An Artificial Neural Network Stratifies the Risks of Reintervention and Mortality after Endovascular Aneurysm Repair; a Retrospective Observational study

Artificial Intelligence in Vascular Diseases: From Clinical Practice to Medical Research and Education

Artificial Intelligence (AI) has brought new opportunities in medicine, with a great potential to improve care provided to patients. Given the technical complexity and continuously evolving field, it can be challenging for vascular specialists to anticipate and foresee how AI will shape their practice. The aim of this review is to provide an overview of the current landscape of applications of AI in clinical practice for the management of non-cardiac vascular diseases including aortic aneurysm, peripheral artery disease, carotid stenosis, and venous diseases. The review describes and highlights how AI has the potential to shape the three pillars in the management of vascular diseases including clinical practice, medical research and education. In the limelight of these results, we show how AI should be considered and developed within a responsible ecosystem favoring transdisciplinary collaboration, where multiple stake holders can work together to face current challenges and move forward future directions.

Atherosclerotic Abdominal Aortic Aneurysms on Computed Tomography Angiography: A Narrative Review on Spectrum of Findings, Structured Reporting, Treatment, Secondary Complications and Differential Diagnosis

Atherosclerotic abdominal aortic aneurysms (AAAs) are a common vascular pathology with significant morbidity and mortality risks. Timely diagnosis, accurate characterization, and standardized reporting are critical for effective management and monitoring of atherosclerotic AAAs. Imaging modalities, particularly computed tomography angiography (CTA), play a pivotal role in the detection, treatment planning, and identification of both primary and secondary complications, as well as distinguishing AAAs from other etiologies. This narrative review provides a comprehensive exploration of the spectrum of imaging findings in atherosclerotic AAAs on CTA, underscoring the importance of structured reporting. Additionally, it examines therapeutic approaches and complications, and it differentiates AAAs from inflammatory, mycotic, and traumatic variants, serving as a primer for radiologists in AAA evaluation.

The Expansion of Artificial Intelligence in Modifying and Enhancing the Current Management of Abdominal Aortic Aneurysms: A Literature Review

An abdominal aortic aneurysm (AAA) is a pathological dilation that is 3 cm or greater resulting in a bulging or balloon appearance. To meet a personalized therapeutic approach for patients, artificial intelligence (AI) can exhibit an array of applications ranging from decoding patterns from large data sets to predicting new data. The review aims to discuss how AI can assist and improve the standard of care and management plans for these patients. A comprehensive non-systematic literature review was carried out for published material on the use of AI relating to AAAs. The PubMed and Google Scholar databases were used to scout for articles relating to the title of this review. The review included 54 literature papers in this study. AI is involved on a genomic level, which assists in screening, diagnosing, and identifying individual risk factors of a patient. Personalized management plans can be created with AI predictions using patient data to reduce the risk of in-hospital mortality following a repair or due to complications. AI represents a promising group of programs aimed at improving patient management and assisting surgeons in making beneficial decisions to improve the patient's prognosis.

Machine learning-based prediction of abdominal aortic aneurysms for individualized patient care

OBJECTIVE

The United States Preventative Services Task Force guidelines for screening for abdominal aortic aneurysms (AAA) are broad and exclude many at risk groups. We analyzed a large AAA screening database to examine the utility of a novel machine learning (ML) model for predicting individual risk of AAA.

METHODS

We created a ML model to predict the presence of AAAs (>3 cm) from the database of a national nonprofit screening organization (AAAneurysm Outreach). Participants self-reported demographics and comorbidities. The model is a two-layered feed-forward shallow network. The ML model then generated AAA probability based on patient characteristics. We evaluated graphs to determine significant factors, and then compared those graphs with a traditional logistic regression model.

RESULTS

We analyzed a cohort of 10,033 patients with an AAA prevalence of 2.74%. Consistent with logistic regression analysis, the ML model identified the following predictors of AAA: Caucasian race, male gender, advancing age, and recent or past smoker with recent smoker having a more profound affect (P < .05). Interestingly, the ML model showed body mass index (BMI) was associated with likelihood of AAAs, especially for younger females. The ML model also identified a higher than predicted risk of AAA in several groups, including female nonsmokers with cardiac disease, female diabetics, those with a family history of AAA, and those with hypertension or hyperlipidemia at older ages. An elevated BMI conveyed a higher than expected risk in male smokers and all females. The ML model also identified a complex relationship of both diabetes mellitus and hyperlipidemia with gender. Family history of AAA was a more important risk factor in the ML model for both men and women too.

CONCLUSIONS

We successfully developed an ML model based on an AAA screening database that unveils a complex relationship between AAA prevalence and many risk factors, including BMI. The model also highlights the need to expand AAA screening efforts in women. Using ML models in the clinical setting has the potential to deliver precise, individualized screening recommendations.

Computational prediction of proximal sealing in endovascular abdominal aortic aneurysm repair with unfavorable necks

BACKGROUND AND OBJECTIVE

Endovascular aortic aneurysm repair (EVAR) has become the standard treatment for abdominal aortic aneurysms in most centers. However, proximal sealing complications leading to endoleaks and migrations sometimes occur, particularly in unfavorable aortic anatomies and are strongly dependent on biomechanical interactions between the aortic wall and the endograft. The objective of the present work is to develop and validate a computational patient-specific model that can accurately predict these complications.

METHODS

Based on pre-operative CT-scans, we developed finite element models of the aorta of 10 patients who underwent endovascular aortic aneurysm repair, 7 with standard morphologies and 3 with unfavorable anatomies. We simulated the deployment of stent grafts in each aorta by solving mechanical equilibrium with a virtual shell method. Eventually we compared the actual stent ring positions from post-operative computed-tomography-scans with the predicted simulated positions.

RESULTS

A successful deployment simulation could be performed for each patient. Relative radial, transverse and longitudinal deviations were 6.3 ± 4.4%, 2.5 ± 0.9 mm and 1.4 ± 1.1 mm, respectively.

CONCLUSIONS

The numerical model predicted accurately stent-graft positions in the aortic neck of 10 patients, even in complex anatomies. This shows the potential of computer simulation to anticipate possible proximal endoleak complications before EVAR interventions.

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.

Future of Artificial Intelligence in Surgery: A Narrative Review

Artificial intelligence (AI) is the capability of a machine to execute cognitive processes that are typically considered to be functions of the human brain. It is the study of algorithms that enable machines to reason and perform mental tasks, including problem-solving, object and word recognition, and decision-making. Once considered science fiction, AI today is a fact and an increasingly prevalent subject in both academic and popular literature. It is expected to reshape medicine, benefiting both healthcare professionals and patients. Machine learning (ML) is a subset of AI that allows machines to learn and make predictions by recognizing patterns, thus empowering the medical team to deliver better care to patients through accurate diagnosis and treatment. ML is expanding its footprint in a variety of surgical specialties, including general surgery, ophthalmology, cardiothoracic surgery, and vascular surgery, to name a few. In recent years, we have seen AI make its way into the operating theatres. Though it has not yet been able to replace the surgeon, it has the potential to become a highly valuable surgical tool. Rest assured that the day is not far off when AI shall play a significant intraoperative role, a projection that is currently marred by safety concerns. This review aims to explore the present application of AI in various surgical disciplines and how it benefits both patients and physicians, as well as the current obstacles and limitations facing its seemingly unstoppable rise.

Artificial intelligence for the vascular surgeon

In recent years, artificial intelligence (AI) has permeated different aspects of vascular surgery to solve challenges in clinical practice. Although AI in vascular surgery is still in its early stages, there have been promising developments in its applications to vascular diagnosis, risk stratification, and outcome prediction. By establishing a baseline knowledge of AI, vascular surgeons are better equipped to use and interpret the data from these types of projects. This review aims to provide an overview of the fundamentals of AI and highlight its role in helping vascular surgeons overcome the challenges of clinical practice. In addition, we discuss the limitations of AI and how they affect AI applications.

A radiomics model for predicting the outcome of endovascular abdominal aortic aneurysm repair based on machine learning

OBJECTIVE

This study aimed to develop a radiomics model to predict the outcome of endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA), based on machine learning (ML) algorithms.

METHODS

We retrospectively reviewed 711 patients with infra-renal AAA who underwent elective EVAR procedures between January 2016 and December 2019 at our single center. The radiomics features of AAA were extracted using Pyradiomics. Pearson correlation analysis, analysis of variance (ANOVA), least absolute shrinkage, and selection operator (LASSO) regression were applied to determine the predictors for EVAR-related severe adverse events (SAEs). Eighty percent of patients were classified as the training set and the remaining 20 percent of patients were classified as the test set. The selected features were used to build a radiomics model in training set using different ML algorithms. The performance of each model was assessed using the area under the curve (AUC) from the receiver operating characteristic (ROC) curve in the test set.

RESULTS

A total of 493 patients were enrolled in this study, the mean follow-up time was 32 months. During the follow-up, 156 (31.6%) patients experienced EVAR-related SAEs. A total of 1223 radiomics features were extracted from each patient, of which 30 radiomics features were finally identified. The quantitative performance assessment and the ROC curves indicated that the logistics regression (LR) model had better predictive value than others, with accuracy, 0.86; AUC, 0.93; and F1 score, 0.91. The Rad-score waterfall plot showed that the overall amount of error was small both in the training set and in the test set. Calibration curve showed that the calibration degree of the training set and the test set were good (p > 0.05). Decision curve analysis (threshold 0.32) demonstrated that the model had good clinical applicability.

CONCLUSION

Our radiomics model could be used as an efficient and adjunctive tool to predict the outcome after EVAR.

Machine learning model predicts the occurrence of acute kidney injury after open surgery for abdominal aortic aneurysm repair

OBJECTIVES

Abdominal aortic aneurysm is a pathological condition in which the abdominal aorta is dilated beyond 3.0 cm. The surgical options include open surgical repair (OSR) and endovascular aneurysm repair (EVAR). Prediction of acute kidney injury (AKI) after OSR is helpful for decision-making during the postoperative phase. To find a more efficient method for making a prediction, this study aims to perform tests on the efficacy of different machine learning models.

METHODS

Perioperative data of 80 OSR patients were retrospectively collected from January 2009 to December 2021 at Xiangya Hospital, Central South University. The vascular surgeon performed the surgical operation. Four commonly used machine learning classification models (logistic regression, linear kernel support vector machine, Gaussian kernel support vector machine, and random forest) were chosen to predict AKI. The efficacy of the models was validated by five-fold cross-validation.

RESULTS

AKI was identified in 33 patients. Five-fold cross-validation showed that among the 4 classification models, random forest was the most precise model for predicting AKI, with an area under the curve of 0.90±0.12.

CONCLUSIONS

Machine learning models can precisely predict AKI during early stages after surgery, which allows vascular surgeons to address complications earlier and may help improve the clinical outcomes of OSR.

RADIC:A tool for diagnosing COVID-19 from chest CT and X-ray scans using deep learning and quad-radiomics

Deep learning (DL) algorithms have demonstrated a high ability to perform speedy and accurate COVID-19 diagnosis utilizing computed tomography (CT) and X-Ray scans. The spatial information in these images was used to train DL models in the majority of relevant studies. However, training these models with images generated by radiomics approaches could enhance diagnostic accuracy. Furthermore, combining information from several radiomics approaches with time-frequency representations of the COVID-19 patterns can increase performance even further. This study introduces "RADIC", an automated tool that uses three DL models that are trained using radiomics-generated images to detect COVID-19. First, four radiomics approaches are used to analyze the original CT and X-ray images. Next, each of the three DL models is trained on a different set of radiomics, X-ray, and CT images. Then, for each DL model, deep features are obtained, and their dimensions are decreased using the Fast Walsh Hadamard Transform, yielding a time-frequency representation of the COVID-19 patterns. The tool then uses the discrete cosine transform to combine these deep features. Four classification models are then used to achieve classification. In order to validate the performance of RADIC, two benchmark datasets (CT and X-Ray) for COVID-19 are employed. The final accuracy attained using RADIC is 99.4% and 99% for the first and second datasets respectively. To prove the competing ability of RADIC, its performance is compared with related studies in the literature. The results reflect that RADIC achieve superior performance compared to other studies. The results of the proposed tool prove that a DL model can be trained more effectively with images generated by radiomics techniques than the original X-Ray and CT images. Besides, the incorporation of deep features extracted from DL models trained with multiple radiomics approaches will improve diagnostic accuracy.

A Framework for Lung and Colon Cancer Diagnosis via Lightweight Deep Learning Models and Transformation Methods

Among the leading causes of mortality and morbidity in people are lung and colon cancers. They may develop concurrently in organs and negatively impact human life. If cancer is not diagnosed in its early stages, there is a great likelihood that it will spread to the two organs. The histopathological detection of such malignancies is one of the most crucial components of effective treatment. Although the process is lengthy and complex, deep learning (DL) techniques have made it feasible to complete it more quickly and accurately, enabling researchers to study a lot more patients in a short time period and for a lot less cost. Earlier studies relied on DL models that require great computational ability and resources. Most of them depended on individual DL models to extract features of high dimension or to perform diagnoses. However, in this study, a framework based on multiple lightweight DL models is proposed for the early detection of lung and colon cancers. The framework utilizes several transformation methods that perform feature reduction and provide a better representation of the data. In this context, histopathology scans are fed into the ShuffleNet, MobileNet, and SqueezeNet models. The number of deep features acquired from these models is subsequently reduced using principal component analysis (PCA) and fast Walsh-Hadamard transform (FHWT) techniques. Following that, discrete wavelet transform (DWT) is used to fuse the FWHT's reduced features obtained from the three DL models. Additionally, the three DL models' PCA features are concatenated. Finally, the diminished features as a result of PCA and FHWT-DWT reduction and fusion processes are fed to four distinct machine learning algorithms, reaching the highest accuracy of 99.6%. The results obtained using the proposed framework based on lightweight DL models show that it can distinguish lung and colon cancer variants with a lower number of features and less computational complexity compared to existing methods. They also prove that utilizing transformation methods to reduce features can offer a superior interpretation of the data, thus improving the diagnosis procedure.

A wavelet-based deep learning pipeline for efficient COVID-19 diagnosis via CT slices

The quick diagnosis of the novel coronavirus (COVID-19) disease is vital to prevent its propagation and improve therapeutic outcomes. Computed tomography (CT) is believed to be an effective tool for diagnosing COVID-19, however, the CT scan contains hundreds of slices that are complex to be analyzed and could cause delays in diagnosis. Artificial intelligence (AI) especially deep learning (DL), could facilitate and speed up COVID-19 diagnosis from such scans. Several studies employed DL approaches based on 2D CT images from a single view, nevertheless, 3D multiview CT slices demonstrated an excellent ability to enhance the efficiency of COVID-19 diagnosis. The majority of DL-based studies utilized the spatial information of the original CT images to train their models, though, using spectral–temporal information could improve the detection of COVID-19. This article proposes a DL-based pipeline called CoviWavNet for the automatic diagnosis of COVID-19. CoviWavNet uses a 3D multiview dataset called OMNIAHCOV. Initially, it analyzes the CT slices using multilevel discrete wavelet decomposition (DWT) and then uses the heatmaps of the approximation levels to train three ResNet CNN models. These ResNets use the spectral–temporal information of such images to perform classification. Subsequently, it investigates whether the combination of spatial information with spectral–temporal information could improve the diagnostic accuracy of COVID-19. For this purpose, it extracts deep spectral–temporal features from such ResNets using transfer learning and integrates them with deep spatial features extracted from the same ResNets trained with the original CT slices. Then, it utilizes a feature selection step to reduce the dimension of such integrated features and use them as inputs to three support vector machine (SVM) classifiers. To further validate the performance of CoviWavNet, a publicly available benchmark dataset called SARS-COV-2-CT-Scan is employed. The results of CoviWavNet have demonstrated that using the spectral–temporal information of the DWT heatmap images to train the ResNets is superior to utilizing the spatial information of the original CT images. Furthermore, integrating deep spectral–temporal features with deep spatial features has enhanced the classification accuracy of the three SVM classifiers reaching a final accuracy of 99.33% and 99.7% for the OMNIAHCOV and SARS-COV-2-CT-Scan datasets respectively. These accuracies verify the outstanding performance of CoviWavNet compared to other related studies. Thus, CoviWavNet can help radiologists in the rapid and accurate diagnosis of COVID-19 diagnosis.

Fully automatic volume segmentation using deep learning approaches to assess aneurysmal sac evolution after infra-renal endovascular aortic repair

OBJECTIVE

Endovascular aortic repair (EVAR) surveillance relies on serial measurements of maximal diameter despite significant inter- and intra-observer variability. Volumetric measurements are more sensitive but general use is hampered by the time required for their implementation. An innovative fully automated software (PRAEVAorta® from Nurea), using artificial intelligence (AI), previously demonstrated fast and robust detection of infra-renal abdominal aortic aneurysm's (AAA) characteristics on pre-operative imaging. This study aimed to assess the robustness of these data on post-EVAR computed tomography (CT) scans.

METHODS

Comparison was made between fully automatic and semi-automatic segmentation manually corrected by a senior surgeon on a dataset of 48 patients (48 early post-EVAR CT scans with 6466 slices, and a total of 101 follow-up CT scans with 13708 slices).

RESULTS

The analyses confirmed an excellent correlation of post-EVAR volumes and surfaces, as well as, proximal neck and maximum aneurysm diameters measured with the fully automatic and manually corrected segmentation methods (Pearson's coefficient correlation >.99, p<.0001). Comparison between the fully automatic and manually corrected segmentation method revealed a mean Dice Similarity Coefficient of 0.950±0.015, Jaccard index of 0.906±0.028, Sensitivity of 0.929±0.028, Specificity of 0.965±0.016, Volumetric Similarity (VS) of 0.973±0.018 and mean Hausdorff Distance/slice of 8.7±10.8mm. The mean VS reached 0.873±0.100 for the lumen and 0.903±0.091 for the thrombus. The segmentation time was 9 times faster with the fully automatic method (2.5 vs 22 min/patient with the manually corrected method; p<.0001). Preliminary analysis also demonstrated that a diameter increase of 2mm can actually represent >5% volume increase.

CONCLUSION

PRAEVAorta® enables a fast, reproducible, and fully automated analysis of post-EVAR AAA sac and neck characteristics, with comparison between different time points. It could become a crucial adjunct for EVAR follow-up through early detection of sac evolution, which may reduce the risk of secondary rupture.

An Intelligent ECG-Based Tool for Diagnosing COVID-19 via Ensemble Deep Learning Techniques

Diagnosing COVID-19 accurately and rapidly is vital to control its quick spread, lessen lockdown restrictions, and decrease the workload on healthcare structures. The present tools to detect COVID-19 experience numerous shortcomings. Therefore, novel diagnostic tools are to be examined to enhance diagnostic accuracy and avoid the limitations of these tools. Earlier studies indicated multiple structures of cardiovascular alterations in COVID-19 cases which motivated the realization of using ECG data as a tool for diagnosing the novel coronavirus. This study introduced a novel automated diagnostic tool based on ECG data to diagnose COVID-19. The introduced tool utilizes ten deep learning (DL) models of various architectures. It obtains significant features from the last fully connected layer of each DL model and then combines them. Afterward, the tool presents a hybrid feature selection based on the chi-square test and sequential search to select significant features. Finally, it employs several machine learning classifiers to perform two classification levels. A binary level to differentiate between normal and COVID-19 cases, and a multiclass to discriminate COVID-19 cases from normal and other cardiac complications. The proposed tool reached an accuracy of 98.2% and 91.6% for binary and multiclass levels, respectively. This performance indicates that the ECG could be used as an alternative means of diagnosis of COVID-19.

Development and Comparison of Multimodal Models for Preoperative Prediction of Outcomes After Endovascular Aneurysm Repair

Objective

The aim of this study was to develop and compare multimodal models for predicting outcomes after endovascular abdominal aortic aneurysm repair (EVAR) based on morphological, deep learning (DL), and radiomic features.

Methods

We retrospectively reviewed 979 patients (January 2010—December 2019) with infrarenal abdominal aortic aneurysms (AAAs) who underwent elective EVAR procedures. A total of 486 patients (January 2010–December 2015) were used for morphological feature model development and optimization. Univariable and multivariable analyses were conducted to determine significant morphological features of EVAR-related severe adverse events (SAEs) and to build a morphological feature model based on different machine learning algorithms. Subsequently, to develop the morphological feature model more easily and better compare with other modal models, 340 patients of AAA with intraluminal thrombosis (ILT) were used for automatic segmentation of ILT based on deep convolutional neural networks (DCNNs). Notably, 493 patients (January 2016–December 2019) were used for the development and comparison of multimodal models (optimized morphological feature, DL, and radiomic models). Of note, 80% of patients were classified as the training set and 20% of patients were classified as the test set. The area under the curve (AUC) was used to evaluate the predictive abilities of different modal models.

Results

The mean age of the patients was 69.9 years, the mean follow-up was 54 months, and 307 (31.4%) patients experienced SAEs. Statistical analysis revealed that short neck, angulated neck, conical neck, ILT, ILT percentage ≥51.6%, luminal calcification, double iliac sign, and common iliac artery index ≥1.255 were associated with SAEs. The morphological feature model based on the support vector machine had a better predictive performance with an AUC of 0.76, an accuracy of 0.76, and an F1 score of 0.82. Our DCNN model achieved a mean intersection over union score of more than 90.78% for the segmentation of ILT and AAA aortic lumen. The multimodal model result showed that the radiomic model based on logistics regression had better predictive performance (AUC 0.93, accuracy 0.86, and F1 score 0.91) than the optimized morphological feature model (AUC 0.62, accuracy 0.69, and F1 score 0.81) and the DL model (AUC 0.82, accuracy 0.85, and F1 score 0.89).

Conclusion

The radiomic model has better predictive performance for patient status after EVAR. The morphological feature model and DL model have their own advantages and could also be used to predict outcomes after EVAR.

ECG-BiCoNet: An ECG-based pipeline for COVID-19 diagnosis using Bi-Layers of deep features integration

The accurate and speedy detection of COVID-19 is essential to avert the fast propagation of the virus, alleviate lockdown constraints and diminish the burden on health organizations. Currently, the methods used to diagnose COVID-19 have several limitations, thus new techniques need to be investigated to improve the diagnosis and overcome these limitations. Taking into consideration the great benefits of electrocardiogram (ECG) applications, this paper proposes a new pipeline called ECG-BiCoNet to investigate the potential of using ECG data for diagnosing COVID-19. ECG-BiCoNet employs five deep learning models of distinct structural design. ECG-BiCoNet extracts two levels of features from two different layers of each deep learning technique. Features mined from higher layers are fused using discrete wavelet transform and then integrated with lower-layers features. Afterward, a feature selection approach is utilized. Finally, an ensemble classification system is built to merge predictions of three machine learning classifiers. ECG-BiCoNet accomplishes two classification categories, binary and multiclass. The results of ECG-BiCoNet present a promising COVID-19 performance with an accuracy of 98.8% and 91.73% for binary and multiclass classification categories. These results verify that ECG data may be used to diagnose COVID-19 which can help clinicians in the automatic diagnosis and overcome limitations of manual diagnosis.

A deep learning-based diagnostic tool for identifying various diseases via facial images

With the current health crisis caused by the COVID-19 pandemic, patients have become more anxious about infection, so they prefer not to have direct contact with doctors or clinicians. Lately, medical scientists have confirmed that several diseases exhibit corresponding specific features on the face the face. Recent studies have indicated that computer-aided facial diagnosis can be a promising tool for the automatic diagnosis and screening of diseases from facial images. However, few of these studies used deep learning (DL) techniques. Most of them focused on detecting a single disease, using handcrafted feature extraction methods and conventional machine learning techniques based on individual classifiers trained on small and private datasets using images taken from a controlled environment. This study proposes a novel computer-aided facial diagnosis system called FaceDisNet that uses a new public dataset based on images taken from an unconstrained environment and could be employed for forthcoming comparisons. It detects single and multiple diseases. FaceDisNet is constructed by integrating several spatial deep features from convolutional neural networks of various architectures. It does not depend only on spatial features but also extracts spatial-spectral features. FaceDisNet searches for the fused spatial-spectral feature set that has the greatest impact on the classification. It employs two feature selection techniques to reduce the large dimension of features resulting from feature fusion. Finally, it builds an ensemble classifier based on stacking to perform classification. The performance of FaceDisNet verifies its ability to diagnose single and multiple diseases. FaceDisNet achieved a maximum accuracy of 98.57% and 98% after the ensemble classification and feature selection steps for binary and multiclass classification categories. These results prove that FaceDisNet is a reliable tool and could be employed to avoid the difficulties and complications of manual diagnosis. Also, it can help physicians achieve accurate diagnoses without the need for physical contact with the patients.

DIAROP: Automated Deep Learning-Based Diagnostic Tool for Retinopathy of Prematurity

Retinopathy of Prematurity (ROP) affects preterm neonates and could cause blindness. Deep Learning (DL) can assist ophthalmologists in the diagnosis of ROP. This paper proposes an automated and reliable diagnostic tool based on DL techniques called DIAROP to support the ophthalmologic diagnosis of ROP. It extracts significant features by first obtaining spatial features from the four Convolution Neural Networks (CNNs) DL techniques using transfer learning and then applying Fast Walsh Hadamard Transform (FWHT) to integrate these features. Moreover, DIAROP explores the best-integrated features extracted from the CNNs that influence its diagnostic capability. The results of DIAROP indicate that DIAROP achieved an accuracy of 93.2% and an area under receiving operating characteristic curve (AUC) of 0.98. Furthermore, DIAROP performance is compared with recent ROP diagnostic tools. Its promising performance shows that DIAROP may assist the ophthalmologic diagnosis of ROP.

Intelligent Dermatologist Tool for Classifying Multiple Skin Cancer Subtypes by Incorporating Manifold Radiomics Features Categories

The rates of skin cancer (SC) are rising every year and becoming a critical health issue worldwide. SC's early and accurate diagnosis is the key procedure to reduce these rates and improve survivability. However, the manual diagnosis is exhausting, complicated, expensive, prone to diagnostic error, and highly dependent on the dermatologist's experience and abilities. Thus, there is a vital need to create automated dermatologist tools that are capable of accurately classifying SC subclasses. Recently, artificial intelligence (AI) techniques including machine learning (ML) and deep learning (DL) have verified the success of computer-assisted dermatologist tools in the automatic diagnosis and detection of SC diseases. Previous AI-based dermatologist tools are based on features which are either high-level features based on DL methods or low-level features based on handcrafted operations. Most of them were constructed for binary classification of SC. This study proposes an intelligent dermatologist tool to accurately diagnose multiple skin lesions automatically. This tool incorporates manifold radiomics features categories involving high-level features such as ResNet-50, DenseNet-201, and DarkNet-53 and low-level features including discrete wavelet transform (DWT) and local binary pattern (LBP). The results of the proposed intelligent tool prove that merging manifold features of different categories has a high influence on the classification accuracy. Moreover, these results are superior to those obtained by other related AI-based dermatologist tools. Therefore, the proposed intelligent tool can be used by dermatologists to help them in the accurate diagnosis of the SC subcategory. It can also overcome manual diagnosis limitations, reduce the rates of infection, and enhance survival rates.

Radiomics and machine learning to predict aggressive type 2 endoleaks after endovascular aneurysm repair: a proof of concept

BACKGROUND

Persistent type 2 endoleaks (T2EL) require lifelong surveillance to avoid potentially life-threatening complications.

PURPOSE

To evaluate the performance of radiomic features (RF) derived from computed tomography angiography (CTA), for differentiating aggressive from benign T2ELs after endovascular aneurysm repair (EVAR).

MATERIAL AND METHODS

A prospective study was performed on patients who underwent EVAR from January 2018 to January 2020. Analysis was performed in patients who were diagnosed with T2EL based on the CTA of the first postoperative month and were followed at six months and one year. Patients were divided into two groups according to the change of aneurysm sac dimensions. Segmentation of T2ELs was performed and RF were extracted. Feature selection for subsequent machine-learning analysis was evaluated by means of artificial intelligence. Two support vector machines (SVM) classifiers were developed to predict the aneurysm sac dimension changes at one year, utilizing RF from T2EL at one- and six-month CTA scans, respectively.

RESULTS

Among the 944 initial RF of T2EL, 58 and 51 robust RF from the one- and six-month CTA scans, respectively, were used for the machine-learning model development. The SVM classifier trained on one-month signatures was able to predict sac expansion at one year with an area under curve (AUC) of 89.3%, presenting 78.6% specificity and 100% sensitivity. Similarly, the SVM classifier developed with six-month radiomics data showed an AUC of 95.5%, specificity of 90.9%, and sensitivity of 100%.

CONCLUSION

Machine-learning algorithms utilizing CTA-derived RF may predict aggressive T2ELs leading to aneurysm sac expansion after EVAR.

Histo-CADx: duo cascaded fusion stages for breast cancer diagnosis from histopathological images

Breast cancer (BC) is one of the most common types of cancer that affects females worldwide. It may lead to irreversible complications and even death due to late diagnosis and treatment. The pathological analysis is considered the gold standard for BC detection, but it is a challenging task. Automatic diagnosis of BC could reduce death rates, by creating a computer aided diagnosis (CADx) system capable of accurately identifying BC at an early stage and decreasing the time consumed by pathologists during examinations. This paper proposes a novel CADx system named Histo-CADx for the automatic diagnosis of BC. Most related studies were based on individual deep learning methods. Also, studies did not examine the influence of fusing features from multiple CNNs and handcrafted features. In addition, related studies did not investigate the best combination of fused features that influence the performance of the CADx. Therefore, Histo-CADx is based on two stages of fusion. The first fusion stage involves the investigation of the impact of fusing several deep learning (DL) techniques with handcrafted feature extraction methods using the auto-encoder DL method. This stage also examines and searches for a suitable set of fused features that could improve the performance of Histo-CADx. The second fusion stage constructs a multiple classifier system (MCS) for fusing outputs from three classifiers, to further improve the accuracy of the proposed Histo-CADx. The performance of Histo-CADx is evaluated using two public datasets; specifically, the BreakHis and the ICIAR 2018 datasets. The results from the analysis of both datasets verified that the two fusion stages of Histo-CADx successfully improved the accuracy of the CADx compared to CADx constructed with individual features. Furthermore, using the auto-encoder for the fusion process has reduced the computation cost of the system. Moreover, the results after the two fusion stages confirmed that Histo-CADx is reliable and has the capacity of classifying BC more accurately compared to other latest studies. Consequently, it can be used by pathologists to help them in the accurate diagnosis of BC. In addition, it can decrease the time and effort needed by medical experts during the examination.

FUSI-CAD: Coronavirus (COVID-19) diagnosis based on the fusion of CNNs and handcrafted features

The precise and rapid diagnosis of coronavirus (COVID-19) at the very primary stage helps doctors to manage patients in high workload conditions. In addition, it prevents the spread of this pandemic virus. Computer-aided diagnosis (CAD) based on artificial intelligence (AI) techniques can be used to distinguish between COVID-19 and non-COVID-19 from the computed tomography (CT) imaging. Furthermore, the CAD systems are capable of delivering an accurate faster COVID-19 diagnosis, which consequently saves time for the disease control and provides an efficient diagnosis compared to laboratory tests. In this study, a novel CAD system called FUSI-CAD based on AI techniques is proposed. Almost all the methods in the literature are based on individual convolutional neural networks (CNN). Consequently, the FUSI-CAD system is based on the fusion of multiple different CNN architectures with three handcrafted features including statistical features and textural analysis features such as discrete wavelet transform (DWT), and the grey level co-occurrence matrix (GLCM) which were not previously utilized in coronavirus diagnosis. The SARS-CoV-2 CT-scan dataset is used to test the performance of the proposed FUSI-CAD. The results show that the proposed system could accurately differentiate between COVID-19 and non-COVID-19 images, as the accuracy achieved is 99%. Additionally, the system proved to be reliable as well. This is because the sensitivity, specificity, and precision attained to 99%. In addition, the diagnostics odds ratio (DOR) is ≥ 100. Furthermore, the results are compared with recent related studies based on the same dataset. The comparison verifies the competence of the proposed FUSI-CAD over the other related CAD systems. Thus, the novel FUSI-CAD system can be employed in real diagnostic scenarios for achieving accurate testing for COVID-19 and avoiding human misdiagnosis that might exist due to human fatigue. It can also reduce the time and exertion made by the radiologists during the examination process.

Prediction, pattern recognition and modelling of complications post-endovascular infra renal aneurysm repair by artificial intelligence

OBJECTIVES

The study evaluates the plausibility and applicability of prediction, pattern recognition and modelling of complications post-endovascular aneurysm repair (EVAR) by artificial intelligence for more accurate surveillance in practice.

METHODS

A single-centre prospective data collection on (n = 250) EVAR cases with n = 26 preoperative attributes (factors) on endpoint of endoleak (types I-VI), occlusion, migration and mortality over a 13-year period was conducted. In addition to the traditional statistical analysis, data was subjected to machine learning algorithm through artificial neural network. The predictive accuracy (specificity and -1 sensitivity) on each endpoint is presented with percentage and receiver operative curve. The pattern recognition and model classification were conducted using discriminate analysis, decision tree, logistic regression, naive Bayes and support vector machines, and the best fit model was deployed for pattern recognition and modelling.

RESULTS

The accuracy of the training, validation and predictive ability of artificial neural network in detection of endoleak type I was 95, 96 and 94%, type II (94, 83, 90 and 82%) and type III was 96, 94 and 96%, respectively. Endpoints are associated with increase in weights through predictive modeling that were not detected through statistical analytics. The overall accuracy of the model was >86%.

CONCLUSION

The study highlights the applicability, accuracy and reliability of artificial intelligence in the detection of adverse outcomes post-EVAR for an accurate surveillance stratification.

Artificial intelligence in abdominal aortic aneurysm

OBJECTIVE

Abdominal aortic aneurysm (AAA) is a life-threatening disease, and the only curative treatment relies on open or endovascular repair. The decision to treat relies on the evaluation of the risk of AAA growth and rupture, which can be difficult to assess in practice. Artificial intelligence (AI) has revealed new insights into the management of cardiovascular diseases, but its application in AAA has so far been poorly described. The aim of this review was to summarize the current knowledge on the potential applications of AI in patients with AAA.

METHODS

A comprehensive literature review was performed. The MEDLINE database was searched according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. The search strategy used a combination of keywords and included studies using AI in patients with AAA published between May 2019 and January 2000. Two authors independently screened titles and abstracts and performed data extraction. The search of published literature identified 34 studies with distinct methodologies, aims, and study designs.

RESULTS

AI was used in patients with AAA to improve image segmentation and for quantitative analysis and characterization of AAA morphology, geometry, and fluid dynamics. AI allowed computation of large data sets to identify patterns that may be predictive of AAA growth and rupture. Several predictive and prognostic programs were also developed to assess patients' postoperative outcomes, including mortality and complications after endovascular aneurysm repair.

CONCLUSIONS

AI represents a useful tool in the interpretation and analysis of AAA imaging by enabling automatic quantitative measurements and morphologic characterization. It could be used to help surgeons in preoperative planning. AI-driven data management may lead to the development of computational programs for the prediction of AAA evolution and risk of rupture as well as postoperative outcomes. AI could also be used to better evaluate the indications and types of surgical treatment and to plan the postoperative follow-up. AI represents an attractive tool for decision-making and may facilitate development of personalized therapeutic approaches for patients with AAA.

A machine leaning approach for abdominal aortic aneurysm severity assessment using geometric, biomechanical, and patient-specific historical clinical features

Recent studies monitoring severity of abdominal aortic aneurysm (AAA) suggested that reliance on only the maximum transverse diameter ( D _max ) may be insufficient to predict AAA rupture risk. Moreover, geometric indices, biomechanical parameters, material properties, and patient-specific historical data affect AAA morphology, indicating the need for an integrative approach that incorporates all factors for more accurate estimation of AAA severity. We implemented a machine learning algorithm using 45 features extracted from 66 patients. The model was generated using the J48 decision tree algorithm with the aim of maximizing model accuracy. Three different feature sets were used to assess the prediction rate: i) using D _max as a single-feature set, ii) using a set of all features, and, lastly iii) using a feature set selected via the BestFirst feature selection algorithm. Our results indicate that BestFirst feature selection yielded the highest prediction accuracy. These results indicate that a combination of several specific parameters that comprehensively capture AAA behavior may enable a suitable assessment of AAA severity, suggesting the potential benefit of machine learning for this application.

Fundamentals in Artificial Intelligence for Vascular Surgeons

Artificial intelligence (AI) corresponds to a broad discipline that aims to design systems, which display properties of human intelligence. While it has led to many advances and applications in daily life, its introduction in medicine is still in its infancy. AI has created interesting perspectives for medical research and clinical practice but has been sometimes associated with hype leading to a misunderstanding of its real capabilities. Here, we aim to introduce the fundamental notions of AI and to bring an overview of its potential applications for medical and surgical practice. In the limelight of current knowledge, limits and challenges to face as well as future directions are discussed.

Noninvasive Evaluation of Liver Fibrosis Reverse Using Artificial Neural Network Model for Chronic Hepatitis B Patients

The diagnostic performance of an artificial neural network model for chronic HBV-induced liver fibrosis reverse is not well established. Our research aims to construct an ANN model for estimating noninvasive predictors of fibrosis reverse in chronic HBV patients after regular antiviral therapy. In our study, 141 consecutive patients requiring liver biopsy at baseline and 1.5 years were enrolled. Several serum biomarkers and liver stiffness were measured during antiviral therapy in both reverse and nonreverse groups. Statistically significant variables between two groups were selected to form an input layer of the ANN model. The ROC (receiver-operating characteristic) curve and AUC (area under the curve) were calculated for comparison of effectiveness of the ANN model and logistic regression model in predicting HBV-induced liver fibrosis reverse. The prevalence of fibrosis reverse of HBV patients was about 39% (55/141) after 78-week antiviral therapy. The Ishak scoring system was used to assess fibrosis reverse. Our study manifested that AST (aspartate aminotransferase; importance coefficient = 0.296), PLT (platelet count; IC = 0.159), WBC (white blood cell; IC = 0.142), CHE (cholinesterase; IC = 0.128), LSM (liver stiffness measurement; IC = 0.125), ALT (alanine aminotransferase; IC = 0.110), and gender (IC = 0.041) were the most crucial predictors of reverse. The AUC of the ANN model and logistic model was 0.809 ± 0.062 and 0.756 ± 0.059, respectively. In our study, we concluded that the ANN model with variables consisting of AST, PLT, WBC, CHE, LSM, ALT, and gender may be useful in diagnosing liver fibrosis reverse for chronic HBV-induced liver fibrosis patients.

Real and predicted mortality under health spending constraints in Italy: a time trend analysis through artificial neural networks

BACKGROUND

After 2008 global economic crisis, Italian governments progressively reduced public healthcare financing. Describing the time trend of health outcomes and health expenditure may be helpful for policy makers during the resources' allocation decision making process. The aim of this paper is to analyze the trend of mortality and health spending in Italy and to investigate their correlation in consideration of the funding constraints experienced by the Italian national health system (SSN).

METHODS

We conducted a 20-year time-series study. Secondary data has been extracted from a national, institution based and publicly accessible retrospective database periodically released by the Italian Institute of Statistics. Age standardized all-cause mortality rate (MR) and health spending (Directly Provided Services - DPS, Agreed-Upon Services - TAUS, and private expenditure) were reviewed. Time trend analysis (1995-2014) through OLS and Multilayer Feed-forward Neural Networks (MFNN) models to forecast mortality and spending trend was performed. The association between healthcare expenditure and MR was analyzed through a fixed effect regression model. We then repeated MFNN time trend forecasting analyses on mortality by adding the spending item resulted significantly related with MR in the fixed effect analyses.

RESULTS

DPS and TAUS decreased since 2011. There was a mismatch in mortality rates between real and predicted values. DPS resulted significantly associated to mortality (p < 0.05). In repeated mortality forecasting analysis, predicted MR was found to be lower when considering the pre-constraints health spending trend.

CONCLUSIONS

Between 2011 and 2014, Italian public health spending items showed a reduction when compared to prior years. Spending on services directly provided free of charge appears to be the financial driving force of the Italian public health system. The overall mortality was found to be higher than the predicted trend and this scenario may be partially attributable to the healthcare funding constraints experienced by the SSN.

Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection

Feature selection is essential in medical area; however, its process becomes complicated with the presence of censoring which is the unique character of survival analysis. Most survival feature selection methods are based on Cox's proportional hazard model, though machine learning classifiers are preferred. They are less employed in survival analysis due to censoring which prevents them from directly being used to survival data. Among the few work that employed machine learning classifiers, partial logistic artificial neural network with auto-relevance determination is a well-known method that deals with censoring and perform feature selection for survival data. However, it depends on data replication to handle censoring which leads to unbalanced and biased prediction results especially in highly censored data. Other methods cannot deal with high censoring. Therefore, in this article, a new hybrid feature selection method is proposed which presents a solution to high level censoring. It combines support vector machine, neural network, and K-nearest neighbor classifiers using simple majority voting and a new weighted majority voting method based on survival metric to construct a multiple classifier system. The new hybrid feature selection process uses multiple classifier system as a wrapper method and merges it with iterated feature ranking filter method to further reduce features. Two endovascular aortic repair datasets containing 91% censored patients collected from two centers were used to construct a multicenter study to evaluate the performance of the proposed approach. The results showed the proposed technique outperformed individual classifiers and variable selection methods based on Cox's model such as Akaike and Bayesian information criterions and least absolute shrinkage and selector operator in p values of the log-rank test, sensitivity, and concordance index. This indicates that the proposed classifier is more powerful in correctly predicting the risk of re-intervention enabling doctor in selecting patients' future follow-up plan.

Feature selection through validation and un-censoring of endovascular repair survival data for predicting the risk of re-intervention

Background

Feature selection (FS) process is essential in the medical area as it reduces the effort and time needed for physicians to measure unnecessary features. Choosing useful variables is a difficult task with the presence of censoring which is the unique characteristic in survival analysis. Most survival FS methods depend on Cox’s proportional hazard model; however, machine learning techniques (MLT) are preferred but not commonly used due to censoring. Techniques that have been proposed to adopt MLT to perform FS with survival data cannot be used with the high level of censoring. The researcher’s previous publications proposed a technique to deal with the high level of censoring. It also used existing FS techniques to reduce dataset dimension. However, in this paper a new FS technique was proposed and combined with feature transformation and the proposed uncensoring approaches to select a reduced set of features and produce a stable predictive model.

Methods

In this paper, a FS technique based on artificial neural network (ANN) MLT is proposed to deal with highly censored Endovascular Aortic Repair (EVAR). Survival data EVAR datasets were collected during 2004 to 2010 from two vascular centers in order to produce a final stable model. They contain almost 91% of censored patients. The proposed approach used a wrapper FS method with ANN to select a reduced subset of features that predict the risk of EVAR re-intervention after 5 years to patients from two different centers located in the United Kingdom, to allow it to be potentially applied to cross-centers predictions. The proposed model is compared with the two popular FS techniques; Akaike and Bayesian information criteria (AIC, BIC) that are used with Cox’s model.

Results

The final model outperforms other methods in distinguishing the high and low risk groups; as they both have concordance index and estimated AUC better than the Cox’s model based on AIC, BIC, Lasso, and SCAD approaches. These models have p-values lower than 0.05, meaning that patients with different risk groups can be separated significantly and those who would need re-intervention can be correctly predicted.

Conclusion

The proposed approach will save time and effort made by physicians to collect unnecessary variables. The final reduced model was able to predict the long-term risk of aortic complications after EVAR. This predictive model can help clinicians decide patients’ future observation plan.

Electronic supplementary material

The online version of this article (doi:10.1186/s12911-017-0508-3) contains supplementary material, which is available to authorized users.

Surgical data science: The new knowledge domain

Healthcare in general, and surgery/interventional care in particular, is evolving through rapid advances in technology and increasing complexity of care, with the goal of maximizing the quality and value of care. Whereas innovations in diagnostic and therapeutic technologies have driven past improvements in the quality of surgical care, future transformation in care will be enabled by data. Conventional methodologies, such as registry studies, are limited in their scope for discovery and research, extent and complexity of data, breadth of analytical techniques, and translation or integration of research findings into patient care. We foresee the emergence of surgical/interventional data science (SDS) as a key element to addressing these limitations and creating a sustainable path toward evidence-based improvement of interventional healthcare pathways. SDS will create tools to measure, model, and quantify the pathways or processes within the context of patient health states or outcomes and use information gained to inform healthcare decisions, guidelines, best practices, policy, and training, thereby improving the safety and quality of healthcare and its value. Data are pervasive throughout the surgical care pathway; thus, SDS can impact various aspects of care, including prevention, diagnosis, intervention, or postoperative recovery. The existing literature already provides preliminary results, suggesting how a data science approach to surgical decision-making could more accurately predict severe complications using complex data from preoperative, intraoperative, and postoperative contexts, how it could support intraoperative decision-making using both existing knowledge and continuous data streams throughout the surgical care pathway, and how it could enable effective collaboration between human care providers and intelligent technologies. In addition, SDS is poised to play a central role in surgical education, for example, through objective assessments, automated virtual coaching, and robot-assisted active learning of surgical skill. However, the potential for transforming surgical care and training through SDS may only be realized through a cultural shift that not only institutionalizes technology to seamlessly capture data but also assimilates individuals with expertise in data science into clinical research teams. Furthermore, collaboration with industry partners from the inception of the discovery process promotes optimal design of data products as well as their efficient translation and commercialization. As surgery continues to evolve through advances in technology that enhance delivery of care, SDS represents a new knowledge domain to engineer surgical care of the future.

Predictors of in-hospital mortality following major lower extremity amputations in type 2 diabetic patients using artificial neural networks

BACKGROUND

Outcome prediction is important in the clinical decision-making process. Artificial neural networks (ANN) have been used to predict the risk of post-operative events, including survival, and are increasingly being used in complex medical decision making. We aimed to use ANN analysis to estimate predictive factors of in-hospital mortality (IHM) in patients with type 2 diabetes (T2DM) after major lower extremity amputation (LEA) in Spain.

METHODS

We design a retrospective, observational study using ANN models. We used the Spanish National Hospital Discharge Database to select all hospital admissions of major LEA procedure in T2DM patients.

MAIN OUTCOME MEASURES

Predictors of IHM using 4 ANN models: i) with all discharge diagnosis included in the database; ii) with all discharge diagnosis included in the database, excluding infectious diseases; iii) comorbidities included in the Charlson Comorbidities Index; iv) comorbidities included in the Elixhauser Comorbidity Index.

RESULTS

From 2003 to 2013, 40,857 major LEAs in patients with T2DM were identified with a 10.0% IHM. We found that Elixhauser Comorbidity Index model performed better in terms of sensitivity, specificity and precision than Charlson Comorbidity Index model (0.7634 vs 0.7444; 0.9602 vs 0.9121; 0.9511 vs 0.888, respectively). The area under the ROC curve for Elixhauser comorbidity model was 91.7% (95% CI 90.3-93.0) and for Charlson comorbidity model was 88.9% (95% CI; 87.590.2) p = 0.043. Models including all discharge diagnosis with and without infectious diseases showed worse results. In the Elixhauser Comorbidity Index model the most sensitive parameter was age (variable sensitive ratio [VSR] 1.451) followed by female sex (VSR 1.433), congestive heart failure (VSR 1.341), renal failure (VSR 1.274) and chronic pulmonary disease (VSR 1.266).

CONCLUSIONS

Elixhauser Comorbidity Index is a superior comorbidity risk-adjustment model for major LEA survival prediction in patients with T2DM than Charlson Comorbidity Index model using ANN models. Female sex, congestive heart failure, and renal failure are strong predictors of mortality in these patients.