Machine Learning to Identify Patients at Risk of Developing New-Onset Atrial Fibrillation after Coronary Artery Bypass.

BACKGROUND: This study aims to get an effective machine learning (ML) prediction model of new-onset postoperative atrial fibrillation (POAF) following coronary artery bypass grafting (CABG) and to highlight the most relevant clinical factors. METHODS: Four ML algorithms were employed to analyze 394 patients undergoing CABG, and their performances were compared: Multivariate Adaptive Regression Spline, Neural Network, Random Forest, and Support Vector Machine. Each algorithm was applied to the training data set to choose the most important features and to build a predictive model. The better performance for each model was obtained by a hyperparameters search, and the Receiver Operating Characteristic Area Under the Curve metric was selected to choose the best model. The best instances of each model were fed with the test data set, and some metrics were generated to assess the performance of the models on the unseen data set. A traditional logistic regression was also performed to be compared with the machine learning models. RESULTS: Random Forest model showed the best performance, and the top five predictive features included age, preoperative creatinine values, time of aortic cross-clamping, body surface area, and Logistic Euro-Score. CONCLUSIONS: The use of ML for clinical predictions requires an accurate evaluation of the models and their hyperparameters. Random Forest outperformed all other models in the clinical prediction of POAF following CABG.

Deep learning based identification of bone scintigraphies containing metastatic bone disease foci.

PURPOSE: Metastatic bone disease (MBD) is the most common form of metastases, most frequently deriving from prostate cancer. MBD is screened with bone scintigraphy (BS), which have high sensitivity but low specificity for the diagnosis of MBD, often requiring further investigations. Deep learning (DL) - a machine learning technique designed to mimic human neuronal interactions- has shown promise in the field of medical imaging analysis for different purposes, including segmentation and classification of lesions. In this study, we aim to develop a DL algorithm that can classify areas of increased uptake on bone scintigraphy scans. METHODS: We collected 2365 BS from three European medical centres. The model was trained and validated on 1203 and 164 BS scans respectively. Furthermore we evaluated its performance on an external testing set composed of 998 BS scans. We further aimed to enhance the explainability of our developed algorithm, using activation maps. We compared the performance of our algorithm to that of 6 nuclear medicine physicians. RESULTS: The developed DL based algorithm is able to detect MBD on BSs, with high specificity and sensitivity (0.80 and 0.82 respectively on the external test set), in a shorter time compared to the nuclear medicine physicians (2.5 min for AI and 30 min for nuclear medicine physicians to classify 134 BSs). Further prospective validation is required before the algorithm can be used in the clinic.

An externally validated fully automated deep learning algorithm to classify COVID-19 and other pneumonias on chest computed tomography.

Purpose: In this study, we propose an artificial intelligence (AI) framework based on three-dimensional convolutional neural networks to classify computed tomography (CT) scans of patients with coronavirus disease 2019 (COVID-19), influenza/community-acquired pneumonia (CAP), and no infection, after automatic segmentation of the lungs and lung abnormalities. Methods: The AI classification model is based on inflated three-dimensional Inception architecture and was trained and validated on retrospective data of CT images of 667 adult patients (no infection n=188, COVID-19 n=230, influenza/CAP n=249) and 210 adult patients (no infection n=70, COVID-19 n=70, influenza/CAP n=70), respectively. The model's performance was independently evaluated on an internal test set of 273 adult patients (no infection n=55, COVID-19 n= 94, influenza/CAP n=124) and an external validation set from a different centre (305 adult patients: COVID-19 n=169, no infection n=76, influenza/CAP n=60). Results: The model showed excellent performance in the external validation set with area under the curve of 0.90, 0.92 and 0.92 for COVID-19, influenza/CAP and no infection, respectively. The selection of the input slices based on automatic segmentation of the abnormalities in the lung reduces analysis time (56 s per scan) and computational burden of the model. The Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) score of the proposed model is 47% (15 out of 32 TRIPOD items). Conclusion: This AI solution provides rapid and accurate diagnosis in patients suspected of COVID-19 infection and influenza.

A review in radiomics: Making personalized medicine a reality via routine imaging.

Radiomics is the quantitative analysis of standard-of-care medical imaging; the information obtained can be applied within clinical decision support systems to create diagnostic, prognostic, and/or predictive models. Radiomics analysis can be performed by extracting hand-crafted radiomics features or via deep learning algorithms. Radiomics has evolved tremendously in the last decade, becoming a bridge between imaging and precision medicine. Radiomics exploits sophisticated image analysis tools coupled with statistical elaboration to extract the wealth of information hidden inside medical images, such as computed tomography (CT), magnetic resonance (MR), and/or Positron emission tomography (PET) scans, routinely performed in the everyday clinical practice. Many efforts have been devoted in recent years to the standardization and validation of radiomics approaches, to demonstrate their usefulness and robustness beyond any reasonable doubts. However, the booming of publications and commercial applications of radiomics approaches warrant caution and proper understanding of all the factors involved to avoid "scientific pollution" and overly enthusiastic claims by researchers and clinicians alike. For these reasons the present review aims to be a guidebook of sorts, describing the process of radiomics, its pitfalls, challenges, and opportunities, along with its ability to improve clinical decision-making, from oncology and respiratory medicine to pharmacological and genotyping studies.

A non-invasive, automated diagnosis of Menière's disease using radiomics and machine learning on conventional magnetic resonance imaging: A multicentric, case-controlled feasibility study.

PURPOSE: This study investigated the feasibility of a new image analysis technique (radiomics) on conventional MRI for the computer-aided diagnosis of Menière's disease. MATERIALS AND METHODS: A retrospective, multicentric diagnostic case-control study was performed. This study included 120 patients with unilateral or bilateral Menière's disease and 140 controls from four centers in the Netherlands and Belgium. Multiple radiomic features were extracted from conventional MRI scans and used to train a machine learning-based, multi-layer perceptron classification model to distinguish patients with Menière's disease from controls. The primary outcomes were accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the classification model. RESULTS: The classification accuracy of the machine learning model on the test set was 82%, with a sensitivity of 83%, and a specificity of 82%. The positive and negative predictive values were 71%, and 90%, respectively. CONCLUSION: The multi-layer perceptron classification model yielded a precise, high-diagnostic performance in identifying patients with Menière's disease based on radiomic features extracted from conventional T2-weighted MRI scans. In the future, radiomics might serve as a fast and noninvasive decision support system, next to clinical evaluation in the diagnosis of Menière's disease.

Privacy preserving distributed learning classifiers - Sequential learning with small sets of data.

BACKGROUND: Artificial intelligence (AI) typically requires a significant amount of high-quality data to build reliable models, where gathering enough data within a single institution can be particularly challenging. In this study we investigated the impact of using sequential learning to exploit very small, siloed sets of clinical and imaging data to train AI models. Furthermore, we evaluated the capacity of such models to achieve equivalent performance when compared to models trained with the same data over a single centralized database. METHODS: We propose a privacy preserving distributed learning framework, learning sequentially from each dataset. The framework is applied to three machine learning algorithms: Logistic Regression, Support Vector Machines (SVM), and Perceptron. The models were evaluated using four open-source datasets (Breast cancer, Indian liver, NSCLC-Radiomics dataset, and Stage III NSCLC). FINDINGS: The proposed framework ensured a comparable predictive performance against a centralized learning approach. Pairwise DeLong tests showed no significant difference between the compared pairs for each dataset. INTERPRETATION: Distributed learning contributes to preserve medical data privacy. We foresee this technology will increase the number of collaborative opportunities to develop robust AI, becoming the default solution in scenarios where collecting enough data from a single reliable source is logistically impossible. Distributed sequential learning provides privacy persevering means for institutions with small but clinically valuable datasets to collaboratively train predictive AI while preserving the privacy of their patients. Such models perform similarly to models that are built on a larger central dataset.

Radiomics in Lung Diseases Imaging: State-of-the-Art for Clinicians.

Artificial intelligence (AI) has increasingly been serving the field of radiology over the last 50 years. As modern medicine is evolving towards precision medicine, offering personalized patient care and treatment, the requirement for robust imaging biomarkers has gradually increased. Radiomics, a specific method generating high-throughput extraction of a tremendous amount of quantitative imaging data using data-characterization algorithms, has shown great potential in individuating imaging biomarkers. Radiomic analysis can be implemented through the following two methods: hand-crafted radiomic features extraction or deep learning algorithm. Its application in lung diseases can be used in clinical decision support systems, regarding its ability to develop descriptive and predictive models in many respiratory pathologies. The aim of this article is to review the recent literature on the topic, and briefly summarize the interest of radiomics in chest Computed Tomography (CT) and its pertinence in the field of pulmonary diseases, from a clinician's perspective.

Deep learning for the fully automated segmentation of the inner ear on MRI.

Segmentation of anatomical structures is valuable in a variety of tasks, including 3D visualization, surgical planning, and quantitative image analysis. Manual segmentation is time-consuming and deals with intra and inter-observer variability. To develop a deep-learning approach for the fully automated segmentation of the inner ear in MRI, a 3D U-net was trained on 944 MRI scans with manually segmented inner ears as reference standard. The model was validated on an independent, multicentric dataset consisting of 177 MRI scans from three different centers. The model was also evaluated on a clinical validation set containing eight MRI scans with severe changes in the morphology of the labyrinth. The 3D U-net model showed precise Dice Similarity Coefficient scores (mean DSC-0.8790) with a high True Positive Rate (91.5%) and low False Discovery Rate and False Negative Rates (14.8% and 8.49% respectively) across images from three different centers. The model proved to perform well with a DSC of 0.8768 on the clinical validation dataset. The proposed auto-segmentation model is equivalent to human readers and is a reliable, consistent, and efficient method for inner ear segmentation, which can be used in a variety of clinical applications such as surgical planning and quantitative image analysis.

The "hype" of hydrops in classifying vestibular disorders: a narrative review.

BACKGROUND: Classifying and diagnosing peripheral vestibular disorders based on their symptoms is challenging due to possible symptom overlap or atypical clinical presentation. To improve the diagnostic trajectory, gadolinium-based contrast-enhanced magnetic resonance imaging of the inner ear is nowadays frequently used for the in vivo confirmation of endolymphatic hydrops in humans. However, hydrops is visualized in both healthy subjects and patients with vestibular disorders, which might make the clinical value of hydrops detection on MRI questionable. OBJECTIVE: To investigate the diagnostic value of clinical and radiological features, including the in vivo visualization of endolymphatic hydrops, for the classification and diagnosis of vestibular disorders. METHODS: A literature search was performed in February and March 2019 to estimate the prevalence of various features in healthy subjects and in common vestibular disorders to make a graphical comparison between healthy and abnormal. RESULTS: Of the features studied, hydrops was found to be a highly prevalent feature in Menière's disease (99.4%). Though, hydrops has also a relatively high prevalence in patients with vestibular schwannoma (48.2%) and in healthy temporal bones (12.5%) as well. In patients diagnosed with (definite or probable) Menière's disease, hydrops is less frequently diagnosed by magnetic resonance imaging compared to the histological confirmation (82.3% versus 99.4%). The mean prevalence of radiologically diagnosed hydrops was 31% in healthy subjects, 28.1% in patients with vestibular migraine, and 25.9% in patients with vestibular schwannoma. An interesting finding was an absolute difference in hydrops prevalence between the two diagnostic techniques (histology and radiology) of 25.2% in patients with Menière's disease and 29% in patients with vestibular schwannoma. CONCLUSIONS: Although the visualization of hydrops has a high diagnostic value in patients with definite Menière's disease, it is important to appreciate the relatively high prevalence of hydrops in healthy populations and other vestibular disorders. Endolymphatic hydrops is not a pathognomic phenomenon, and detecting hydrops should not directly indicate a diagnosis of Menière's disease. Both symptom-driven and hydrops-based classification systems have disadvantages. Therefore, it might be worth to explore features "beyond" hydrops. New analysis techniques, such as Radiomics, might play an essential role in (re)classifying vestibular disorders in the future.

Development and Validation of an Automated Radiomic CT Signature for Detecting COVID-19.

The coronavirus disease 2019 (COVID-19) outbreak has reached pandemic status. Drastic measures of social distancing are enforced in society and healthcare systems are being pushed to and beyond their limits. To help in the fight against this threat on human health, a fully automated AI framework was developed to extract radiomics features from volumetric chest computed tomography (CT) exams. The detection model was developed on a dataset of 1381 patients (181 COVID-19 patients plus 1200 non COVID control patients). A second, independent dataset of 197 RT-PCR confirmed COVID-19 patients and 500 control patients was used to assess the performance of the model. Diagnostic performance was assessed by the area under the receiver operating characteristic curve (AUC). The model had an AUC of 0.882 (95% CI: 0.851-0.913) in the independent test dataset (641 patients). The optimal decision threshold, considering the cost of false negatives twice as high as the cost of false positives, resulted in an accuracy of 85.18%, a sensitivity of 69.52%, a specificity of 91.63%, a negative predictive value (NPV) of 94.46% and a positive predictive value (PPV) of 59.44%. Benchmarked against RT-PCR confirmed cases of COVID-19, our AI framework can accurately differentiate COVID-19 from routine clinical conditions in a fully automated fashion. Thus, providing rapid accurate diagnosis in patients suspected of COVID-19 infection, facilitating the timely implementation of isolation procedures and early intervention.