The use of machine learning for the identification of peripheral artery disease and future mortality risk

Leveraging Artificial Intelligence to Optimize the Care of Peripheral Artery Disease Patients

Peripheral artery disease is a major atherosclerotic disease that is associated with poor outcomes such as limb loss, cardiovascular morbidity, and death. Artificial intelligence (AI) has seen increasing integration in medicine, and its various applications can optimize the care of peripheral artery disease (PAD) patients in diagnosis, predicting patient outcomes, and imaging interpretation. In this review, we introduce various AI applications such as natural language processing, supervised machine learning, and deep learning, and we analyze the current literature in which these algorithms have been applied to PAD.

Earned outcomes correlate with reliability-adjusted surgical mortality after abdominal aortic aneurysm repair and predict future performance

OBJECTIVE

Cumulative, probability-based metrics are regularly used to measure quality in professional sports, but these methods have not been applied to health care delivery. These techniques have the potential to be particularly useful in describing surgical quality, where case volume is variable and outcomes tend to be dominated by statistical "noise." The established statistical technique used to adjust for differences in case volume is reliability-adjustment, which emphasizes statistical "signal" but has several limitations. We sought to validate a novel measure of surgical quality based on earned outcomes methods (deaths above average [DAA]) against reliability-adjusted mortality rates, using abdominal aortic aneurysm (AAA) repair outcomes to illustrate the measure's performance.

METHODS

Earned outcomes methods were used to calculate the outcome of interest for each patient: DAA. Hospital-level DAA was calculated for non-ruptured open AAA repair and endovascular aortic repair (EVAR) in the Vascular Quality Initiative database from 2016 to 2019. DAA for each center is the sum of observed - predicted risk of death for each patient; predicted risk of death was calculated using established multivariable logistic regression modeling. Correlations of DAA with reliability-adjusted mortality rates and procedure volume were determined. Because an accurate quality metric should correlate with future results, outcomes from 2016 to 2017 were used to categorize hospital quality based on: (1) risk-adjusted mortality; (2) risk- and reliability-adjusted mortality; and (3) DAA. The best performing quality metric was determined by comparing the ability of these categories to predict 2018 to 2019 risk-adjusted outcomes.

RESULTS

During the study period, 3734 patients underwent open repair (106 hospitals), and 20,680 patients underwent EVAR (183 hospitals). DAA was closely correlated with reliability-adjusted mortality rates for open repair (r = 0.94; P < .001) and EVAR (r = 0.99; P < .001). DAA also correlated with hospital case volume for open repair (r = -.54; P < .001), but not EVAR (r = 0.07; P = .3). In 2016 to 2017, most hospitals had 0% mortality (55% open repair, 57% EVAR), making it impossible to evaluate these hospitals using traditional risk-adjusted mortality rates alone. Further, zero mortality hospitals in 2016 to 2017 did not demonstrate improved outcomes in 2018 to 2019 for open repair (3.8% vs 4.6%; P = .5) or EVAR (0.8% vs 1.0%; P = .2) compared with all other hospitals. In contrast to traditional risk-adjustment, 2016 to 2017 DAA evenly divided centers into quality quartiles that predicted 2018 to 2019 performance with increased mortality rate associated with each decrement in quality quartile (Q1, 3.2%; Q2, 4.0%; Q3, 5.1%; Q4, 6.0%). There was a significantly higher risk of mortality at worst quartile open repair hospitals compared with best quartile hospitals (odds ratio, 2.01; 95% confidence interval, 1.07-3.76; P = .03). Using 2016 to 2019 DAA to define quality, highest quality quartile open repair hospitals had lower median DAA compared with lowest quality quartile hospitals (-1.18 DAA vs +1.32 DAA; P < .001), correlating with lower median reliability-adjusted mortality rates (3.6% vs 5.1%; P < .001).

CONCLUSIONS

Adjustment for differences in hospital volume is essential when measuring hospital-level outcomes. Earned outcomes accurately categorize hospital quality and correlate with reliability-adjustment but are easier to calculate and interpret. From 2016 to 2019, highest quality open AAA repair hospitals prevented >40 perioperative deaths compared with the average hospital, and >80 perioperative deaths compared with lowest quality hospitals.

Wearable technology in vascular surgery: Current applications and future perspectives

The COVID-19 pandemic exposed the vulnerabilities of global health care systems, underscoring the need for innovative solutions to meet the demands of an aging population, workforce shortages, and rising physician burnout. In recent years, wearable technology has helped segue various medical specialties into the digital era, yet its adoption in vascular surgery remains limited. This article explores the applications of wearable devices in vascular surgery and explores their potential outlets, such as enhancing primary and secondary prevention, optimizing perioperative care, and supporting surgical training. The integration of artificial intelligence and machine learning with wearable technology further expands its applications, enabling predictive analytics, personalized care, and remote monitoring. Despite the promising prospects, challenges such as regulatory complexities, data security, and interoperability must be addressed. As the digital health movement unfolds, wearable technology could play a pivotal role in reshaping vascular surgery while offering cost-effective, accessible, and patient-centered care.

Current Applications and Future Perspectives of Artificial and Biomimetic Intelligence in Vascular Surgery and Peripheral Artery Disease

Artificial Intelligence (AI) made its first appearance in 1956, and since then it has progressively introduced itself in healthcare systems and patients' information and care. AI functions can be grouped under the following headings: Machine Learning (ML), Deep Learning (DL), Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Computer Vision (CV). Biomimetic intelligence (BI) applies the principles of systems of nature to create biological algorithms, such as genetic and neural network, to be used in different scenarios. Chronic limb-threatening ischemia (CLTI) represents the last stage of peripheral artery disease (PAD) and has increased over recent years, together with the rise in prevalence of diabetes and population ageing. Nowadays, AI and BI grant the possibility of developing new diagnostic and treatment solutions in the vascular field, given the possibility of accessing clinical, biological, and imaging data. By assessing the vascular anatomy in every patient, as well as the burden of atherosclerosis, and classifying the level and degree of disease, sizing and planning the best endovascular treatment, defining the perioperative complications risk, integrating experiences and resources between different specialties, identifying latent PAD, thus offering evidence-based solutions and guiding surgeons in the choice of the best surgical technique, AI and BI challenge the role of the physician's experience in PAD treatment.

Machine Learning in Hypertrophic Cardiomyopathy: Nonlinear Model From Clinical and CMR Features Predicting Cardiovascular Events

BACKGROUND

The cumulative burden of hypertrophic cardiomyopathy (HCM) is significant, with a noteworthy percentage (10%-15%) of patients with HCM per year experiencing major adverse cardiovascular events (MACEs). A current risk stratification scheme for HCM had only limited accuracy in predicting sudden cardiac death (SCD) and failed to account for a broader spectrum of adverse cardiovascular events and cardiac magnetic resonance (CMR) parameters.

OBJECTIVES

This study sought to develop and evaluate a machine learning (ML) framework that integrates CMR imaging and clinical characteristics to predict MACEs in patients with HCM.

METHODS

A total of 758 patients with HCM (67% male; aged 49 ± 14 years) who were admitted between 2010 and 2017 from 4 medical centers were included. The ML model was built on the internal discovery cohort (533 patients with HCM, admitted to Fuwai Hospital, Beijing, China) by using the light gradient-boosting machine and internally evaluated using cross-validation. The external test cohort consisted of 225 patients with HCM from 3 medical centers. A total of 14 CMR imaging features (strain and late gadolinium enhancement [LGE]) and 23 clinical variables were evaluated and used to inform the ML model. MACEs included a composite of arrhythmic events, SCD, heart failure, and atrial fibrillation-related stroke.

RESULTS

MACEs occurred in 191 (25%) patients over a median follow-up period of 109.0 months (Q1-Q3: 73.0-118.8 months). Our ML model achieved areas under the curve (AUCs) of 0.830 and 0.812 (internally and externally, respectively). The model outperformed the classic HCM Risk-SCD model, with significant improvement (P < 0.001) of 22.7% in the AUC. Using the cubic spline analysis, the study showed that the extent of LGE and the impairment of global radial strain (GRS) and global circumferential strain (GCS) were nonlinearly correlated with MACEs: an elevated risk of adverse cardiovascular events was observed when these parameters reached the high enough second tertiles (11.6% for LGE, 25.8% for GRS, -17.3% for GCS).

CONCLUSIONS

ML-empowered risk stratification using CMR and clinical features enabled accurate MACE prediction beyond the classic HCM Risk-SCD model. In addition, the nonlinear correlation between CMR features (LGE and left ventricular pressure gradient) and MACEs uncovered in this study provides valuable insights for the clinical assessment and management of HCM.

Contrast-Enhanced Magnetic Resonance Imaging Based T1 Mapping and Extracellular Volume Fractions Are Associated with Peripheral Artery Disease

BACKGROUND

Extracellular volume fraction (ECV), measured with contrast-enhanced magnetic resonance imaging (CE-MRI), has been utilized to study myocardial fibrosis, but its role in peripheral artery disease (PAD) remains unknown. We hypothesized that T1 mapping and ECV differ between PAD patients and matched controls.

METHODS AND RESULTS

A total of 37 individuals (18 PAD patients and 19 matched controls) underwent 3.0T CE-MRI. Skeletal calf muscle T1 mapping was performed before and after gadolinium contrast with a motion-corrected modified look-locker inversion recovery (MOLLI) pulse sequence. T1 values were calculated with a three-parameter Levenberg-Marquardt curve fitting algorithm. ECV and T1 maps were quantified in five calf muscle compartments (anterior [AM], lateral [LM], and deep posterior [DM] muscle groups; soleus [SM] and gastrocnemius [GM] muscles). Averaged peak blood pool T1 values were obtained from the posterior and anterior tibialis and peroneal arteries. T1 values and ECV are heterogeneous across calf muscle compartments. Native peak T1 values of the AM, LM, and DM were significantly higher in PAD patients compared to controls (all p < 0.028). ECVs of the AM and SM were significantly higher in PAD patients compared to controls (AM: 26.4% (21.2, 31.6) vs. 17.3% (10.2, 25.1), p = 0.046; SM: 22.7% (19.5, 27.8) vs. 13.8% (10.2, 19.1), p = 0.020).

CONCLUSIONS

Native peak T1 values across all five calf muscle compartments, and ECV fractions of the anterior muscle group and the soleus muscle were significantly elevated in PAD patients compared with matched controls. Non-invasive T1 mapping and ECV quantification may be of interest for the study of PAD.

CASCADE: Context-Aware Data-Driven AI for Streamlined Multidisciplinary Tumor Board Recommendations in Oncology

This study addresses the potential of machine learning in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). Using an IRB-approved retrospective study of patients discussed at a multidisciplinary tumor board, clinical and imaging variables were extracted and used in a gradient-boosting machine learning algorithm, XGBoost. The algorithm's performance was assessed using confusion matrix metrics and the area under the Receiver Operating Characteristics (ROC) curve. The study included 140 patients (mean age 67.7 ± 8.9 years), and the algorithm was found to be predictive of all eight treatment recommendations made by the board. The model's predictions were more accurate than those based on published therapeutic guidelines by ESMO and NCCN. The study concludes that a machine learning model incorporating clinical and imaging variables can predict treatment recommendations made by an expert multidisciplinary tumor board, potentially aiding clinical decision-making in settings lacking subspecialty expertise.

Identifying the risk factors of ICU-acquired fungal infections: clinical evidence from using machine learning

Background

Fungal infections are associated with high morbidity and mortality in the intensive care unit (ICU), but their diagnosis is difficult. In this study, machine learning was applied to design and define the predictive model of ICU-acquired fungi (ICU-AF) in the early stage of fungal infections using Random Forest.

Objectives

This study aimed to provide evidence for the early warning and management of fungal infections.

Methods

We analyzed the data of patients with culture-positive fungi during their admission to seven ICUs of the First Affiliated Hospital of Chongqing Medical University from January 1, 2015, to December 31, 2019. Patients whose first culture was positive for fungi longer than 48 h after ICU admission were included in the ICU-AF cohort. A predictive model of ICU-AF was obtained using the Least Absolute Shrinkage and Selection Operator and machine learning, and the relationship between the features within the model and the disease severity and mortality of patients was analyzed. Finally, the relationships between the ICU-AF model, antifungal therapy and empirical antifungal therapy were analyzed.

Results

A total of 1,434 cases were included finally. We used lasso dimensionality reduction for all features and selected six features with importance ≥0.05 in the optimal model, namely, times of arterial catheter, enteral nutrition, corticosteroids, broadspectrum antibiotics, urinary catheter, and invasive mechanical ventilation. The area under the curve of the model for predicting ICU-AF was 0.981 in the test set, with a sensitivity of 0.960 and specificity of 0.990. The times of arterial catheter (p = 0.011, OR = 1.057, 95% CI = 1.053-1.104) and invasive mechanical ventilation (p = 0.007, OR = 1.056, 95%CI = 1.015-1.098) were independent risk factors for antifungal therapy in ICU-AF. The times of arterial catheter (p = 0.004, OR = 1.098, 95%CI = 0.855-0.970) were an independent risk factor for empirical antifungal therapy.

Conclusion

The most important risk factors for ICU-AF are the six time-related features of clinical parameters (arterial catheter, enteral nutrition, corticosteroids, broadspectrum antibiotics, urinary catheter, and invasive mechanical ventilation), which provide early warning for the occurrence of fungal infection. Furthermore, this model can help ICU physicians to assess whether empiric antifungal therapy should be administered to ICU patients who are susceptible to fungal infections.

Artificial Intelligence of Arterial Doppler Waveforms to Predict Major Adverse Outcomes Among Patients Evaluated for Peripheral Artery Disease

BACKGROUND

Patients with peripheral artery disease are at increased risk for major adverse cardiac events, major adverse limb events, and all-cause death. Developing tools capable of identifying those patients with peripheral artery disease at greatest risk for major adverse events is the first step for outcome prevention. This study aimed to determine whether computer-assisted analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with peripheral artery disease at greatest risk for adverse outcome events.

METHODS AND RESULTS

Consecutive patients (April 1, 2015, to December 31, 2020) undergoing ankle-brachial index testing were included. Patients were randomly allocated to training, validation, and testing subsets (60%/20%/20%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict major adverse cardiac events, major adverse limb events, and all-cause death at 5 years. Patients were then analyzed in groups based on the quartiles of each prediction score in the training set. Among 11 384 total patients, 10 437 patients met study inclusion criteria (mean age, 65.8±14.8 years; 40.6% women). The test subset included 2084 patients. During 5 years of follow-up, there were 447 deaths, 585 major adverse cardiac events, and 161 MALE events. After adjusting for age, sex, and Charlson comorbidity index, deep neural network analysis of the posterior tibial artery waveform provided independent prediction of death (hazard ratio [HR], 2.44 [95% CI, 1.78-3.34]), major adverse cardiac events (HR, 1.97 [95% CI, 1.49-2.61]), and major adverse limb events (HR, 11.03 [95% CI, 5.43-22.39]) at 5 years.

CONCLUSIONS

An artificial intelligence-enabled analysis of Doppler arterial waveforms enables identification of major adverse outcomes among patients with peripheral artery disease, which may promote early adoption and adherence of risk factor modification.

A machine learning-based approach to identify peripheral artery disease using texture features from contrast-enhanced magnetic resonance imaging

Diagnosing and assessing the risk of peripheral artery disease (PAD) has long been a focal point for medical practitioners. The impaired blood circulation in PAD patients results in altered microvascular perfusion patterns in the calf muscles which is the primary location of intermittent claudication pain. Consequently, we hypothesized that changes in perfusion and increase in connective tissue could lead to alterations in the appearance or texture patterns of the skeletal calf muscles, as visualized with non-invasive imaging techniques. We designed an automatic pipeline for textural feature extraction from contrast-enhanced magnetic resonance imaging (CE-MRI) scans and used the texture features to train machine learning models to detect the heterogeneity in the muscle pattern among PAD patients and matched controls. CE-MRIs from 36 PAD patients and 20 matched controls were used for preparing training and testing data at a 7:3 ratio with cross-validation (CV) techniques. We employed feature arrangement and selection methods to optimize the number of features. The proposed method achieved a peak accuracy of 94.11% and a mean testing accuracy of 84.85% in a 2-class classification approach (controls vs. PAD). A three-class classification approach was performed to identify a high-risk PAD sub-group which yielded an average test accuracy of 83.23% (matched controls vs. PAD without diabetes vs. PAD with diabetes). Similarly, we obtained 78.60% average accuracy among matched controls, PAD treadmill exercise completers, and PAD exercise treadmill non-completers. Machine learning and imaging-based texture features may be of interest in the study of lower extremity ischemia.

Diagnosis of disease affecting gait with a body acceleration-based model using reflected marker data for training and a wearable accelerometer for implementation

This paper demonstrates the value of a framework for processing data on body acceleration as a uniquely valuable tool for diagnosing diseases that affect gait early. As a case study, we used this model to identify individuals with peripheral artery disease (PAD) and distinguish them from those without PAD. The framework uses acceleration data extracted from anatomical reflective markers placed in different body locations to train the diagnostic models and a wearable accelerometer carried at the waist for validation. Reflective marker data have been used for decades in studies evaluating and monitoring human gait. They are widely available for many body parts but are obtained in specialized laboratories. On the other hand, wearable accelerometers enable diagnostics outside lab conditions. Models trained by raw marker data at the sacrum achieve an accuracy of 92% in distinguishing PAD patients from non-PAD controls. This accuracy drops to 28% when data from a wearable accelerometer at the waist validate the model. This model was enhanced by using features extracted from the acceleration rather than the raw acceleration, with the marker model accuracy only dropping from 86 to 60% when validated by the wearable accelerometer data.

Applying Artificial Intelligence to Predict Complications After Endovascular Aneurysm Repair

Objective: Complications after Endovascular Aneurysm Repair (EVAR) can be fatal. Patient follow-up for surveillance imaging is becoming more challenging as fewer patients are seen, particularly after the first year. The aim of this study was to develop an artificial intelligence model to predict the complication probability of individual patients to better identify those needing more intensive post-operative surveillance. Methods: Pre-operative CTA 3D reconstruction images of AAA from 273 patients who underwent EVAR from 2011-2020 were collected. Of these, 48 patients had post-operative complications including endoleak, AAA rupture, graft limb occlusion, renal artery occlusion, and neck dilation. A deep convolutional neural network model (VascAI©) was developed which utilized pre-operative 3D CT images to predict risk of complications after EVAR. The model was built with TensorFlow software and run on the Google Colab Platform. An initial training subset of 40 randomly selected patients with complications and 189 without were used to train the AI model while the remaining 8 positive and 36 negative cases tested its performance and prediction accuracy. Data down-sampling was used to alleviate data imbalance and data augmentation methodology to further boost model performance. Results: Successful training was completed on the 229 cases in the training set and then applied to predict the complication probability of each individual in the held-out performance testing cases. The model provided a complication sensitivity of 100% and identified all the patients who later developed complications after EVAR. Of 36 patients without complications, 16 (44%) were falsely predicted to develop complications. The results therefore demonstrated excellent sensitivity for identifying patients who would benefit from more stringent surveillance and decrease the frequency of surveillance in 56% of patients unlike to develop complications. Conclusion: AI models can be developed to predict the risk of post-operative complications with high accuracy. Compared to existing methods, the model developed in this study did not require any expert-annotated data but only the AAA CTA images as inputs. This model can play an assistive role in identifying patients at high risk for post-EVAR complications and the need for greater compliance in surveillance.

Identifying target ion channel-related genes to construct a diagnosis model for insulinoma

Background: Insulinoma is the most common functional pancreatic neuroendocrine tumor (PNET) with abnormal insulin hypersecretion. The etiopathogenesis of insulinoma remains indefinable. Based on multiple bioinformatics methods and machine learning algorithms, this study proposed exploring the molecular mechanism from ion channel-related genes to establish a genetic diagnosis model for insulinoma. Methods: The mRNA expression profile dataset of GSE73338 was applied to the analysis, which contains 17 insulinoma samples, 63 nonfunctional PNET (NFPNET) samples, and four normal islet samples. Differently expressed ion channel-related genes (DEICRGs) enrichment analyses were performed. We utilized the protein-protein interaction (PPI) analysis and machine learning of LASSO and support vector machine-recursive feature elimination (SVM-RFE) to identify the target genes. Based on these target genes, a nomogram diagnostic model was constructed and verified by a receiver operating characteristic (ROC) curve. Moreover, immune infiltration analysis, single-gene gene set enrichment analysis (GSEA), and gene set variation analysis (GSVA) were executed. Finally, a drug-gene interaction network was constructed. Results: We identified 29 DEICRGs, and enrichment analyses indicated they were primarily enriched in ion transport, cellular ion homeostasis, pancreatic secretion, and lysosome. Moreover, the PPI network and machine learning recognized three target genes (MCOLN1, ATP6V0E1, and ATP4A). Based on these target genes, we constructed an efficiently predictable diagnosis model for identifying insulinomas with a nomogram and validated it with the ROC curve (AUC = 0.801, 95% CI 0.674-0.898). Then, single-gene GSEA analysis revealed that these target genes had a significantly positive correlation with insulin secretion and lysosome. In contrast, the TGF-beta signaling pathway was negatively associated with them. Furthermore, statistically significant discrepancies in immune infiltration were revealed. Conclusion: We identified three ion channel-related genes and constructed an efficiently predictable diagnosis model to offer a novel approach for diagnosing insulinoma.

Artificial intelligence in clinical workflow processes in vascular surgery and beyond

In the past decade, artificial intelligence (AI)-based applications have exploded in health care. In cardiovascular disease, and vascular surgery specifically, AI tools such as machine learning, natural language processing, and deep neural networks have been applied to automatically detect underdiagnosed diseases, such as peripheral artery disease, abdominal aortic aneurysms, and atherosclerotic cardiovascular disease. In addition to disease detection and risk stratification, AI has been used to identify guideline-concordant statin therapy use and reasons for nonuse, which has important implications for population-based cardiovascular disease health. Although many studies highlight the potential applications of AI, few address true clinical workflow implementation of available AI-based tools. Specific examples, such as determination of optimal statin treatment based on individual patient risk factors and enhancement of intraoperative fluoroscopy and ultrasound imaging, demonstrate the potential promise of AI integration into clinical workflow. Many challenges to AI implementation in health care remain, including data interoperability, model bias and generalizability, prospective evaluation, privacy and security, and regulation. Multidisciplinary and multi-institutional collaboration, as well as adopting a framework for integration, will be critical for the successful implementation of AI tools into clinical practice.

Artificial intelligence-based predictive models in vascular diseases

Cardiovascular disease represents a source of major health problems worldwide, and although medical and technical advances have been achieved, they are still associated with high morbidity and mortality rates. Personalized medicine would benefit from novel tools to better predict individual prognosis and outcomes after intervention. Artificial intelligence (AI) has brought new insights to cardiovascular medicine, especially with the use of machine learning techniques that allow the identification of hidden patterns and complex associations in health data without any a priori assumptions. This review provides an overview on the use of artificial intelligence-based prediction models in vascular diseases, specifically focusing on aortic aneurysm, lower extremity arterial disease, and carotid stenosis. Potential benefits include the development of precision medicine in patients with vascular diseases. In addition, the main challenges that remain to be overcome to integrate artificial intelligence-based predictive models in clinical practice are discussed.

Protecting patient safety and privacy in the era of artificial intelligence

The promise of artificial intelligence (AI) in health care has propelled a significant uptrend in the number of clinical trials in AI and global market spending in this novel technology. In vascular surgery, this technology has the ability to diagnose disease, predict disease outcomes, and assist with image-guided surgery. As we enter an era of rapid change, it is critical to evaluate the ethical concerns of AI, particularly as it may impact patient safety and privacy. This is particularly important to discuss in the early stages of AI, as technology frequently outpaces the policies and ethical guidelines regulating it. Issues at the forefront include patient privacy and confidentiality, protection of patient autonomy and informed consent, accuracy and applicability of this technology, and propagation of health care disparities. Vascular surgeons should be equipped to work with AI, as well as discuss its novel risks to patient safety and privacy.

Bias in artificial intelligence in vascular surgery

Application of artificial intelligence (AI) has revolutionized the utilization of big data, especially in patient care. The potential of deep learning models to learn without a priori assumption, or without prior learning, to connect seemingly unrelated information mixes excitement alongside hesitation to fully understand AI's limitations. Bias, ranging from data collection and input to algorithm development to finally human review of algorithm output affects AI's application to clinical patient presents unique challenges that differ significantly from biases in traditional analyses. Algorithm fairness, a new field of research within AI, aims to mitigate bias by evaluating the data at the preprocessing stage, optimizing during algorithm development, and evaluating algorithm output at the postprocessing stage. As the field continues to develop, being cognizant of the inherent biases and limitations related to black box decision making, biased data sets agnostic to patient-level disparities, wide variation of present methodologies, and lack of common reporting standards will require ongoing research to provide transparency to AI and its applications.

Potential applications of artificial intelligence and machine learning on diagnosis, treatment, and outcome prediction to address health care disparities of chronic limb-threatening ischemia

Chronic limb-threatening ischemia (CLTI) is the most advanced form of peripheral artery disease. CLTI has an extremely poor prognosis and is associated with considerable risk of major amputation, cardiac morbidity, mortality, and poor quality of life. Early diagnosis and targeted treatment of CLTI is critical for improving patient's prognosis. However, this objective has proven elusive, time-consuming, and challenging due to existing health care disparities among patients. In this article, we reviewed how artificial intelligence (AI) and machine learning (ML) can be helpful to accurately diagnose, improve outcome prediction, and identify disparities in the treatment of CLTI. We demonstrate the importance of AI/ML approaches for management of these patients and how available data could be used for computer-guided interventions. Although AI/ML applications to mitigate health care disparities in CLTI are in their infancy, we also highlighted specific AI/ML methods that show potential for addressing health care disparities in CLTI.

Identifying Patients With Peripheral Artery Disease Using the Electronic Health Record: A Pragmatic Approach

BACKGROUND

Peripheral artery disease (PAD) is underdiagnosed due to poor patient and clinician awareness. Despite this, no widely accepted PAD screening is recommended.

OBJECTIVES

The authors used machine learning to develop an automated risk stratification tool for identifying patients with a high likelihood of PAD.

METHODS

Using data from the electronic health record (EHR), ankle-brachial indices (ABIs) were extracted for 3,298 patients. In addition to ABI, we extracted 60 other patient characteristics and used a random forest model to rank the features by association with ABI. The model identified several features independently correlated with PAD. We then built a logistic regression model to predict PAD status on a validation set of patients (n = 1,089), an external cohort of patients (n = 2,922), and a national database (n = 2,488). The model was compared to an age-based and random forest model.

RESULTS

The model had an area under the curve (AUC) of 0.68 in the validation set. When evaluated on an external population using EHR data, it performed similarly with an AUC of 0.68. When evaluated on a national database, it had an AUC of 0.72. The model outperformed an age-based model (AUC: 0.62; P < 0.001). A random forest model with inclusion of all 60 features did not perform significantly better (AUC: 0.71; P = 0.31).

CONCLUSIONS

Statistical techniques can be used to build models which identify individuals at high risk for PAD using information accessible from the EHR. Models such as this may allow large health care systems to efficiently identify patients that would benefit from aggressive preventive strategies or targeted-ABI screening.

Application of machine learning algorithms in electronic medical records to predict amputation-free survival after first revascularization in patients with peripheral artery disease

BACKGROUND

This study aimed to apply eight machine learning algorithms to develop the optimal model to predict amputation-free survival (AFS) after first revascularization in patients with peripheral artery disease (PAD).

METHODS

Among 2130 patients from 2011 to 2020, 1260 patients who underwent revascularization were randomly assigned to training set and validation set in an 8:2 ratio. 67 clinical parameters were analyzed by lasso regression analysis. Logistic regression, gradient boosting machine, random forest, decision tree, eXtreme gradient boosting, neural network, Cox regression, and random survival forest (RSF) were applied to develop prediction models. The optimal model was compared with GermanVasc score in testing set comprising patients from 2010.

RESULTS

The postoperative 1/3/5-year AFS were 90%, 79.4%, and 74.1%. Age (HR:1.035, 95%CI: 1.015-1.056), atrial fibrillation (HR:2.257, 95%CI: 1.193-4.271), cardiac ejection fraction (HR:0.064, 95%CI: 0.009-0.413), Rutherford grade ≥ 5 (HR:1.899, 95%CI: 1.296-2.782), creatinine (HR:1.03, 95%CI: 1.02-1.04), surgery duration (HR:1.03, 95%CI: 1.01-1.05), and fibrinogen (HR:1.292, 95%CI: 1.098-1.521) were independent risk factors. The optimal model was developed by RSF algorithm, with 1/3/5-year AUCs in training set of 0.866 (95% CI:0.819-0.912), 0.854 (95% CI:0.811-0.896), 0.844 (95% CI:0.793-0.894), in validation set of 0.741 (95% CI:0.580-0.902), 0.768 (95% CI:0.654-0.882), 0.836 (95% CI:0.719-0.953), and in testing set of 0.821 (95%CI: 0.711-0.931), 0.802 (95%CI: 0.684-0.919), 0.798 (95%CI: 0.657-0.939). The c-index of the model outperformed GermanVasc Score (0.788 vs 0.730). A dynamic nomogram was published on shinyapp (https://wyy2023.shinyapps.io/amputation/).

CONCLUSION

The optimal prediction model for AFS after first revascularization in patients with PAD was developed by RSF algorithm, which exhibited outstanding prediction performance.

Applications of artificial intelligence for patients with peripheral artery disease

OBJECTIVE

Applications of artificial intelligence (AI) have been reported in several cardiovascular diseases but its interest in patients with peripheral artery disease (PAD) has been so far less reported. The aim of this review was to summarize current knowledge on applications of AI in patients with PAD, to discuss current limits, and highlight perspectives in the field.

METHODS

We performed a narrative review based on studies reporting applications of AI in patients with PAD. The MEDLINE database was independently searched by two authors using a combination of keywords to identify studies published between January 1995 and December 2021. Three main fields of AI were investigated including natural language processing (NLP), computer vision and machine learning (ML).

RESULTS

NLP and ML brought new tools to improve the screening, the diagnosis and classification of the severity of PAD. ML was also used to develop predictive models to better assess the prognosis of patients and develop real-time prediction models to support clinical decision-making. Studies related to computer vision mainly aimed at creating automatic detection and characterization of arterial lesions based on Doppler ultrasound examination or computed tomography angiography. Such tools could help to improve screening programs, enhance diagnosis, facilitate presurgical planning, and improve clinical workflow.

CONCLUSIONS

AI offers various applications to support and likely improve the management of patients with PAD. Further research efforts are needed to validate such applications and investigate their accuracy and safety in large multinational cohorts before their implementation in daily clinical practice.

Lower-extremity pressure, staging, and grading thresholds to identify chronic limb-threatening ischemia

INTRODUCTION

The Society for Vascular Surgery Threatened Limb Classification System ('WIfI') is used to predict risk of limb loss and identify peripheral artery disease in patients with foot ulcers or gangrene. We estimated the diagnostic sensitivity of multiple clinical and noninvasive arterial parameters to identify chronic limb-threatening ischemia (CLTI).

METHODS

We performed a single-center review of 100 consecutive patients who underwent angiography for foot gangrene or ulcers. WIfI stages and grades were determined for each patient. Toe, ankle, and brachial pressure measurements were performed by registered vascular technologists. CLTI severity was characterized using Global Limb Anatomic Staging System (GLASS stages) and angiosomes. Medial artery calcification in the foot was quantified on foot radiographs.

RESULTS

GLASS NA (not applicable), I, II, and III angiographic findings were seen in 21, 21, 23, and 35 patients, respectively. A toe-brachial index < 0.7 and minimum ipsilateral ankle-brachial index < 0.9 performed well in identifying GLASS II and III angiographic findings, with sensitivity rates 97.8% and 91.5%, respectively. The diagnostic accuracy rates of noninvasive measures peaked at 74.7% and 89.3% for identifying GLASS II/III and GLASS I+ angiographic findings, respectively. The presence of medial artery calcification significantly diminished the sensitivity of most noninvasive parameters.

CONCLUSIONS

The use of alternative noninvasive arterial testing parameters improves sensitivity for detecting PAD. Abnormal noninvasive results should suggest the need for diagnostic angiography to further characterize arterial anatomy of the affected limb. Testing strategies with better accuracy are needed.

Artificial intelligence in atherosclerotic disease: Applications and trends

Atherosclerotic cardiovascular disease (ASCVD) is the most common cause of death globally. Increasing amounts of highly diverse ASCVD data are becoming available and artificial intelligence (AI) techniques now bear the promise of utilizing them to improve diagnosis, advance understanding of disease pathogenesis, enable outcome prediction, assist with clinical decision making and promote precision medicine approaches. Machine learning (ML) algorithms in particular, are already employed in cardiovascular imaging applications to facilitate automated disease detection and experts believe that ML will transform the field in the coming years. Current review first describes the key concepts of AI applications from a clinical standpoint. We then provide a focused overview of current AI applications in four main ASCVD domains: coronary artery disease (CAD), peripheral arterial disease (PAD), abdominal aortic aneurysm (AAA), and carotid artery disease. For each domain, applications are presented with refer to the primary imaging modality used [e.g., computed tomography (CT) or invasive angiography] and the key aim of the applied AI approaches, which include disease detection, phenotyping, outcome prediction, and assistance with clinical decision making. We conclude with the strengths and limitations of AI applications and provide future perspectives.

Machine Learning-Based Peripheral Artery Disease Identification Using Laboratory-Based Gait Data

Peripheral artery disease (PAD) manifests from atherosclerosis, which limits blood flow to the legs and causes changes in muscle structure and function, and in gait performance. PAD is underdiagnosed, which delays treatment and worsens clinical outcomes. To overcome this challenge, the purpose of this study is to develop machine learning (ML) models that distinguish individuals with and without PAD. This is the first step to using ML to identify those with PAD risk early. We built ML models based on previously acquired overground walking biomechanics data from patients with PAD and healthy controls. Gait signatures were characterized using ankle, knee, and hip joint angles, torques, and powers, as well as ground reaction forces (GRF). ML was able to classify those with and without PAD using Neural Networks or Random Forest algorithms with 89% accuracy (0.64 Matthew's Correlation Coefficient) using all laboratory-based gait variables. Moreover, models using only GRF variables provided up to 87% accuracy (0.64 Matthew's Correlation Coefficient). These results indicate that ML models can classify those with and without PAD using gait signatures with acceptable performance. Results also show that an ML gait signature model that uses GRF features delivers the most informative data for PAD classification.

Early prediction of hypothermia in pediatric intensive care units using machine learning

Hypothermia is a life-threatening condition where the temperature of the body drops below 35°C and is a key source of concern in Intensive Care Units (ICUs). Early identification can help to nudge clinical management to initiate early interventions. Despite its importance, very few studies have focused on the early prediction of hypothermia. In this study, we aim to monitor and predict Hypothermia (30 min-4 h) ahead of its onset using machine learning (ML) models developed on physiological vitals and to prospectively validate the best performing model in the pediatric ICU. We developed and evaluated ML algorithms for the early prediction of hypothermia in a pediatric ICU. Sepsis advanced forecasting engine ICU Database (SafeICU) data resource is an in-house ICU source of data built in the Pediatric ICU at the All-India Institute of Medical Science (AIIMS), New Delhi. Each time-stamp at 1-min resolution was labeled for the presence of hypothermia to construct a retrospective cohort of pediatric patients in the SafeICU data resource. The training set consisted of windows of the length of 4.2 h with a lead time of 30 min-4 h from the onset of hypothermia. A set of 3,835 hand-engineered time-series features were calculated to capture physiological features from the time series. Features selection using the Boruta algorithm was performed to select the most important predictors of hypothermia. A battery of models such as gradient boosting machine, random forest, AdaBoost, and support vector machine (SVM) was evaluated utilizing five-fold test sets. The best-performing model was prospectively validated. A total of 148 patients with 193 ICU stays were eligible for the model development cohort. Of 3,939 features, 726 were statistically significant in the Boruta analysis for the prediction of Hypothermia. The gradient boosting model performed best with an Area Under the Receiver Operating Characteristic curve (AUROC) of 85% (SD = 1.6) and a precision of 59.2% (SD = 8.8) for a 30-min lead time before the onset of Hypothermia onset. As expected, the model showed a decline in model performance at higher lead times, such as AUROC of 77.2% (SD = 2.3) and precision of 41.34% (SD = 4.8) for 4 h ahead of Hypothermia onset. Our GBM(gradient boosting machine) model produced equal and superior results for the prospective validation, where an AUROC of 79.8% and a precision of 53% for a 30-min lead time before the onset of Hypothermia whereas an AUROC of 69.6% and a precision of 38.52% for a (30 min-4 h) lead time prospective validation of Hypothermia. Therefore, this work establishes a pipeline termed ThermoGnose for predicting hypothermia, a major complication in pediatric ICUs.

Perceptions of Canadian vascular surgeons toward artificial intelligence and machine learning

Background

Artificial intelligence (AI) and machine learning (ML) are rapidly advancing fields with increasing utility in health care. We conducted a survey to determine the perceptions of Canadian vascular surgeons toward AI/ML.

Methods

An online questionnaire was distributed to 162 members of the Canadian Society for Vascular Surgery. Self-reported knowledge, attitudes, and perceptions with respect to potential applications, limitations, and facilitators of AI/ML were assessed.

Results

Overall, 50 of the 162 Canadian vascular surgeons (31%) responded to the survey. Most respondents were aged 30 to 59 years (72%), male (80%), and White (67%) and practiced in academic settings (72%). One half of the participants reported that their knowledge of AI/ML was poor or very poor. Most were excited or very excited about AI/ML (66%) and were interested or very interested in learning more about the field (83.7%). The respondents believed that AI/ML would be useful or very useful for diagnosis (62%), prognosis (72%), patient selection (56%), image analysis (64%), intraoperative guidance (52%), research (88%), and education (80%). The limitations that the participants were most concerned about were errors leading to patient harm (42%), bias based on patient demographics (42%), and lack of clinician knowledge and skills in AI/ML (40%). Most were not concerned or were mildly concerned about job replacement (86%). The factors that were most important to encouraging clinicians to use AI/ML models were improvements in efficiency (88%), accurate predictions (84%), and ease of use (84%). The comments from respondents focused on the pressing need for the implementation of AI/ML in vascular surgery owing to the potential to improve care delivery.

Conclusions

Canadian vascular surgeons have positive views on AI/ML and believe this technology can be applied to multiple aspects of the specialty to improve patient care, research, and education. Current self-reported knowledge is poor, although interest was expressed in learning more about the field. The facilitators and barriers to the effective use of AI/ML identified in the present study can guide future development of these tools in vascular surgery.

Performance and usability testing of an automated tool for detection of peripheral artery disease using electronic health records

Peripheral artery disease (PAD) is a common cardiovascular disorder that is frequently underdiagnosed, which can lead to poorer outcomes due to lower rates of medical optimization. We aimed to develop an automated tool to identify undiagnosed PAD and evaluate physician acceptance of a dashboard representation of risk assessment. Data were derived from electronic health records (EHR). We developed and compared traditional risk score models to novel machine learning models. For usability testing, primary and specialty care physicians were recruited and interviewed until thematic saturation. Data from 3168 patients with PAD and 16,863 controls were utilized. Results showed a deep learning model that utilized time engineered features outperformed random forest and traditional logistic regression models (average AUCs 0.96, 0.91 and 0.81, respectively), P < 0.0001. Of interviewed physicians, 75% were receptive to an EHR-based automated PAD model. Feedback emphasized workflow optimization, including integrating risk assessments directly into the EHR, using dashboard designs that minimize clicks, and providing risk assessments for clinically complex patients. In conclusion, we demonstrate that EHR-based machine learning models can accurately detect risk of PAD and that physicians are receptive to automated risk detection for PAD. Future research aims to prospectively validate model performance and impact on patient outcomes.

Machine learning prediction of hematoma expansion in acute intracerebral hemorrhage

To examine whether machine learning (ML) approach can be used to predict hematoma expansion in acute intracerebral hemorrhage (ICH) with accuracy and widespread applicability, we applied ML algorithms to multicenter clinical data and CT findings on admission. Patients with acute ICH from three hospitals (n = 351) and those from another hospital (n = 71) were retrospectively assigned to the development and validation cohorts, respectively. To develop ML predictive models, the k-nearest neighbors (k-NN) algorithm, logistic regression, support vector machines (SVMs), random forests, and XGBoost were applied to the patient data in the development cohort. The models were evaluated for their performance on the patient data in the validation cohort, which was compared with previous scoring methods, the BAT, BRAIN, and 9-point scores. The k-NN algorithm achieved the highest area under the receiver operating characteristic curve (AUC) of 0.790 among all ML models, and the sensitivity, specificity, and accuracy were 0.846, 0.733, and 0.775, respectively. The BRAIN score achieved the highest AUC of 0.676 among all previous scoring methods, which was lower than the k-NN algorithm (p = 0.016). We developed and validated ML predictive models of hematoma expansion in acute ICH. The models demonstrated good predictive ability, showing better performance than the previous scoring methods.

Machine learning-based classification of arterial spectral waveforms for the diagnosis of peripheral artery disease in the context of diabetes: A proof-of-concept study

BACKGROUND

Point-of-care duplex ultrasound has emerged as a promising test for the diagnosis of peripheral artery disease (PAD). However, the interpretation of morphologically diverse Doppler arterial spectral waveforms is challenging and associated with wide inter-observer variation. The aim of this study is to evaluate the utility of machine learning techniques for the diagnosis of PAD from Doppler arterial spectral waveforms sampled at the level of the ankle in patients with diabetes.

METHODS

In two centres, 590 Doppler arterial spectral waveform images (PAD 369, no-PAD 221) from 305 patients were prospectively collected. Doppler arterial spectral waveform signals were reconstructed. Blinded full lower-limb reference duplex ultrasound results were used to label waveform according to PAD status (i.e., PAD, no-PAD). Statistical metrics and multiscale wavelet variance were extracted as discriminatory features. A long short-term memory (LSTM) network was used for the classification of raw signals, and logistic regression (LR) and support vector machines (SVM) were used for classification of extracted features. Signals and feature vectors were randomly divided into training (80%) and testing (20%) sets.

RESULTS

The highest overall accuracy was achieved using a logistic regression model with a combination of statistical and multiscale wavelet variance features, with 88% accuracy, 92% sensitivity, and 82% specificity. The area under the receiver operating characteristics curve (AUC) was 0.93.

CONCLUSION

We have constructed a machine learning algorithm with high discriminatory ability for the diagnosis of PAD using Doppler arterial spectral waveforms sampled at the ankle vessels.

Artificial intelligence for the evaluation of peripheral artery disease using arterial Doppler waveforms to predict abnormal ankle-brachial index

BACKGROUND

Patients with peripheral artery disease (PAD) are at increased risk for major adverse limb and cardiac events including mortality. Developing screening tools capable of accurate PAD identification is a necessary first step for strategies of adverse outcome prevention. This study aimed to determine whether machine analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with PAD.

METHODS

Consecutive patients (4/1/2015 - 12/31/2020) undergoing rest and postexercise ankle-brachial index (ABI) testing were included. Patients were randomly allocated to training, validation, and testing subsets (70%/15%/15%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict normal (> 0.9) or PAD (⩽ 0.9) using rest and postexercise ABI. A separate dataset of 151 patients who underwent testing during a period after the model had been created and validated (1/1/2021 - 3/31/2021) was used for secondary validation. Area under the receiver operating characteristic curves (AUC) were constructed to evaluate test performance.

RESULTS

Among 11,748 total patients, 3432 patients met study criteria: 1941 with PAD (mean age 69 ± 12 years) and 1491 without PAD (64 ± 14 years). The predictive model with highest performance identified PAD with an AUC 0.94 (CI = 0.92-0.96), sensitivity 0.83, specificity 0.88, accuracy 0.85, and positive predictive value (PPV) 0.90. Results were similar for the validation dataset: AUC 0.94 (CI = 0.91-0.98), sensitivity 0.91, specificity 0.85, accuracy 0.89, and PPV 0.89 (postexercise ABI comparison).

CONCLUSION

An artificial intelligence-enabled analysis of a resting Doppler arterial waveform permits identification of PAD at a clinically relevant performance level.

Novel Biomarkers of Atherosclerotic Vascular Disease-Latest Insights in the Research Field

The atherosclerotic vascular disease is a cardiovascular continuum in which the main role is attributed to atherosclerosis, from its appearance to its associated complications. The increasing prevalence of cardiovascular risk factors, population ageing, and burden on both the economy and the healthcare system have led to the development of new diagnostic and therapeutic strategies in the field. The better understanding or discovery of new pathophysiological mechanisms and molecules modulating various signaling pathways involved in atherosclerosis have led to the development of potential new biomarkers, with key role in early, subclinical diagnosis. The evolution of technological processes in medicine has shifted the attention of researchers from the profiling of classical risk factors to the identification of new biomarkers such as midregional pro-adrenomedullin, midkine, stromelysin-2, pentraxin 3, inflammasomes, or endothelial cell-derived extracellular vesicles. These molecules are seen as future therapeutic targets associated with decreased morbidity and mortality through early diagnosis of atherosclerotic lesions and future research directions.

A machine learning approach to predict progression on active surveillance for prostate cancer

PURPOSE

Robust prediction of progression on active surveillance (AS) for prostate cancer can allow for risk-adapted protocols. To date, models predicting progression on AS have invariably used traditional statistical approaches. We sought to evaluate whether a machine learning (ML) approach could improve prediction of progression on AS.

PATIENTS AND METHODS

We performed a retrospective cohort study of patients diagnosed with very-low or low-risk prostate cancer between 1997 and 2016 and managed with AS at our institution. In the training set, we trained a traditional logistic regression (T-LR) classifier, and alternate ML classifiers (support vector machine, random forest, a fully connected artificial neural network, and ML-LR) to predict grade-progression. We evaluated model performance in the test set. The primary performance metric was the F1 score.

RESULTS

Our cohort included 790 patients. With a median follow-up of 6.29 years, 234 developed grade-progression. In descending order, the F1 scores were: support vector machine 0.586 (95% CI 0.579 - 0.591), ML-LR 0.522 (95% CI 0.513 - 0.526), artificial neural network 0.392 (95% CI 0.379 - 0.396), random forest 0.376 (95% CI 0.364 - 0.380), and T-LR 0.182 (95% CI 0.151 - 0.185). All alternate ML models had a significantly higher F1 score than the T-LR model (all p <0.001).

CONCLUSION

In our study, ML methods significantly outperformed T-LR in predicting progression on AS for prostate cancer. While our specific models require further validation, we anticipate that a ML approach will help produce robust prediction models that will facilitate individualized risk-stratification in prostate cancer AS.

Applicability of the Vascular Quality Initiative (VQI) mortality prediction model for infrainguinal revascularization in a tertiary limb preservation center population

OBJECTIVE

Patients undergoing revascularization for chronic limb-threatening ischemia (CLTI) are at elevated risk for both mortality and limb loss. To facilitate therapeutic decision-making, a mortality prediction model derived from the Vascular Quality Initiative (VQI) database has stratified patients into low, medium, and high risk, defined by 30-day mortality estimated of ≤3%, 3-5%, or >5% and 2-year mortality estimates of ≤30%, 30-50%, or ≥50%, respectively. The purpose of this study was to compare expected mortality risk derived from this model with observed outcomes in a tertiary center.

METHODS

Consecutive patients treated at a single center between 2016 and 2019 were analyzed. Baseline demographics, approach, and mortality events were reviewed. Observed mortality was obtained using life-table methods and compared using a log-rank test with the expected mortality risk which was calculated using the VQI model.

RESULTS

This study cohort consisted of 195 revascularization procedures in 169 unique patients stratified into 128 (66%) low, 50 (26%) medium, and 17 (8%) high-risk cases based on the VQI model. 90% of revascularizations were performed for tissue loss. Compared with the VQI population, comorbidities were prevalent and included unstable angina or myocardial infarction within 6 months (6% vs. 2.4% in VQI; p<0.001), congestive heart failure (30% vs. 23%; p<0.001), and dialysis dependence (14% vs. 0.9%; p<0.001). Patients were also older (31% vs. 21% ≥80 years old; p<0.001) and more likely to be frail (45% vs. 64% independent; p<0.001). High-risk patients were more prevalent in the endovascular group (11% of 132 endovascular interventions vs. 3% of 63 bypasses; p=0.056). 30-day observed mortality exceeded expected VQI prediction model mortality in all groups, although was not statistically significant. The VQI model adequately stratified the studied population into risk groups (p<0.001). Low risk CLTI patients (65% of the overall cohort) experienced 2- year mortality of 18.9%. However, observed mortality for medium and high-risk VQI strata were similar. After a median follow-up of 28 months, medium-risk patients incurred a significantly higher mortality than predicted (53.5%±2.1% vs. 36.8%±1.1%; p=0.016).

CONCLUSIONS

The VQI mortality prediction model discriminates mortality risk after limb revascularization in CLTI, accurately identifying a majority subgroup of patients who are suitable for either open or endovascular intervention. However, it may underestimate mortality in a tertiary referral population with high comorbidity burden and was not well calibrated for the medium-risk group. It may be more appropriate to dichotomize CLTI patients who are candidates for limb salvage into an average risk and high-risk group.

Analyzing the Performance of Machine Learning Techniques in Disease Prediction

The history of data stored can be used to forecast potential patterns and help companies make competitive decisions to increase their success and benefits. Many analysts look at healthcare sector data to identify and forecast illnesses in order to benefit patients and physicians in a variety of ways. This study is concerned with the diagnosis and estimation of heart disease. Heart disease is one of the most dangerous illnesses for humans, leading to death all over the world. Many different groups of researchers have used knowledge exploration methods in diverse fields to forecast heart disease and have shown acceptable degrees of precision. There were no real-time methods for analyzing and forecasting heart disease in its early stages. For the prediction of heart disease, decision trees are used to analyze various training and evaluation datasets. Classification algorithms such as Naive Bayes, ID3, C4.5, and SVM are being investigated. The UCI machinery heart disease data set is used in experimental studies.

Artificial Intelligence and Cardiovascular Genetics

Polygenic diseases, which are genetic disorders caused by the combined action of multiple genes, pose unique and significant challenges for the diagnosis and management of affected patients. A major goal of cardiovascular medicine has been to understand how genetic variation leads to the clinical heterogeneity seen in polygenic cardiovascular diseases (CVDs). Recent advances and emerging technologies in artificial intelligence (AI), coupled with the ever-increasing availability of next generation sequencing (NGS) technologies, now provide researchers with unprecedented possibilities for dynamic and complex biological genomic analyses. Combining these technologies may lead to a deeper understanding of heterogeneous polygenic CVDs, better prognostic guidance, and, ultimately, greater personalized medicine. Advances will likely be achieved through increasingly frequent and robust genomic characterization of patients, as well the integration of genomic data with other clinical data, such as cardiac imaging, coronary angiography, and clinical biomarkers. This review discusses the current opportunities and limitations of genomics; provides a brief overview of AI; and identifies the current applications, limitations, and future directions of AI in genomics.

Prediction of 2-Year Major Adverse Limb Event-Free Survival After Percutaneous Transluminal Angioplasty and Stenting for Lower Limb Atherosclerosis Obliterans: A Machine Learning-Based Study

Background

The current scoring systems could not predict prognosis after endovascular therapy for peripheral artery disease. Machine learning could make predictions for future events by learning a specific pattern from existing data. This study aimed to demonstrate machine learning could make an accurate prediction for 2-year major adverse limb event-free survival (MFS) after percutaneous transluminal angioplasty (PTA) and stenting for lower limb atherosclerosis obliterans (ASO).

Methods

A lower limb ASO cohort of 392 patients who received PTA and stenting was split to the training set and test set by 4:1 in chronological order. Demographic, medical, and imaging data were used to build machine learning models to predict 2-year MFS. The discrimination and calibration of artificial neural network (ANN) and random forest models were compared with the logistic regression model, using the area under the receiver operating curve (ROCAUC) with DeLong test, and the calibration curve with Hosmer–Lemeshow goodness-of-fit test, respectively.

Results

The ANN model (ROCAUC = 0.80, 95% CI: 0.68–0.89) but not the random forest model (ROCAUC = 0.78, 95% CI: 0.66–0.87) significantly outperformed the logistic regression model (ROCAUC = 0.73, 95% CI: 0.60–0.83, P = 0.01 and P = 0.24). The ANN model the logistic regression model demonstrated good calibration performance (P = 0.73 and P = 0.28), while the random forest model showed poor calibration (P < 0.01). The calibration curve of the ANN model was visually the closest to the perfectly calibrated line.

Conclusion

Machine learning models could accurately predict 2-year MFS after PTA and stenting for lower limb ASO, in which the ANN model had better discrimination and calibration. Machine learning-derived prediction tools might be clinically useful to automatically identify candidates for PTA and stenting.

Machine learning in vascular surgery: a systematic review and critical appraisal

Machine learning (ML) is a rapidly advancing field with increasing utility in health care. We conducted a systematic review and critical appraisal of ML applications in vascular surgery. MEDLINE, Embase, and Cochrane CENTRAL were searched from inception to March 1, 2021. Study screening, data extraction, and quality assessment were performed by two independent reviewers, with a third author resolving discrepancies. All original studies reporting ML applications in vascular surgery were included. Publication trends, disease conditions, methodologies, and outcomes were summarized. Critical appraisal was conducted using the PROBAST risk-of-bias and TRIPOD reporting adherence tools. We included 212 studies from a pool of 2235 unique articles. ML techniques were used for diagnosis, prognosis, and image segmentation in carotid stenosis, aortic aneurysm/dissection, peripheral artery disease, diabetic foot ulcer, venous disease, and renal artery stenosis. The number of publications on ML in vascular surgery increased from 1 (1991-1996) to 118 (2016-2021). Most studies were retrospective and single center, with no randomized controlled trials. The median area under the receiver operating characteristic curve (AUROC) was 0.88 (range 0.61-1.00), with 79.5% [62/78] studies reporting AUROC ≥ 0.80. Out of 22 studies comparing ML techniques to existing prediction tools, clinicians, or traditional regression models, 20 performed better and 2 performed similarly. Overall, 94.8% (201/212) studies had high risk-of-bias and adherence to reporting standards was poor with a rate of 41.4%. Despite improvements over time, study quality and reporting remain inadequate. Future studies should consider standardized tools such as PROBAST and TRIPOD to improve study quality and clinical applicability.

Personalizing cholesterol treatment recommendations for primary cardiovascular disease prevention

Statin therapy is the cornerstone of preventing atherosclerotic cardiovascular disease (ASCVD), primarily by reducing low density lipoprotein cholesterol (LDL-C) levels. Optimal statin therapy decisions rely on shared decision making and may be uncertain for a given patient. In areas of clinical uncertainty, personalized approaches based on real-world data may help inform treatment decisions. We sought to develop a personalized statin recommendation approach for primary ASCVD prevention based on historical real-world outcomes in similar patients. Our retrospective cohort included adults from a large Northern California electronic health record (EHR) aged 40–79 years with no prior cardiovascular disease or statin use. The cohort was split into training and test sets. Weighted-K-nearest-neighbor (wKNN) regression models were used to identify historical EHR patients similar to a candidate patient. We modeled four statin decisions for each patient: none, low-intensity, moderate-intensity, and high-intensity. For each candidate patient, the algorithm recommended the statin decision that was associated with the greatest percentage reduction in LDL-C after 1 year in similar patients. The overall cohort consisted of 50,576 patients (age 54.6 ± 9.8 years) with 55% female, 48% non-Hispanic White, 32% Asian, and 7.4% Hispanic patients. Among 8383 test-set patients, 52%, 44%, and 4% were recommended high-, moderate-, and low-intensity statins, respectively, for a maximum predicted average 1-yr LDL-C reduction of 16.9%, 20.4%, and 14.9%, in each group, respectively. Overall, using aggregate EHR data, a personalized statin recommendation approach identified the statin intensity associated with the greatest LDL-C reduction in historical patients similar to a candidate patient. Recommendations included low- or moderate-intensity statins for maximum LDL-C lowering in nearly half the test set, which is discordant with their expected guideline-based efficacy. A data-driven personalized statin recommendation approach may inform shared decision making in areas of uncertainty, and highlight unexpected efficacy-effectiveness gaps.

Predicting survival after radical prostatectomy: Variation of machine learning performance by race

BACKGROUND

Robust prediction of survival can facilitate clinical decision-making and patient counselling. Non-Caucasian males are underrepresented in most prostate cancer databases. We evaluated the variation in performance of a machine learning (ML) algorithm trained to predict survival after radical prostatectomy in race subgroups.

METHODS

We used the National Cancer Database (NCDB) to identify patients undergoing radical prostatectomy between 2004 and 2016. We grouped patients by race into Caucasian, African-American, or non-Caucasian, non-African-American (NCNAA) subgroups. We trained an Extreme Gradient Boosting (XGBoost) classifier to predict 5-year survival in different training samples: naturally race-imbalanced, race-specific, and synthetically race-balanced. We evaluated performance in the test sets.

RESULTS

A total of 68,630 patients met inclusion criteria. Of these, 57,635 (84%) were Caucasian, 8173 (12%) were African-American, and 2822 (4%) were NCNAA. For the classifier trained in the naturally race-imbalanced sample, the F1 scores were 0.514 (95% confidence interval: 0.513-0.511), 0.511 (0.511-0.512), 0.545 (0.541-0.548), and 0.378 (0.378-0.389) in the race-imbalanced, Caucasian, African-American, and NCNAA test samples, respectively. For all race subgroups, the F1 scores of classifiers trained in the race-specific or synthetically race-balanced samples demonstrated similar performance compared to training in the naturally race-imbalanced sample.

CONCLUSIONS

A ML algorithm trained using NCDB data to predict survival after radical prostatectomy demonstrates variation in performance by race, regardless of whether the algorithm is trained in a naturally race-imbalanced, race-specific, or synthetically race-balanced sample. These results emphasize the importance of thoroughly evaluating ML algorithms in race subgroups before clinical deployment to avoid potential disparities in care.

Current applications of artificial intelligence in vascular surgery

Basic foundations of artificial intelligence (AI) include analyzing large amounts of data, recognizing patterns, and predicting outcomes. At the core of AI are well-defined areas, such as machine learning, natural language processing, artificial neural networks, and computer vision. Although research and development of AI in health care is being conducted in many medical subspecialties, only a few applications have been implemented in clinical practice. This is true in vascular surgery, where applications are mostly in the translational research stage. These AI applications are being evaluated in the realms of vascular diagnostics, perioperative medicine, risk stratification, and outcome prediction, among others. Apart from the technical challenges of AI and research outcomes on safe and beneficial use in patient care, ethical issues and policy surrounding AI will present future challenges for its successful implementation. This review will give a brief overview and a basic understanding of AI and summarize the currently available and used clinical AI applications in vascular surgery.

Heart rate n-variability (HRnV) measures for prediction of mortality in sepsis patients presenting at the emergency department

Sepsis is a potentially life-threatening condition that requires prompt recognition and treatment. Recently, heart rate variability (HRV), a measure of the cardiac autonomic regulation derived from short electrocardiogram tracings, has been found to correlate with sepsis mortality. This paper presents using novel heart rate n-variability (HRnV) measures for sepsis mortality risk prediction and comparing against current mortality prediction scores. This study was a retrospective cohort study on patients presenting to the emergency department of a tertiary hospital in Singapore between September 2014 to April 2017. Patients were included if they were above 21 years old and were suspected of having sepsis by their attending physician. The primary outcome was 30-day in-hospital mortality. Stepwise multivariable logistic regression model was built to predict the outcome, and the results based on 10-fold cross-validation were presented using receiver operating curve analysis. The final predictive model comprised 21 variables, including four vital signs, two HRV parameters, and 15 HRnV parameters. The area under the curve of the model was 0.77 (95% confidence interval 0.70–0.84), outperforming several established clinical scores. The HRnV measures may have the potential to allow for a rapid, objective, and accurate means of patient risk stratification for sepsis severity and mortality. Our exploration of the use of wealthy inherent information obtained from novel HRnV measures could also create a new perspective for data scientists to develop innovative approaches for ECG analysis and risk monitoring.

Use of Artificial Intelligence in Non-Oncologic Interventional Radiology: Current State and Future Directions

The future of radiology is disproportionately linked to the applications of artificial intelligence (AI). Recent exponential advancements in AI are already beginning to augment the clinical practice of radiology. Driven by a paucity of review articles in the area, this article aims to discuss applications of AI in non-oncologic IR across procedural planning, execution, and follow-up along with a discussion on the future directions of the field. Applications in vascular imaging, radiomics, touchless software interactions, robotics, natural language processing, post-procedural outcome prediction, device navigation, and image acquisition are included. Familiarity with AI study analysis will help open the current 'black box' of AI research and help bridge the gap between the research laboratory and clinical practice.

An integrated review on machine learning approaches for heart disease prediction: Direction towards future research gaps

Objectives

To make a clear literature review on state-of-the-art heart disease prediction models.

Methods

It reviews 61 research papers and states the significant analysis. Initially, the analysis addresses the contributions of each literature works and observes the simulation environment. Here, different types of machine learning algorithms deployed in each contribution. In addition, the utilized dataset for existing heart disease prediction models was observed.

Results

The performance measures computed in entire papers like prediction accuracy, prediction error, specificity, sensitivity, f-measure, etc., are learned. Further, the best performance is also checked to confirm the effectiveness of entire contributions.

Conclusions

The comprehensive research challenges and the gap are portrayed based on the development of intelligent methods concerning the unresolved challenges in heart disease prediction using data mining techniques.

Bench-to-Bedside in Vascular Medicine: Optimizing the Translational Pipeline for Patients With Peripheral Artery Disease

Peripheral arterial disease is a growing worldwide problem with a wide spectrum of clinical severity and is projected to consume >$21 billion per year in the United States alone. While vascular researchers have brought several therapies to the clinic in recent years, few of these approaches have leveraged advances in high-throughput discovery screens, novel translational models, or innovative trial designs. In the following review, we discuss recent advances in unbiased genomics and broader omics technology platforms, along with preclinical vascular models designed to enhance our understanding of disease pathobiology and prioritize targets for additional investigation. Furthermore, we summarize novel approaches to clinical studies in subjects with claudication and ischemic ulceration, with an emphasis on streamlining and accelerating bench-to-bedside translation. By providing a framework designed to enhance each aspect of future clinical development programs, we hope to enrich the pipeline of therapies that may prevent loss of life and limb for those with peripheral arterial disease.

Leveraging Machine Learning and Artificial Intelligence to Improve Peripheral Artery Disease Detection, Treatment, and Outcomes

Peripheral artery disease is an atherosclerotic disorder which, when present, portends poor patient outcomes. Low diagnosis rates perpetuate poor management, leading to limb loss and excess rates of cardiovascular morbidity and death. Machine learning algorithms and artificially intelligent systems have shown great promise in application to many areas in health care, such as accurately detecting disease, predicting patient outcomes, and automating image interpretation. Although the application of these technologies to peripheral artery disease are in their infancy, their promises are tremendous. In this review, we provide an introduction to important concepts in the fields of machine learning and artificial intelligence, detail the current state of how these technologies have been applied to peripheral artery disease, and discuss potential areas for future care enhancement with advanced analytics.

Cardiovascular Disease Prediction by Machine Learning Algorithms Based on Cytokines in Kazakhs of China

Background

Cardiovascular disease (CVD) is the leading cause of mortality worldwide. Accurately identifying subjects at high-risk of CVD may improve CVD outcomes. We sought to systematically examine the feasibility and performance of 7 widely used machine learning (ML) algorithms in predicting CVD risks.

Methods

The final analysis included 1508 Kazakh subjects in China without CVD at baseline who completed follow-up. All subjects were randomly divided into the training set (80%) and the test set (20%). L1-penalized logistic regression (LR), support vector machine with radial basis function (SVM), decision tree (DT), random forest (RF), k-nearest neighbors (KNN), Gaussian naive Bayes (NB), and extreme gradient boosting (XGB) were employed for prediction CVD outcomes. Ten-fold cross-validation was used during model developing and hyperparameters tuning in the training set. Model performance was evaluated in the test set in light of discrimination, calibration, and clinical usefulness. RF was applied to obtain the variable importance of included variables. Twenty-two variables, including sociodemographic characteristics, medical history, cytokines, and synthetic indices, were used for model development.

Results

Among 1508 subjects, 203 were diagnosed with CVD over a median follow-up of 5.17 years. All 7 models had moderate to excellent discrimination (AUC ranged from 0.770 to 0.872) and were well calibrated. LR and SVM performed identically with an AUC of 0.872 (95% CI: 0.829–0.907) and 0.868 (95% CI: 0.825–0.904), respectively. LR had the lowest Brier score (0.078) and the highest sensitivity (97.1%). Decision curve analysis indicated that SVM was slightly better than LR. The inflammatory cytokines, such as hs-CRP and IL-6, were identified as strong predictors of CVD.

Conclusion

SVM and LR can be applied to guide clinical decision-making in the Kazakh Chinese population, and further study is required to ensure their accuracies.

Development and head-to-head comparison of machine-learning models to identify patients requiring prostate biopsy

Background

Machine learning has many attractive theoretic properties, specifically, the ability to handle non predefined relations. Additionally, studies have validated the clinical utility of mpMRI for the detection and localization of CSPCa (Gleason score ≥ 3 + 4). In this study, we sought to develop and compare machine-learning models incorporating mpMRI parameters with traditional logistic regression analysis for prediction of PCa (Gleason score ≥ 3 + 3) and CSPCa on initial biopsy.

Methods

A total of 688 patients with no prior prostate cancer diagnosis and tPSA ≤ 50 ng/ml, who underwent mpMRI and prostate biopsy were included between 2016 and 2020. We used four supervised machine-learning algorithms in a hypothesis-free manner to build models to predict PCa and CSPCa. The machine-learning models were compared to the logistic regression analysis using AUC, calibration plot, and decision curve analysis.

Results

The artificial neural network (ANN), support vector machine (SVM), and random forest (RF) yielded similar diagnostic accuracy with logistic regression, while classification and regression tree (CART, AUC = 0.834 and 0.867) had significantly lower diagnostic accuracy than logistic regression (AUC = 0.894 and 0.917) in prediction of PCa and CSPCa (all P < 0.05). However, the CART illustrated best calibration for PCa (SSR = 0.027) and CSPCa (SSR = 0.033). The ANN, SVM, RF, and LR for PCa had higher net benefit than CART across the threshold probabilities above 5%, and the five models for CSPCa displayed similar net benefit across the threshold probabilities below 40%. The RF (53% and 57%, respectively) and SVM (52% and 55%, respectively) for PCa and CSPCa spared more unnecessary biopsies than logistic regression (35% and 47%, respectively) at 95% sensitivity for detection of CSPCa.

Conclusion

Machine-learning models (SVM and RF) yielded similar diagnostic accuracy and net benefit, while spared more biopsies at 95% sensitivity for detection of CSPCa, compared with logistic regression. However, no method achieved desired performance. All methods should continue to be explored and used in complementary ways.