SVM recursive feature elimination analyses of structural brain MRI predicts near-term relapses in patients with clinically isolated syndromes suggestive of multiple sclerosis

An analytical review on the use of artificial intelligence and machine learning in diagnosis, prediction, and risk factor analysis of multiple sclerosis

Medical research offers potential for disease prediction, like Multiple Sclerosis (MS). This neurological disorder damages nerve cell sheaths, with treatments focusing on symptom relief. Manual MS detection is time-consuming and error prone. Though MS lesion detection has been studied, limited attention has been paid to clinical analysis and computational risk factor prediction. Artificial intelligence (AI) techniques and Machine Learning (ML) methods offer accurate and effective alternatives to mapping MS progression. However, there are challenges in accessing clinical data and interdisciplinary collaboration. By analyzing 103 papers, we recognize the trends, strengths and weaknesses of AI, ML, and statistical methods applied to MS diagnosis. AI/ML-based approaches are suggested to identify MS risk factors, select significant MS features, and improve the diagnostic accuracy, such as Rule-based Fuzzy Logic (RBFL), Adaptive Fuzzy Inference System (ANFIS), Artificial Neural Network methods (ANN), Support Vector Machine (SVM), and Bayesian Networks (BNs). Meanwhile, applications of the Expanded Disability Status Scale (EDSS) and Magnetic Resonance Imaging (MRI) can enhance MS diagnostic accuracy. By examining established risk factors like obesity, smoking, and education, some research tackled the issue of disease progression. The performance metrics varied across different aspects of MS studies: Diagnosis: Sensitivity ranged from 60 % to 98 %, specificity from 60 % to 98 %, and accuracy from 61 % to 97 %. Prediction: Sensitivity ranged from 76 % to 98 %, specificity from 65 % to 98 %, and accuracy from 62 % to 99 %. Segmentation: Accuracy ranged up to 96.7 %. Classification: Sensitivity ranged from 78 % to 97.34 %, specificity from 65 % to 99.32 %, and accuracy from 71 % to 97.94 %. Furthermore, the literature shows that combining techniques can improve efficiency, exploiting their strengths for better overall performance.

Identifying gray matter alterations in Cushing's disease using machine learning: An interpretable approach

BACKGROUND

Cushing's Disease (CD) is a rare clinical syndrome characterized by excessive secretion of adrenocorticotrophic hormone, leading to significant functional and structural brain alterations as observed in Magnetic Resonance Imaging (MRI). While traditional statistical analysis has been widely employed to investigate these MRI changes in CD, it has lacked the ability to predict individual-level outcomes.

PURPOSE

To address this problem, this paper has proposed an interpretable machine learning (ML) framework, including model-level assessment, feature-level assessment, and biology-level assessment to ensure a comprehensive analysis based on structural MRI of CD.

METHODS

The ML framework has effectively identified the changes in brain regions in the stage of model-level assessment, verified the effectiveness of these altered brain regions to predict CD from normal controls in the stage of feature-level assessment, and carried out a correlation analysis between altered brain regions and clinical symptoms in the stage of biology-level assessment.

RESULTS

The experimental results of this study have demonstrated that the Insula, Fusiform gyrus, Superior frontal gyrus, Precuneus, and the opercular portion of the Inferior frontal gyrus of CD showed significant alterations in brain regions. Furthermore, our study has revealed significant correlations between clinical symptoms and the frontotemporal lobes, insulin, and olfactory cortex, which also have been confirmed by previous studies.

CONCLUSIONS

The ML framework proposed in this study exhibits exceptional potential in uncovering the intricate pathophysiological mechanisms underlying CD, with potential applicability in diagnosing other diseases.

Differentiation between suicide attempt and suicidal ideation in patients with major depressive disorder using cortical functional network

Studies exploring the neurophysiology of suicide are scarce and the neuropathology of related disorders is poorly understood. This study investigated source-level cortical functional networks using resting-state electroencephalography (EEG) in drug-naïve depressed patients with suicide attempt (SA) and suicidal ideation (SI). EEG was recorded in 55 patients with SA and in 54 patients with SI. Particularly, all patients with SA were evaluated using EEG immediately after their SA (within 7 days). Graph-theory-based source-level weighted functional networks were assessed using strength, clustering coefficient (CC), and path length (PL) in seven frequency bands. Finally, we applied machine learning to differentiate between the two groups using source-level network features. At the global level, patients with SA showed lower strength and CC and higher PL in the high alpha band than those with SI. At the nodal level, compared with patients with SI, patients with SA showed lower high alpha band nodal CCs in most brain regions. The best classification performances for SA and SI showed an accuracy of 73.39%, a sensitivity of 76.36%, and a specificity of 70.37% based on high alpha band network features. Our findings suggest that abnormal high alpha band functional network may reflect the pathophysiological characteristics of suicide and serve as a clinical biomarker for suicide.

Artificial intelligence applied to MRI data to tackle key challenges in multiple sclerosis

Artificial intelligence (AI) is the branch of science aiming at creating algorithms able to carry out tasks that typically require human intelligence. In medicine, there has been a tremendous increase in AI applications thanks to increasingly powerful computers and the emergence of big data repositories. Multiple sclerosis (MS) is a chronic autoimmune condition affecting the central nervous system with a complex pathogenesis, a challenging diagnostic process strongly relying on magnetic resonance imaging (MRI) and a high and largely unexplained variability across patients. Therefore, AI applications in MS have the great potential of helping us better support the diagnosis, find markers for prognosis to eventually design more powerful randomised clinical trials and improve patient management in clinical practice and eventually understand the mechanisms of the disease. This topical review aims to summarise the recent advances in AI applied to MRI data in MS to illustrate its achievements, limitations and future directions.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

Prognostic models for predicting clinical disease progression, worsening and activity in people with multiple sclerosis

BACKGROUND

Multiple sclerosis (MS) is a chronic inflammatory disease of the central nervous system that affects millions of people worldwide. The disease course varies greatly across individuals and many disease-modifying treatments with different safety and efficacy profiles have been developed recently. Prognostic models evaluated and shown to be valid in different settings have the potential to support people with MS and their physicians during the decision-making process for treatment or disease/life management, allow stratified and more precise interpretation of interventional trials, and provide insights into disease mechanisms. Many researchers have turned to prognostic models to help predict clinical outcomes in people with MS; however, to our knowledge, no widely accepted prognostic model for MS is being used in clinical practice yet.

OBJECTIVES

To identify and summarise multivariable prognostic models, and their validation studies for quantifying the risk of clinical disease progression, worsening, and activity in adults with MS.

SEARCH METHODS

We searched MEDLINE, Embase, and the Cochrane Database of Systematic Reviews from January 1996 until July 2021. We also screened the reference lists of included studies and relevant reviews, and references citing the included studies.

SELECTION CRITERIA

We included all statistically developed multivariable prognostic models aiming to predict clinical disease progression, worsening, and activity, as measured by disability, relapse, conversion to definite MS, conversion to progressive MS, or a composite of these in adult individuals with MS. We also included any studies evaluating the performance of (i.e. validating) these models. There were no restrictions based on language, data source, timing of prognostication, or timing of outcome.

DATA COLLECTION AND ANALYSIS

Pairs of review authors independently screened titles/abstracts and full texts, extracted data using a piloted form based on the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), assessed risk of bias using the Prediction Model Risk Of Bias Assessment Tool (PROBAST), and assessed reporting deficiencies based on the checklist items in Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD). The characteristics of the included models and their validations are described narratively. We planned to meta-analyse the discrimination and calibration of models with at least three external validations outside the model development study but no model met this criterion. We summarised between-study heterogeneity narratively but again could not perform the planned meta-regression.

MAIN RESULTS

We included 57 studies, from which we identified 75 model developments, 15 external validations corresponding to only 12 (16%) of the models, and six author-reported validations. Only two models were externally validated multiple times. None of the identified external validations were performed by researchers independent of those that developed the model. The outcome was related to disease progression in 39 (41%), relapses in 8 (8%), conversion to definite MS in 17 (18%), and conversion to progressive MS in 27 (28%) of the 96 models or validations. The disease and treatment-related characteristics of included participants, and definitions of considered predictors and outcome, were highly heterogeneous amongst the studies. Based on the publication year, we observed an increase in the percent of participants on treatment, diversification of the diagnostic criteria used, an increase in consideration of biomarkers or treatment as predictors, and increased use of machine learning methods over time. Usability and reproducibility All identified models contained at least one predictor requiring the skills of a medical specialist for measurement or assessment. Most of the models (44; 59%) contained predictors that require specialist equipment likely to be absent from primary care or standard hospital settings. Over half (52%) of the developed models were not accompanied by model coefficients, tools, or instructions, which hinders their application, independent validation or reproduction. The data used in model developments were made publicly available or reported to be available on request only in a few studies (two and six, respectively). Risk of bias We rated all but one of the model developments or validations as having high overall risk of bias. The main reason for this was the statistical methods used for the development or evaluation of prognostic models; we rated all but two of the included model developments or validations as having high risk of bias in the analysis domain. None of the model developments that were externally validated or these models' external validations had low risk of bias. There were concerns related to applicability of the models to our research question in over one-third (38%) of the models or their validations. Reporting deficiencies Reporting was poor overall and there was no observable increase in the quality of reporting over time. The items that were unclearly reported or not reported at all for most of the included models or validations were related to sample size justification, blinding of outcome assessors, details of the full model or how to obtain predictions from it, amount of missing data, and treatments received by the participants. Reporting of preferred model performance measures of discrimination and calibration was suboptimal.

AUTHORS' CONCLUSIONS

The current evidence is not sufficient for recommending the use of any of the published prognostic prediction models for people with MS in clinical routine today due to lack of independent external validations. The MS prognostic research community should adhere to the current reporting and methodological guidelines and conduct many more state-of-the-art external validation studies for the existing or newly developed models.

Subject-specific whole-brain parcellations of nodes and boundaries are modulated differently under 10 Hz rTMS

Repetitive transcranial magnetic stimulation (rTMS) has gained considerable importance in the treatment of neuropsychiatric disorders, including major depression. However, it is not yet understood how rTMS alters brain's functional connectivity. Here we report changes in functional connectivity captured by resting state functional magnetic resonance imaging (rsfMRI) within the first hour after 10 Hz rTMS. We apply subject-specific parcellation schemes to detect changes (1) in network nodes, where the strongest functional connectivity of regions is observed, and (2) in network boundaries, where functional transitions between regions occur. We use support vector machine (SVM), a widely used machine learning algorithm that is robust and effective, for the classification and characterization of time intervals of changes in node and boundary maps. Our results reveal that changes in connectivity at the boundaries are slower and more complex than in those observed in the nodes, but of similar magnitude according to accuracy confidence intervals. These results were strongest in the posterior cingulate cortex and precuneus. As network boundaries are indeed under-investigated in comparison to nodes in connectomics research, our results highlight their contribution to functional adjustments to rTMS.

Integration of cancer-related genetic landscape of Eph receptors and ephrins with proteomics identifies a crosstalk between EPHB6 and EGFR

Eph receptors and their ephrin ligands are viewed as promising targets for cancer treatment; however, targeting them is hindered by their context-dependent functionalities. To circumvent this, we explore molecular landscapes underlying their pro- and anti-malignant activities. Using unbiased bioinformatics approaches, we construct a cancer-related network of genetic interactions (GIs) of all Ephs and ephrins to assist in their therapeutic manipulation. We also apply genetic screening and BioID proteomics and integrate them with machine learning approaches to select the most relevant GIs of one Eph receptor, EPHB6. This identifies a crosstalk between EPHB6 and EGFR, and further experiments confirm the ability of EPHB6 to modulate EGFR signaling, enhancing the proliferation of cancer cells and tumor development. Taken together, our observations show EPHB6 involvement in EGFR action, suggesting its targeting might be beneficial in EGFR-dependent tumors, and confirm that the Eph family genetic interactome presented here can be effectively exploited in developing cancer treatment approaches.

Accounting for uncertainty in training data to improve machine learning performance in predicting new disease activity in early multiple sclerosis

Introduction

Machine learning (ML) has great potential for using health data to predict clinical outcomes in individual patients. Missing data are a common challenge in training ML algorithms, such as when subjects withdraw from a clinical study, leaving some samples with missing outcome labels. In this study, we have compared three ML models to determine whether accounting for label uncertainty can improve a model's predictions.

Methods

We used a dataset from a completed phase-III clinical trial that evaluated the efficacy of minocycline for delaying the conversion from clinically isolated syndrome to multiple sclerosis (MS), using the McDonald 2005 diagnostic criteria. There were a total of 142 participants, and at the 2-year follow-up 81 had converted to MS, 29 remained stable, and 32 had uncertain outcomes. In a stratified 7-fold cross-validation, we trained three random forest (RF) ML models using MRI volumetric features and clinical variables to predict the conversion outcome, which represented new disease activity within 2 years of a first clinical demyelinating event. One RF was trained using subjects with the uncertain labels excluded (RF_exclude), another RF was trained using the entire dataset but with assumed labels for the uncertain group (RF_naive), and a third, a probabilistic RF (PRF, a type of RF that can model label uncertainty) was trained on the entire dataset, with probabilistic labels assigned to the uncertain group.

Results

Probabilistic random forest outperformed both the RF models with the highest AUC (0.76, compared to 0.69 for RF_exclude and 0.71 for RF_naive) and F1-score (86.6% compared to 82.6% for RF_exclude and 76.8% for RF_naive).

Conclusion

Machine learning algorithms capable of modeling label uncertainty can improve predictive performance in datasets in which a substantial number of subjects have unknown outcomes.

Present and future of the diagnostic work-up of multiple sclerosis: the imaging perspective

In recent years, the use of magnetic resonance imaging (MRI) for the diagnostic work-up of multiple sclerosis (MS) has evolved considerably. The 2017 McDonald criteria show high sensitivity and accuracy in predicting a second clinical attack in patients with a typical clinically isolated syndrome and allow an earlier diagnosis of MS. They have been validated, are evidence-based, simplify the clinical use of MRI criteria and improve MS patients' management. However, to limit the risk of misdiagnosis, they should be applied by expert clinicians only after the careful exclusion of alternative diagnoses. Recently, new MRI markers have been proposed to improve diagnostic specificity for MS and reduce the risk of misdiagnosis. The central vein sign and chronic active lesions (i.e., paramagnetic rim lesions) may increase the specificity of MS diagnostic criteria, but further effort is necessary to validate and standardize their assessment before implementing them in the clinical setting. The feasibility of subpial demyelination assessment and the clinical relevance of leptomeningeal enhancement evaluation in the diagnostic work-up of MS appear more limited. Artificial intelligence tools may capture MRI attributes that are beyond the human perception, and, in the future, artificial intelligence may complement human assessment to further ameliorate the diagnostic work-up and patients' classification. However, guidelines that ensure reliability, interpretability, and validity of findings obtained from artificial intelligence approaches are still needed to implement them in the clinical scenario. This review provides a summary of the most recent updates regarding the application of MRI for the diagnosis of MS.

Radiomics based on diffusion-weighted imaging for differentiation between focal-type autoimmune pancreatitis and pancreatic carcinoma

OBJECTIVE

To evaluate the parameters of support vector machine (SVM) using imaging data generated from the apparent diffusion coefficient (ADC) to differentiate between focal-type autoimmune pancreatitis (f-AIP) and pancreatic ductal adenocarcinoma (PDAC) when using SVM based on diffusion-weighted imaging.

METHODS

The 2D-ADCmean and texture parameters (16 texture features × [non-filter+17 filters]) were retrospectively segmented by 2 readers in 28 patients with f-AIP and 77 patients with pathologically proven PDAC. The diagnostic accuracy of the SVM model was evaluated by receiver operating characteristic curve analysis and calculation of the area under the curve (AUC). Interreader reliability was assessed by intraclass correlation coefficient (ICC).

RESULTS

The 2D-ADCmean and 3D-ADCmean were significantly lower in cases of f-AIP (1.10-1.15 × 10-3 mm2/s and 1.21-1.23× 10-3 mm2/s, respectively) vs PDAC (1.29-1.33 × 10-3 mm2/s and 1.41-1.43 × 10-3 mm2/s, respectively), with excellent and good interreader reliability, respectively (ICC = 0.909 and 0.891, respectively). Among the texture parameters, energy with exponential filtering yielded the highest AUC (Reader 1: 74.7%, Reader 2: 81.5%), with fair interreader reliability (ICC = 0.707). The non-linear SVM, a combination of 2D-ADCmean, object volume and exponential-energy showed an AUC value of 96.2% in the testing cohorts.

CONCLUSION

Our results suggest that non-linear SVM using a combination of 2D-ADCmean, object volume, and exponential-energy may assist in differentiating f-AIP from PDAC.

ADVANCES IN KNOWLEDGE

The radiomics based on an apparent diffusion coefficient value may assist in differentiating f-AIP from PDAC.

Prediction of the information processing speed performance in multiple sclerosis using a machine learning approach in a large multicenter magnetic resonance imaging data set

Many patients with multiple sclerosis (MS) experience information processing speed (IPS) deficits, and the Symbol Digit Modalities Test (SDMT) has been recommended as a valid screening test. Magnetic resonance imaging (MRI) has markedly improved the understanding of the mechanisms associated with cognitive deficits in MS. However, which structural MRI markers are the most closely related to cognitive performance is still unclear. We used the multicenter 3T-MRI data set of the Italian Neuroimaging Network Initiative to extract multimodal data (i.e., demographic, clinical, neuropsychological, and structural MRIs) of 540 MS patients. We aimed to assess, through machine learning techniques, the contribution of brain MRI structural volumes in the prediction of IPS deficits when combined with demographic and clinical features. We trained and tested the eXtreme Gradient Boosting (XGBoost) model following a rigorous validation scheme to obtain reliable generalization performance. We carried out a classification and a regression task based on SDMT scores feeding each model with different combinations of features. For the classification task, the model trained with thalamus, cortical gray matter, hippocampus, and lesions volumes achieved an area under the receiver operating characteristic curve of 0.74. For the regression task, the model trained with cortical gray matter and thalamus volumes, EDSS, nucleus accumbens, lesions, and putamen volumes, and age reached a mean absolute error of 0.95. In conclusion, our results confirmed that damage to cortical gray matter and relevant deep and archaic gray matter structures, such as the thalamus and hippocampus, is among the most relevant predictors of cognitive performance in MS.

Machine Learning to Predict Successful Opioid Dose Reduction or Stabilization After Spinal Cord Stimulation

BACKGROUND

Spinal cord stimulation (SCS) effectively reduces opioid usage in some patients, but preoperatively, there is no objective measure to predict who will most benefit.

OBJECTIVE

To predict successful reduction or stabilization of opioid usage after SCS using machine learning models we developed and to assess if deep learning provides a significant benefit over logistic regression (LR).

METHODS

We used the IBM MarketScan national databases to identify patients undergoing SCS from 2010 to 2015. Our models predict surgical success as defined by opioid dose stability or reduction 1 year after SCS. We incorporated 30 predictors, primarily regarding medication patterns and comorbidities. Two machine learning algorithms were applied: LR with recursive feature elimination and deep neural networks (DNNs). To compare model performances, we used nested 5-fold cross-validation to calculate area under the receiver operating characteristic curve (AUROC).

RESULTS

The final cohort included 7022 patients, of whom 66.9% had successful surgery. Our 5-variable LR performed comparably with the full 30-variable version (AUROC difference <0.01). The DNN and 5-variable LR models demonstrated similar AUROCs of 0.740 (95% CI, 0.727-0.753) and 0.737 (95% CI, 0.728-0.746) ( P = .25), respectively. The simplified model can be accessed at SurgicalML.com .

CONCLUSION

We present the first machine learning-based models for predicting reduction or stabilization of opioid usage after SCS. The DNN and 5-variable LR models demonstrated comparable performances, with the latter revealing significant associations with patients' pre-SCS pharmacologic patterns. This simplified, interpretable LR model may augment patient and surgeon decision making regarding SCS.

Prediction of high and low disease activity in early MS patients using multiple kernel learning identifies importance of lateral ventricle intensity

Background

Lack of easy-to-interpret disease activity prediction methods in early MS can lead to worse patient prognosis.

Objectives

Using machine learning (multiple kernel learning – MKL) models, we assessed the prognostic value of various clinical and MRI measures for disease activity.

Methods

Early MS patients ( n = 148) with at least two associated clinical and MRI visits were investigated. T2-weighted MRIs were cropped to contain mainly the lateral ventricles (LV). High disease activity was defined as surpassing NEDA-3 Criteria more than once per year. Clinical demographic, MRI-extracted image-derived phenotypes (IDP), and MRI data were used as inputs for separate kernels to predict future disease activity with MKL. Model performance was compared using bootstrapped effect size analysis of mean differences.

Results

A total of 681 visits were included, where 81 (55%) patients had high disease activity in a combined end point measure using all follow-up visits. MKL model discrimination performance was moderate (AUC ≥ 0.62); however, modelling with combined clinical and cropped LV kernels gave the highest prediction performance (AUC = 0.70).

Conclusions

MRIs contain valuable information on future disease activity, especially in and around the LV. MKL techniques for combining different data types can be used for the prediction of disease activity in a relatively small MS cohort.

Classification of Parkinson's disease using a region-of-interest- and resting-state functional magnetic resonance imaging-based radiomics approach

To investigate the value of combining amplitude of low-frequency fluctuations-based radiomics and the support vector machine classifier method in distinguishing patients with Parkinson's disease from healthy controls. A total of 123 patients with Parkinson's disease and 90 healthy controls from three centers with functional and structural MRI images were included in this study. We extracted radiomics features using the Brainnetome 246 atlas from the mean amplitude of low-frequency fluctuations maps. Two-sample t-tests and recursive feature elimination combined with support vector machine method were applied for feature selection and dimensionality reduction. We used support vector machine classifier to construct model and identify the discriminative features. The automated anatomical labeling 90 atlas and fivefold cross-validation were used to evaluate the robustness and generalization of the classifier. We found our model obtained a high classification performance with an accuracy of 78.07%, and AUC, sensitivity, and specificity of 0.8597, 78.80%, and 76.08%, respectively. We detected 7 discriminative brain subregions. The fivefold cross-validation and automated anatomical labeling 90 atlas also got high classification accuracy, and we found Brainnetome 246 atlas achieved a higher classification performance than the automated anatomical labeling 90 atlas both with tenfold and fivefold cross-validation. Our findings may help the early diagnosis of Parkinson's disease and provide support for research on Parkinson's disease mechanisms and clinical evaluation.

Role of artificial intelligence in MS clinical practice

•

For medical applications, machine learning (including deep learning) are the most commonly used artificial intelligence (AI) approaches.

•

It can improve multiple sclerosis (MS) diagnosis, prognostication and treatment monitoring.

•

Thanks to AI, MRI and cognitive phenotypes of MS patients were identified.

•

AI can shorten MRI protocols for MS, allowing the application of advanced techniques.

•

It can reduce the human effort for MRI analysis, especially for lesion segmentation.

Machine learning (ML) and its subset, deep learning (DL), are branches of artificial intelligence (AI) showing promising findings in the medical field, especially when applied to imaging data. Given the substantial role of MRI in the diagnosis and management of patients with multiple sclerosis (MS), this disease is an ideal candidate for the application of AI techniques. In this narrative review, we are going to discuss the potential applications of AI for MS clinical practice, together with their limitations. Among their several advantages, ML algorithms are able to automate repetitive tasks, to analyze more data in less time and to achieve higher accuracy and reproducibility than the human counterpart. To date, these algorithms have been applied to MS diagnosis, prognosis, disease and treatment monitoring. Other fields of application have been improvement of MRI protocols as well as automated lesion and tissue segmentation. However, several challenges remain, including a better understanding of the information selected by AI algorithms, appropriate multicenter and longitudinal validations of results and practical aspects regarding hardware and software integration. Finally, one cannot overemphasize the paramount importance of human supervision, in order to optimize the use and take full advantage of the potential of AI approaches.

Machine Learning-Based Prediction Method for Tremors Induced by Tacrolimus in the Treatment of Nephrotic Syndrome

Tremors have been reported even with a low dose of tacrolimus in patients with nephrotic syndrome and are responsible for hampering the day-to-day work of young active patients with nephrotic syndrome. This study proposes a neural network model based on seven variables to predict the development of tremors following tacrolimus. The sensitivity and specificity of this algorithm are high. A total of 252 patients were included in this study, out of which 39 (15.5%) experienced tremors, 181 patients (including 32 patients who experienced tremors) were randomly assigned to a training dataset, and the remaining were assigned to an external validation set. We used a recursive feature elimination algorithm to train the training dataset, in turn, through 10-fold cross-validation. The classification performance of the classifer was then used as the evaluation criterion for these subsets to find the subset of optimal features. A neural network was used as a classification algorithm to accurately predict tremors using the subset of optimal features. This model was subsequently tested in the validation dataset. The subset of optimal features contained seven variables (creatinine, D-dimer, total protein, calcium ion, platelet distribution width, serum kalium, and fibrinogen), and the highest accuracy obtained was 0.8288. The neural network model based on these seven variables obtained an area under the curve (AUC) value of 0.9726, an accuracy of 0.9345, a sensitivity of 0.9712, and a specificity of 0.7586 in the training set. Meanwhile, the external validation achieved an accuracy of 0.8214, a sensitivity of 0.8378, and a specificity of 0.7000 in the validation dataset. This model was capable of predicting tremors caused by tacrolimus with an excellent degree of accuracy, which can be beneficial in the treatment of nephrotic syndrome patients.

Tumor-Educated Platelets as a Promising Biomarker for Blood-Based Detection of Renal Cell Carcinoma

Purpose

Tumor-educated platelets (TEPs) are a promising liquid biopsy in many cancers. However, their role in renal cell carcinoma (RCC) is unknown. Thus, this study explored the diagnostic value of TEPs in RCC patients.

Methods

Platelets were prospectively collected from 24 RCC patients and 25 controls. RNA-seq was performed to identify the differentially expressed genes (DEGs) between RCC patients and controls. Besides, RNA-seq data of pan-cancer TEPs were downloaded and randomly divided into training and validation sets. A pan-cancer TEP model was developed in the training set using the support vector machine (SVM) and validated in the validation set and our RCC dataset. Finally, an RCC-based TEP model was developed and optimized through the SVM algorithms and recursive feature elimination (RFE) method.

Result

Two hundred three DEGs, 64 (31.5%) upregulated and 139 (68.5%) downregulated, were detected in the platelets of RCC patients compared with controls. The pan-cancer TEP model had a high accuracy in detecting cancer in the internal validation (training set, accuracy 98.8%, AUC: 0.999; validation set, accuracy 95.4%, AUC: 0.972; different tumor subtypes, accuracy 86.6%–96.1%, AUC: 0.952–1.000). However, the pan-cancer TEP model in the external validation had a scarce diagnostic value in RCC patients (accuracy 48.7%, AUC: 0.615). Therefore, to develop the RCC-based TEP model, the gene biomarkers mostly contributing to the model were selected using the RFE method. The RCC-based TEP model containing 68 gene biomarkers reached a diagnostic accuracy of 100% (AUC: 1.000) in the training set, 88.9% (AUC: 0.963) in the validation set, and 95.9% (AUC: 0.988) in the overall cohort.

Conclusion

TEPs could function as a minimally invasive blood biomarker in the detection of RCC.

Machine Learning for Detecting Parkinson's Disease by Resting-State Functional Magnetic Resonance Imaging: A Multicenter Radiomics Analysis

Parkinson's disease (PD) is one of the most common progressive degenerative diseases, and its diagnosis is challenging on clinical grounds. Clinically, effective and quantifiable biomarkers to detect PD are urgently needed. In our study, we analyzed data from two centers, the primary set was used to train the model, and the independent external validation set was used to validate our model. We applied amplitude of low-frequency fluctuation (ALFF)-based radiomics method to extract radiomics features (including first- and high-order features). Subsequently, t-test and least absolute shrinkage and selection operator (LASSO) were harnessed for feature selection and data dimensionality reduction, and grid search method and nested 10-fold cross-validation were applied to determine the optimal hyper-parameter λ of LASSO and evaluate the performance of the model, in which a support vector machine was used to construct the classification model to classify patients with PD and healthy controls (HCs). We found that our model achieved good performance [accuracy = 81.45% and area under the curve (AUC) = 0.850] in the primary set and good generalization in the external validation set (accuracy = 67.44% and AUC = 0.667). Most of the discriminative features were high-order radiomics features, and the identified brain regions were mainly located in the sensorimotor network and lateral parietal cortex. Our study indicated that our proposed method can effectively classify patients with PD and HCs, ALFF-based radiomics features that might be potential biomarkers of PD, and provided further support for the pathological mechanism of PD, that is, PD may be related to abnormal brain activity in the sensorimotor network and lateral parietal cortex.

Prognosis of a second clinical event from baseline MRI in patients with a CIS: a multicenter study using a machine learning approach

PURPOSE

To predict the occurrence of a second clinical event in patients with a CIS suggestive of MS, from baseline magnetic resonance imaging (MRI), by means of a pattern recognition approach.

METHODS

Two hundred sixty-six patients with a CIS were recruited from four participating centers. Over a follow-up of 3 years, 130 patients had a second clinical episode and 136 did not. Grey matter and white matter T1-hypointensities masks segmented from 3D T1-weighted images acquired on 3 T scanners were used as features for the classification approach. Differences between CIS that remained CIS and those that developed a second event were assessed at a global level and at a regional level, arranging the regions according to their contribution to the classification model.

RESULTS

All classification metrics were around or even below 50% for both global and regional approaches. Accuracies did not change when T1-hypointensity maps were added to the model; just the specificity was increased up to 80%. Among the 30 regions with the largest contribution, 26 were grey matter and 4 were white matter regions. For grey matter, regions contributing showed either a larger or a smaller volume in the group of patients that remained CIS, compared to those with a second event. The volume of T1-hypointensities was always larger for the group that presented a second event.

CONCLUSIONS

Prediction of a second clinical event in CIS patients from baseline MRI seems to present a highly heterogeneous pattern, leading to very low classification accuracies. Adding the T1-hypointensity maps does not seem to improve the accuracy of the classification model.

Plasma host protein biomarkers correlating with increasing Mycobacterium tuberculosis infection activity prior to tuberculosis diagnosis in people living with HIV

BACKGROUND

Biomarkers correlating with Mycobacterium tuberculosis infection activity/burden in asymptomatic individuals are urgently needed to identify and treat those at highest risk for developing active tuberculosis (TB). Our main objective was to identify plasma host protein biomarkers that change over time prior to developing TB in people living with HIV (PLHIV).

METHODS

Using multiplex MRM-MS, we investigated host protein expressions from 2 years before until time of TB diagnosis in longitudinally collected (every 3-6 months) and stored plasma from PLHIV with incident TB, identified within a South African (SA) and US cohort. We performed temporal trend and discriminant analyses for proteins, and, to assure clinical relevance, we further compared protein levels at TB diagnosis to interferon-gamma release assay (IGRA; SA) or tuberculin-skin test (TST; US) positive and negative cohort subjects without TB. SA and US exploratory data were analyzed separately.

FINDINGS

We identified 15 proteins in the SA (n=30) and 10 in the US (n=24) incident TB subjects which both changed from 2 years prior until time of TB diagnosis after controlling for 10% false discovery rate, and were significantly different at time of TB diagnosis compared to non-TB subjects (p<0.01). Five proteins, CD14, A2GL, NID1, SCTM1, and A1AG1, overlapped between both cohorts. Furthermore, after cross-validation, panels of 5 - 12 proteins were able to predict TB up to two years before diagnosis.

INTERPRETATION

Host proteins can be biomarkers for increasing Mycobacterium tuberculosis infection activity/burden, incipient TB, and predict TB development in PLHIV.

FUNDING

NIH/NIAID AI117927, AI146329, and AI127173 to JMA.

Opportunities for Understanding MS Mechanisms and Progression With MRI Using Large-Scale Data Sharing and Artificial Intelligence

Patients with multiple sclerosis (MS) have heterogeneous clinical presentations, symptoms, and progression over time, making MS difficult to assess and comprehend in vivo. The combination of large-scale data sharing and artificial intelligence creates new opportunities for monitoring and understanding MS using MRI. First, development of validated MS-specific image analysis methods can be boosted by verified reference, test, and benchmark imaging data. Using detailed expert annotations, artificial intelligence algorithms can be trained on such MS-specific data. Second, understanding disease processes could be greatly advanced through shared data of large MS cohorts with clinical, demographic, and treatment information. Relevant patterns in such data that may be imperceptible to a human observer could be detected through artificial intelligence techniques. This applies from image analysis (lesions, atrophy, or functional network changes) to large multidomain datasets (imaging, cognition, clinical disability, genetics). After reviewing data sharing and artificial intelligence, we highlight 3 areas that offer strong opportunities for making advances in the next few years: crowdsourcing, personal data protection, and organized analysis challenges. Difficulties as well as specific recommendations to overcome them are discussed, in order to best leverage data sharing and artificial intelligence to improve image analysis, imaging, and the understanding of MS.

Predicting Motor Outcome of Subthalamic Nucleus Deep Brain Stimulation for Parkinson's Disease Using Quantitative Susceptibility Mapping and Radiomics: A Pilot Study

Background

Emerging evidence indicates that iron distribution is heterogeneous within the substantia nigra (SN) and it may reflect patient-specific trait of Parkinson’s Disease (PD). We assume it could account for variability in motor outcome of subthalamic nucleus deep brain stimulation (STN-DBS) in PD.

Objective

To investigate whether SN susceptibility features derived from radiomics with machine learning (RA-ML) can predict motor outcome of STN-DBS in PD.

Methods

Thirty-three PD patients underwent bilateral STN-DBS were recruited. The bilateral SN were segmented based on preoperative quantitative susceptibility mapping to extract susceptibility features using RA-ML. MDS-UPDRS III scores were recorded 1–3 days before and 6 months after STN-DBS surgery. Finally, we constructed three predictive models using logistic regression analyses: (1) the RA-ML model based on radiomics features, (2) the RA-ML+LCT (levodopa challenge test) response model which combined radiomics features with preoperative LCT response, (3) the LCT response model alone.

Results

For the predictive performances of global motor outcome, the RA-ML model had 82% accuracy (AUC = 0.85), while the RA-ML+LCT response model had 74% accuracy (AUC = 0.83), and the LCT response model alone had 58% accuracy (AUC = 0.55). For the predictive performance of rigidity outcome, the accuracy of the RA-ML model was 80% (AUC = 0.85), superior to those of the RA-ML+LCT response model (76% accuracy, AUC = 0.82), and the LCT response model alone (58% accuracy, AUC = 0.42).

Conclusion

Our findings demonstrated that SN susceptibility features from radiomics could predict global motor and rigidity outcomes of STN-DBS in PD. This RA-ML predictive model might provide a novel approach to counsel candidates for STN-DBS.

Machine-learning-based diagnosis of drug-naive adult patients with attention-deficit hyperactivity disorder using mismatch negativity

Relatively little is investigated regarding the neurophysiology of adult attention-deficit/hyperactivity disorder (ADHD). Mismatch negativity (MMN) is an event-related potential component representing pre-attentive auditory processing, which is closely associated with cognitive status. We investigated MMN features as biomarkers to classify drug-naive adult patients with ADHD and healthy controls (HCs). Sensor-level features (amplitude and latency) and source-level features (source activation) of MMN were investigated and compared between the electroencephalograms of 34 patients with ADHD and 45 HCs using a passive auditory oddball paradigm. Correlations between MMN features and ADHD symptoms were analyzed. Finally, we applied machine learning to differentiate the two groups using sensor- and source-level features of MMN. Adult patients with ADHD showed significantly lower MMN amplitudes at the frontocentral electrodes and reduced MMN source activation in the frontal, temporal, and limbic lobes, which were closely associated with MMN generators and ADHD pathophysiology. Source activities were significantly correlated with ADHD symptoms. The best classification performance for adult ADHD patients and HCs showed an 81.01% accuracy, 82.35% sensitivity, and 80.00% specificity based on MMN source activity features. Our results suggest that abnormal MMN reflects the adult ADHD patients' pathophysiological characteristics and might serve clinically as a neuromarker of adult ADHD.

Machine Learning of Schizophrenia Detection with Structural and Functional Neuroimaging

Schizophrenia (SZ) is a severe psychiatric illness, and it affects around 1% of the general population; however, its reliable diagnosis is challenging. Functional MRI (fMRI) and structural MRI (sMRI) are useful techniques for investigating the functional and structural abnormalities of the human brain, and a growing number of studies have reported that multimodal brain data can improve diagnostic accuracy. Machine learning (ML) is widely used in the diagnosis of neuroscience and neuropsychiatry diseases, and it can obtain high accuracy. However, the conventional ML which concatenated the features into a longer feature vector could not be sufficiently effective to combine different features from different modalities. There are considerable controversies over the use of global signal regression (GSR), and few studies have explored the role of GSR in ML in diagnosing neurological diseases. The current study utilized fMRI and sMRI data to implement a new method named multimodal imaging and multilevel characterization with multiclassifier (M3) to classify SZs and healthy controls (HCs) and investigate the influence of GSR in SZ classification. We found that when we used Brainnetome 246 atlas and without performed GSR, our method obtained a classification accuracy of 83.49%, with a sensitivity of 68.69%, a specificity of 93.75%, and an AUC of 0.8491, respectively. We also got great classification performances with different processing methods (with/without GSR and different brain parcellation schemes). We found that the accuracy and specificity of the models without GSR were higher than that of the models with GSR. Our findings indicate that the M3 method is an effective tool to distinguish SZs from HCs, and it can identify discriminative regions to detect SZ to explore the neural mechanisms underlying SZ. The global signal may contain important neuronal information; it can improve the accuracy and specificity of SZ detection.

Predicting Length of Stay of Coronary Artery Bypass Grafting Patients Using Machine Learning

BACKGROUND

There is a growing need to identify which bits of information are most valuable for healthcare providers. The aim of this study was to search for the highest impact variables in predicting postsurgery length of stay (LOS) for patients who undergo coronary artery bypass grafting (CABG).

MATERIALS AND METHODS

Using a single institution's Society of Thoracic Surgeons (STS) Registry data, 2121 patients with elective or urgent, isolated CABG were analyzed across 116 variables. Two machine learning techniques of random forest and artificial neural networks (ANNs) were used to search for the highest impact variables in predicting LOS, and results were compared against multiple linear regression. Out-of-sample validation of the models was performed on 105 patients.

RESULTS

Of the 10 highest impact variables identified in predicting LOS, four of the most impactful variables were duration intubated, last preoperative creatinine, age, and number of intraoperative packed red blood cell transfusions. The best performing model was an ANN using the ten highest impact variables (testing sample mean absolute error (MAE) = 1.685 d, R² = 0.232), which performed consistently in the out-of-sample validation (MAE = 1.612 d, R² = 0.150).

CONCLUSION

Using machine learning, this study identified several novel predictors of postsurgery LOS and reinforced certain known risk factors. Out of the entire STS database, only a few variables carry most of the predictive value for LOS in this population. With this knowledge, a simpler linear regression model has been shared and could be used elsewhere after further validation.

Current review and next steps for artificial intelligence in multiple sclerosis risk research

In the last few decades, the prevalence of multiple sclerosis (MS), a chronic inflammatory disease of the nervous system, has increased, particularly in Northern European countries, the United States, and United Kingdom. The promise of artificial intelligence (AI) and machine learning (ML) as tools to address problems in MS research has attracted increasing interest in these methods. Bayesian networks offer a clear advantage since they can integrate data and causal knowledge allowing for visualizing interactions between dependent variables and potential confounding factors. A review of AI/ML research methods applied to MS found 216 papers using terms "Multiple Sclerosis", "machine learning", "artificial intelligence", "Bayes", and "Bayesian", of which 90 were relevant and recently published. More than half of these involve the detection and segmentation of MS lesions for quantitative analysis; however clinical and lifestyle risk factor assessment and prediction have largely been ignored. Of those that address risk factors, most provide only association studies for some factors and often fail to include the potential impact of confounding factors and bias (especially where these have causal explanations) that could affect data interpretation, such as reporting quality and medical care access in various countries. To address these gaps in the literature, we propose a causal Bayesian network approach to assessing risk factors for MS, which can address deficiencies in current epidemiological methods of producing risk measurements and makes better use of observational data.

Machine Learning Use for Prognostic Purposes in Multiple Sclerosis

The course of multiple sclerosis begins with a relapsing-remitting phase, which evolves into a secondarily progressive form over an extremely variable period, depending on many factors, each with a subtle influence. To date, no prognostic factors or risk score have been validated to predict disease course in single individuals. This is increasingly frustrating, since several treatments can prevent relapses and slow progression, even for a long time, although the possible adverse effects are relevant, in particular for the more effective drugs. An early prediction of disease course would allow differentiation of the treatment based on the expected aggressiveness of the disease, reserving high-impact therapies for patients at greater risk. To increase prognostic capacity, approaches based on machine learning (ML) algorithms are being attempted, given the failure of other approaches. Here we review recent studies that have used clinical data, alone or with other types of data, to derive prognostic models. Several algorithms that have been used and compared are described. Although no study has proposed a clinically usable model, knowledge is building up and in the future strong tools are likely to emerge.

A systematic review of the application of machine-learning algorithms in multiple sclerosis

INTRODUCTION

The applications of artificial intelligence, and in particular automatic learning or "machine learning" (ML), constitute both a challenge and a great opportunity in numerous scientific, technical, and clinical disciplines. Specific applications in the study of multiple sclerosis (MS) have been no exception, and constitute an area of increasing interest in recent years.

OBJECTIVE

We present a systematic review of the application of ML algorithms in MS.

MATERIALS AND METHODS

We used the PubMed search engine, which allows free access to the MEDLINE medical database, to identify studies including the keywords "machine learning" and "multiple sclerosis." We excluded review articles, studies written in languages other than English or Spanish, and studies that were mainly technical and did not specifically apply to MS. The final selection included 76 articles, and 38 were rejected.

CONCLUSIONS

After the review process, we established 4 main applications of ML in MS: 1) classifying MS subtypes; 2) distinguishing patients with MS from healthy controls and individuals with other diseases; 3) predicting progression and response to therapeutic interventions; and 4) other applications. Results found to date have shown that ML algorithms may offer great support for health professionals both in clinical settings and in research into MS.

Machine learning for predictive data analytics in medicine: A review illustrated by cardiovascular and nuclear medicine examples

The evidence-based medicine allows the physician to evaluate the risk-benefit ratio of a treatment through setting and data. Risk-based choices can be done by the doctor using different information. With the emergence of new technologies, a large amount of data is recorded offering interesting perspectives with machine learning for predictive data analytics. Machine learning is an ensemble of methods that process data to model a learning problem. Supervised machine learning algorithms consist in using annotated data to construct the model. This category allows to solve prediction data analytics problems. In this paper, we detail the use of supervised machine learning algorithms for predictive data analytics problems in medicine. In the medical field, data can be split into two categories: medical images and other data. For brevity, our review deals with any kind of medical data excluding images. In this article, we offer a discussion around four supervised machine learning approaches: information-based, similarity-based, probability-based and error-based approaches. Each method is illustrated with detailed cardiovascular and nuclear medicine examples. Our review shows that model ensemble (ME) and support vector machine (SVM) methods are the most popular. SVM, ME and artificial neural networks often lead to better results than those given by other algorithms. In the coming years, more studies, more data, more tools and more methods will, for sure, be proposed.

AI in Radiology: Where are we today in Multiple Sclerosis Imaging?

Background MR imaging is an essential component in managing patients with Multiple sclerosis (MS). This holds true for the initial diagnosis as well as for assessing the clinical course of MS. In recent years, a growing number of computer tools were developed to analyze imaging data in MS. This review gives an overview of the most important applications with special emphasis on artificial intelligence (AI).

Methods Relevant studies were identified through a literature search in recognized databases, and through parsing the references in studies found this way. Literature published as of November 2019 was included with a special focus on recent studies from 2018 and 2019.

Results There are a number of studies which focus on optimizing lesion visualization and lesion segmentation. Some of these studies accomplished these tasks with high accuracy, enabling a reproducible quantitative analysis of lesion loads. Some studies took a radiomics approach and aimed at predicting clinical endpoints such as the conversion from a clinically isolated syndrome to definite MS. Moreover, recent studies investigated synthetic imaging, i. e. imaging data that is not measured during an MR scan but generated by a computer algorithm to optimize the contrast between MS lesions and brain parenchyma.

Conclusion Computer-based image analysis and AI are hot topics in imaging MS. Some applications are ready for use in clinical routine. A major challenge for the future is to improve prediction of expected disease courses and thereby helping to find optimal treatment decisions on an individual level. With technical improvements, more questions arise about the integration of new tools into the radiological workflow.

Key Points: 

Citation Format

Detecting Abnormal Brain Regions in Schizophrenia Using Structural MRI via Machine Learning

Utilizing neuroimaging and machine learning (ML) to differentiate schizophrenia (SZ) patients from normal controls (NCs) and for detecting abnormal brain regions in schizophrenia has several benefits and can provide a reference for the clinical diagnosis of schizophrenia. In this study, structural magnetic resonance images (sMRIs) from SZ patients and NCs were used for discriminative analysis. This study proposed an ML framework based on coarse-to-fine feature selection. The proposed framework used two-sample t-tests to extract the differences between groups first, then further eliminated the nonrelevant and redundant features with recursive feature elimination (RFE), and finally utilized the support vector machine (SVM) to learn the decision models with selected gray matter (GM) and white matter (WM) features. Previous studies have tended to report differences at the group level instead of at the individual level and cannot be widely applied. The method proposed in this study extends the diagnosis to the individual level and has a higher recognition rate than previous methods. The experimental results of this study demonstrate that the proposed framework distinguishes SZ patients from NCs, with the highest classification accuracy reaching over 85%. The identified biomarkers are also consistent with previous literature findings. As a universal method, the proposed framework can be extended to diagnose other diseases.