6-127.7), p = 0.0002]. MACE rates were similar between ECG subgroups, in both EIST and PIST. CONCLUSION: In symptomatic patients without known CAD undergoing stress imaging, indeterminate and discordant ECG changes results may indicate presence of obstructive CAD despite normal imaging results and predict increased likelihood of coronary revascularization despite no significant difference in MACE.

Influence of Iron Deficiency on Clinical and Haemodynamic Parameters in Pulmonary Arterial Hypertension Cohorts.

BACKGROUND: Iron deficiency (Fedef) has been shown to be common in patients with group 1 or pulmonary arterial hypertension (PAH). Several studies have shown a negative impact of Fedef on clinical and haemodynamic parameters of the disease, but data from individual studies have not been strong enough to lead to incorporation of the finding of Fedef into prognostic or therapeutic algorithms. The goal of this meta-analysis was to combine data from available studies to better define any associations between Fedef and established variables of prognostic importance in PAH. METHODS: A literature search identified nine studies with extractable data relevant to the study questions. The impact of Fedef upon the following parameters was evaluated: 6-minute walk distance (6MWD), WHO-functional class, N-terminal pro-brain natriuretic peptide (NT-proBNP) levels, echocardiography, and findings from right heart catheterisation (RHC). Pooled results were reported as mean difference or risk difference with 95% confidence intervals utilising a random effects modeling approach. RESULTS: Fedef in the PAH population was common (47% of cases) and was associated with cardiovascular dysfunction (lower tricuspid annular plane systolic excursion [TAPSE], elevated NT-proBNP, and lower mixed venous oxygen saturation) and with reduction in functional capacity (lower 6MWD and higher functional class). CONCLUSION: This meta-analysis strengthens the relationships between Fedef and several markers of poor outcome in PAH. Fedef in patients with PAH warrants further scrutiny and merits consideration as a cause of clinical deterioration. Even though causation and longitudinal relationships between Fedef and PAH could not be identified, effect of Fedef on factors that affect disease prognosis is noteworthy and worthy of more focussed studies.

Effects of sodium-glucose cotransporter 1 and 2 inhibitors on cardiovascular and kidney outcomes in type 2 diabetes: A meta-analysis update.

In this report, we aim to provide an updated meta-analysis of the sodium-glucose cotransporter 2 (SGLT2) inhibitors trial data with the new trial data on sotagliflozin, a first-in-class dual SGLT1 and SGLT2 inhibitor. We searched Medline, Cochrane library, and Embase databases for randomized clinical trials comparing cardiovascular and kidney outcomes between SGLT2 and dual SGLT1/2 inhibitors and placebo. Nine randomized clinical trials with a total of 60,914 patients with type 2 diabetes were included. In patients with type 2 diabetes, the use of SGLT2 and dual SGLT1/2 inhibitors improves the cardiovascular and kidney outcome.

Effect of sodium-glucose cotransporter 2 inhibitors on cardiovascular and kidney outcomes-Systematic review and meta-analysis of randomized placebo-controlled trials.

Sodium-glucose cotransporter 2 inhibitor (SGLT2i) use is associated with improved cardiovascular and kidney outcomes. However, the magnitude and potential heterogeneity of effect across patients with varying types of cardiometabolic and kidney disease is unclear. To examine the effect of SGLT2i on cardiovascular and kidney outcomes among patients with type 2 diabetes mellitus (T2DM), and independent of T2DM status, among patients with heart failure (HF), and chronic kidney disease. METHOD: Medline, Embase, Cochrane library and scientific conferences were searched from inception till September 24, 2020 for randomized controlled trials comparing cardiovascular and kidney outcomes between SGLT2i and placebo. Random effects hazard ratios (HR) with 95% confidence intervals (CIs) were calculated. RESULTS: Eight trials with a combined 59,747 patients were included. In the overall population, SGLT2i reduced the risk of all-cause mortality (HR 0.84; 95% CI [0.78-0.91]), cardiovascular mortality (HR 0.84; 95% CI [0.76-0.93]) hospitalization for HF (HR 0.69; 95% CI [0.64-0.74]), myocardial infarction (HR 0.91; 95% CI [0.84-0.99]), and composite kidney outcome (HR 0.62; 95% CI [0.56-0.70]). There was no significant effect on the risk of stroke (HR 0.98; 95% CI [0.86-1.11]). Results were consistent across subgroups stratified by diabetes and HF status. SGLT2i use was not associated with a greater risk of hypoglycemia (OR 0.92; 95% CI [0.84-1.01]) or amputation (OR 1.25; 95% CI [0.97-1.62]). There were 64 diabetic ketoacidosis events with SGLT2i use and 18 with placebo (OR 2.86; 95% CI [1.39-5.86]). CONCLUSIONS: In patients with cardiometabolic and kidney disease, SGLT2i improved cardiovascular and kidney outcomes, regardless of T2DM, HF, and/or CKD status. The magnitude of risk reduction was largest for hospitalization for HF and progression of kidney disease, more modest for mortality and MI and absent for stroke.

18F-Sodium Fluoride Positron Emission Tomography/Computed Tomography in Ex Vivo Human Coronary Arteries With Histological Correlation.

OBJECTIVE: 18F-sodium fluoride (NaF) position emission tomography (PET) activity correlates with high-risk plaque. We examined the correlation between 18F-NaF PET activity and extent of calcification (microcalcification and macrocalcification) in coronary arteries. Approach and Results: Eighteen ex vivo human coronary arteries were imaged with 18F-NaF PET/CT, and target to background ratios were analyzed from 101 plaques. Histopathologic analysis evaluated for microcalcification and macrocalcification, plaque morphology, and inflammation. Plaques with microcalcification demonstrated higher 18F-NaF PET activity (n=84; mean target to background ratio±SD, 9.0±9.7,) than plaques without microcalcification (n=17, 2.9±3.8; P<0.0001). Higher 18F-NaF PET activity was associated with advanced plaques characterized by fibroatheroma (n=54, 10.7±10.3) compared with plaques with intimal thickening (n=22, 3.5±3.9) or pathological intimal thickening (n=25, 6.1±8.4; P=0.004). No significant association was found between 18F-NaF PET activity and inflammation (P=0.08). CONCLUSIONS: In ex vivo human coronary arteries, higher 18F-NaF PET activity was associated with microcalcification and advanced plaque morphology. Since microcalcification and fibroatheromas are high-risk plaque features, 18F-NaF PET/CT may improve risk-stratification.

Direct Oral Anticoagulants Versus Warfarin in Left Ventricular Thrombus: A Systematic Review and Meta-Analysis.

BACKGROUND: There are conflicting results regarding the safety and efficacy of direct oral anticoagulants (DOACs) in the management of left ventricular thrombus (LVT) compared with the vitamin K antagonist warfarin. STUDY QUESTION: What is the safety and efficacy of DOACs in the management of LVT compared with warfarin? DATA SOURCE: Randomized clinical trials and cohort studies in the MEDLINE and Cochrane databases from inception till April 4, 2021. STUDY DESIGN: The present analysis is a systematic review and meta-analysis. Desired outcomes were all-cause mortality, complete resolution of LVT, stroke and systemic emboli, and major bleeding. The risk ratio (RR) of the outcomes and 95% confidence intervals (CIs) were calculated using a random-effects modeling approach. RESULTS: Twelve studies with a total of 2322 patients were included. There was no difference between the 2 interventions in the resolution of LVT [RR 0.97 (CI 0.93-1.02)], stroke and systemic embolism [RR 0.95 (CI 0.63-1.45)], bleeding [RR 1.14 (CI 0.81-1.60)], and all-cause mortality [RR 0.99 (CI 0.67, 1.46)]. CONCLUSIONS: DOACs and warfarin have comparable safety and efficacy outcomes in the management of LVT.

Machine learning of clinical variables and coronary artery calcium scoring for the prediction of obstructive coronary artery disease on coronary computed tomography angiography: analysis from the CONFIRM registry.

AIMS: Symptom-based pretest probability scores that estimate the likelihood of obstructive coronary artery disease (CAD) in stable chest pain have moderate accuracy. We sought to develop a machine learning (ML) model, utilizing clinical factors and the coronary artery calcium score (CACS), to predict the presence of obstructive CAD on coronary computed tomography angiography (CCTA). METHODS AND RESULTS: The study screened 35 281 participants enrolled in the CONFIRM registry, who underwent ≥64 detector row CCTA evaluation because of either suspected or previously established CAD. A boosted ensemble algorithm (XGBoost) was used, with data split into a training set (80%) on which 10-fold cross-validation was done and a test set (20%). Performance was assessed of the (1) ML model (using 25 clinical and demographic features), (2) ML + CACS, (3) CAD consortium clinical score, (4) CAD consortium clinical score + CACS, and (5) updated Diamond-Forrester (UDF) score. The study population comprised of 13 054 patients, of whom 2380 (18.2%) had obstructive CAD (≥50% stenosis). Machine learning with CACS produced the best performance [area under the curve (AUC) of 0.881] compared with ML alone (AUC of 0.773), CAD consortium clinical score (AUC of 0.734), and with CACS (AUC of 0.866) and UDF (AUC of 0.682), P < 0.05 for all comparisons. CACS, age, and gender were the highest ranking features. CONCLUSION: A ML model incorporating clinical features in addition to CACS can accurately estimate the pretest likelihood of obstructive CAD on CCTA. In clinical practice, the utilization of such an approach could improve risk stratification and help guide downstream management.

Clinical applications of machine learning in cardiovascular disease and its relevance to cardiac imaging.

Artificial intelligence (AI) has transformed key aspects of human life. Machine learning (ML), which is a subset of AI wherein machines autonomously acquire information by extracting patterns from large databases, has been increasingly used within the medical community, and specifically within the domain of cardiovascular diseases. In this review, we present a brief overview of ML methodologies that are used for the construction of inferential and predictive data-driven models. We highlight several domains of ML application such as echocardiography, electrocardiography, and recently developed non-invasive imaging modalities such as coronary artery calcium scoring and coronary computed tomography angiography. We conclude by reviewing the limitations associated with contemporary application of ML algorithms within the cardiovascular disease field.

Prognostic value of coronary computed tomographic angiography findings in asymptomatic individuals: a 6-year follow-up from the prospective multicentre international CONFIRM study.

Aim: The long-term prognostic benefit of coronary computed tomographic angiography (CCTA) findings of coronary artery disease (CAD) in asymptomatic populations is unknown. Methods and results: From the prospective multicentre international CONFIRM long-term study, we evaluated asymptomatic subjects without known CAD who underwent both coronary artery calcium scoring (CACS) and CCTA (n = 1226). Coronary computed tomographic angiography findings included the severity of coronary artery stenosis, plaque composition, and coronary segment location. Using the C-statistic and likelihood ratio tests, we evaluated the incremental prognostic utility of CCTA findings over a base model that included a panel of traditional risk factors (RFs) as well as CACS to predict long-term all-cause mortality. During a mean follow-up of 5.9 ± 1.2 years, 78 deaths occurred. Compared with the traditional RF alone (C-statistic 0.64), CCTA findings including coronary stenosis severity, plaque composition, and coronary segment location demonstrated improved incremental prognostic utility beyond traditional RF alone (C-statistics range 0.71-0.73, all P < 0.05; incremental χ2 range 20.7-25.5, all P < 0.001). However, no added prognostic benefit was offered by CCTA findings when added to a base model containing both traditional RF and CACS (C-statistics P > 0.05, for all). Conclusions: Coronary computed tomographic angiography improved prognostication of 6-year all-cause mortality beyond a set of conventional RF alone, although, no further incremental value was offered by CCTA when CCTA findings were added to a model incorporating RF and CACS.

Imaging to Assess Ischemic Heart Disease in Women.

PURPOSE OF REVIEW: Ischemic heart disease is a leading cause of morbidity and mortality for women and men around the world. However, traditional cardiovascular risk factors do not fully capture cardiac risk in women. This review summarizes sex-based differences in the clinical presentation, pathophysiology, and risk assessment of ischemic heart disease. We also examine the use of anatomic and functional imaging modalities in the diagnosis of ischemic heart disease in women. RECENT FINDINGS: Recent studies with women subjects have bolstered the predictive value of the coronary artery calcium (CAC) score in predicting atherosclerotic cardiovascular disease risk and major adverse cardiac events in a graded fashion. In addition, combined CAC scoring and coronary computed tomography (CCTA) has shown promise in excluding coronary artery disease (CAD). Using CCTA, data have suggested that increasing cardiovascular risk factors are associated with an increase in noncalcified coronary plaque in women compared with an increase in both calcified and noncalcified plaque in men with cardiac risk factors. Some data have suggested that women obtain greater prognostic benefit from CCTA than from other noninvasive tests. Fractional flow reserve obtained from a CCTA (FFRCT) is a new mathematical assessment of coronary blood flow that determines the presence of lesion-specific myocardial ischemia. Prevention and identification of ischemic heart disease remains a foundation of cardiology and public health. In women, atypical symptoms and limitations in traditional risk factor assessment lead to challenges in the identification of ischemic heart disease. With improvements in technologies such as CAC scoring, CCTA, instantaneous flow reserve (iFR), optical coherence tomography (OCT), and FFRCT, there is great promise for identification of ischemic heart disease, and the future of prevention in women. Future studies with strong female representation should investigate the role of novel imaging techniques in women.

Bioprosthetic mitral valve paravalvular leak closure using intracardiac echocardiography-guided three dimensional electroanatomic mapping.

The development of paravalvular leak (PVL) following surgical replacement of an aortic or mitral valve is an uncommon complication with significant morbidity and mortality. Surgical or percutaneous repair of PVL can be technically challenging. We describe the application of intracardiac echocardiography guided 3-dimensional electroanatomic mapping to facilitate PVL closure in a symptomatic patient with a previously placed bioprosthetic mitral valve. © 2017 Wiley Periodicals, Inc.

Use of mechanical circulatory support in patients undergoing percutaneous coronary intervention: insights from the National Cardiovascular Data Registry.

BACKGROUND: Little is known about the contemporary use of intra-aortic balloon pump (IABP) and other mechanical circulatory support (O-MCS) devices in patients undergoing percutaneous coronary intervention (PCI) in the setting of cardiogenic shock. METHODS AND RESULTS: We identified 76 474 patients who underwent PCI in the setting of cardiogenic shock at one of 1429 National Cardiovascular Data Registry CathPCI participating hospitals from 2009 to 2013. Temporal trends and hospital-level variation in the use of IABP and O-MCS were evaluated. No mechanical circulatory support was used in 41 286 (54%) patients, 29 730 (39%) received IABP only, 2711 (3.5%) received O-MCS only, and 2747 (3.6%) received both IABP and O-MCS. At the start of the study period, 45% of patients undergoing PCI in the setting of cardiogenic shock received an IABP and 6.7% received O-MCS. The proportion of patients receiving IABP declined at an average rate of 0.3% per quarter, whereas the rate of O-MCS use was unchanged over the study period. The predicted probability of IABP use varied significantly by site (hospital median 42%, interquartile range 33% to 51%, range 8% to 85%). The probability of O-MCS use was <5% for half of hospitals and >20% in less than one-tenth of hospitals. CONCLUSIONS: In this large national registry, the use of IABP in the setting of PCI for cardiogenic shock decreased over time without a concurrent increase in O-MCS use. The probability of IABP and O-MCS use varied across hospitals, and the use of O-MCS was clustered at a small number of hospitals.

Renal Biomarkers in Heart Failure: Systematic Review and Meta-Analysis.

Background: Cystatin C, neutrophil gelatinase-associated lipocalin (NGAL), and kidney injury molecule (KIM)-1 are renal biomarkers increasingly appreciated for their role in the risk stratification and prognostication of heart failure (HF) patients. However, very few have been adopted clinically, owing to the lack of consistency. Objectives: The authors aimed to study the association between cystatin C, NGAL, and KIM-1 and outcomes, mortality, hospitalizations, and worsening renal function (WRF) in patients with acute and chronic HF. Methods: We included peer-reviewed English-language articles from PubMed and EMBASE published up to December 2021. We analyzed the above associations using random-effects meta-analysis. Publication bias was assessed using funnel plots. Results: Among 2,631 articles, 100 articles, including 45,428 patients, met the inclusion criteria. Top-tertile of serum cystatin C, when compared to the bottom-tertile, carried a higher pooled hazard ratio (pHR) for mortality (pHR: 1.59, 95% CI: 1.42-1.77) and for the composite outcome of mortality and HF hospitalizations (pHR: 1.49, 95% CI: 1.23-1.75). Top-tertile of serum NGAL had a higher hazard for mortality (pHR: 2.91, 95% CI: 1.49-5.67) and composite outcome (HR: 4.11, 95% CI: 2.69-6.30). Serum and urine NGAL were significantly associated with WRF, with pHRs of 2.40 (95% CI: 1.48-3.90) and 2.01 (95% CI: 1.21-3.35). Urine KIM-1 was significantly associated with WRF (pHR: 1.60, 95% CI: 1.24-2.07) but not with other outcomes. High heterogeneity was noted between studies without an obvious explanation based on meta-regression. Conclusions: Serum cystatin C and serum NGAL are independent predictors of adverse outcomes in HF. Serum and urine NGAL are important predictors of WRF in HF.

Hidden Flaws Behind Expert-Level Accuracy of Multimodal GPT-4 Vision in Medicine.

Recent studies indicate that Generative Pre-trained Transformer 4 with Vision (GPT-4V) outperforms human physicians in medical challenge tasks. However, these evaluations primarily focused on the accuracy of multi-choice questions alone. Our study extends the current scope by conducting a comprehensive analysis of GPT-4V's rationales of image comprehension, recall of medical knowledge, and step-by-step multimodal reasoning when solving New England Journal of Medicine (NEJM) Image Challenges - an imaging quiz designed to test the knowledge and diagnostic capabilities of medical professionals. Evaluation results confirmed that GPT-4V performs comparatively to human physicians regarding multi-choice accuracy (81.6% vs. 77.8%). GPT-4V also performs well in cases where physicians incorrectly answer, with over 78% accuracy. However, we discovered that GPT-4V frequently presents flawed rationales in cases where it makes the correct final choices (35.5%), most prominent in image comprehension (27.2%). Regardless of GPT-4V's high accuracy in multi-choice questions, our findings emphasize the necessity for further in-depth evaluations of its rationales before integrating such multimodal AI models into clinical workflows.

Application of deep neural networks for inferring pressure in polymeric acoustic transponders/sensors.

Passive sensor-transponders have raised interest for the last few decades, due to their capability of low-cost remote monitoring without the need for energy storage. Their operating principle includes receiving a signal from a source and then reflecting the signal. While well-established transponders operate through electromagnetic antennas, those with a fully acoustic design have advantages such as lower cost and simplicity. Therefore, detection of pressures using the ultrasound signal that is backscattered from an acoustic resonator has been of interest recently. In order to infer the pressure from the backscattered signal, the established approach has been based upon the principle of detection of the shift to the frequency of resonance. Nevertheless, regression of the pressure from the signal with a small error is challenging and has been subject to research. Here in this paper, we explore an approach that employs deep learning for inferring pressure from the ultrasound reflections of polymeric resonators. We assess if neural network regressors can efficiently infer pressure reflected from a fully acoustic transponder. For this purpose, we compare the performance of several regressors such as a convolutional neural network, a network inspired by the ResNet, and a fully connected neural network. We observe that deep neural networks are advantageous in inferring pressure information with a minimal need for analyzing the signal. Our work suggests that a deep learning approach has the potential to be integrated with or replace other traditional approaches for inferring pressure from an ultrasound signal reflected from fully acoustic transponders or passive sensors.

Low-cost prototyping of nitinol wires/frames using polymeric cores and sacrificial fixtures with application in individualized frames anchoring through the atrial septum.

Self-expanding frames for minimally invasive implants are typically made from nitinol wires and are heat treated to maintain the desired shapes. In the process of heat treatment, nitinol structures are placed in a high-temperature oven, while they are confined by a fixture. During this process, nitinol exerts a high amount of force. Accordingly, a fixture requires high mechanical strength and temperature resistance; this is why fixtures are typically made from metals. The use of metal fixture also increases the turnaround time and cost. However, accelerating this process is beneficial in many applications, such as rapid development of medical implants that are patient-specific. Inspired by the use of sacrificial layers in microfabrication technology, here we propose a novel method for shape setting nitinol wires using a sacrificial metal fixture. In this process, the nitinol wires are first aligned inside copper hypotubes. Next, the forming process is done using hand-held tools to shape complex geometrical structures, annealing the nitinol reinforced by copper, and then selectively etching copper hypotubes in ammonium persulfate solutions. In this process, other sacrificial cores, which are 3D printed or cast from low-cost polymers, are also used. This combination of polymeric cores and minimal use of metals enables reducing the cost and the turnaround time. As a proof of concept, we showed that this process was capable of fabricating springs with mm or sub-mm diameters. The result showed a change of less than 5% in the intended diameter of the nitinol spring with diameters ranging from ~ 0.7 to 1.9 mm, which confirms copper as a suitable sacrificial fixture to obtain the desired complex geometry for nitinol. A metric, based on the elastic strain stored in copper is suggested to predict the possible variation of the intended dimensions in this process. Finally, to demonstrate the potential of this method, as proof of concept, we fabricated NiTi wire frames designed for anchoring through the atrial septum. These frames demonstrated septal defect occluders that were designed based on a patient's cardiac image available in the public domain. This low-cost rapid fabrication technique is highly beneficial for a variety of applications in engineering and medicine with specific applications in rapid prototyping of medical implants.