Multi-lesion radiomics model for discrimination of relapsing-remitting multiple sclerosis and neuropsychiatric systemic lupus erythematosus

Case report: Case analysis of multiple sclerosis with preclinical systemic lupus erythematosus presenting as rare bilateral horizontal gaze palsy

We present an analysis of a case initially manifesting as bilateral horizontal gaze palsy, eventually diagnosed as multiple sclerosis (MS) with preclinical systemic lupus erythematosus (p-SLE). The patient, a 25-year-old male, exhibited restricted movement in both eyes. Cranial MRI revealed multiple demyelinating lesions; serum analyses indicated elevated levels of antinuclear antibodies (ANA), anti-Sm antibodies, and anti-nRNP antibodies. Oligoclonal bands were identified in the cerebrospinal fluid. Neurophysiological assessments demonstrated damage to the optic, auditory, and facial nerves. Given the clinical presentation, laboratory findings, and the progression of the disease, the final diagnosis was confirmed as MS associated with p-SLE. The onset of MS with oculomotor disturbances is rare and may be easily confused with neuropsychiatric systemic lupus erythematosus (NPSLE). Furthermore, the differentiation of p-SLE from undifferentiated connective tissue disease (UCTD) in the early stages presents significant challenges. Early identification of risk factors and close monitoring of disease activity is crucial for an accurate diagnosis.

Artificial Intelligence and Multiple Sclerosis

In this paper, we analyse the different advances in artificial intelligence (AI) approaches in multiple sclerosis (MS). AI applications in MS range across investigation of disease pathogenesis, diagnosis, treatment, and prognosis. A subset of AI, Machine learning (ML) models analyse various data sources, including magnetic resonance imaging (MRI), genetic, and clinical data, to distinguish MS from other conditions, predict disease progression, and personalize treatment strategies. Additionally, AI models have been extensively applied to lesion segmentation, identification of biomarkers, and prediction of outcomes, disease monitoring, and management. Despite the big promises of AI solutions, model interpretability and transparency remain critical for gaining clinician and patient trust in these methods. The future of AI in MS holds potential for open data initiatives that could feed ML models and increasing generalizability, the implementation of federated learning solutions for training the models addressing data sharing issues, and generative AI approaches to address challenges in model interpretability, and transparency. In conclusion, AI presents an opportunity to advance our understanding and management of MS. AI promises to aid clinicians in MS diagnosis and prognosis improving patient outcomes and quality of life, however ensuring the interpretability and transparency of AI-generated results is going to be key for facilitating the integration of AI into clinical practice.

Pattern of heterogeneity in normal brain ageing: screening for mild cognitive impairment and its risk of progression with a radiomics model

PURPOSE

This study aimed to develop a normal brain ageing model based on magnetic resonance imaging and radiomics, therefore identifying radscore, an imaging indicator representing white matter heterogeneity and exploring the significance of radscore in detecting people's cognitive changes.

METHODS

Three hundred sixty cognitively normal (CN) subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database and 105 CN subjects from the Parkinson's Progression Markers Initiative database were used to develop the model. In ADNI, 230 mild cognitive impairment (MCI) subjects were matched with 230 CN old-aged subjects to evaluate their heterogeneity difference. One hundred four MCI subjects with 48 months of follow-up were divided into low and high heterogeneity groups. Kaplan-Meier survival curve analysis was used to observe the importance of heterogeneity results for predicting MCI progression.

RESULTS

The area under the receiver operating characteristic curve of the model in the training, internal test and external test sets was 0.7503, 0.7512 and 0.7514, respectively. There was a significantly positive correlation between age and radscore of CN subjects (r = 0.501; P < .001). The radscore of MCI subjects was significantly higher than that of matched CN subjects (P < .001). The median radscore ratios of MCI to CN from four age groups (66-70y, 71-75y, 76-80y and 81-85y) were 1.611, 1.760, 1.340 and 1.266, respectively. The probability to progression of low and high heterogeneity groups had a significant difference (P = .002).

CONCLUSION

When radscore is significantly higher than that of normal ageing, it is necessary to alert the possibility of cognitive impairment and deterioration.

Joint radiomics and spatial distribution model for MRI-based discrimination of multiple sclerosis, neuromyelitis optica spectrum disorder, and myelin-oligodendrocyte-glycoprotein-IgG-associated disorder

OBJECTIVE

To develop a discrimination pipeline concerning both radiomics and spatial distribution features of brain lesions for discrimination of multiple sclerosis (MS), aquaporin-4-IgG-seropositive neuromyelitis optica spectrum disorder (NMOSD), and myelin-oligodendrocyte-glycoprotein-IgG-associated disorder (MOGAD).

METHODS

Hyperintensity T2 lesions were delineated in 212 brain MRI scans of MS (n = 63), NMOSD (n = 87), and MOGAD (n = 45) patients. To avoid the effect of fixed training/test dataset sampling when developing machine learning models, patients were allocated into 4 sub-groups for cross-validation. For each scan, 351 radiomics and 27 spatial distribution features were extracted. Three models, i.e., multi-lesion radiomics, spatial distribution, and joint models, were constructed using random forest and logistic regression algorithms for differentiating: MS from the others (MS models) and MOGAD from NMOSD (MOG-NMO models), respectively. Then, the joint models were combined with demographic characteristics (i.e., age and sex) to create MS and MOG-NMO discriminators, respectively, based on which a three-disease discrimination pipeline was generated and compared with radiologists.

RESULTS

For classification of both MS-others and MOG-NMO, the joint models performed better than radiomics or spatial distribution model solely. The MS discriminator achieved AUC = 0.909 ± 0.027 and bias-corrected C-index = 0.909 ± 0.027, and the MOG-NMO discriminator achieved AUC = 0.880 ± 0.064 and bias-corrected C-index = 0.883 ± 0.068. The three-disease discrimination pipeline differentiated MS, NMOSD, and MOGAD patients with 75.0% accuracy, prominently outperforming the three radiologists (47.6%, 56.6%, and 66.0%).

CONCLUSIONS

The proposed pipeline integrating multi-lesion radiomics and spatial distribution features could effectively differentiate MS, NMOSD, and MOGAD.

CLINICAL RELEVANCE STATEMENT

The discrimination pipeline merging both radiomics and spatial distribution features of brain lesions may facilitate the differential diagnoses of multiple sclerosis, neuromyelitis optica spectrum disorder, and myelin-oligodendrocyte-glycoprotein-IgG-associated disorder.

KEY POINTS

• Our study introduces an approach by combining radiomics and spatial distribution models. • The joint model exhibited superior performance in distinguishing multiple sclerosis from aquaporin-4-IgG-seropositive neuromyelitis optica spectrum disorder and myelin-oligodendrocyte-glycoprotein-IgG-associated disorder as well as discriminating the latter two diseases. • The three-disease discrimination pipeline showcased remarkable accuracy, surpassing the performance of experienced radiologists, highlighting its potential as a valuable diagnostic tool.

Systemic lupus in the era of machine learning medicine

Artificial intelligence and machine learning applications are emerging as transformative technologies in medicine. With greater access to a diverse range of big datasets, researchers are turning to these powerful techniques for data analysis. Machine learning can reveal patterns and interactions between variables in large and complex datasets more accurately and efficiently than traditional statistical methods. Machine learning approaches open new possibilities for studying SLE, a multifactorial, highly heterogeneous and complex disease. Here, we discuss how machine learning methods are rapidly being integrated into the field of SLE research. Recent reports have focused on building prediction models and/or identifying novel biomarkers using both supervised and unsupervised techniques for understanding disease pathogenesis, early diagnosis and prognosis of disease. In this review, we will provide an overview of machine learning techniques to discuss current gaps, challenges and opportunities for SLE studies. External validation of most prediction models is still needed before clinical adoption. Utilisation of deep learning models, access to alternative sources of health data and increased awareness of the ethics, governance and regulations surrounding the use of artificial intelligence in medicine will help propel this exciting field forward.

A Radiomic "Warning Sign" of Progression on Brain MRI in Individuals with MS

BACKGROUND AND PURPOSE

MS is a chronic progressive, idiopathic, demyelinating disorder whose diagnosis is contingent on the interpretation of MR imaging. New MR imaging lesions are an early biomarker of disease progression. We aimed to evaluate a machine learning model based on radiomics features in predicting progression on MR imaging of the brain in individuals with MS.

MATERIALS AND METHODS

This retrospective cohort study with external validation on open-access data obtained full ethics approval. Longitudinal MR imaging data for patients with MS were collected and processed for machine learning. Radiomics features were extracted at the future location of a new lesion in the patients' prior MR imaging ("prelesion"). Additionally, "control" samples were obtained from the normal-appearing white matter for each participant. Machine learning models for binary classification were trained and tested and then evaluated the external data of the model.

RESULTS

The total number of participants was 167. Of the 147 in the training/test set, 102 were women and 45 were men. The average age was 42 (range, 21-74 years). The best-performing radiomics-based model was XGBoost, with accuracy, precision, recall, and F1-score of 0.91, 0.91, 0.91, and 0.91 on the test set, and 0.74, 0.74, 0.74, and 0.70 on the external validation set. The 5 most important radiomics features to the XGBoost model were associated with the overall heterogeneity and low gray-level emphasis of the segmented regions. Probability maps were produced to illustrate potential future clinical applications.

CONCLUSIONS

Our machine learning model based on radiomics features successfully differentiated prelesions from normal-appearing white matter. This outcome suggests that radiomics features from normal-appearing white matter could serve as an imaging biomarker for progression of MS on MR imaging.

Non-invasive prediction of the chronic degree of lupus nephropathy based on ultrasound radiomics

OBJECTIVE

Through machine learning (ML) analysis of the radiomics features of ultrasound extracted from patients with lupus nephritis (LN), this attempt was made to non-invasively predict the chronicity index (CI)of LN.

METHODS

A retrospective collection of 136 patients with LN who had renal biopsy was retrospectively collected, and the patients were randomly divided into training set and validation set according to 7:3. Radiomics features are extracted from ultrasound images, independent factors are obtained by using LASSO dimensionality reduction, and then seven ML models were used to establish predictive models. At the same time, a clinical model and an US model were established. The diagnostic efficacy of the model is evaluated by analysis of the receiver operating characteristics (ROC) curve, accuracy, specificity, and sensitivity. The performance of the seven machine learning models was compared with each other and with clinical and US models.

RESULTS

A total of 1314 radiomics features are extracted from ultrasound images, and 5 features are finally screened out by LASSO for model construction, and the average ROC of the seven ML is 0.683, among which the Xgboost model performed the best, and the AUC in the test set is 0.826 (95% CI: 0.681-0.936). For the same test set, the AUC of clinical model constructed based on eGFR is 0.560 (95% CI: 0.357-0.761), and the AUC of US model constructed based on Ultrasound parameters is 0.679 (95% CI: 0.489-0.853). The Xgboost model is significantly more efficient than the clinical and US models.

CONCLUSION

ML model based on ultrasound radiomics features can accurately predict the chronic degree of LN, which can provide a valuable reference for clinicians in the treatment strategy of LN patients.

Artificial intelligence-assisted dermatology diagnosis: From unimodal to multimodal

Artificial Intelligence (AI) is progressively permeating medicine, notably in the realm of assisted diagnosis. However, the traditional unimodal AI models, reliant on large volumes of accurately labeled data and single data type usage, prove insufficient to assist dermatological diagnosis. Augmenting these models with text data from patient narratives, laboratory reports, and image data from skin lesions, dermoscopy, and pathologies could significantly enhance their diagnostic capacity. Large-scale pre-training multimodal models offer a promising solution, exploiting the burgeoning reservoir of clinical data and amalgamating various data types. This paper delves into unimodal models' methodologies, applications, and shortcomings while exploring how multimodal models can enhance accuracy and reliability. Furthermore, integrating cutting-edge technologies like federated learning and multi-party privacy computing with AI can substantially mitigate patient privacy concerns in dermatological datasets and further fosters a move towards high-precision self-diagnosis. Diagnostic systems underpinned by large-scale pre-training multimodal models can facilitate dermatology physicians in formulating effective diagnostic and treatment strategies and herald a transformative era in healthcare.

Supporting the differential diagnosis of connective tissue diseases with neurological involvement by blood and cerebrospinal fluid flow cytometry

OBJECTIVE

Neurological manifestations of autoimmune connective tissue diseases (CTD) are poorly understood and difficult to diagnose. We here aimed to address this shortcoming by studying immune cell compositions in CTD patients with and without neurological manifestation.

METHODS

Using flow cytometry, we retrospectively investigated paired cerebrospinal fluid (CSF) and blood samples of 28 CTD patients without neurological manifestation, 38 CTD patients with neurological manifestation (N-CTD), 38 non-inflammatory controls, and 38 multiple sclerosis (MS) patients, a paradigmatic primary neuroinflammatory disease.

RESULTS

We detected an expansion of plasma cells in the blood of both N-CTD and CTD compared to non-inflammatory controls and MS. Blood plasma cells alone distinguished the clinically similar entities N-CTD and MS with high discriminatory performance (AUC: 0.81). Classical blood monocytes indicated higher disease activity in systemic lupus erythematosus (SLE) patients. Surprisingly, immune cells in the CSF did not differ significantly between N-CTD and CTD, while CD4⁺ T cells and the CD4⁺/CD8⁺ ratio were elevated in the blood of N-CTD compared to CTD. Several B cell-associated parameters partially overlapped in the CSF in MS and N-CTD. We built a machine learning model that distinguished N-CTD from MS with high discriminatory power using either blood or CSF.

CONCLUSION

We here find that blood flow cytometry alone surprisingly suffices to distinguish CTD with neurological manifestations from clinically similar entities, suggesting that a rapid blood test could support clinicians in the differential diagnosis of N-CTD.

Machine Learning for Diagnosis of Systemic Lupus Erythematosus: A Systematic Review and Meta-Analysis

Background

Application of machine learning (ML) for identification of systemic lupus erythematosus (SLE) has been recently drawing increasing attention, while there is still lack of evidence-based support.

Methods

Systematic review and meta-analysis are conducted to evaluate its diagnostic accuracy and application prospect. PubMed, Embase, Cochrane Library, and Web of Science libraries are searched, in combination with manual searching and literature retrospection, for studies regarding machine learning for identifying SLE and neuropsychiatric systemic lupus erythematosus (NPSLE). Quality Assessment of Diagnostic Accuracy Studies (QUADA-2) is applied to assess the quality of included studies. Diagnostic accuracy of the SLE model and NPSLE model is assessed using the bivariate fixed-effect model, and the data are pooled. Summary receiver operator characteristic curve (SROC) is plotted, and area under the curve (AUC) is calculated.

Results

Eighteen (18) studies are included, in which ten (10) focused on SLE and eight (8) on NPSLE. The AUC of SLE identification is 0.95, the sensitivity is 0.90, the specificity is 0.89, the PLR is 8.4, the NLR is 0.12, and the DOR is 73. AUC of NPSLE identification is 0.89, the sensitivity is 0.83, the specificity is 0.83, the PLR is 5.0, the NLR is 0.20, and the DOR is 25.

Conclusion

Machine learning presented remarkable performance in identification of SLE and NPSLE. Based on the convenience for inclusion factor collection and non-invasiveness of detection, machine learning is expected to be widely applied in clinical practice to assist medical decision making.

An MRI-based joint model of radiomics and spatial distribution differentiates autoimmune encephalitis from low-grade diffuse astrocytoma

BACKGROUND

The differential diagnosis between autoimmune encephalitis and low-grade diffuse astrocytoma remains challenging. We aim to develop a quantitative model integrating radiomics and spatial distribution features derived from MRI for discriminating these two conditions.

METHODS

In our study, we included 188 patients with confirmed autoimmune encephalitis (n = 81) and WHO grade II diffuse astrocytoma (n = 107). Patients with autoimmune encephalitis (AE, n = 59) and WHO grade II diffuse astrocytoma (AS, n = 79) were divided into training and test sets, using stratified sampling according to MRI scanners. We further included an independent validation set (22 patients with AE and 28 patients with AS). Hyperintensity fluid-attenuated inversion recovery (FLAIR) lesions were segmented for each subject. Ten radiomics and eight spatial distribution features were selected via the least absolute shrinkage and selection operator (LASSO), and joint models were constructed by logistic regression for disease classification. Model performance was measured in the test set using the area under the receiver operating characteristic (ROC) curve (AUC). The discrimination performance of the joint model was compared with neuroradiologists.

RESULTS

The joint model achieved better performance (AUC 0.957/0.908, accuracy 0.914/0.840 for test and independent validation sets, respectively) than the radiomics and spatial distribution models. The joint model achieved lower performance than a senior neuroradiologist (AUC 0.917/0.875) but higher performance than a junior neuroradiologist (AUC 0.692/0.745) in the test and independent validation sets.

CONCLUSION

The joint model of radiomics and spatial distribution from a single FLAIR could effectively classify AE and AS, providing clinical decision support for the differential diagnosis between the two conditions.